Search results for: large-scale modeling and simulation

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 65

Authors: Tayebeh Sahraeibelverdi, Ahmad Shirazi Hadi Veladi, Mazdak Radmalekshah

Abstract:

Optical sensors became attractive due to preciseness, low power consumption, and intrinsic electromagnetic interference-free characteristic. Among the waveguide optical sensors, cavity-based ones attended for the high Q-factor. Micro ring resonators as a potential platform have been investigated for various applications as biosensors to pressure sensors thanks to their sensitive ring structure responding to any small change in the refractive index. Furthermore, these small micron size structures can come in an array, bringing the opportunity to have any of the resonance in a specific wavelength and be addressed in this way. Another exciting application is applying a strain to the ring and making them an optical strain gauge where the traditional ones are based on the piezoelectric material. Making them in arrays needs electrical wiring and about fifty times bigger in size. Any physical element that impacts the waveguide cross-section, Waveguide elastic-optic property change, or ring circumference can play a role. In comparison, ring size change has a larger effect than others. Here an engineered ring structure is investigated to study the strain effect on the ring resonance wavelength shift and its potential for more sensitive strain devices. At the same time, these devices can measure any strain by mounting on the surface of interest. The idea is to change the" O" shape ring to a "C" shape ring with a small opening starting from 2π/360 or one degree. We used the Mode solution of Lumbrical software to investigate the effect of changing the ring's opening and the shift induced by applied strain. The designed ring radius is a three Micron silicon on isolator ring which can be fabricated by standard complementary metal-oxide-semiconductor (CMOS) micromachining. The measured wavelength shifts from1-degree opening of the ring to a 6-degree opening have been investigated. Opening the ring for 1-degree affects the ring's quality factor from 3000 to 300, showing an order of magnitude Q-factor reduction. Assuming a strain making the ring-opening from 1 degree to 6 degrees, our simulation results showing negligible Q-factor reduction from 300 to 280. A ring resonator quality factor can reach up to 108 where an order of magnitude reduction is negligible. The resonance wavelength shift showed a blue shift and was obtained to be 1581, 1579,1578,1575nm for 1-, 2-, 4- and 6-degree ring-opening, respectively. This design can find the direction of the strain-induced by applying the opening on different parts of the ring. Moreover, by addressing the specified wavelength, we can precisely find the direction. We can open a significant opportunity to find cracks and any surface mechanical property very specifically and precisely. This idea can be implemented on polymer ring resonators while they can come with a flexible substrate and can be very sensitive to any strain making the two ends of the ring in the slit part come closer or further.

Keywords: optical ring resonator, strain gauge, strain sensor, surface mechanical property analysis

Procedia PDF Downloads 127

Authors: Mohammadamin Hashemi, Mohammadreza Kashizadeh

Abstract:

Droughts pose a significant threat to sustainable water resource management, agriculture, and socioeconomic sectors, particularly in the field of climate change. This study investigates drought simulation using rainfall-runoff modelling in the Cuneo district, Italy, over the past 60-year period. The study leverages the TUW model, a lumped conceptual rainfall-runoff model with a semi-distributed operation capability. Similar in structure to the widely used Hydrologiska Byråns Vattenbalansavdelning (HBV) model, the TUW model operates on daily timesteps for input and output data specific to each catchment. It incorporates essential routines for snow accumulation and melting, soil moisture storage, and streamflow generation. Multiple catchments' discharge data within the Cuneo district form the basis for thorough model calibration employing the Kling-Gupta Efficiency (KGE) metric. A crucial metric for reliable drought analysis is one that can accurately represent low-flow events during drought periods. This ensures that the model provides a realistic picture of water availability during these critical times. Subsequent validation of monthly discharge simulations thoroughly evaluates overall model performance. Beyond model development, the investigation delves into drought analysis using the robust Standardized Runoff Index (SRI). This index allows for precise characterization of drought occurrences within the study area. A meticulous comparison of observed and simulated discharge data is conducted, with particular focus on low-flow events that characterize droughts. Additionally, the study explores the complex interplay between land characteristics (e.g., soil type, vegetation cover) and climate variables (e.g., precipitation, temperature) that influence the severity and duration of hydrological droughts. The study's findings demonstrate successful calibration of the TUW model across most catchments, achieving commendable model efficiency. Comparative analysis between simulated and observed discharge data reveals significant agreement, especially during critical low-flow periods. This agreement is further supported by the Pareto coefficient, a statistical measure of goodness-of-fit. The drought analysis provides critical insights into the duration, intensity, and severity of drought events within the Cuneo district. This newfound understanding of spatial and temporal drought dynamics offers valuable information for water resource management strategies and drought mitigation efforts. This research deepens our understanding of drought dynamics in the Cuneo region. Future research directions include refining hydrological modelling techniques and exploring future drought projections under various climate change scenarios.

Keywords: hydrologic extremes, hydrological drought, hydrological modelling, machine learning, rainfall-runoff modelling

Procedia PDF Downloads 43

Authors: Frea Van Steenweghen, Lander Hollevoet, Johan A. Martens

Abstract:

Compared to other hydrogen (H₂) carriers, ammonia (NH₃) is one of the most promising carriers as it contains 17.6 wt% hydrogen. It is easily liquefied at ≈ 9–10 bar pressure at ambient temperature. More importantly, NH₃ is a carbon-free hydrogen carrier with no CO₂ emission at final decomposition. Ammonia has a well-defined regulatory framework and a good track record regarding safety concerns. Furthermore, the industry already has an existing transport infrastructure consisting of pipelines, tank trucks and shipping technology, as ammonia has been manufactured and distributed around the world for over a century. While NH₃ synthesis and transportation technological solutions are at hand, a missing link in the hydrogen delivery scheme from ammonia is an energy-lean and efficient technology for cracking ammonia into H₂ and N₂. The most explored option for ammonia decomposition is thermo-catalytic cracking which is, by itself, the most energy-efficient approach compared to other technologies, such as plasma and electrolysis, as it is the most energy-lean and robust option. The decomposition reaction is favoured only at high temperatures (> 300°C) and low pressures (1 bar) as the thermocatalytic ammonia cracking process is faced with thermodynamic limitations. At 350°C, the thermodynamic equilibrium at 1 bar pressure limits the conversion to 99%. Gaining additional conversion up to e.g. 99.9% necessitates heating to ca. 530°C. However, reaching thermodynamic equilibrium is infeasible as a sufficient driving force is needed, requiring even higher temperatures. Limiting the conversion below the equilibrium composition is a more economical option. Thermocatalytic ammonia cracking is documented in scientific literature. Among the investigated metal catalysts (Ru, Co, Ni, Fe, …), ruthenium is known to be most active for ammonia decomposition with an onset of cracking activity around 350°C. For establishing > 99% conversion reaction, temperatures close to 600°C are required. Such high temperatures are likely to reduce the round-trip efficiency but also the catalyst lifetime because of the sintering of the supported metal phase. In this research, the first focus was on catalyst bed design, avoiding diffusion limitation. Experiments in our packed bed tubular reactor set-up showed that extragranular diffusion limitations occur at low concentrations of NH₃ when reaching high conversion, a phenomenon often overlooked in experimental work. A second focus was thermocatalyst development for ammonia cracking, avoiding the use of noble metals. To this aim, candidate metals and mixtures were deposited on a range of supports. Sintering resistance at high temperatures and the basicity of the support were found to be crucial catalyst properties. The catalytic activity was promoted by adding alkaline and alkaline earth metals. A third focus was studying the optimum process configuration by process simulations. A trade-off between conversion and favorable operational conditions (i.e. low pressure and high temperature) may lead to different process configurations, each with its own pros and cons. For example, high-pressure cracking would eliminate the need for post-compression but is detrimental for the thermodynamic equilibrium, leading to an optimum in cracking pressure in terms of energy cost.

Keywords: ammonia cracking, catalyst research, kinetics, process simulation, thermodynamic equilibrium

Procedia PDF Downloads 68

Authors: M. Pienaar, J. W. Odendaal, J. C. Smit, J. Joubert

Abstract:

Simulations are commonly used to predict the bistatic radar cross section (RCS) of military targets since characterization measurements can be expensive and time consuming. It is thus important to accurately predict the bistatic RCS of targets. Computational electromagnetic (CEM) methods can be used for bistatic RCS prediction. CEM methods are divided into full-wave and asymptotic methods. Full-wave methods are numerical approximations to the exact solution of Maxwell’s equations. These methods are very accurate but are computationally very intensive and time consuming. Asymptotic techniques make simplifying assumptions in solving Maxwell's equations and are thus less accurate but require less computational resources and time. Asymptotic techniques can thus be very valuable for the prediction of bistatic RCS of electrically large targets, due to the decreased computational requirements. This study extends previous work by validating the accuracy of asymptotic techniques to predict bistatic RCS through comparison with full-wave simulations as well as measurements. Validation is done with canonical structures as well as complex realistic aircraft models instead of only looking at a complex slicy structure. The slicy structure is a combination of canonical structures, including cylinders, corner reflectors and cubes. Validation is done over large bistatic angles and at different polarizations. Bistatic RCS measurements were conducted in a compact range, at the University of Pretoria, South Africa. The measurements were performed at different polarizations from 2 GHz to 6 GHz. Fixed bistatic angles of β = 30.8°, 45° and 90° were used. The measurements were calibrated with an active calibration target. The EM simulation tool FEKO was used to generate simulated results. The full-wave multi-level fast multipole method (MLFMM) simulated results together with the measured data were used as reference for validation. The accuracy of physical optics (PO) and geometrical optics (GO) was investigated. Differences relating to amplitude, lobing structure and null positions were observed between the asymptotic, full-wave and measured data. PO and GO were more accurate at angles close to the specular scattering directions and the accuracy seemed to decrease as the bistatic angle increased. At large bistatic angles PO did not perform well due to the shadow regions not being treated appropriately. PO also did not perform well for canonical structures where multi-bounce was the main scattering mechanism. PO and GO do not account for diffraction but these inaccuracies tended to decrease as the electrical size of objects increased. It was evident that both asymptotic techniques do not properly account for bistatic structural shadowing. Specular scattering was calculated accurately even if targets did not meet the electrically large criteria. It was evident that the bistatic RCS prediction performance of PO and GO depends on incident angle, frequency, target shape and observation angle. The improved computational efficiency of the asymptotic solvers yields a major advantage over full-wave solvers and measurements; however, there is still much room for improvement of the accuracy of these asymptotic techniques.

Keywords: asymptotic techniques, bistatic RCS, geometrical optics, physical optics

Procedia PDF Downloads 260

Authors: M. Kadela

Abstract:

The load caused by the traffic movement should be transferred in the road constructions in a harmless way to the pavement as follows: − on the stiff upper layers of the structure (e.g. layers of asphalt: abrading and binding), and − through the layers of principal and secondary substructure, − on the subsoil, directly or through an improved subsoil layer. Reliable description of the interaction proceeding in a system “road construction – subsoil” should be in such case one of the basic requirements of the assessment of the size of internal forces of structure and its durability. Analyses of road constructions are based on: − elements of mechanics, which allows to create computational models, and − results of the experiments included in the criteria of fatigue life analyses. Above approach is a fundamental feature of commonly used mechanistic methods. They allow to use in the conducted evaluations of the fatigue life of structures arbitrarily complex numerical computational models. Considering the work of the system “road construction – subsoil”, it is commonly accepted that, as a result of repetitive loads on the subsoil under pavement, the growth of relatively small deformation in the initial phase is recognized, then this increase disappears, and the deformation takes the character completely reversible. The reliability of calculation model is combined with appropriate use (for a given type of analysis) of constitutive relationships. Phenomena occurring in the initial stage of the system “road construction – subsoil” is unfortunately difficult to interpret in the modeling process. The classic interpretation of the behavior of the material in the elastic-plastic model (e-p) is that elastic phase of the work (e) is undergoing to phase (e-p) by increasing the load (or growth of deformation in the damaging structure). The paper presents the essence of the calibration process of cooperating subsystem in the calculation model of the system “road construction – subsoil”, created for the mechanistic analysis. Calibration process was directed to show the impact of applied constitutive models on its deformation and stress response. The proper comparative base for assessing the reliability of created. This work was supported by the on-going research project “Stabilization of weak soil by application of layer of foamed concrete used in contact with subsoil” (LIDER/022/537/L-4/NCBR/2013) financed by The National Centre for Research and Development within the LIDER Programme. M. Kadela is with the Department of Building Construction Elements and Building Structures on Mining Areas, Building Research Institute, Silesian Branch, Katowice, Poland (phone: +48 32 730 29 47; fax: +48 32 730 25 22; e-mail: m.kadela@ itb.pl). models should be, however, the actual, monitored system “road construction – subsoil”. The paper presents too behavior of subsoil under cyclic load transmitted by pavement layers. The response of subsoil to cyclic load is recorded in situ by the observation system (sensors) installed on the testing ground prepared for this purpose, being a part of the test road near Katowice, in Poland. A different behavior of the homogeneous subsoil under pavement is observed for different seasons of the year, when pavement construction works as a flexible structure in summer, and as a rigid plate in winter. Albeit the observed character of subsoil response is the same regardless of the applied load and area values, this response can be divided into: - zone of indirect action of the applied load; this zone extends to the depth of 1,0 m under the pavement, - zone of a small strain, extending to about 2,0 m.

Keywords: road structure, constitutive model, calculation model, pavement, soil, FEA, response of soil, monitored system

Procedia PDF Downloads 357

Authors: Bing Chen, Xiang Ni, Eric Li

Abstract:

With the population ageing, the number of patients suffering from chronic diseases is increasing, among which stroke is a high incidence for the elderly. In addition, there is a gradual increase in the number of patients with orthopedic or neurological conditions such as spinal cord injuries, nerve injuries, and other knee injuries. These diseases are chronic, with high recurrence and complications, and normal walking is difficult for such patients. Nowadays, robotic knee exoskeletons have been developed for individuals with knee impairments. However, the currently available robotic knee exoskeletons are generally developed with heavyweight, which makes the patients uncomfortable to wear, prone to wearing fatigue, shortening the wearing time, and reducing the efficiency of exoskeletons. Some lightweight materials, such as carbon fiber and titanium alloy, have been used for the development of robotic knee exoskeletons. However, this increases the cost of the exoskeletons. This paper illustrates the design of a new ultra-light and ultra-stiff truss type of lattice structure. The lattice structures are arranged in a fan shape, which can fit well with circular arc surfaces such as circular holes, and it can be utilized in the design of rods, brackets, and other parts of a robotic knee exoskeleton to reduce the weight. The metamaterial is formed by continuous arrangement and combination of small truss structure unit cells, which changes the diameter of the pillar section, geometrical size, and relative density of each unit cell. It can be made quickly through additive manufacturing techniques such as metal 3D printing. The unit cell of the truss structure is small, and the machined parts of the robotic knee exoskeleton, such as connectors, rods, and bearing brackets, can be filled and replaced by gradient arrangement and non-uniform distribution. Under the condition of satisfying the mechanical properties of the robotic knee exoskeleton, the weight of the exoskeleton is reduced, and hence, the patient’s wearing fatigue is relaxed, and the wearing time of the exoskeleton is increased. Thus, the efficiency and wearing comfort, and safety of the exoskeleton can be improved. In this paper, a brief description of the hardware design of the prototype of the robotic knee exoskeleton is first presented. Next, the design of the ultra-light and ultra-stiff truss type of lattice structures is proposed, and the mechanical analysis of the single-cell unit is performed by establishing the theoretical model. Additionally, simulations are performed to evaluate the maximum stress-bearing capacity and compressive performance of the uniform arrangement and gradient arrangement of the cells. Finally, the static analysis is performed for the cell-filled rod and the unmodified rod, respectively, and the simulation results demonstrate the effectiveness and feasibility of the designed ultra-light and ultra-stiff truss type of lattice structures. In future studies, experiments will be conducted to further evaluate the performance of the designed lattice structures.

Keywords: additive manufacturing, lattice structures, metamaterial, robotic knee exoskeleton

Procedia PDF Downloads 107

Authors: Mbonigaba Swale

Abstract:

Malaria is an infection or disease caused by parasites (Plasmodium Falciparum — causes severe Malaria, plasmodium Vivax, Plasmodium Ovale, and Plasmodium Malariae), transmitted by bites of infected anopheles (female) mosquitoes to humans. These vectors comprise of two types in Africa, particularly in Uganda, i.e. anopheles fenestus and Anopheles gambaie (‘example Anopheles arabiensis,,); feeds on man inside the house mainly at dusk, mid-night and dawn and rests indoors and makes them effective transmitters (vectors) of the disease. People in both urban and rural areas have consistently become prone to repetitive attacks of malaria, causing a lot of deaths and significantly increasing the poverty levels of the rural poor. Malaria is a national problem; it causes a lot of maternal pre-natal and antenatal disorders, anemia in pregnant mothers, low birth weights for the newly born, convulsions and epilepsy among the infants. Cumulatively, it kills about one million children every year in sub-Saharan Africa. It has been estimated to account for 25-35% of all outpatient visits, 20-45% of acute hospital admissions and 15-35% of hospital deaths. Uganda is the leading victim country, for which Rakai and Masaka districts are the most affected. So, it is not clear whether these abhorrent situations and episodes of recurrences and failure to cure from the disease are a result of poor diagnosis, prescription and dosing, treatment habits and compliance of the patients to the drugs or the ethical domain of the stake holders in relation to the main stream methodology of malaria management. The research is aimed at offering an alternative approach to manage and deal absolutely with problem by using a knowledge based software model of Artificial Intelligence (Al) that is capable of performing common-sense and cognitive reasoning so as to take decisions like the human brain would do to provide instantaneous expert solutions so as to avoid speculative simulation of the problem during differential diagnosis in the most accurate and literal inferential aspect. This system will assist physicians in many kinds of medical diagnosis, prescribing treatments and doses, and in monitoring patient responses, basing on the body weight and age group of the patient, it will be able to provide instantaneous and timely information options, alternative ways and approaches to influence decision making during case analysis. The computerized system approach, a new model in Uganda termed as “Software Aided Treatment” (SAT) will try to change the moral and ethical approach and influence conduct so as to improve the skills, experience and values (social and ethical) in the administration and management of the disease and drugs (combination therapy and generics) by both the patient and the health worker.

Keywords: knowledge based software, management, treatment, diagnosis

Procedia PDF Downloads 57

Authors: Thomas Rockstuhl, Kok Yee Ng, Guido Gianasso, Soon Ang

Abstract:

Two meta-analyses show that intercultural experience is not related to intercultural adaptation or performance in international assignments. These findings have prompted calls for a deeper grounding of research on international experience in the phenomenon of global work. Two issues, in particular, may limit current understanding of the relationship between international experience and global work performance. First, intercultural experience is too broad a construct that may not sufficiently capture the essence of global work, which to a large part involves sensemaking and managing intercultural conflicts. Second, the psychological mechanisms through which intercultural experience affects performance remains under-explored, resulting in a poor understanding of how experience is translated into learning and performance outcomes. Drawing on recognition primed decision-making (RPD) research, the current study advances a cognitive processing model to highlight the importance of intercultural conflict familiarity. Compared to intercultural experience, intercultural conflict familiarity is a more targeted construct that captures individuals’ previous exposure to dealing with intercultural conflicts. Drawing on RPD theory, we argue that individuals’ intercultural conflict familiarity enhances their ability to make accurate judgments and generate effective responses when intercultural conflicts arise. In turn, the ability to make accurate situation judgements and effective situation responses is an important predictor of global work performance. A relocation program within a multinational enterprise provided the context to test these hypotheses using a time-lagged, multi-source field study. Participants were 165 employees (46% female; with an average of 5 years of global work experience) from 42 countries who relocated from country to regional offices as part a global restructuring program. Within the first two weeks of transfer to the regional office, employees completed measures of their familiarity with intercultural conflicts, cultural intelligence, cognitive ability, and demographic information. They also completed an intercultural situational judgment test (iSJT) to assess their situation judgment and situation response. The iSJT comprised four validated multimedia vignettes of challenging intercultural work conflicts and prompted employees to provide protocols of their situation judgment and situation response. Two research assistants, trained in intercultural management but blind to the study hypotheses, coded the quality of employee’s situation judgment and situation response. Three months later, supervisors rated employees’ global work performance. Results using multilevel modeling (vignettes nested within employees) support the hypotheses that greater familiarity with intercultural conflicts is positively associated with better situation judgment, and that situation judgment mediates the effect of intercultural familiarity on situation response quality. Also, aggregated situation judgment and situation response quality both predicted supervisor-rated global work performance. Theoretically, our findings highlight the important but under-explored role of familiarity with intercultural conflicts; a shift in attention from the general nature of international experience assessed in terms of number and length of overseas assignments. Also, our cognitive approach premised on RPD theory offers a new theoretical lens to understand the psychological mechanisms through which intercultural conflict familiarity affects global work performance. Third, and importantly, our study contributes to the global talent identification literature by demonstrating that the cognitive processes engaged in resolving intercultural conflicts predict actual performance in the global workplace.

Keywords: intercultural conflict familiarity, job performance, judgment and decision making, situational judgment test

Procedia PDF Downloads 179

Authors: Suhrita Saha

Abstract:

Barbie is a fashion doll manufactured by the American toy company Mattel Inc and it made debut at the American International Toy Fair in New York in 9 March 1959. From being a fashion doll to a symbol of fetishistic commodification, Barbie has come a long way. A Barbie doll is sold every three seconds across the world, which makes the billion dollar brand the world’s most popular doll for the girls. The 11.5 inch moulded plastic doll has a height of 5 feet 9 inches at 1/6 scale. Her vital statistics have been estimated at 36 inches (chest), 18 inches (waist) and 33 inches (hips). Her weight is permanently set at 110 pounds which would be 35 pounds underweight. Ruth Handler, the creator of Barbie wanted a doll that represented adulthood and allowed children to imagine themselves as teenagers or adults. While Barbie might have been intended to be independent, imaginative and innovative, the physical uniqueness does not confine the doll to the status of a play thing. It is a cultural icon but with far reaching critical implications. The doll is a commodity bearing more social value than practical use value. The way Barbie is produced represents industrialization and commodification of the process of symbolic production. And this symbolic production and consumption is a standardized planned one that produce stereotypical ‘pseudo-individuality’ and suppresses cultural alternatives. Children are being subject to and also arise as subjects in this consumer context. A very gendered, physiologically dissected sexually charged symbolism is imposed upon children (both male and female), childhood, their social worlds, identity, and relationship formation. Barbie is also very popular among Indian children. While the doll is essentially an imaginative representation of the West, it is internalized by the Indian sensibilities. Through observation and questionnaire-based interview within a sample population of adolescent children (primarily female, a few male) and parents (primarily mothers) in Kolkata, an Indian metropolis, the paper puts forth findings of sociological relevance. 1. Barbie creates, recreates, and accentuates already existing divides between the binaries like male- female, fat- thin, sexy- nonsexy, beauty- brain and more. 2. The Indian girl child in her associative process with Barbie wants to be like her and commodifies her own self. The male child also readily accepts this standardized commodification. Definition of beauty is thus based on prejudice and stereotype. 3. Not being able to become Barbie creates health issues both psychological and physiological varying from anorexia to obesity as well as personality disorder. 4. From being a plaything Barbie becomes the game maker. Barbie along with many other forms of simulation further creates a consumer culture and market for all kind of fitness related hyper enchantment and subsequent disillusionment. The construct becomes the reality and the real gets lost in the play world. The paper would thus argue that Barbie from being an innocuous doll transports itself into becoming social construct with long term and irreversible adverse impact.

Keywords: barbie, commodification, personality disorder, sterotype

Procedia PDF Downloads 365

Authors: Pauline Nyssen, Ange Mouithys-Mickalad, Maryse Hoebeke

Abstract:

Inflammation is a complex physiological phenomenon involving chemical and enzymatic mechanisms. Polymorphonuclear neutrophil leukocytes (PMNs) play an important role by producing reactive oxygen species (ROS) and releasing myeloperoxidase (MPO), a pro-oxidant enzyme. Released both in the phagolysosome and the extracellular medium, MPO produces during its peroxidase and halogenation cycles oxidant species, including hypochlorous acid, involved in the destruction of pathogen agents, like bacteria or viruses. Inflammatory pathologies, like rheumatoid arthritis, atherosclerosis induce an excessive stimulation of the PMNs and, therefore, an uncontrolled release of ROS and MPO in the extracellular medium, causing severe damages to the surrounding tissues and biomolecules such as proteins, lipids, and DNA. The treatment of chronic inflammatory pathologies remains a challenge. For many years, MPO has been used as a target for the development of effective treatments. Numerous studies have been focused on the design of new drugs presenting more efficient MPO inhibitory properties. However, some designed inhibitors can be toxic. An alternative consists of assessing the potential inhibitory action of clinically-known molecules, having antioxidant activity. Propofol, 2,6-diisopropyl phenol, which is used as an intravenous anesthetic agent, meets these requirements. Besides its anesthetic action employed to induce a sedative state during surgery or in intensive care units, propofol and its injectable form Diprivan indeed present antioxidant properties and act as ROS and free radical scavengers. A study has also evidenced the ability of propofol to inhibit the formation of the neutrophil extracellular traps fibers, which are important to trap pathogen microorganisms during the inflammation process. The aim of this study was to investigate the potential inhibitory action mechanism of propofol and Diprivan on MPO activity. To go into the anti-inflammatory action of propofol in-depth, two of its oxidative derivatives, 2,6-diisopropyl-1,4-p-benzoquinone (PPFQ) and 3,5,3’,5’-tetra isopropyl-(4,4’)-diphenoquinone (PPFDQ), were studied regarding their inhibitory action. Specific immunological extraction followed by enzyme detection (SIEFED) and molecular modeling have evidenced the low anti-catalytic action of propofol. Stopped-flow absorption spectroscopy and direct MPO activity analysis have proved that propofol acts as a reversible MPO inhibitor by interacting as a reductive substrate in the peroxidase cycle and promoting the accumulation of redox compound II. Overall, Diprivan exhibited a weaker inhibitory action than the active molecule propofol. In contrast, PPFQ seemed to bind and obstruct the enzyme active site, preventing the trigger of the MPO oxidant cycles. PPFQ induced a better chlorination cycle inhibition at basic and neutral pH in comparison to propofol. PPFDQ did not show any MPO inhibition activity. The three interest molecules have also demonstrated their inhibition ability on an important step of the inflammation pathway, the PMNs superoxide anions production, thanks to EPR spectroscopy and chemiluminescence. In conclusion, propofol presents an interesting immunomodulatory activity by acting as a reductive substrate in the peroxidase cycle of MPO, slowing down its activity, whereas PPFQ acts more as an anti-catalytic substrate. Although PPFDQ has no impact on MPO, it can act on the inflammation process by inhibiting the superoxide anions production by PMNs.

Keywords: Diprivan, inhibitor, myeloperoxidase, propofol, spectroscopy

Procedia PDF Downloads 149

Authors: Mike-Franck Mienlam Essi, Joseph Quentin Yene Atangana, Mbida Yem

Abstract:

The Kribi-Campo sub-basin belongs to the southern domain of the Cameroon Atlantic Margin in the Gulf of Guinea. It is the African homologous segment of the Sergipe-Alagoas Basin, located at the northeast side of the Brazil margin. The onset of the seafloor spreading period in the Southwest African Margin in general and the study area particularly remains controversial. Various studies locate this event during the Cretaceous times (Early Aptian to Late Albian), while others suggested that this event occurred during Pre-Cretaceous period (Palaeozoic or Jurassic). This work analyses 02 Cameroon Span seismic lines to re-examine the Early marine incursion period of the study area for a better understanding of the margin evolution. The methodology of analysis in this study is based on the delineation of the first seismic sequence, using the reflector’s terminations tracking and the analysis of its internal reflections associated to the external configuration of the package. The results obtained indicate from the bottom upwards that the first deposits overlie a first seismic horizon (H1) associated to “onlap” terminations at its top and underlie a second horizon which shows “Downlap” terminations at its top (H2). The external configuration of this package features a prograded fill pattern, and it is observed within the depocenter area with discontinuous reflections that pinch out against the basement. From east to west, this sequence shows two seismic facies (SF1 and SF2). SF1 has parallel to subparallel reflections, characterized by high amplitude, and SF2 shows parallel and stratified reflections, characterized by low amplitude. The distribution of these seismic facies reveals a lateral facies variation observed. According to the fundamentals works on seismic stratigraphy and the literature review of the geological context of the study area, particularly, the stratigraphical natures of the identified horizons and seismic facies have been highlighted. The seismic horizons H1 and H2 correspond to Top basement and “Downlap Surface,” respectively. SF1 indicates continental sediments (Sands/Sandstone) and SF2 marine deposits (shales, clays). Then, the prograding configuration observed suggests a marine regression. The correlation of these results with the lithochronostratigraphic chart of Sergipe-Alagoas Basin reveals that the first marine deposits through the study area are dated from Pre-Cretaceous times (Palaeozoic or Jurassic). The first deposits onto the basement represents the end of a cycle of sedimentation. The hypothesis of Mike.F. Mienlam Essi is with the Earth Sciences Department of the Faculty of Science of the University of Yaoundé I, P.O. BOX 812 CAMEROON (e-mail: [email protected]). Joseph.Q. Yene Atangana is with the Earth Sciences Department of the Faculty of Science of the University of Yaoundé I, P.O. BOX 812 CAMEROON (e-mail: [email protected]). Mbida Yem is with the Earth Sciences Department of the Faculty of Science of the University of Yaoundé I, P.O. BOX 812 CAMEROON (e-mail: [email protected]). Cretaceous seafloor spreading through the study area is the onset of another cycle of sedimentation. Furthermore, the presence of marine sediments into the first deposits implies that this package could contain marine source rocks. The spatial tracking of these deposits reveals that they could be found in some onshore parts of the Kribi-Campo area or even in the northern side.

Keywords: cameroon span seismic, early marine incursion, kribi-campo sub-basin, pre-cretaceous period, sergipe-alagoas basin

Procedia PDF Downloads 108

Authors: Hamid Reza Mahdipoor, Mehdi Bahrami, Mohammad Bodaghi, Seyed Ali Akbar Mansoori

Abstract:

Nowadays, with stricter limitations to reduce emissions, considerable penalties are imposed if pollution limits are exceeded. Therefore, refineries, along with focusing on improving the quality of their products, are also focused on producing products with the least environmental impact. The duty of the sulfur recovery unit (SRU) is to convert H₂S gas coming from the upstream units to elemental sulfur and minimize the burning of sulfur compounds to SO₂. The Claus process is a common process for converting H₂S to sulfur, including a reaction furnace followed by catalytic reactors and sulfur condensers. In addition to a Claus section, SRUs usually consist of a tail gas treatment (TGT) section to decrease the concentration of SO₂ in the flue gas below the emission limits. To operate an SRU properly, the flow rate of combustion air to the reaction furnace must be adjusted so that the Claus reaction is performed according to stoichiometry. Accurate control of the air demand leads to an optimum recovery of sulfur during the flow and composition fluctuations in the acid gas feed. Therefore, the major control system in the SRU is the air demand control loop, which includes a feed-forward control system based on predetermined feed flow rates and a feed-back control system based on the signal from the tail gas online analyzer. The use of online analyzers requires compliance with the installation and operation instructions. Unfortunately, most of these analyzers in Iran are out of service for different reasons, like the low importance of environmental issues and a lack of access to after-sales services due to sanctions. In this paper, an SRU in Iran was simulated and calibrated using industrial experimental data. Afterward, the effect of the malfunction of the online analyzer on the performance of SRU was investigated using the calibrated simulation. The results showed that an increase in the SO₂ concentration in the tail gas led to an increase in the temperature of the reduction reactor in the TGT section. This increase in temperature caused the failure of TGT and increased the concentration of SO₂ from 750 ppm to 35,000 ppm. In addition, the lack of a control system for the adjustment of the combustion air caused further increases in SO₂ emissions. In some processes, the major variable cannot be controlled directly due to difficulty in measurement or a long delay in the sampling system. In these cases, a secondary variable, which can be measured more easily, is considered to be controlled. With the correct selection of this variable, the main variable is also controlled along with the secondary variable. This strategy for controlling a process system is referred to as inferential control" and is considered in this paper. Therefore, a sensitivity analysis was performed to investigate the sensitivity of other measurable parameters to input disturbances. The results revealed that the output temperature of the first Claus reactor could be used for inferential control of the combustion air. Applying this method to the operation led to maximizing the sulfur recovery in the Claus section.

Keywords: sulfur recovery, online analyzer, inferential control, SO₂ emission

Procedia PDF Downloads 76

Authors: Maryam Ziaee

Abstract:

This research proposes a new approach and provides an opportunity for manufacturing companies to produce large amounts of products that meet their prospective customers’ tastes, needs, and expectations and simultaneously enable manufacturers to increase their profit. Mass customization is the production of products or services to meet each individual customer’s desires to the greatest possible extent in high quantities and at reasonable prices. This process takes place at different levels such as the customization of goods’ design, assembly, sale, and delivery status, and classifies in several categories. The main focus of this study is on one class of mass customization, called optional customization, in which companies try to provide their customers with as many options as possible to customize their products. These options could range from the design phase to the manufacturing phase, or even methods of delivery. Mass customization values customers’ tastes, but it is only one side of clients’ satisfaction; on the other side is companies’ fast responsiveness delivery. It brings the concept of agility, which is the ability of a company to respond rapidly to changes in volatile markets in terms of volume and variety. Indeed, mass customization is not effectively feasible without integrating the concept of agility. To gain the customers’ satisfaction, the companies need to be quick in responding to their customers’ demands, thus highlighting the significance of agility. This research offers a different method that successfully integrates mass customization and fast production in manufacturing industries. This research is built upon the hypothesis that the success key to being agile in mass customization is to forecast demand, cooperate with suppliers, and control inventory. Therefore, the significance of the supply chain (SC) is more pertinent when it comes to this stage. Since SC behavior is dynamic and its behavior changes constantly, companies have to apply one of the predicting techniques to identify the changes associated with SC behavior to be able to respond properly to any unwelcome events. System dynamics utilized in this research is a simulation approach to provide a mathematical model among different variables to understand, control, and forecast SC behavior. The final stage is delayed differentiation, the production strategy considered in this research. In this approach, the main platform of products is produced and stocked and when the company receives an order from a customer, a specific customized feature is assigned to this platform and the customized products will be created. The main research question is to what extent applying system dynamics for the prediction of SC behavior improves the agility of mass customization. This research is built upon a qualitative approach to bring about richer, deeper, and more revealing results. The data is collected through interviews and is analyzed through NVivo software. This proposed model offers numerous benefits such as reduction in the number of product inventories and their storage costs, improvement in the resilience of companies’ responses to their clients’ needs and tastes, the increase of profits, and the optimization of productivity with the minimum level of lost sales.

Keywords: agility, manufacturing, resilience, supply chain

Procedia PDF Downloads 91

Authors: Abderrhamane Jarou, Dominique Sauter, Christophe Aubrun

Abstract:

Over the past decade, the growing demand for energy efficiency in buildings has attracted the attention of the control community. Failures in HVAC (heating, ventilation and air conditioning) systems in buildings can have a significant impact on the desired and expected energy performance of buildings and on the user's comfort as well. FTC is a recent technology area that studies the adaptation of control algorithms to faulty operating conditions of a system. The application of Fault-Tolerant Control (FTC) in HVAC systems has gained attention in the last two decades. The objective is to maintain the variations in system performance due to faults within an acceptable range with respect to the desired nominal behavior. This paper considers the so-called active approach, which is based on fault and identification scheme combined with a control reconfiguration algorithm that consists in determining a new set of control parameters so that the reconfigured performance is "as close as possible, "in some sense, to the nominal performance. Thermal models of buildings and their HVAC systems are described by non-linear (usually bi-linear) equations. Most of the works carried out so far in FDI (fault diagnosis and isolation) or FTC consider a linearized model of the studied system. However, this model is only valid in a reduced range of variation. This study presents a new fault diagnosis (FD) algorithm based on a bilinear observer for the detection and accurate estimation of the magnitude of the HVAC system failure. The main contribution of the proposed FD algorithm is that instead of using specific linearized models, the algorithm inherits the structure of the actual bilinear model of the building thermal dynamics. As an immediate consequence, the algorithm is applicable to a wide range of unpredictable operating conditions, i.e., weather dynamics, outdoor air temperature, zone occupancy profile. A bilinear fault detection observer is proposed for a bilinear system with unknown inputs. The residual vector in the observer design is decoupled from the unknown inputs and, under certain conditions, is made sensitive to all faults. Sufficient conditions are given for the existence of the observer and results are given for the explicit computation of observer design matrices. Dedicated observer schemes (DOS) are considered for sensor FDI while unknown input bilinear observers are considered for actuator or system components FDI. The proposed strategy for FTC works as follows: At a first level, FDI algorithms are implemented, making it also possible to estimate the magnitude of the fault. Once the fault is detected, the fault estimation is then used to feed the second level and reconfigure the control low so that that expected performances are recovered. This paper is organized as follows. A general structure for fault-tolerant control of buildings is first presented and the building model under consideration is introduced. Then, the observer-based design for Fault Diagnosis of bilinear systems is studied. The FTC approach is developed in Section IV. Finally, a simulation example is given in Section V to illustrate the proposed method.

Keywords: bilinear systems, fault diagnosis, fault-tolerant control, multi-zones building

Procedia PDF Downloads 173

Authors: Ali Reza Vaezi, Naser Fakori Ivand, Fereshteh Azarifam

Abstract:

Interrill erosion is the detachment and transfer of soil particles between the rills due to the impact of raindrops and the shear stress of shallow surface runoff. This erosion can be affected by some soil properties such as texture, amount of organic matter and stability of soil aggregates. Information on the temporal variation of interrill erosion during a rainfall event and the effect soil properties have on it can help in understanding the process of runoff production and soil loss between the rills in hillslopes. The importance of this study is especially grate in semi-arid regions, where the soil is weakly aggregated and vegetation cover is mostly poor. Therefore, this research was conducted to investigate the temporal variation of surface flow and interrill erosion and the effect of soil properties on it in some semi-arid soils. A field experiment was done in eight different soil textures under simulated rainfalls with uniform intensity. A total of twenty four plots were installed for eight study soils with three replicates in the form of a random complete block design along the land. The plots were 1.2 m (length) × 1 m (width) in dimensions which designed with a distance of 3 m from each other across the slope. Then, soil samples were purred into the plots. The plots were surrounded by a galvanized sheet, and runoff and soil erosion equipment were placed at their outlets. Rainfall simulation experiments were done using a designed portable simulator with an intensity of 60 mm per hour for 60 minutes. A plastic cover was used around the rainfall simulator frame to prevent the impact of the wind on the free fall of water drops. Runoff production and soil loss were measured during 1 hour time with 5-min intervals. In order to study soil properties, such as particle size distribution, aggregate stability, bulk density, ESP and Ks were determined in the laboratory. Correlation and regression analysis was done to determine the effect of soil properties on runoff and interrill erosion. Results indicated that the study soils have lower booth organic matter content and aggregate stability. The soils, except for coarse textured textures, are calcareous and with relatively higher exchangeable sodium percentages (ESP). Runoff production and soil loss didn’t occur in sand, which was associated with higher infiltration and drainage rates. In other study soils, interrill erosion occurred simultaneously with the generation of runoff. A strong relationship was found between interrill erosion and surface runoff (R2 = 0.75, p< 0.01). The correlation analysis showed that surface runoff was significantly affected by some soil properties consisting of sand, silt, clay, bulk density, gravel, hydraulic conductivity (Ks), lime (calcium carbonate), and ESP. The soils with lower Ks such as fine-textured soils, produced higher surface runoff and more interrill erosion. In the soils, Surface runoff production temporally increased during rainfall and finally reached a peak after about 25-35 min. Time to peak was very short (30 min) in fine-textured soils, especially clay, which was related to their lower infiltration rate.

Keywords: erosion plot, rainfall simulator, soil properties, surface flow

Procedia PDF Downloads 69

Authors: Hamda Ajmal, Karen Young, Ruth Melia, John Bogue, Mary O'Sullivan, Jim Duggan, Hannah Wood

Abstract:

The Covid-19 pandemic led to a range of public health mitigation strategies in order to suppress the SARS-CoV-2 virus. The drastic changes in everyday life due to lockdowns had the potential for a significant negative impact on public mental health, and a key public health goal is to now assess the evidence from available Irish datasets to provide useful insights on this issue. Text-50808 is an online text-based mental health support service, established in Ireland in 2020, and can provide a measure of revealed distress and mental health concerns across the population. The aim of this study is to explore statistical associations between public mental health in Ireland and the Covid-19 pandemic. Uniquely, this study combines two measures of emotional wellbeing in Ireland: (1) weekly text volume at Text-50808, and (2) emotional wellbeing indicators reported by respondents of the Amárach public opinion survey, carried out on behalf of the Department of Health, Ireland. For this analysis, a multivariate graphical exploratory data analysis (EDA) was performed on the Text-50808 dataset dated from 15th June 2020 to 30th June 2021. This was followed by time-series analysis of key mental health indicators including: (1) the percentage of daily/weekly texts at Text-50808 that mention Covid-19 related issues; (2) the weekly percentage of people experiencing anxiety, boredom, enjoyment, happiness, worry, fear and stress in Amárach survey; and Covid-19 related factors: (3) daily new Covid-19 case numbers; (4) daily stringency index capturing the effect of government non-pharmaceutical interventions (NPIs) in Ireland. The cross-correlation function was applied to measure the relationship between the different time series. EDA of the Text-50808 dataset reveals significant peaks in the volume of texts on days prior to level 3 lockdown and level 5 lockdown in October 2020, and full level 5 lockdown in December 2020. A significantly high positive correlation was observed between the percentage of texts at Text-50808 that reported Covid-19 related issues and the percentage of respondents experiencing anxiety, worry and boredom (at a lag of 1 week) in Amárach survey data. There is a significant negative correlation between percentage of texts with Covid-19 related issues and percentage of respondents experiencing happiness in Amárach survey. Daily percentage of texts at Text-50808 that reported Covid-19 related issues to have a weak positive correlation with daily new Covid-19 cases in Ireland at a lag of 10 days and with daily stringency index of NPIs in Ireland at a lag of 2 days. The sudden peaks in text volume at Text-50808 immediately prior to new restrictions in Ireland indicate an association between a rise in mental health concerns following the announcement of new restrictions. There is also a high correlation between emotional wellbeing variables in the Amárach dataset and the number of weekly texts at Text-50808, and this confirms that Text-50808 reflects overall public sentiment. This analysis confirms the benefits of the texting service as a community surveillance tool for mental health in the population. This initial EDA will be extended to use multivariate modeling to predict the effect of additional Covid-19 related factors on public mental health in Ireland.

Keywords: COVID-19 pandemic, data analysis, digital health, mental health, public health, digital health

Procedia PDF Downloads 144

Authors: Domenico Carmelo Mongelli

Abstract:

The context of this research is that of the Italian reality, which, in order to adapt to the EU Directives that prohibit the production of internal combustion engines in favor of electric mobility from 2035, is extremely concerned about the significant loss of jobs resulting from the difficulty of the automotive industry in converting in such a short time and due to the reticence of potential buyers in the face of such an epochal change. The aim of the research is to evaluate for Italy the potential of the most valid alternative to this transition to electric: leaving the current production of diesel engines unchanged, no longer powered by gasoil, imported and responsible for greenhouse gas emissions, but powered entirely by a nationally produced and eco-sustainable fuel such as biodiesel. Today in Italy, the percentage of biodiesel mixed with gasoil for diesel engines is too low (around 10%); for this reason, this research aims to evaluate the functioning of current diesel engines powered 100% by biodiesel and the ability of the Italian production system to cope to this hypothesis. The research geographically identifies those abandoned lands in Italy, now out of the food market, which is best suited to an energy crop for the final production of biodiesel. The cultivation of oilseeds is identified, which for the Italian agro-industrial reality allows maximizing the agricultural and industrial yields of the transformation of the agricultural product into a final energy product and minimizing the production costs of the entire agro-industrial chain. To achieve this objective, specific databases are used, and energy and economic balances are prepared for the different agricultural product alternatives. Solutions are proposed and tested that allow the optimization of all production phases in both the agronomic and industrial phases. The biodiesel obtained from the most feasible of the alternatives examined is analyzed, and its compatibility with current diesel engines is identified, and from the evaluation of its thermo-fluid-dynamic properties, the engineering measures that allow the perfect functioning of current internal combustion engines are examined. The results deriving from experimental tests on the engine bench are evaluated to evaluate the performance of different engines fueled with biodiesel alone in terms of power, torque, specific consumption and useful thermal efficiency and compared with the performance of engines fueled with the current mixture of fuel on the market. The results deriving from experimental tests on the engine bench are evaluated to evaluate the polluting emissions of engines powered only by biodiesel and compared with current emissions. At this point, we proceed with the simulation of the total replacement of gasoil with biodiesel as a fuel for the current fleet of diesel vehicles in Italy, drawing the necessary conclusions in technological, energy, economic, and environmental terms and in terms of social and employment implications. The results allow us to evaluate the potential advantage of a total replacement of diesel fuel with biodiesel for powering road vehicles with diesel cycle internal combustion engines without significant changes to the current vehicle fleet and without requiring future changes to the automotive industry.

Keywords: biodiesel, economy, engines, environment

Procedia PDF Downloads 75

Authors: Ali R. Alshawawreh, Francisco Liébana-Cabanillas, Francisco J. Blanco-Encomienda

Abstract:

Collaboration between marketing and business intelligence (BI) is crucial in today's ever-evolving business landscape. These two domains play pivotal roles in molding customers' experiential knowledge. Marketing insights offer valuable information regarding customer needs, preferences, and behaviors. Conversely, BI facilitates data-driven decision-making, leading to heightened operational efficiency, product quality, and customer satisfaction. Customer experiential knowledge (CEK) encompasses customers' implicit comprehension of consumption experiences influenced by diverse factors, including social and cultural influences. This study primarily focuses on telecommunications companies in Jordan, scrutinizing how experiential customer knowledge mediates the relationship between marketing intelligence and business intelligence. Drawing on theoretical frameworks such as the resource-based view (RBV) and service-dominant logic (SDL), the research aims to comprehend how organizations utilize their resources, particularly knowledge, to foster Evolution. Employing a quantitative research approach, the study collected and analyzed primary data to explore hypotheses. Structural equation modeling (SEM) facilitated by Smart PLS software evaluated the relationships between the constructs, followed by mediation analysis to assess the indirect associations in the model. The study findings offer insights into the intricate dynamics of organizational Creation, uncovering the interconnected relationships between business intelligence, customer experiential knowledge-based innovation (CEK-DI), marketing intelligence (MI), and product and service innovation (PSI), underscoring the pivotal role of advanced intelligence capabilities in developing innovative practices rooted in a profound understanding of customer experiences. Furthermore, the positive impact of BI on PSI reaffirms the significance of data-driven decision-making in shaping the innovation landscape. The significant impact of CEK-DI on PSI highlights the critical role of customer experiences in driving an organization. Companies that actively integrate customer insights into their opportunity creation processes are more likely to create offerings that match customer expectations, which drives higher levels of product and service sophistication. Additionally, the positive and significant impact of MI on CEK-DI underscores the critical role of market insights in shaping evolutionary strategies. While the relationship between MI and PSI is positive, the slightly weaker significance level indicates a subtle association, suggesting that while MI contributes to the development of ideas, In conclusion, the study emphasizes the fundamental role of intelligence capabilities, especially artificial intelligence, emphasizing the need for organizations to leverage market and customer intelligence to achieve effective and competitive innovation practices. Collaborative efforts between marketing and business intelligence serve as pivotal drivers of development, influencing customer experiential knowledge and shaping organizational strategies and practices. Future research could adopt longitudinal designs and gather data from various sectors to offer broader insights. Additionally, the study focuses on the effects of marketing intelligence, business intelligence, customer experiential knowledge, and innovation, but other unexamined variables may also influence innovation processes. Future studies could investigate additional factors, mediators, or moderators, including the role of emerging technologies like AI and machine learning in driving innovation.

Keywords: marketing intelligence, business intelligence, product, customer experiential knowledge-driven innovation

Procedia PDF Downloads 35

Authors: Olga Hernán-Vega, Patricia López-Rodríguez, David Escot-Bocanegra, Raúl Fernández-Recio, Ignacio Bravo

Abstract:

Non-Cooperative Target Identification has become a key research domain in the Defense industry since it provides the ability to recognize targets at long distance and under any weather condition. High Resolution Range Profiles, one-dimensional radar images where the reflectivity of a target is projected onto the radar line of sight, are widely used for identification of flying targets. According to that, to face this problem, an approach to Non-Cooperative Target Identification based on the exploitation of Singular Value Decomposition to a matrix of range profiles is presented. Target Identification based on one-dimensional radar images compares a collection of profiles of a given target, namely test set, with the profiles included in a pre-loaded database, namely training set. The classification is improved by using Singular Value Decomposition since it allows to model each aircraft as a subspace and to accomplish recognition in a transformed domain where the main features are easier to extract hence, reducing unwanted information such as noise. Singular Value Decomposition permits to define a signal subspace which contain the highest percentage of the energy, and a noise subspace which will be discarded. This way, only the valuable information of each target is used in the recognition process. The identification algorithm is based on finding the target that minimizes the angle between subspaces and takes place in a transformed domain. Two metrics, F1 and F2, based on Singular Value Decomposition are accomplished in the identification process. In the case of F2, the angle is weighted, since the top vectors set the importance in the contribution to the formation of a target signal, on the contrary F1 simply shows the evolution of the unweighted angle. In order to have a wide database or radar signatures and evaluate the performance, range profiles are obtained through numerical simulation of seven civil aircraft at defined trajectories taken from an actual measurement. Taking into account the nature of the datasets, the main drawback of using simulated profiles instead of actual measured profiles is that the former implies an ideal identification scenario, since measured profiles suffer from noise, clutter and other unwanted information and simulated profiles don't. In this case, the test and training samples have similar nature and usually a similar high signal-to-noise ratio, so as to assess the feasibility of the approach, the addition of noise has been considered before the creation of the test set. The identification results applying the unweighted and weighted metrics are analysed for demonstrating which algorithm provides the best robustness against noise in an actual possible scenario. So as to confirm the validity of the methodology, identification experiments of profiles coming from electromagnetic simulations are conducted, revealing promising results. Considering the dissimilarities between the test and training sets when noise is added, the recognition performance has been improved when weighting is applied. Future experiments with larger sets are expected to be conducted with the aim of finally using actual profiles as test sets in a real hostile situation.

Keywords: HRRP, NCTI, simulated/synthetic database, SVD

Procedia PDF Downloads 354

Authors: Ayon Mukherjee

Abstract:

Covariate-adjusted response-adaptive (CARA) designs use the available responses to skew the treatment allocation in a clinical trial in towards treatment found at an interim stage to be best for a given patient's covariate profile. Extensive research has been done on various aspects of CARA designs with the patient responses assumed to follow a parametric model. However, ranges of application for such designs are limited in real-life clinical trials where the responses infrequently fit a certain parametric form. On the other hand, robust estimates for the covariate-adjusted treatment effects are obtained from the parametric assumption. To balance these two requirements, designs are developed which are free from distributional assumptions about the survival responses, relying only on the assumption of proportional hazards for the two treatment arms. The proposed designs are developed by deriving two types of optimum allocation designs, and also by using a distribution function to link the past allocation, covariate and response histories to the present allocation. The optimal designs are based on biased coin procedures, with a bias towards the better treatment arm. These are the doubly-adaptive biased coin design (DBCD) and the efficient randomized adaptive design (ERADE). The treatment allocation proportions for these designs converge to the expected target values, which are functions of the Cox regression coefficients that are estimated sequentially. These expected target values are derived based on constrained optimization problems and are updated as information accrues with sequential arrival of patients. The design based on the link function is derived using the distribution function of a probit model whose parameters are adjusted based on the covariate profile of the incoming patient. To apply such designs, the treatment allocation probabilities are sequentially modified based on the treatment allocation history, response history, previous patients’ covariates and also the covariates of the incoming patient. Given these information, an expression is obtained for the conditional probability of a patient allocation to a treatment arm. Based on simulation studies, it is found that the ERADE is preferable to the DBCD when the main aim is to minimize the variance of the observed allocation proportion and to maximize the power of the Wald test for a treatment difference. However, the former procedure being discrete tends to be slower in converging towards the expected target allocation proportion. The link function based design achieves the highest skewness of patient allocation to the best treatment arm and thus ethically is the best design. Other comparative merits of the proposed designs have been highlighted and their preferred areas of application are discussed. It is concluded that the proposed CARA designs can be considered as suitable alternatives to the traditional balanced randomization designs in survival trials in terms of the power of the Wald test, provided that response data are available during the recruitment phase of the trial to enable adaptations to the designs. Moreover, the proposed designs enable more patients to get treated with the better treatment during the trial thus making the designs more ethically attractive to the patients. An existing clinical trial has been redesigned using these methods.

Keywords: censored response, Cox regression, efficiency, ethics, optimal allocation, power, variability

Procedia PDF Downloads 165

Authors: Wiam El Kheir, Anais Dumais, Maude Beaudoin, Bernard Marcos, Nick Virgilio, Benoit Paquette, Nathalie Faucheux, Marc-Antoine Lauzon

Abstract:

The high infiltrative pattern of glioblastoma multiforme cells (GBM) is the main cause responsible for the actual standard treatments failure. The tumor high heterogeneity, the interstitial fluid flow (IFF) and chemokines guides GBM cells migration in the brain parenchyma resulting in tumor recurrence. Drug delivery systems emerged as an alternative approach to develop effective treatments for the disease. Some recent studies have proposed to harness the effect CXC-lchemokine-ligand-12 to direct and control the cancer cell migration through delivery system. However, the dynamics of the brain environment on the delivery system remains poorly understood. Nanoparticles (NPs) and hydrogels are known as good carriers for the encapsulation of different agents and control their release. We studied the release of CXCL12 (free or loaded into NPs) from an alginate-based hydrogel under static and indirect perfusion (IP) conditions. Under static conditions, the main phenomena driving CXCL12 release from the hydrogel was diffusion with the presence of strong interactions between the positively charged CXCL12 and the negatively charge alginate. CXCL12 release profiles were independent from the initial mass loadings. Afterwards, we demonstrated that the release could tuned by loading CXCL12 into Alginate/Chitosan-Nanoparticles (Alg/Chit-NPs) and embedded them into alginate-hydrogel. The initial burst release was substantially attenuated and the overall cumulative release percentages of 21%, 16% and 7% were observed for initial mass loadings of 0.07, 0.13 and 0.26 µg, respectively, suggesting stronger electrostatic interactions. Results were mathematically modeled based on Fick’s second law of diffusion framework developed previously to estimate the effective diffusion coefficient (Deff) and the mass transfer coefficient. Embedding the CXCL12 into NPs decreased the Deff an order of magnitude, which was coherent with experimental data. Thereafter, we developed an in-vitro 3D model that takes into consideration the convective contribution of the brain IFF to study CXCL12 release in an in-vitro microenvironment that mimics as faithfully as possible the human brain. From is unique design, the model also allowed us to understand the effect of IP on CXCL12 release in respect to time and space. Four flow rates (0.5, 3, 6.5 and 10 µL/min) which may increase CXCL12 release in-vivo depending on the tumor location were assessed. Under IP, cumulative percentages varying between 4.5-7.3%, 23-58.5%, 77.8-92.5% and 89.2-95.9% were released for the three initial mass loadings of 0.08, 0.16 and 0.33 µg, respectively. As the flow rate increase, IP culture conditions resulted in a higher release of CXCL12 compared to static conditions as the convection contribution became the main driving mass transport phenomena. Further, depending on the flow rate, IP had a direct impact on CXCL12 distribution within the simulated brain tissue, which illustrates the importance of developing such 3D in-vitro models to assess the efficiency of a delivery system targeting the brain. In future work, using this very model, we aim to understand the impact of the different phenomenon occurring on GBM cell behaviors in response to the resulting chemokine gradient subjected to various flow while allowing them to express their invasive characteristics in an in-vitro microenvironment that mimics the in-vivo brain parenchyma.

Keywords: 3D culture system, chemokines gradient, glioblastoma multiforme, kinetic release, mathematical modeling

Procedia PDF Downloads 85

Authors: Susmita Ghosh

Abstract:

Catchment area of Damodar River, India experiences seasonal rains due to the south-west monsoon every year and depending upon the intensity of the storms, floods occur. During the monsoon season, the rainfall in the area is mainly due to active monsoon conditions. The upstream reach of Damodar river system has five dams store the water for utilization for various purposes viz, irrigation, hydro-power generation, municipal supplies and last but not the least flood moderation. But, in the downstream reach of Damodar River, known as Lower Damodar region, is severely and frequently suffering from flood due to heavy monsoon rainfall and also release from upstream reservoirs. Therefore, an effective flood management study is required to know in depth the nature and extent of flood, water logging, and erosion related problems, affected area, and damages in the Lower Damodar region, by conducting mathematical model study. The design flood or discharge is needed to decide to assign the respective model for getting several scenarios from the simulation runs. The ultimate aim is to achieve a sustainable flood management scheme from the several alternatives. there are various methods for estimating flood discharges to be carried through the rivers and their tributaries for quick drainage from inundated areas due to drainage congestion and excess rainfall. In the present study, the flood frequency analysis is performed to decide the design flood discharge of the study area. This, on the other hand, has limitations in respect of availability of long peak flood data record for determining long type of probability density function correctly. If sufficient past records are available, the maximum flood on a river with a given frequency can safely be determined. The floods of different frequency for the Damodar has been calculated by five candidate distributions i.e., generalized extreme value, extreme value-I, Pearson type III, Log Pearson and normal. Annual peak discharge series are available at Durgapur barrage for the period of 1979 to 2013 (35 years). The available series are subjected to frequency analysis. The primary objective of the flood frequency analysis is to relate the magnitude of extreme events to their frequencies of occurrence through the use of probability distributions. The design flood for return periods of 10, 15 and 25 years return period at Durgapur barrage are estimated by flood frequency method. It is necessary to develop flood hydrographs for the above floods to facilitate the mathematical model studies to find the depth and extent of inundation etc. Null hypothesis that the distributions fit the data at 95% confidence is checked with goodness of fit test, i.e., Chi Square Test. It is revealed from the goodness of fit test that the all five distributions do show a good fit on the sample population and is therefore accepted. However, it is seen that there is considerable variation in the estimation of frequency flood. It is therefore considered prudent to average out the results of these five distributions for required frequencies. The inundated area from past data is well matched using this flood.

Keywords: design discharge, flood frequency, goodness of fit, sustainable flood management

Procedia PDF Downloads 203

Authors: Anwar Beg, Sireetorn Kuharat, Rashid Mehmood, Rabil Tabassum, Meisam Babaie

Abstract:

Nano-polymeric solar paints and sol-gels have emerged as a major new development in solar cell/collector coatings offering significant improvements in durability, anti-corrosion and thermal efficiency. They also exhibit substantial viscosity variation with temperature which can be exploited in solar collector designs. Modern manufacturing processes for such nano-rheological materials frequently employ stagnation flow dynamics under high temperature which invokes radiative heat transfer. Motivated by elaborating in further detail the nanoscale heat, mass and momentum characteristics of such sol gels, the present article presents a mathematical and computational study of the steady, two-dimensional, non-aligned thermo-fluid boundary layer transport of copper metal-doped water-based nano-polymeric sol gels under radiative heat flux. To simulate real nano-polymer boundary interface dynamics, thermal slip is analysed at the wall. A temperature-dependent viscosity is also considered. The Tiwari-Das nanofluid model is deployed which features a volume fraction for the nanoparticle concentration. This approach also features a Maxwell-Garnet model for the nanofluid thermal conductivity. The conservation equations for mass, normal and tangential momentum and energy (heat) are normalized via appropriate transformations to generate a multi-degree, ordinary differential, non-linear, coupled boundary value problem. Numerical solutions are obtained via the stable, efficient Runge-Kutta-Fehlberg scheme with shooting quadrature in MATLAB symbolic software. Validation of solutions is achieved with a Variational Iterative Method (VIM) utilizing Langrangian multipliers. The impact of key emerging dimensionless parameters i.e. obliqueness parameter, radiation-conduction Rosseland number (Rd), thermal slip parameter (α), viscosity parameter (m), nanoparticles volume fraction (ϕ) on non-dimensional normal and tangential velocity components, temperature, wall shear stress, local heat flux and streamline distributions is visualized graphically. Shear stress and temperature are boosted with increasing radiative effect whereas local heat flux is reduced. Increasing wall thermal slip parameter depletes temperatures. With greater volume fraction of copper nanoparticles temperature and thermal boundary layer thickness is elevated. Streamlines are found to be skewed markedly towards the left with positive obliqueness parameter.

Keywords: non-orthogonal stagnation-point heat transfer, solar nano-polymer coating, MATLAB numerical quadrature, Variational Iterative Method (VIM)

Procedia PDF Downloads 136

Authors: Atefeh Omidkhah Kharashtomi, Rasoul Hedayat Nejad, Saeed Bakhtiyari

Abstract:

Circulation paths and indoor connection network of the building play an important role both in the daily operation of the building and during evacuation in emergency situations. The degree of legibility of the paths for navigation inside the building has a deep connection with the perceptive and cognitive system of human, and the way the surrounding environment is being perceived. Human perception of the space is based on the sensory systems in a three-dimensional environment, and non-linearly, so it is necessary to avoid reducing its representations in architectural design as a two-dimensional and linear issue. Today, the advances in the field of virtual reality (VR) technology have led to various applications, and architecture and building science can benefit greatly from these capabilities. Especially in cases where the design solution requires a detailed and complete understanding of the human perception of the environment and the behavioral response, special attention to VR technologies could be a priority. Way-finding in the indoor circulation network is a proper example for such application. Success in way-finding could be achieved if human perception of the route and the behavioral reaction have been considered in advance and reflected in the architectural design. This paper discusses the VR technology applications for the way-finding improvements in indoor engineering of the building. In a systematic review, with a database consisting of numerous studies, firstly, four categories for VR applications for circulation way-finding have been identified: 1) data collection of key parameters, 2) comparison of the effect of each parameter in virtual environment versus real world (in order to improve the design), 3) comparing experiment results in the application of different VR devices/ methods with each other or with the results of building simulation, and 4) training and planning. Since the costs of technical equipment and knowledge required to use VR tools lead to the limitation of its use for all design projects, priority buildings for the use of VR during design are introduced based on case-studies analysis. The results indicate that VR technology provides opportunities for designers to solve complex buildings design challenges in an effective and efficient manner. Then environmental parameters and the architecture of the circulation routes (indicators such as route configuration, topology, signs, structural and non-structural components, etc.) and the characteristics of each (metrics such as dimensions, proportions, color, transparency, texture, etc.) are classified for the VR way-finding experiments. Then, according to human behavior and reaction in the movement-related issues, the necessity of scenario-based and experiment design for using VR technology to improve the design and receive feedback from the test participants has been described. The parameters related to the scenario design are presented in a flowchart in the form of test design, data determination and interpretation, recording results, analysis, errors, validation and reporting. Also, the experiment environment design is discussed for equipment selection according to the scenario, parameters under study as well as creating the sense of illusion in the terms of place illusion, plausibility and illusion of body ownership.

Keywords: virtual reality (VR), way-finding, indoor, circulation, design

Procedia PDF Downloads 75

Authors: Linmin Zhang

Abstract:

Entrained-flow gasification technology is considered the most promising gasification technology because of its clean and efficient utilization characteristics. The stable fluidity of slag at high temperatures is the key to affecting the long-period operation of the gasifier. The diversity and differences of coal ash-slag systems make it difficult to meet the requirements for stable slagging in entrained-flow gasifiers. Therefore, coal blending or adding fluxes has been used in industry for a long time to improve the flow behavior of coal ash. As a by-product of the indirect coal liquefaction process, indirect coal liquefaction residue (ICLR) is a kind of industrial solid waste that is usually disposed of by stacking or landfilling. However, this disposal method will not only occupy land resources but also cause serious pollution to soil and water bodies by leachate containing toxic and harmful metals. As a carbon-containing matrix, ICLR is not only a kind of waste but also a kind of energy substance. Utilizing existing industrial gasifiers to blend combustion ICLR can not only transform industrial solid waste into fuel but also save coal resources. Moreover, the ICLR usually contains a unique ash chemical composition different from coal, which will affect the slagging performance of the gasifier. Therefore, exploring the effect of the ash addition in ICLR on the coal ash flow behavior can not only improve the slagging performance and gasification efficiency of entrained-flow gasifier by using the unique ash chemical composition of ICLR but also provide some theoretical support for the large-scale consumption of industrial solid waste. Combining molecular dynamics simulation with Raman spectroscopy experiment, the effect of ICLR addition on slag structure and fluidity was explained, and the relationship between the evolution law of slag short/medium range microstructure and macroscopic flow behavior was discussed. The research found that the high silicon and aluminum content in coal ash led to the formation of complex [SiO₄]⁴- tetrahedron and [AlO₄]⁵- tetrahedron structures at high temperature, and the [SiO₄]⁴- tetrahedron and [AlO₄]⁵- tetrahedron were connected by oxygen atoms to form a multi-membered ring structure with high polymerization degree. Due to the action of the multi-membered ring structure, the internal friction in the slag increased, and the viscosity value was higher on the macro-level. As a network-modified ion, Fe2+ could replace Si4+ and Al3+ in the multi-membered ring structure and combine with O2-, which will destroy the bridge oxygen (BO) structure and transform more complex tri cluster oxygen (TO) and bridge oxygen (BO) into simple non-bridge oxygen (NBO) structure. As a result, a large number of multi-membered rings with high polymerization degrees were depolymerized into low-membered rings with low polymerization degrees. The evolution of oxygen types and ring structures in slag reduced the structure complexity and polymerization degree of coal ash slag, resulting in a decrease in the viscosity of coal ash slag.

Keywords: ash slag, coal gasification, fluidity, industrial solid waste, slag structure

Procedia PDF Downloads 31

Authors: A. Kourou, A. Ioakeimidou, S. Hadjiefthymiades, V. Abramea

Abstract:

During the last decades, the task of engaging governments, communities and citizens to reduce risk and vulnerability of the populations has made variable progress. Experience has demonstrated that lack of awareness, education and preparedness may result in significant material and other losses both on the onset of the disaster. Schools play a vital role in the community and are important elements of values and culture of the society. A proper school education not only teaches children, but also is a key factor in the promotion of a safety culture into the wider community. In Greece School Earthquake Safety Initiative has been undertaken by Earthquake Planning and Protection Ogranization with specific actions (seminars, lectures, guidelines, educational material, campaigns, national or EU projects, drills etc.). The objective of this initiative is to develop disaster-resilient school communities through awareness, self-help, cooperation and education. School preparedness requires the participation of Principals, teachers, students, parents, and competent authorities. Preparation and earthquake readiness involves: a) learning what should be done before, during, and after earthquake; b) doing or preparing to do these things now, before the next earthquake; and c) developing teachers’ and students’ skills to cope efficiently in case of an earthquake. In the above given framework this paper presents the results of a survey aimed to identify the level of education and preparedness of school community in Greece. More specifically, the survey questionnaire investigates issues regarding earthquake protection actions, appropriate attitudes and behaviors during an earthquake and existence of contingency plans at elementary and secondary schools. The questionnaires were administered to Principals and teachers from different regions of the country that attend the EPPO national training project 'Earthquake Safety at Schools'. A closed-form questionnaire was developed for the survey, which contained questions regarding the following: a) knowledge of self protective actions b) existence of emergency planning at home and c) existence of emergency planning at school (hazard mitigation actions, evacuation plan, and performance of drills). Survey results revealed that a high percentage of teachers have taken the appropriate preparedness measures concerning non-structural hazards at schools, emergency school plan and simulation drills every year. In order to improve the action-planning for ongoing school disaster risk reduction, the implementation of earthquake drills, the involvement of students with disabilities and the evaluation of school emergency plans, EPPO participates in E-PreS project. The main objective of this project is to create smart tools which define, simulate and evaluate all hazards emergency steps customized to the unique district and school. The project comes up with a holistic methodology using real-time evaluation involving different categories of actors, districts, steps and metrics. The project is supported by EU Civil Protection Financial Instrument with a duration of two years. Coordinator is the Kapodistrian University of Athens and partners are from four countries; Greece, Italy, Romania and Bulgaria.

Keywords: drills, earthquake, emergency plans, E-PreS project

Procedia PDF Downloads 236

Authors: Shelley Y. Hawkins

Abstract:

Introduction/Background: As technology has grown exponentially in healthcare, nurse educators must prepare Advanced Practice Registered Nurse (APRN) graduates with the knowledge and skills in information systems/technology to support and improve patient care and health care systems. APRN’s are expected to lead in caring for populations who lack accessibility and availability through the use of technology, specifically telehealth. The capacity to effectively and efficiently use technology in patient care delivery is clearly delineated in the American Association of Colleges of Nursing (AACN) Doctor of Nursing Practice (DNP) and Master of Science in Nursing (MSN) Essentials. However, APRN’s have minimal, or no, exposure to formalized telehealth education and lack necessary technical skills needed to incorporate telehealth into their patient care. APRN’s must successfully master the technology using telehealth/telemedicine, electronic health records, health information technology, and clinical decision support systems to advance health. Furthermore, APRN’s must be prepared to lead the coordination and collaboration with other healthcare providers in their use and application. Aim/Goal/Purpose: The purpose of this presentation is to establish and operationalize telehealth-focused educational partnerships between one University School of Nursing and two health care systems in order to enhance the preparation of APRN NP students for practice, teaching, and/or scholarly endeavors. Methods: The proposed project was initially presented by the project director to selected multidisciplinary stakeholders including leadership, home telehealth personnel, primary care providers, and decision support systems within two major health care systems to garner their support for acceptance and implementation. Concurrently, backing was obtained from key university-affiliated colleagues including the Director of Simulation and Innovative Learning Lab and Coordinator of the Health Care Informatics Program. Technology experts skilled in design and production in web applications and electronic modules were secured from two local based technology companies. Results: Two telehealth-focused APRN Program academic/practice partnerships have been established. Students have opportunities to engage in clinically based telehealth experiences focused on: (1) providing patient care while incorporating various technology with a specific emphasis on telehealth; (2) conducting research and/or evidence-based practice projects in order to further develop the scientific foundation regarding incorporation of telehealth with patient care; and (3) participating in the production of patient-level educational materials related to specific topical areas. Conclusions: Evidence-based APRN student telehealth clinical experiences will assist in preparing graduates who can effectively incorporate telehealth into their clinical practice. Greater access for diverse populations will be available as a result of the telehealth service model as well as better care and better outcomes at lower costs. Furthermore, APRN’s will provide the necessary leadership and coordination through interprofessional practice by transforming health care through new innovative care models using information systems and technology.

Keywords: academic/practice partnerships, advanced practice nursing, nursing education, telehealth

Procedia PDF Downloads 242

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 91

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 150