Search results for: mental training component

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 105

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 144

Authors: Jara Kaye S. Villanueva, M. Rosario Concepcion O. Ang

Abstract:

For the past few years, Philippines has depended most of its energy source on oil, coal, and fossil fuel. According to the Department of Energy (DOE), the dominance of coal in the energy mix will continue until the year 2020. The expanding energy needs in the country have led to increasing efforts to promote and develop renewable energy. This research is a part of the government initiative in preparation for renewable energy development and expansion in the country. The Philippine Renewable Energy Resource Mapping from Light Detection and Ranging (LiDAR) Surveys is a three-year government project which aims to assess and quantify the renewable energy potential of the country and to put them into usable maps. This study focuses on the site suitability analysis of the four renewable energy sources – biomass (coconut, corn, rice, and sugarcane), hydro, solar, and wind energy. The site assessment is a key component in determining and assessing the most suitable locations for the construction of renewable energy power plants. This method maximizes the use of both the technical methods in resource assessment, as well as taking into account the environmental, social, and accessibility aspect in identifying potential sites by utilizing and integrating two different methods: the Multi-Criteria Decision Analysis (MCDA) method and Geographic Information System (GIS) tools. For the MCDA, Analytical Hierarchy Processing (AHP) is employed to determine the parameters needed for the suitability analysis. To structure these site suitability parameters, various experts from different fields were consulted – scientists, policy makers, environmentalists, and industrialists. The need to have a well-represented group of people to consult with is relevant to avoid bias in the output parameter of hierarchy levels and weight matrices. AHP pairwise matrix computation is utilized to derive weights per level out of the expert’s gathered feedback. Whereas from the threshold values derived from related literature, international studies, and government laws, the output values were then consulted with energy specialists from the DOE. Geospatial analysis using GIS tools translate this decision support outputs into visual maps. Particularly, this study uses Euclidean distance to compute for the distance values of each parameter, Fuzzy Membership algorithm which normalizes the output from the Euclidean Distance, and the Weighted Overlay tool for the aggregation of the layers. Using the Natural Breaks algorithm, the suitability ratings of each of the map are classified into 5 discrete categories of suitability index: (1) not suitable (2) least suitable, (3) suitable, (4) moderately suitable, and (5) highly suitable. In this method, the classes are grouped based on the best groups similar values wherein each subdivision are set from the rest based on the big difference in boundary values. Results show that in the entire Philippine area of responsibility, biomass has the highest suitability rating with rice as the most suitable at 75.76% suitability percentage, whereas wind has the least suitability percentage with score 10.28%. Solar and Hydro fall in the middle of the two, with suitability values 28.77% and 21.27%.

Keywords: site suitability, biomass energy, hydro energy, solar energy, wind energy, GIS

Procedia PDF Downloads 129

Authors: T. Thein, S. Kalyar Myo

Abstract:

Human uses visual information for understanding the speech contents in noisy conditions or in situations where the audio signal is not available. The primary advantage of visual information is that it is not affected by the acoustic noise and cross talk among speakers. Using visual information from the lip movements can improve the accuracy and robustness of automatic speech recognition. However, a major challenge with most automatic lip reading system is to find a robust and efficient method for extracting the linguistically relevant speech information from a lip image sequence. This is a difficult task due to variation caused by different speakers, illumination, camera setting and the inherent low luminance and chrominance contrast between lip and non-lip region. Several researchers have been developing methods to overcome these problems; the one is lip reading. Moreover, it is well known that visual information about speech through lip reading is very useful for human speech recognition system. Lip reading is the technique of a comprehensive understanding of underlying speech by processing on the movement of lips. Therefore, lip reading system is one of the different supportive technologies for hearing impaired or elderly people, and it is an active research area. The need for lip reading system is ever increasing for every language. This research aims to develop a visual teaching method system for the hearing impaired persons in Myanmar, how to pronounce words precisely by identifying the features of lip movement. The proposed research will work a lip reading system for Myanmar Consonants, one syllable consonants (င (Nga)၊ ည (Nya)၊ မ (Ma)၊ လ (La)၊ ၀ (Wa)၊ သ (Tha)၊ ဟ (Ha)၊ အ (Ah) ) and two syllable consonants ( က(Ka Gyi)၊ ခ (Kha Gway)၊ ဂ (Ga Nge)၊ ဃ (Ga Gyi)၊ စ (Sa Lone)၊ ဆ (Sa Lain)၊ ဇ (Za Gwe) ၊ ဒ (Da Dway)၊ ဏ (Na Gyi)၊ န (Na Nge)၊ ပ (Pa Saug)၊ ဘ (Ba Gone)၊ ရ (Ya Gaug)၊ ဠ (La Gyi) ). In the proposed system, there are three subsystems, the first one is the lip localization system, which localizes the lips in the digital inputs. The next one is the feature extraction system, which extracts features of lip movement suitable for visual speech recognition. And the final one is the classification system. In the proposed research, Two Dimensional Discrete Cosine Transform (2D-DCT) and Linear Discriminant Analysis (LDA) with Active Contour Model (ACM) will be used for lip movement features extraction. Support Vector Machine (SVM) classifier is used for finding class parameter and class number in training set and testing set. Then, experiments will be carried out for the recognition accuracy of Myanmar consonants using the only visual information on lip movements which are useful for visual speech of Myanmar languages. The result will show the effectiveness of the lip movement recognition for Myanmar Consonants. This system will help the hearing impaired persons to use as the language learning application. This system can also be useful for normal hearing persons in noisy environments or conditions where they can find out what was said by other people without hearing voice.

Keywords: feature extraction, lip reading, lip localization, Active Contour Model (ACM), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Two Dimensional Discrete Cosine Transform (2D-DCT)

Procedia PDF Downloads 263

Authors: F. A. Thomas, M. Schrafl-Altermatt, R. Treier, S. Kaufmann

Abstract:

Stroke is the main cause of adult disability. Especially upper limb function is affected in most patients. Recently, cooperative hand movements have been shown to be a promising type of upper limb training in stroke rehabilitation. In these movements, which are frequently found in activities of daily living (e.g. opening a bottle, winding up a blind), the force of one upper limb has to be equally counteracted by the other limb to successfully accomplish a task. The use of standardized and reliable clinical assessments is essential to evaluate the efficacy of therapy and the functional outcome of a patient. Many assessments for upper limb function or impairment are available. However, the evaluation of cooperative hand movement tasks are rarely included in those. Thus, the aim of this study was (i) to develop a novel clinical assessment (CASA - Cooperative Activity Stroke Assessment) for the evaluation of patients’ capacity to perform cooperative hand movements and (ii) to test its inter- and interrater reliability. Furthermore, CASA scores were compared to current gold standard assessments for upper extremity in stroke patients (i.e. Fugl-Meyer Assessment, Box & Blocks Test). The CASA consists of five cooperative activities of daily living including (1) opening a jar, (2) opening a bottle, (3) open and closing of a zip, (4) unscrew a nut and (5) opening a clipbox. Here, the goal is to accomplish the tasks as fast as possible. In addition to the quantitative rating (i.e. time) which is converted to a 7-point scale, also the quality of the movement is rated in a 4-point scale. To test the reliability of CASA, fifteen stroke subjects were tested within a week twice by the same two raters. Intra-and interrater reliability was calculated using the intraclass correlation coefficient (ICC) for total CASA score and single items. Furthermore, Pearson-correlation was used to compare the CASA scores to the scores of Fugl-Meyer upper limb assessment and the box and blocks test, which were assessed in every patient additionally to the CASA. ICC scores of the total CASA score indicated an excellent- and single items established a good to excellent inter- and interrater reliability. Furthermore, the CASA score was significantly correlated to the Fugl-Meyer and Box & Blocks score. The CASA provides a reliable assessment for cooperative hand movements which are crucial for many activities of daily living. Due to its non-costly setup, easy and fast implementation, we suggest it to be well suitable for clinical application. In conclusion, the CASA is a useful tool in assessing the functional status and therapy related recovery in cooperative hand movement capacity in stroke patients.

Keywords: activitites of daily living, clinical assessment, cooperative hand movements, reliability, stroke

Procedia PDF Downloads 295

Authors: Hazel James P. Agngarayngay, Arnold R. Elepaño

Abstract:

Mango is the third most important export fruit in the Philippines. Despite the expanding mango trade in world market, problems on postharvest losses caused by pests and diseases are still prevalent. Many disease control and pest disinfestation methods have been studied and adopted. Heat treatment is necessary to eliminate pests and diseases to be able to pass the quarantine requirements of importing countries. During heat treatments, temperature and time are critical because fruits can easily be damaged by over-exposure to heat. Modeling the process enables researchers and engineers to study the behaviour of temperature distribution within the fruit over time. Understanding physical processes through modeling and simulation also saves time and resources because of reduced experimentation. This research aimed to simulate the heat transfer mechanism and predict the temperature distribution in ‘Carabao' mangoes during hot water treatment (HWT) and extended hot water treatment (EHWT). The simulation was performed in ANSYS CFD Software, using ANSYS CFX Solver. The simulation process involved model creation, mesh generation, defining the physics of the model, solving the problem, and visualizing the results. Boundary conditions consisted of the convective heat transfer coefficient and a constant free stream temperature. The three-dimensional energy equation for transient conditions was numerically solved to obtain heat flux and transient temperature values. The solver utilized finite volume method of discretization. To validate the simulation, actual data were obtained through experiment. The goodness of fit was evaluated using mean temperature difference (MTD). Also, t-test was used to detect significant differences between the data sets. Results showed that the simulations were able to estimate temperatures accurately with MTD of 0.50 and 0.69 °C for the HWT and EHWT, respectively. This indicates good agreement between the simulated and actual temperature values. The data included in the analysis were taken at different locations of probe punctures within the fruit. Moreover, t-tests showed no significant differences between the two data sets. Maximum heat fluxes obtained at the beginning of the treatments were 394.15 and 262.77 J.s-1 for HWT and EHWT, respectively. These values decreased abruptly at the first 10 seconds and gradual decrease was observed thereafter. Data on heat flux is necessary in the design of heaters. If underestimated, the heating component of a certain machine will not be able to provide enough heat required by certain operations. Otherwise, over-estimation will result in wasting of energy and resources. This study demonstrated that the simulation was able to estimate temperatures accurately. Thus, it can be used to evaluate the influence of various treatment conditions on the temperature-time history in mangoes. When combined with information on insect mortality and quality degradation kinetics, it could predict the efficacy of a particular treatment and guide appropriate selection of treatment conditions. The effect of various parameters on heat transfer rates, such as the boundary and initial conditions as well as the thermal properties of the material, can be systematically studied without performing experiments. Furthermore, the use of ANSYS software in modeling and simulation can be explored in modeling various systems and processes.

Keywords: heat transfer, heat treatment, mango, modeling and simulation

Procedia PDF Downloads 229

Authors: Martin Pellon Consunji

Abstract:

Due to the rise in popularity of Bitcoin and other crypto assets as a store of wealth and speculative investment, there is an ever-growing demand for automated trading tools, such as bots, in order to gain an advantage over the market. Traditionally, trading in the stock market was done by professionals with years of training who understood patterns and exploited market opportunities in order to gain a profit. However, nowadays a larger portion of market participants are at minimum aided by market-data processing bots, which can generally generate more stable signals than the average human trader. The rise in trading bot usage can be accredited to the inherent advantages that bots have over humans in terms of processing large amounts of data, lack of emotions of fear or greed, and predicting market prices using past data and artificial intelligence, hence a growing number of approaches have been brought forward to tackle this task. However, the general limitation of these approaches can still be broken down to the fact that limited historical data doesn’t always determine the future, and that a lot of market participants are still human emotion-driven traders. Moreover, developing markets such as those of the cryptocurrency space have even less historical data to interpret than most other well-established markets. Due to this, some human traders have gone back to the tried-and-tested traditional technical analysis tools for exploiting market patterns and simplifying the broader spectrum of data that is involved in making market predictions. This paper proposes a method which uses neuro evolution techniques on both sentimental data and, the more traditionally human-consumed, technical analysis data in order to gain a more accurate forecast of future market behavior and account for the way both automated bots and human traders affect the market prices of Bitcoin and other cryptocurrencies. This study’s approach uses evolutionary algorithms to automatically develop increasingly improved populations of bots which, by using the latest inflows of market analysis and sentimental data, evolve to efficiently predict future market price movements. The effectiveness of the approach is validated by testing the system in a simulated historical trading scenario, a real Bitcoin market live trading scenario, and testing its robustness in other cryptocurrency and stock market scenarios. Experimental results during a 30-day period show that this method outperformed the buy and hold strategy by over 260% in terms of net profits, even when taking into consideration standard trading fees.

Keywords: neuro-evolution, Bitcoin, trading bots, artificial neural networks, technical analysis, evolutionary algorithms

Procedia PDF Downloads 94

Authors: Emily Cherono Sawe, Elisha Ondieki Makori

Abstract:

Knowledge and digital economies have brought challenges and potential opportunities for universities to innovate and improve the quality of learning. Disruption technologies and information dynamics continue to transform and change the landscape in teaching, scholarship, and research activities across universities. Digital literacy is a fundamental and imperative element in higher education and training, as witnessed during the new norm. COVID-19 caused unprecedented disruption in universities, where teaching and learning depended on digital innovations and applications. Academic services and activities were provided online, including library information services. Information professionals were forced to adopt various digital platforms in order to provide information services to patrons. University libraries’ roles in fulfilling educational responsibilities continue to evolve in response to changes in pedagogy, technology, economy, society, policies, and strategies of parent institutions. Libraries are currently undergoing considerable transformational change as a result of the inclusion of a digital environment. Academic libraries have been at the forefront of providing online learning resources and online information services, as well as supporting students and staff to develop digital literacy skills via online courses, tutorials, and workshops. Digital literacy transformation and information staff are crucial elements reminiscent of the prioritization of skills and knowledge for lifelong learning. The purpose of this baseline research is to assess the implications of digital literacy transformation in institutions of higher learning in Kenya and share appropriate strategies to leverage and sustain teaching and research. Objectives include examining the leverage and preparedness of the digital literacy environment in streamlining learning in the universities, exploring and benchmarking imperative digital competence for information professionals, establishing the perception of information professionals towards digital literacy skills, and determining lessons, best practices, and strategies to accelerate digital literacy transformation for effective research and learning in the universities. The study will adopt a descriptive research design using questionnaires and document analysis as the instruments for data collection. The targeted population is librarians and information professionals, as well as academics in public and private universities teaching information literacy programmes. Data and information are to be collected through an online structured questionnaire and digital face-to-face interviews. Findings and results will provide promising lessons together with best practices and strategies to transform and change digital literacies in university libraries in Kenya.

Keywords: digital literacy, digital innovations, information professionals, librarians, higher education, university libraries, digital information literacy

Procedia PDF Downloads 65

Authors: Chunyang Miao, Bingxin Li, Shanglong Ning, Christopher J. B. Ford

Abstract:

While it is challenging to fabricate electronic devices close to atomic dimensions in conventional top-down lithography, molecular electronics is promising to help maintain the exponential increase in component densities via using molecular building blocks to fabricate electronic components from the bottom up. It offers smaller, faster, and more energy-efficient electronic and photonic systems. A self-assembled monolayer (SAM) of molecules is a layer of molecules that self-assembles on a substrate. They are mechanically flexible, optically transparent, low-cost, and easy to fabricate. A large-area multi-layer structure has been designed and investigated by the team, where a SAM of designed molecules is sandwiched between graphene and gold electrodes. Each molecule can act as a quantum dot, with all molecules conducting in parallel. When a source-drain bias is applied, significant current flows only if a molecular orbital (HOMO or LUMO) lies within the source-drain energy window. If electrons tunnel sequentially on and off the molecule, the charge on the molecule is well-defined and the finite charging energy causes Coulomb blockade of transport until the molecular orbital comes within the energy window. This produces ‘Coulomb diamonds’ in the conductance vs source-drain and gate voltages. For different tunnel barriers at either end of the molecule, it is harder for electrons to tunnel out of the dot than in (or vice versa), resulting in the accumulation of two or more charges and a ‘Coulomb staircase’ in the current vs voltage. This nanostructure exhibits highly reproducible Coulomb-staircase patterns, together with additional oscillations, which are believed to be attributed to molecular vibrations. Molecules are more isolated than semiconductor dots, and so have a discrete phonon spectrum. When tunnelling into or out of a molecule, one or more vibronic states can be excited in the molecule, providing additional transport channels and resulting in additional peaks in the conductance. For useful molecular electronic devices, achieving the optimum orbital alignment of molecules to the Fermi energy in the leads is essential. To explore it, a drop of ionic liquid is employed on top of the graphene to establish an electric field at the graphene, which screens poorly, gating the molecules underneath. Results for various molecules with different alignments of Fermi energy to HOMO have shown highly reproducible Coulomb-diamond patterns, which agree reasonably with DFT calculations. In summary, this large-area SAM molecular junction is a promising candidate for future electronic circuits. (1) The small size (1-10nm) of the molecules and good flexibility of the SAM lead to the scalable assembly of ultra-high densities of functional molecules, with advantages in cost, efficiency, and power dissipation. (2) The contacting technique using graphene enables mass fabrication. (3) Its well-observed Coulomb blockade behaviour, narrow molecular resonances, and well-resolved vibronic states offer good tuneability for various functionalities, such as switches, thermoelectric generators, and memristors, etc.

Keywords: molecular electronics, Coulomb blokade, electron-phonon coupling, self-assembled monolayer

Procedia PDF Downloads 34

Authors: María Luisa Gonzalez-SanJose, Mihaela Mihnea, Vicente Gomez-Miguel

Abstract:

The zoning methodology currently recommended by the OIVV as official methodology to carry out viticulture zoning studies and to define and delimit the ‘terroirs’ has been applied in this study. This methodology has been successfully applied on the most significant an important Spanish Oenological D.O. regions, such as Ribera de Duero, Rioja, Rueda and Toro, but also it have been applied around the world in Portugal, different countries of South America, and so on. This is a complex methodology that uses edaphoclimatic data but also other corresponding to vineyards and other soils’ uses The methodology is useful to determine Homogeneous Soil Units (HSU) to different scale depending on the interest of each study, and has been applied from viticulture regions to particular vineyards. It seems that this methodology is an appropriate method to delimit correctly the medium in order to enhance its uses and to obtain the best viticulture and oenological products. The present work is focused on the comparison of volatile composition of wines made from grapes grown in different HSU that coexist in a particular viticulture region of Castile-Lion cited near to Burgos. Three different HSU were selected for this study. They represented around of 50% of the global area of vineyards of the studied region. Five different vineyards on each HSU under study were chosen. To reduce variability factors, other criteria were also considered as grape variety, clone, rootstocks, vineyard’s age, training systems and cultural practices. This study was carried out during three consecutive years, then wine from three different vintage were made and analysed. Different red wines were made from grapes harvested in the different vineyards under study. Grapes were harvested to ‘Technological maturity’, which are correlated with adequate levels of sugar, acidity, phenolic content (nowadays named phenolic maturity), good sanitary stages and adequate levels of aroma precursors. Results of the volatile profile of the wines produced from grapes of each HSU showed significant differences among them pointing out a direct effect of the edaphoclimatic characteristic of each UHT on the composition of the grapes and then on the volatile composition of the wines. Variability induced by HSU co-existed with the well-known inter-annual variability correlated mainly with the specific climatic conditions of each vintage, however was most intense, so the wine of each HSU were perfectly differenced. A discriminant analysis allowed to define the volatiles with discriminant capacities which were 21 of the 74 volatiles analysed. Detected discriminant volatiles were chemical different, although .most of them were esters, followed by were superior alcohols and fatty acid of short chain. Only one lactone and two aldehydes were selected as discriminant variable, and no varietal aroma compounds were selected, which agree with the fact that all the wine were made from the same grape variety.

Keywords: viticulture zoning, terroir, wine, volatile profile

Procedia PDF Downloads 196

Authors: Asma Ben Hmidene, Mizuho Hanaki, Kazuma Murakami, Kazuhiro Irie, Hiroko Isoda, Hideyuki Shigemori

Abstract:

Type 2 diabetes mellitus (T2DM) and Alzheimer’s disease (AD) are characterized as a peripheral metabolic disorder and a degenerative disease of the central nervous system, respectively. It is now widely recognized that T2DM and AD share many pathophysiological features including glucose metabolism, increased oxidative stress and amyloid aggregation. Amyloid beta (Aβ) is the components of the amyloid deposits in the AD brain and while the component of the amyloidogenic peptide deposit in the pancreatic islets of Langerhans is identified as human islet amyloid polypeptide (hIAPP). These two proteins are originated from the amyloid precursor protein and have a high sequence similarity. Although the amino acid sequences of amyloidogenic proteins are diverse, they all adopt a similar structure in aggregates called cross-beta-spine. Add at that, extensive studies in the past years have found that like Aβ1-42, IAPP forms early intermediate assemblies as spherical oligomers, implicating that these oligomers possess a common folding pattern or conformation. These similarities can be used in the search for effective pharmacotherapy for DM, since potent therapeutic agents such as antioxidants with a catechol moiety, proved to inhibit Aβ aggregation, may play a key role in the inhibit the aggregation of hIAPP treatment of patients with DM. Tamarix gallica is one of the halophyte species having a powerful antioxidant system. Although it was traditionally used for the treatment of various liver metabolic disorders, there is no report about the use of this plant for the treatment or prevention of T2DM and AD. Therefore, the aim of this work is to investigate their protective effect towards T2DM and AD by isolation and identification of α-glucosidase inhibitors, with antioxidant potential, that play an important role in the glucose metabolism in diabetic patient, as well as, the polymerization of hIAPP and Aβ aggregation inhibitors. Structure-activity relationship study was conducted for both assays. And as for α-glucosidase inhibitors, their mechanism of action and their synergistic potential when applied with a very low concentration of acarbose were also suggesting that they can be used not only as α-glucosidase inhibitors but also be combined with established α-glucosidase inhibitors to reduce their adverse effect. The antioxidant potential of the purified substances was evaluated by DPPH and SOD assays. Th-T assay using 42-mer amyloid β-protein (Aβ42) for AD and hIAPP which is a 37-residue peptide secreted by the pancreatic β –cells for T2DM and Transmission electronic microscopy (TEM) were conducted to evaluate the amyloid aggragation of the actives substances. For α-glucosidase, p-NPG and glucose oxidase assays were performed for determining the inhibition potential and structure-activity relationship study. The Enzyme kinetic protocol was used to study the mechanism of action. From this research, it was concluded that polyphenols playing a role in the glucose metabolism and oxidative stress can also inhibit the amyloid aggregation, and that substances with a catechol and glucuronide moieties inhibiting amyloid-β aggregation, might be used to inhibit the aggregation of hIAPP.

Keywords: α-glucosidase inhibitors, amyloid aggregation inhibition, mechanism of action, polyphenols, structure activity relationship, synergistic potential, tamarix gallica

Procedia PDF Downloads 256

Authors: Ali Ateş, Ansar B. Mwimbo, Ali H. Abdulkarim

Abstract:

General transport equation has a wide range of application in Fluid Mechanics and Heat Transfer problems. In this equation, generally when φ variable which represents a flow property is used to represent fluid velocity component, general transport equation turns into momentum equations or with its well known name Navier-Stokes equations. In these non-linear differential equations instead of seeking for analytic solutions, preferring numerical solutions is a more frequently used procedure. Finite difference method is a commonly used numerical solution method. In these equations using velocity and pressure gradients instead of stress tensors decreases the number of unknowns. Also, continuity equation, by integrating the system, number of equations is obtained as number of unknowns. In this situation, velocity and pressure components emerge as two important parameters. In the solution of differential equation system, velocities and pressures must be solved together. However, in the considered grid system, when pressure and velocity values are jointly solved for the same nodal points some problems confront us. To overcome this problem, using staggered grid system is a referred solution method. For the computerized solutions of the staggered grid system various algorithms were developed. From these, two most commonly used are SIMPLE and SIMPLER algorithms. In this study Navier-Stokes equations were numerically solved for Newtonian flow, whose mass or gravitational forces were neglected, for incompressible and laminar fluid, as a hydro dynamically fully developed region and in two dimensional cartesian coordinate system. Finite difference method was chosen as the solution method. This is a parametric study in which varying values of velocity components, pressure and Reynolds numbers were used. Differential equations were discritized using central difference and hybrid scheme. The discritized equation system was solved by Gauss-Siedel iteration method. SIMPLE and SIMPLER were used as solution algorithms. The obtained results, were compared for central difference and hybrid as discritization methods. Also, as solution algorithm, SIMPLE algorithm and SIMPLER algorithm were compared to each other. As a result, it was observed that hybrid discritization method gave better results over a larger area. Furthermore, as computer solution algorithm, besides some disadvantages, it can be said that SIMPLER algorithm is more practical and gave result in short time. For this study, a code was developed in DELPHI programming language. The values obtained in a computer program were converted into graphs and discussed. During sketching, the quality of the graph was increased by adding intermediate values to the obtained result values using Lagrange interpolation formula. For the solution of the system, number of grid and node was found as an estimated. At the same time, to indicate that the obtained results are satisfactory enough, by doing independent analysis from the grid (GCI analysis) for coarse, medium and fine grid system solution domain was obtained. It was observed that when graphs and program outputs were compared with similar studies highly satisfactory results were achieved.

Keywords: finite difference method, GCI analysis, numerical solution of the Navier-Stokes equations, SIMPLE and SIMPLER algoritms

Procedia PDF Downloads 364

Authors: Ewa Bednorz, Marek Polrolniczak, Bartosz Czernecki, Arkadiusz Marek Tomczyk

Abstract:

This study is meant as a contribution to the research of the upwelling phenomenon, which is one of the most pronounced examples of the sea-atmosphere coupling. The aim is to confirm the atmospheric forcing of the sea waters circulation and sea surface temperature along the variously oriented Baltic Sea coasts and to find out macroscale and regional circulation patterns triggering upwelling along different sections of this relatively small and semi-closed sea basin. The mean daily sea surface temperature data from the summer seasons (June–August) of the years 1982–2017 made the basis for the detection of upwelling cases. For the atmospheric part of the analysis, monthly indices of the Northern Hemisphere macroscale circulation patterns were used. Besides, in order to identify the local direction of airflow, the daily zonal and meridional regional circulation indices were constructed and introduced to the analysis. Finally, daily regional circulation patterns over the Baltic Sea region were distinguished by applying the principal component analysis to the gridded mean daily sea level pressure data. Within the Baltic Sea, upwelling is the most frequent along the zonally oriented northern coast of the Gulf of Finland, southern coasts of Sweden, and along the middle part of the western Gulf of Bothnia coast. Among the macroscale circulation patterns, the Scandinavian type (SCAND), with a primary circulation center located over Scandinavia, has the strongest impact on the horizontal flow of surface sea waters in the Baltic Sea, which triggers upwelling. An anticyclone center over Scandinavia in the positive phase of SCAND enhances the eastern airflow, which increases upwelling frequency along southeastern Baltic coasts. It was proved in the study that the zonal circulation has a stronger impact on upwelling occurrence than the meridional one, and it could increase/decrease a chance of upwelling formation by more than 70% in some coastal sections. Positive and negative phases of six distinguished regional daily circulation patterns made 12 different synoptic situations which were analyzed in the terms of their influence on the upwelling formation. Each of them revealed some impact on the frequency of upwelling in some coastal section of the Baltic Sea; however, two kinds of synoptic situations seemed to have the strongest influence, namely, the first kind representing pressure patterns enhancing the zonal flow and the second kind representing synoptic patterns with a cyclone/anticyclone centers over southern Scandinavia. Upwelling occurrence appeared to be particularly strongly reliant on the atmospheric conditions in some specific coastal sections, namely: the Gulf of Finland, the south eastern Baltic coasts (Polish and Latvian-Lithuanian section), and the western part of the Gulf of Bothnia. Concluding, it can be stated that atmospheric conditions strongly control the occurrence of upwelling within the Baltic Sea basin. Both local and macroscale circulation patterns expressed by the location of the pressure centers influence the frequency of this phenomenon; however, the impact strength varies, depending on the coastal region. Acknowledgment: This research was funded by the National Science Centre, Poland, grant number 2016/21/B/ST10/01440.

Keywords: Baltic Sea, circulation patterns, coastal upwelling, synoptic conditions

Procedia PDF Downloads 100

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 81

Authors: Sharon Jackson, Lynn Kelly

Abstract:

This paper proposes a conceptual review of the interdisciplinary literature which has theorised the concept of ‘children’s voices’. The primary aim is to identify and consider the theoretical relevance of conceptual thought on ‘children’s voices’ for research and practice in child protection contexts. Attending to the ‘voice of the child’ has become a core principle of social work practice in contemporary child protection contexts. Discourses of voice permeate the legislative, policy and practice frameworks of child protection practices within the UK and internationally. Voice is positioned within a ‘child-centred’ moral imperative to ‘hear the voices’ of children and take their preferences and perspectives into account. This practice is now considered to be central to working in a child-centered way. The genesis of this call to voice is revealed through sociological analysis of twentieth-century child welfare reform as rooted inter alia in intersecting political, social and cultural discourses which have situated children and childhood as cites of state intervention as enshrined in the 1989 United Nations Convention on the Rights of the Child ratified by the UK government in 1991 and more specifically Article 12 of the convention. From a policy and practice perspective, the professional ‘capturing’ of children’s voices has come to saturate child protection practice. This has incited a stream of directives, resources, advisory publications and ‘how-to’ guides which attempt to articulate practice methods to ‘listen’, ‘hear’ and above all – ‘capture’ the ‘voice of the child’. The idiom ‘capturing the voice of the child’ is frequently invoked within the literature to express the requirements of the child-centered practice task to be accomplished. Despite the centrality of voice, and an obsession with ‘capturing’ voices, evidence from research, inspection processes, serious case reviews, child abuse and death inquires has consistently highlighted professional neglect of ‘the voice of the child’. Notable research studies have highlighted the relative absence of the child’s voice in social work assessment practices, a troubling lack of meaningful engagement with children and the need to more thoroughly examine communicative practices in child protection contexts. As a consequence, the project of capturing ‘the voice of the child’ has intensified, and there has been an increasing focus on developing methods and professional skills to attend to voice. This has been guided by a recognition that professionals often lack the skills and training to engage with children in age-appropriate ways. We argue however that the problem with ‘capturing’ and [re]representing ‘voice’ in child protection contexts is, more fundamentally, a failure to adequately theorise the concept of ‘voice’ in the ‘voice of the child’. For the most part, ‘The voice of the child’ incorporates psychological conceptions of child development. While these concepts are useful in the context of direct work with children, they fail to consider other strands of sociological thought, which position ‘the voice of the child’ within an agentic paradigm to emphasise the active agency of the child.

Keywords: child-centered, child protection, views of the child, voice of the child

Procedia PDF Downloads 111

Authors: Dibyendu Rakshit, Santosh K. Sarkar

Abstract:

The study illustrates a comprehensive account of large-scale changes plankton community structure in relevance to water quality characteristics due to anthropogenic stresses, mainly concerned for Annual Gangasagar Festival (AGF) at the southern tip of Sagar Island of Indian Sundarban wetland for 3-year duration (2012-2014; n=36). This prograding, vulnerable and tide-dominated megadelta has been formed in the estuarine phase of the Hooghly Estuary infested by largest continuous tract of luxurious mangrove forest, enriched with high native flora and fauna. The sampling strategy was designed to characterize the changes in plankton community and water quality considering three diverse phases, namely during festival period (January) and its pre - (December) as well as post (February) events. Surface water samples were collected for estimation of different environmental variables as well as for phytoplankton and microzooplankton biodiversity measurement. The preservation and identification techniques of both biotic and abiotic parameters were carried out by standard chemical and biological methods. The intensive human activities lead to sharp ecological changes in the context of poor water quality index (WQI) due to high turbidity (14.02±2.34 NTU) coupled with low chlorophyll a (1.02±0.21 mg m-3) and dissolved oxygen (3.94±1.1 mg l-1), comparing to pre- and post-festival periods. Sharp reduction in abundance (4140 to 2997 cells l-1) and diversity (H′=2.72 to 1.33) of phytoplankton and microzooplankton tintinnids (450 to 328 ind l-1; H′=4.31 to 2.21) was very much pronounced. The small size tintinnid (average lorica length=29.4 µm; average LOD=10.5 µm) composed of Tintinnopsis minuta, T. lobiancoi, T. nucula, T. gracilis are predominant and reached some of the greatest abundances during the festival period. Results of ANOVA revealed a significant variation in different festival periods with phytoplankton (F= 1.77; p=0.006) and tintinnid abundance (F= 2.41; P=0.022). RELATE analyses revealed a significant correlation between the variations of planktonic communities with the environmental data (R= 0.107; p= 0.005). Three distinct groups were delineated from principal component analysis, in which a set of hydrological parameters acted as the causative factor(s) for maintaining diversity and distribution of the planktonic organisms. The pronounced adverse impact of anthropogenic stresses on plankton community could lead to environmental deterioration, disrupting the productivity of benthic and pelagic ecosystems as well as fishery potentialities which directly related to livelihood services. The festival can be considered as multiple drivers of changes in relevance to beach erosion, shoreline changes, pollution from discarded plastic and electronic wastes and destruction of natural habitats resulting loss of biodiversity. In addition, deterioration in water quality was also evident from immersion of idols, causing detrimental effects on aquatic biota. The authors strongly recommend for adopting integrated scientific and administrative strategies for resilience, sustainability and conservation of this megadelta.

Keywords: Gangasagar festival, phytoplankton, Sundarban megadelta, tintinnid

Procedia PDF Downloads 206

Authors: Jason Blair, Adeboye Adebayo, Mohamed Saad, Jeannette M. Byrne, Fabien A. Basset

Abstract:

Running economy is a key physiological parameter of an individual’s running efficacy and a valid tool for predicting performance outcomes. Of the many factors known to influence running economy (RE), footwear certainly plays a role owing to its characteristics that vary substantially from model to model. Although minimalist footwear is believed to enhance RE and thereby endurance performance, conclusive research reports are scarce. Indeed, debates remain as to which footwear characteristics most alter RE. The purposes of this study were, therefore, two-fold: (a) to determine whether wearing minimalist shoes results in better RE compared to shod and to identify relationships with kinematic and muscle activation patterns; (b) to determine whether changes in RE with minimalist shoes are still evident following a fatiguing bout of exercise. Well-trained male distance runners (n=10; 29.0 ± 7.5 yrs; 71.0 ± 4.8 kg; 176.3 ± 6.5 cm) partook first in a maximal O₂ uptake determination test (VO₂ₘₐₓ = 61.6 ± 7.3 ml min⁻¹ kg⁻¹) 7 days prior to the experimental sessions. Second, in a fully randomized fashion, an RE test consisting of three 8-min treadmill runs in shod and minimalist footwear were performed prior to and following exercise induced fatigue (EIF). The minimalist and shod conditions were tested with a minimum of 7-day wash-out period between conditions. The RE bouts, interspaced by 2-min rest periods, were run at 2.79, 3.33, and 3.89 m s⁻¹ with a 1% grade. EIF consisted of 7 times 1000 m at 94-97% VO₂ₘₐₓ interspaced with 3-min recovery. Cardiorespiratory, electromyography (EMG), kinematics, rate of perceived exertion (RPE) and blood lactate were measured throughout the experimental sessions. A significant main speed effect on RE (p=0.001) and stride frequency (SF) (p=0.001) was observed. The pairwise comparisons showed that running at 2.79 m s⁻¹ was less economic compared to 3.33, and 3.89 m s⁻¹ (3.56 ± 0.38, 3.41 ± 0.45, 3.40 ± 0.45 ml O₂ kg⁻¹ km⁻¹; respectively) and that SF increased as a function of speed (79 ± 5, 82 ± 5, 84 ± 5 strides min⁻¹). Further, EMG analyses revealed that root mean square EMG significantly increased as a function of speed for all muscles (Biceps femoris, Gluteus maximus, Gastrocnemius, Tibialis anterior, Vastus lateralis). During EIF, the statistical analysis revealed a significant main effect of time on lactate production (from 2.7 ± 5.7 to 11.2 ± 6.2 mmol L⁻¹), RPE scores (from 7.6 ± 4.0 to 18.4 ± 2.7) and peak HR (from 171 ± 30 to 181 ± 20 bpm), expect for the recovery period. Surprisingly, a significant main footwear effect was observed on running speed during intervals (p=0.041). Participants ran faster with minimalist shoes compared to shod (3:24 ± 0:44 min [95%CI: 3:14-3:34] vs. 3:30 ± 0:47 min [95%CI: 3:19-3:41]). Although EIF altered lactate production and RPE scores, no other effect was noticeable on RE, EMG, and SF pre- and post-EIF, except for the expected speed effect. The significant footwear effect on running speed during EIF was unforeseen but could be due to shoe mass and/or heel-toe-drop differences. We also cannot discard the effect of speed on foot-strike pattern and therefore, running performance.

Keywords: exercise-induced fatigue, interval training, minimalist footwear, running economy

Procedia PDF Downloads 215

Authors: Melanie Redding

Abstract:

Historic widespread nitrate contamination of the Lower Yakima Valley aquifer in Washington State initiated a community-based effort to reduce nitrate concentrations to below-drinking water standards. This group commissioned studies on characterizing local nitrogen sources, deep soil assessments, drinking water, and assessing nitrate concentrations at the water table. Nitrate is the most prevalent groundwater contaminant with common sources from animal and human waste, fertilizers, plants and precipitation. It is challenging to address groundwater contamination when common sources, such as agriculture, on-site sewage systems, and animal production, are widespread. Remediation is not possible, so mitigation is essential. The Lower Yakima Valley is located over 175,000 acres, with a population of 56,000 residents. Approximately 25% of the population do not have access to safe, clean drinking water, and 20% of the population is at or below the poverty level. Agriculture is the primary economic land-use activity. Irrigated agriculture and livestock production make up the largest percentage of acreage and nitrogen load. Commodities include apples, grapes, hops, dairy, silage corn, triticale, alfalfa and cherries. These commodities are important to the economic viability of the residents of the Lower Yakima Valley, as well as Washington State. Mitigation of nitrate in groundwater is challenging. The goal is to ensure everyone has safe drinking water. There are no easy remedies due to the extensive and pervasiveness of the contamination. Monitoring at the water table indicates that 45% of the 30 spatially distributed monitoring wells exceeded the drinking water standard. This indicates that there are multiple sources that are impacting water quality. Washington State has several areas which have extensive groundwater nitrate contamination. The groundwater in these areas continues to degrade over time. However, the Lower Yakima Valley is being successful in addressing this health issue because of the following reasons: the community is engaged and committed; there is one common goal; there has been extensive public education and outreach to citizens; and generating credible data using sound scientific methods. Work in this area is continuing as an ambient groundwater monitoring network is established to assess the condition of the aquifer over time. Nitrate samples are being collected from 170 wells, spatially distributed across the aquifer. This research entails quarterly sampling for two years to characterize seasonal variability and then continue annually afterward. This assessment will provide the data to statistically determine trends in nitrate concentrations across the aquifer, over time. Thirty-three of these wells are monitoring wells that are screened across the aquifer. The water quality from these wells are indicative of activities at the land surface. Additional work is being conducted to identify land use management practices that are effective in limiting nitrate migration through the soil column. Tracking nitrate in the soil column every season is an important component of bridging land-use practices with the fate and transport of nitrate through the subsurface. Patience, tenacity, and the ability to think outside the box are essential for dealing with widespread nitrate contamination of groundwater.

Keywords: community, groundwater, monitoring, nitrate

Procedia PDF Downloads 151

Authors: Selin Top, Raul Marcos, M. Sinan Bilgili

Abstract:

Although there have been several studies related to collection, temporary storage, handling and disposal of solid wastes generated by hospitals, there are only a few studies related to liquid wastes generated by hospitals or hospital wastewaters. There is an important amount of water consumptions in hospitals. While minimum domestic water consumption per person is 100 L/day, water consumption per bed in hospitals is generally ranged between 400-1200 L. This high amount of consumption causes high amount of wastewater. The quantity of wastewater produced in a hospital depends on different factors: bed numbers, hospital age, accessibility to water, general services present inside the structure (kitchen, laundry, laboratory, diagnosis, radiology, and air conditioning), number and type of wards and units, institution management policies and awareness in managing the structure in safeguarding the environment, climate and cultural and geographic factors. In our country, characterization of hospital wastewaters conducted by classical parameters in a very few studies. However, as mentioned above, this type of wastewaters may contain different compounds than domestic wastewaters. Hospital Wastewater (HWW) is wastewater generated from all activities of the hospital, medical and non medical. Nowadays, hospitals are considered as one of the biggest sources of wastewater along with urban sources, agricultural effluents and industrial sources. As a health-care waste, hospital wastewater has the same quality as municipal wastewater, but may also potentially contain various hazardous components due to using disinfectants, pharmaceuticals, radionuclides and solvents making not suitable the connection of hospital wastewater to the municipal sewage network. These characteristics may represent a serious health hazard and children, adults and animals all have the potential to come into contact with this water. Therefore, the treatment of hospital wastewater is an important current interest point to focus on. This paper aims to approach on the investigation of hospital wastewater treatment by membrane systems. This study aim is to determined hospital wastewater’s characterization and also evaluates the efficiency of hospital wastewater treatment by high pressure filtration systems such as ultrafiltration (UF). Hospital wastewater samples were taken directly from sewage system from Şişli Etfal Training and Research Hospital, located in the district of Şişli, in the European part of Istanbul. The hospital is a 784 bed tertiary care center with a daily outpatient department of 3850 patients. Ultrafiltration membrane is used as an experimental treatment and the influence of the pressure exerted on the membranes was examined, ranging from 1 to 3 bar. The permeate flux across the membrane was observed to define the flooding membrane points. The global COD and BOD5 removal efficiencies were 54% and 75% respectively for ultrafiltration, all the SST removal efficiencies were above 90% and a successful removal of the pathological bacteria measured was achieved.

Keywords: hospital wastewater, membrane, ultrafiltration, treatment

Procedia PDF Downloads 277

Authors: Shayla He

Abstract:

Background and Purpose: According to Chamie (2017), it’s estimated that no less than 150 million people, or about 2 percent of the world’s population, are homeless. The homeless population in the United States has grown rapidly in the past four decades. In New York City, the sheltered homeless population has increased from 12,830 in 1983 to 62,679 in 2020. Knowing the trend on the homeless population is crucial at helping the states and the cities make affordable housing plans, and other community service plans ahead of time to better prepare for the situation. This study utilized the data from New York City, examined the key factors associated with the homelessness, and developed systematic modeling to predict homeless populations of the future. Using the best model developed, named HP-RNN, an analysis on the homeless population change during the months of 2020 and 2021, which were impacted by the COVID-19 pandemic, was conducted. Moreover, HP-RNN was tested on the data from Seattle. Methods: The methodology involves four phases in developing robust prediction methods. Phase 1 gathered and analyzed raw data of homeless population and demographic conditions from five urban centers. Phase 2 identified the key factors that contribute to the rate of homelessness. In Phase 3, three models were built using Linear Regression, Random Forest, and Recurrent Neural Network (RNN), respectively, to predict the future trend of society's homeless population. Each model was trained and tuned based on the dataset from New York City for its accuracy measured by Mean Squared Error (MSE). In Phase 4, the final phase, the best model from Phase 3 was evaluated using the data from Seattle that was not part of the model training and tuning process in Phase 3. Results: Compared to the Linear Regression based model used by HUD et al (2019), HP-RNN significantly improved the prediction metrics of Coefficient of Determination (R2) from -11.73 to 0.88 and MSE by 99%. HP-RNN was then validated on the data from Seattle, WA, which showed a peak %error of 14.5% between the actual and the predicted count. Finally, the modeling results were collected to predict the trend during the COVID-19 pandemic. It shows a good correlation between the actual and the predicted homeless population, with the peak %error less than 8.6%. Conclusions and Implications: This work is the first work to apply RNN to model the time series of the homeless related data. The Model shows a close correlation between the actual and the predicted homeless population. There are two major implications of this result. First, the model can be used to predict the homeless population for the next several years, and the prediction can help the states and the cities plan ahead on affordable housing allocation and other community service to better prepare for the future. Moreover, this prediction can serve as a reference to policy makers and legislators as they seek to make changes that may impact the factors closely associated with the future homeless population trend.

Keywords: homeless, prediction, model, RNN

Procedia PDF Downloads 96

Authors: Raman Sharma, Ashok Kumar, Vipin Koushal

Abstract:

Healthcare facilities are always seen as places of haven and protection for managing the external incidents, but the situation becomes more difficult and challenging when such facilities themselves are affected from internal hazards. Such internal hazards are arguably more disruptive than external incidents affecting vulnerable ones, as patients are always dependent on supportive measures and are neither in a position to respond to such crisis situation nor do they know how to respond. The situation becomes more arduous and exigent to manage if, in case critical care areas like Intensive Care Units (ICUs) and Operating Rooms (OR) are convoluted. And, due to these complexities of patients’ in-housed there, it becomes difficult to move such critically ill patients on immediate basis. Healthcare organisations use different types of electrical equipment, inflammable liquids, and medical gases often at a single point of use, hence, any sort of error can spark the fire. Even though healthcare facilities face many fire hazards, damage caused by smoke rather than flames is often more severe. Besides burns, smoke inhalation is primary cause of fatality in fire-related incidents. The greatest cause of illness and mortality in fire victims, particularly in enclosed places, appears to be the inhalation of fire smoke, which contains a complex mixture of gases in addition to carbon monoxide. Therefore, healthcare organizations are required to have a well-planned disaster mitigation strategy, proactive and well prepared manpower to cater all types of exigencies resulting from internal as well as external hazards. This case report delineates a true OR fire incident in Emergency Operation Theatre (OT) of a tertiary care multispecialty hospital and details the real life evidence of the challenges encountered by OR staff in preserving both life and property. No adverse event was reported during or after this fire commotion, yet, this case report aimed to congregate the lessons identified of the incident in a sequential and logical manner. Also, timely smoke evacuation and preventing the spread of smoke to adjoining patient care areas by opting appropriate measures, viz. compartmentation, pressurisation, dilution, ventilation, buoyancy, and airflow, helped to reduce smoke-related fatalities. Henceforth, precautionary measures may be implemented to mitigate such incidents. Careful coordination, continuous training, and fire drill exercises can improve the overall outcomes and minimize the possibility of these potentially fatal problems, thereby making a safer healthcare environment for every worker and patient.

Keywords: healthcare, fires, smoke, management, strategies

Procedia PDF Downloads 44

Authors: Elizabeth Ankiambom Chiatii

Abstract:

The effective participation of graduates as leaders in entrepreneurial resilience is a key driver to achieving sustainable job creation and curbing unemployment issues in the urban and rural communities of Cameroon. The unemployment problem is a global challenge in the Labour market, especially for youths graduating from universities. Statistics from the Cameroon National Institute of statistics indicate that the unemployment rate in the country increased to 3.9% in 2021 from 3.8% in 2020. One of the main causes of unemployment challenges and job hooping among university graduates is the high expectation for “white-collar jobs syndrome” as opposed to involvement in ‘blue-collar jobs’. In the recent years, the Catholic University of Cameroon has engaged its resources in problem and project based learning (PBL) approaches in order to enable the students at the end of their course work to be competent and resourceful in impacting their communities and the world at large. It is so encouraging to notice that most of our current and female ex-students have engaged as leaders in fostering entrepreneurial resilience through small and medium size ‘blue-collar’ enterprises like seamstresses or tailors, designers, catering services, poultry owners, traditional regalia designers, phone booth operators, farming (gardening) activities, saloon owners, wedding designers, restaurant operators and many other creative jobs where they also act as petty employers. A good number of them sponsor their university studies through these self-income generating activities. Part one of this paper centres on the introduction and background of study. Part two embodies some literature review in which we concentrate on some related conceptual issues. For example, we have some analogy of employment difficulties faced by the university graduates. Secondly, we will examine the details on entrepreneurial resilience within the context of Bamenda- Cameroon. Thirdly, we expound on the leadership role played by these graduates in building resilience as entrepreneurs stemming from their university training. The primary method of data collection is implemented, where questionnaires are distributed to at least 100 of these graduates engaged in building entrepreneurial resilience. The IVProbit regression analysis is used to determine the effect of these graduate participation as leader on entrepreneurial resilience. The results can contribute to the development of entrepreneurial resilience, and recommendations will be made to CATUC Bamenda, some communities and government leaders to enhance their policies to empower these young graduates in fostering these resourceful activities.

Keywords: graduates entrepreneurial resilience, unemployment challenges, white-collar job syndrome, small and medium size blue-collar enterprises

Procedia PDF Downloads 42

Authors: Esther Paul, Ibrahim A. M. Alzaydani, Al Hakami, Caryl Beynon

Abstract:

Research Objectives and Goal: The main aim of the current study was to explore the perspectives of healthcare workers on Healthcare-associated infections (HAI) and infection control measures in a tertiary care Hospital in Abha, Saudi Arabia. As per our knowledge, this is perhaps the first qualitative study on HAI to be done in Saudi Arabia. The goal of the study was to understand the perspectives of the healthcare workers on the current protocol and guidelines for HAI and infections control measures in the hospital, the effectiveness of the current protocol for HAI and infection control measures and ways of reducing the incidence of HAI and improve infection control measures. Methods used: A qualitative research design was used to collect the data from 25 healthcare workers consisting of doctors and nurses, recruited by Snowball strategy via semi-structured interviews which were audio-recorded and transcribed verbatim immediately. An interview guide consisting of open-ended questions about the existing HAI and infection control practices in the healthcare facility, the awareness of the healthcare workers about HAI and the need for safe infection control measures were used to collect the data. The transcribed data were analyzed using the thematic analysis method. Results: Using thematic analysis four themes were identified.1.Knowledge of HAI and infection control 2. Infection control measures in practice 3. The gap in infection control measures and HAI 4. Required Implementations. The first theme covered the participants' knowledge on HAI, its definition, the types of HAI and the infection control measures.Most of the participants were aware of HAI and had some idea of the definition of HAI, its significance and the dangers posed by HAI, but few residents had no idea of the types of HAI. The second theme was focussed on the infection control measures in practice. Most of the participants were aware of the importance of infection control measures like hand hygiene, catheter care, and waste disposal. The nurses were responsible for most of the disinfection and sterilization measures and practiced it effectively. However, some doctors and residents had no inkling about these measures. The third theme emphasized that although most of the participants were aware of HAI and infection control measures and were in practice. There were some lacunae regarding their knowledge of the different types of HAI, Personal Protective Equipment practices, communication among the healthcare personnel and the hospital administrations and the means of waste disposal. The fourth and the final theme identified that most of the participants felt the need for implementations of changes regarding existing protocols, workshops/seminars, methods of waste disposal and sterilization and disinfection practices. Conclusion: The current qualitative study concluded that there is a need for better educational programs and hands-on training for all the healthcare personnel including the paramedical staff as well. The residents should have adequate knowledge of infection control practices to guide the nurses and should share the responsibility with the nurses in the practice of effective infection control measures

Keywords: healthcare-associated infections, infection control measures, perspectives, qualitative

Procedia PDF Downloads 198

Authors: Aditi Madan, Jayant Kumar Routray

Abstract:

Purpose: Over the years flood related risks have compounded due to increasing vulnerability caused by rapid urbanisation and growing population. This increase is an indication of the need for enhancing the preparedness of institutions to respond to floods. The study describes disaster management structure and its linkages with institutions involved in managing disasters. It addresses issues and challenges associated with readiness of disaster management institutions to respond to floods. It suggests policy options for enhancing the current state of readiness of institutions to respond by considering factors like institutional, manpower, financial, technical, leadership & networking, training and awareness programs, monitoring and evaluation. Methodology: The study is based on qualitative data with statements and outputs from primary and secondary sources to understand the institutional framework for disaster management in India. Primary data included field visits, interviews with officials from institutions managing disasters and the affected community to identify the challenges faced in engaging national, state, district and local level institutions in managing disasters. For focus group discussions, meetings were held with district project officers and coordinators, local officials, community based organisation, civil defence volunteers and community heads. These discussions were held to identify the challenges associated with preparedness to respond of institutions to floods. Findings: Results show that disasters are handled by district authority and the role of local institutions is limited to a reactive role during disaster. Data also indicates that although the existing institutional setup is well coordinated at the district level but needs improvement at the local level. Wide variations exist in awareness and perception among the officials engaged in managing disasters. Additionally, their roles and responsibilities need to be clearly defined with adequate budget and dedicated permanent staff for managing disasters. Institutions need to utilise the existing manpower through proper delegation of work. Originality: The study suggests that disaster risk reduction needs to focus more towards inclusivity of the local urban bodies. Wide variations exist in awareness and perception among the officials engaged in managing disasters. In order to ensure community participation, it is important to address their social and economic problems since such issues can overshadow attempts made for reducing risks. Thus, this paper suggests development of direct linkages among institutions and community for enhancing preparedness to respond to floods.

Keywords: preparedness, response, disaster, flood, community, institution

Procedia PDF Downloads 206

Authors: Qianxi Lv, Junying Liang

Abstract:

Among the various modes of interpreting, simultaneous interpreting (SI) is regarded as a ‘complex’ and ‘extreme condition’ of cognitive tasks while consecutive interpreters (CI) do not have to share processing capacity between tasks. Given that SI exerts great cognitive demand, it makes sense to posit that the output of SI may be more compromised than that of CI in the linguistic features. The bulk of the research has stressed the varying cognitive demand and processes involved in different modes of interpreting; however, related empirical research is sparse. In keeping with our interest in investigating the quantitative linguistic factors discriminating between SI and CI, the current study seeks to examine the potential lexical simplification, syntactic complexity and sequential organization mechanism with a self-made inter-model corpus of transcribed simultaneous and consecutive interpretation, translated speech and original speech texts with a total running word of 321960. The lexical features are extracted in terms of the lexical density, list head coverage, hapax legomena, and type-token ratio, as well as core vocabulary percentage. Dependency distance, an index for syntactic complexity and reflective of processing demand is employed. Frequency motif is a non-grammatically-bound sequential unit and is also used to visualize the local function distribution of interpreting the output. While SI is generally regarded as multitasking with high cognitive load, our findings evidently show that CI may impose heavier or taxing cognitive resource differently and hence yields more lexically and syntactically simplified output. In addition, the sequential features manifest that SI and CI organize the sequences from the source text in different ways into the output, to minimize the cognitive load respectively. We reasoned the results in the framework that cognitive demand is exerted both on maintaining and coordinating component of Working Memory. On the one hand, the information maintained in CI is inherently larger in volume compared to SI. On the other hand, time constraints directly influence the sentence reformulation process. The temporal pressure from the input in SI makes the interpreters only keep a small chunk of information in the focus of attention. Thus, SI interpreters usually produce the output by largely retaining the source structure so as to relieve the information from the working memory immediately after formulated in the target language. Conversely, CI interpreters receive at least a few sentences before reformulation, when they are more self-paced. CI interpreters may thus tend to retain and generate the information in a way to lessen the demand. In other words, interpreters cope with the high demand in the reformulation phase of CI by generating output with densely distributed function words, more content words of higher frequency values and fewer variations, simpler structures and more frequently used language sequences. We consequently propose a revised effort model based on the result for a better illustration of cognitive demand during both interpreting types.

Keywords: cognitive demand, corpus-based, dependency distance, frequency motif, interpreting types, lexical simplification, sequential units distribution, syntactic complexity

Procedia PDF Downloads 146

Authors: Ram Sharma, Esha Chatterjee, Santosh Kumar Guru, Kunal Nepali

Abstract:

A tractable anti-lung cancer agent was identified via the installation of a Ring C expanded synthetic analogue of the alkaloid vasicinone [7,8,9,10-tetrahydroazepino[2,1-b] quinazolin-12(6H)-one (TAZQ)] as a surface recognition part in the HDAC inhibitory three-component model. Noteworthy to mention that the candidature of TAZQ was deemed suitable for accommodation in HDAC inhibitory pharmacophore as per the results of the fragment recruitment process conducted by our laboratory. TAZQ was pinpointed through the fragment screening program as a synthetically flexible fragment endowed with some moderate cell growth inhibitory activity against the lung cancer cell lines, and it was anticipated that the use of the aforementioned fragment to generate hydroxamic acid functionality (zinc-binding motif) bearing HDAC inhibitors would boost the antitumor efficacy of TAZQ. Consistent with our aim of applying epigenetic targets to the treatment of lung cancer, a strikingly potent anti-lung cancer scaffold (compound 6) was pinpointed through a series of in-vitro experiments. Notably, the compounds manifested a magnificent activity profile against KRAS and EGFR mutant lung cancer cell lines (IC50 = 0.80 - 0.96 µM), and the effects were found to be mediated through preferential HDAC6 inhibition (IC50 = 12.9 nM). In addition to HDAC6 inhibition, the compounds also elicited HDAC1 and HDAC3 inhibitory activity with an IC50 value of 49.9 nM and 68.5 nM, respectively. The HDAC inhibitory ability of compound 6 was also confirmed from the results of the western blot experiment that revealed its potential to decrease the expression levels of HDAC isoforms (HDAC1, HDAC3, and HDAC6). Noteworthy to mention that complete downregulation of the HDAC6 isoform was exerted by compound 6 at 0.5 and 1 µM. Moreover, in another western blot experiment, treatment with hydroxamic acid 6 led to upregulation of H3 acK9 and α-Tubulin acK40 levels, ascertaining its inhibitory activity toward both the class I HDACs and Class II B HDACs. The results of other assays were also encouraging as treatment with compound 6 led to the suppression of the colony formation ability of A549 cells, induction of apoptosis, and increase in autophagic flux. In silico studies led us to rationalize the results of the experimental assay, and some key interactions of compound 6 with the amino acid residues of HDAC isoforms were identified. In light of the impressive activity spectrum of compound 6, a pH-responsive nanocarrier (hyaluronic acid-compound 6 nanoparticles) was prepared. The dialysis bag approach was used for the assessment of the nanoparticles under both normal and acidic circumstances, and the pH-sensitive nature of hyaluronic acid-compound 6 nanoparticles was confirmed. Delightfully, the nanoformulation was devoid of cytotoxicity against the L929 mouse fibroblast cells (normal settings) and exhibited selective cytotoxicity towards the A549 lung cancer cell lines. In a nutshell, compound 6 appears to be a promising adduct, and a detailed investigation of this compound might yield a therapeutic for the treatment of lung cancer.

Keywords: HDAC inhibitors, lung cancer, scaffold, hyaluronic acid, nanoparticles

Procedia PDF Downloads 69

Authors: Аndrey Marchenko, Oleg Linkov, Alexander Osetrov, Sergiy Kravchenko

Abstract:

The low-calorie of gases include biogas, coal gas, coke oven gas, associated petroleum gas, gases sewage, etc. These gases are usually released into the atmosphere or burned on flares, causing substantial damage to the environment. However, with the right approach, low-calorie gas fuel can become a valuable source of energy. Specified determines the relevance of areas related to the development of low-calorific gas utilization technologies. As an example, in the work considered one of way of utilization of coalmine gas, because Ukraine ranks fourth in the world in terms of coal mine gas emission (4.7% of total global emissions, or 1.2 billion m³ per year). Experts estimate that coal mine gas is actively released in the 70-80 percent of existing mines in Ukraine. The main component of coal mine gas is methane (25-60%) Methane in 21 times has a greater impact on the greenhouse effect than carbon dioxide disposal problem has become increasingly important in the context of the increasing need to address the problems of climate, ecology and environmental protection. So marked causes negative effect of both local and global nature. The efforts of the United Nations and the World Bank led to the adoption of the program 'Zero Routine Flaring by 2030' dedicated to the cessation of these gases burn in flares and disposing them with the ability to generate heat and electricity. This study proposes to use coal gas as a fuel for gas engines to generate heat and electricity. Analyzed the physical-chemical properties of low-calorie gas fuels were allowed to choose a suitable engine, as well as estimate the influence of the composition of the fuel at its techno-economic indicators. Most suitable for low-calorie gas is engine with pre-combustion chamber jet ignition. In Ukraine is accumulated extensive experience in exploitation and production of gas engines with capacity of 1100 kW type GD100 (10GDN 207/2 * 254) fueled by natural gas. By using system pre- combustion chamber jet ignition and quality control in the engines type GD100 introduces the concept of burning depleted burn fuel mixtures, which in turn leads to decrease in the concentration of harmful substances of exhaust gases. The main problems of coal mine gas as a fuel for ICE is low calorific value, the presence of components that adversely affect combustion processes and terms of operation of the ICE, the instability of the composition, weak ignition. In some cases, these problems can be solved by adaptation engine design using coal mine gas as fuel (changing compression ratio, fuel injection quantity increases, change ignition time, increase energy plugs, etc.). It is shown that the use of coal mine gas engines with prechamber has not led to significant changes in the indicator parameters (ηi = 0.43 - 0.45). However, this significantly increases the volumetric fuel consumption, which requires increased fuel injection quantity to ensure constant nominal engine power. Thus, the utilization of low-calorie gas fuels in stationary gas engine type-based GD100 will significantly reduce emissions of harmful substances into the atmosphere when the generate cheap electricity and heat.

Keywords: gas engine, low-calorie gas, methane, pre-combustion chamber, utilization

Procedia PDF Downloads 241

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 107

Authors: Chang-Hui Shen, Michelle Esposito, Andrew J. Shen, Michael Adejokun, Diana Laterman

Abstract:

The packaging of DNA into nucleosomes is critical to genomic compaction, yet it can leave gene promoters inaccessible to activator proteins or transcription machinery and thus prevents transcriptional initiation. Both chromatin remodelers and histone acetylases (HATs) are the two main transcription co-activators that can reconfigure chromatin structure for transcriptional activation. Ino80p is the core component of the INO80 remodeling complex. Recently, it was shown that Ino80p dissociates from the yeast INO1 promoter after induction. However, when certain HATs were deleted or mutated, Ino80p accumulated at the promoters during gene activation. This suggests a link between HATs’ presence and Ino80p’s dissociation. However, it has yet to be demonstrated that Ino80p can be acetylated. To determine if Ino80p can be acetylated, wild-type Saccharomyces cerevisiae cells carrying Ino80p engineered with a double FLAG tag (MATa INO80-FLAG his3∆200 leu2∆0 met15∆0 trp1∆63 ura3∆0) were grown to mid log phase, as were non-tagged wild type (WT) (MATa his3∆200 leu2∆0 met15∆0 trp1∆63 ura3∆0) and ino80∆ (MATa ino80∆::TRP1 his3∆200 leu2∆0 met15∆0 trp1∆63 ura3∆0) cells as controls. Cells were harvested, and the cell lysates were subjected to immunoprecipitation (IP) with α-FLAG resin to isolate Ino80p. These eluted IP samples were subjected to SDS-PAGE and Western blot analysis. Subsequently, the blots were probed with the α-FLAG and α-acetyl lysine antibodies, respectively. For the blot probed with α-FLAG, one prominent band was shown in the INO80-FLAG cells, but no band was detected in the IP samples from the WT and ino80∆ cells. For the blot probed with the α-acetyl lysine antibody, we detected acetylated Ino80p in the INO80-FLAG strain while no bands were observed in the control strains. As such, our results showed that Ino80p can be acetylated. This acetylation can explain the co-activator’s recruitment patterns observed in current gene activation models. In yeast INO1, it has been shown that Ino80p is recruited to the promoter during repression, and then dissociates from the promoter once de-repression begins. Histone acetylases, on the other hand, have the opposite pattern of recruitment, as they have an increased presence at the promoter as INO1 de-repression commences. This Ino80p recruitment pattern significantly changes when HAT mutant strains are studied. It was observed that instead of dissociating, Ino80p accumulates at the promoter in the absence of functional HATs, such as Gcn5p or Esa1p, under de-repressing processes. As such, Ino80p acetylation may be required for its proper dissociation from the promoters. The remodelers’ dissociation mechanism may also have a wide range of implications with respect to transcriptional initiation, elongation, or even repression as it allows for increased spatial access to the promoter for the various transcription factors and regulators that need to bind in that region. Our findings here suggest a previously uncharacterized interaction between Ino80p and other co-activators recruited to promoters. As such, further analysis of Ino80p acetylation not only will provide insight into the role of epigenetic modifications in transcriptional activation, but also gives insight into the interactions occurring between co-activators at gene promoters during gene regulation.

Keywords: acetylation, chromatin remodeler, epigenetic modification, Ino80p

Procedia PDF Downloads 150

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 63