Search results for: 3D textured model

Authors: Promise Ekpo Osaine, Daniel Melesse

Abstract:

Image captioning is an active area of research in the multi-modal artificial intelligence (AI) community as it connects vision and language understanding, especially in settings where it is required that a model understands the content shown in an image and generates semantically and grammatically correct descriptions. In this project, we followed a standard approach to a deep learning-based image captioning model, injecting architecture for the encoder-decoder setup, where the encoder extracts image features, and the decoder generates a sequence of words that represents the image content. As such, we investigated image encoders, which are ResNet101, InceptionResNetV2, EfficientNetB7, EfficientNetV2M, and CLIP. As a caption generation structure, we explored long short-term memory (LSTM). The CLIP-LSTM model demonstrated superior performance compared to the encoder-decoder models, achieving a BLEU-1 score of 0.904 and a BLEU-4 score of 0.640. Additionally, among the CNN-LSTM models, EfficientNetV2M-LSTM exhibited the highest performance with a BLEU-1 score of 0.896 and a BLEU-4 score of 0.586 while using a single-layer LSTM.

Keywords: multi-modal AI systems, image captioning, encoder, decoder, BLUE score

Procedia PDF Downloads 79

Authors: Jiazhen Chen, Yue Sun, Joanne Yip, Kit-Lun Yick

Abstract:

The design of sports bras poses a considerable challenge due to the difficulty in accurately predicting the wearing result after computer-aided design (CAD). It needs repeated physical try-on or virtual try-on to obtain a comfortable pressure range during motion. Specifically, in the context of running, the exact support area and force exerted on the breasts remain unclear. Consequently, obtaining an effective method to design the sports bra pads shape becomes particularly challenging. This predicament hinders the successful creation and production of sports bras that cater to women's health needs. The purpose of this study is to propose an effective method to obtain the 3D shape of sports bra pads and to understand the relationship between the supporting force and the 3D shape parameters of the pads. Firstly, the static 3D shape of the sports bra pad and human motion data (Running) are obtained by using the 3D scanner and advanced 4D scanning technology. The 3D shape of the sports bra pad is parameterised and simplified by Free-form Deformation (FFD). Then the sub-models of sports bra and human body are constructed by segmenting and meshing them with MSC Apex software. The material coefficient of sports bras is obtained by material testing. The Marc software is then utilised to establish a dynamic contact model between the human breast and the sports bra pad. To realise the reverse design of the sports bra pad, this contact model serves as a forward model for calculating the inverse problem. Based on the forward contact model, the inverse problem of the 3D shape parameters of the sports bra pad with the target bra-wearing pressure range as the boundary condition is solved. Finally, the credibility and accuracy of the simulation are validated by comparing the experimental results with the simulations by the FE model on the pressure distribution. On the one hand, this research allows for a more accurate understanding of the support area and force distribution on the breasts during running. On the other hand, this study can contribute to the customization of sports bra pads for different individuals. It can help to obtain sports bra pads with comfortable dynamic pressure.

Keywords: sports bra design, breast motion, running, inverse problem, finite element dynamic model

Procedia PDF Downloads 60

Authors: Brian Connett, Bryan O'Halloran

Abstract:

Systems assets within critical infrastructures were seemingly safe from the exploitation or attack by nefarious cyberspace actors. Now, critical infrastructure is a target and the resources to exploit the cyber physical systems exist. These resources are characterized in terms of patience, stealth, replication-ability and extraordinary robustness. System owners are obligated to maintain a high level of protection measures. The difficulty lies in knowing when to fortify a critical infrastructure against an impending attack. Models currently exist that demonstrate the value of knowing the attacker’s capabilities in the cyber realm and the strength of the target. The shortcomings of these models are that they are not designed to respond to the inherent fast timing of an attack, an impetus that can be derived based on open-source reporting, common knowledge of exploits of and the physical architecture of the infrastructure. A useful model will inform systems owners how to align infrastructure architecture in a manner that is responsive to the capability, willingness and timing of the attacker. This research group has used an existing theoretical model for estimating parameters, and through analysis, to develop a decision tool for would-be target owners. The continuation of the research develops further this model by estimating the variable parameters. Understanding these parameter estimations will uniquely position the decision maker to posture having revealed the vulnerabilities of an attacker’s, persistence and stealth. This research explores different approaches to improve on current attacker-defender models that focus on cyber threats. An existing foundational model takes the point of view of an attacker who must decide what cyber resource to use and when to use it to exploit a system vulnerability. It is valuable for estimating parameters for the model, and through analysis, develop a decision tool for would-be target owners.

Keywords: critical infrastructure, cyber physical systems, modeling, exploitation

Procedia PDF Downloads 194

Authors: Jun-Ho Chung, Sung-Hyun Yoo, In-Hwan Choi, Hyun-Kook Lee, Moon-Kyu Song, Choon-Ki Ahn

Abstract:

The extended finite impulse response (EFIR) filter is addressed to optimize membership functions (MFs) of the fuzzy model that has strong nonlinearity. MFs are important parts of the fuzzy logic system (FLS) and, thus optimizing MFs of FLS is one of approaches to improve the performance of output. We employ the EFIR as an alternative optimization option to nonlinear fuzzy model. The performance of EFIR is demonstrated on a fuzzy cruise control via a numerical example.

Keywords: fuzzy logic system, optimization, membership function, extended FIR filter

Procedia PDF Downloads 724

Authors: Bernard Doherty, Andrew Jelfs, Aveek Dasgupta, Patrick Holden

Abstract:

Many companies have moved to agile and hybrid agile methodologies where portions of the Software Design Life-cycle (SDLC) and Software Test Life-cycle (STLC) can be time boxed in order to enhance delivery speed, quality and to increase flexibility to changes in software requirements. Despite widespread proliferation of agile practices, implementation often fails due to lack of adequate project management support, decreased motivation or fear of increased interaction. Consequently, few organizations effectively adopt agile processes with tailoring often required to integrate agile methodology in large scale environments. This paper provides an overview of the challenges in implementing an innovative large-scale tailored realization of the agile methodology termed the Agile Factory Model (AFM), with the aim of comparing and contrasting issues of specific importance to organizations undertaking large scale agile development. The conclusions demonstrate that agile practices can be effectively translated to a globally distributed development environment.

Keywords: agile, agile factory model, globally distributed development, large-scale agile

Procedia PDF Downloads 294

Authors: M. Mana, M. S. Ouali, L. C. de Menorval

Abstract:

A spent bleaching earth from an edible oil refinery has been treated by impregnation with a normal sodium hydroxide solution followed by mild thermal treatment (100°C). The obtained material (TSBE) was washed, dried and characterized by X-ray diffraction, FTIR, SEM, BET, and thermal analysis. The clay structure was not apparently affected by the treatment and the impregnated organic matter was quantitatively removed. We have investigated the comparative sorption of safranine and methylene blue on this material, the spent bleaching earth (SBE) and the virgin bleaching earth (VBE). The kinetic results fit the pseudo second order kinetic model and the Weber & Morris, intra-particle diffusion model. The pH had no effect on the sorption efficiency. The sorption isotherms followed the Langmuir model for various sorbent concentrations with good values of determination coefficient. A linear relationship was found between the calculated maximum removal capacity and the solid/solution ratio. A comparison between the results obtained with this material and those of the literature highlighted the low cost and the good removal capacity of the treated spent bleaching earth.

Keywords: basic dyes, isotherms, sorption, spent bleaching earth

Procedia PDF Downloads 250

Authors: Erez Yerushalmi, Sani Ziv

Abstract:

The rising demand for healthcare services, without a corresponding rise in public supply, led to a debate on whether to increase private healthcare provision - especially in hospital services and second-tier healthcare. Proponents for increasing private healthcare highlight gains in efficiency, while opponents its risk to social welfare. None, however, provide a measure of the social value and its impact on the economy in terms of a monetary value. In this paper, we impute a minimum social value of public healthcare that corresponds to indifference between gains in efficiency, with losses to social welfare. Our approach resembles contingent valuation methods that introduce a hypothetical market for non-commodities, but is different from them because we use numerical simulation techniques to exploit certain market failure conditions. In this paper, we develop a general equilibrium model that distinguishes between public-private healthcare services and public-private financing. Furthermore, the social value is modelled as a by product of healthcare services. The model is then calibrated to our unique health focused Social Accounting Matrix of Israel, and simulates the introduction of a hypothetical health-labour market - given that it is heavily regulated in the baseline (i.e., the true situation in Israel today). For baseline parameters, we estimate the minimum social value at around 18% public healthcare financing. The intuition is that the gain in economic welfare from improved efficiency, is offset by the loss in social welfare due to a reduction in available social value. We furthermore simulate a deregulated healthcare scenario that internalizes the imputed value of social value and searches for the optimal weight of public and private healthcare provision.

Keywords: contingent valuation method (CVM), general equilibrium model, hypothetical market, private-public healthcare, social value of public healthcare

Procedia PDF Downloads 148

Authors: Vytautas Galvanauskas, Rimvydas Simutis, Donatas Levisauskas, Vykantas Grincas, Renaldas Urniezius

Abstract:

The paper deals with model-based development and implementation of efficient control strategies for recombinant protein synthesis in fed-batch E.coli cultivation processes. Based on experimental data, a kinetic dynamic model for cultivation process was developed. This model was used to determine substrate feeding strategies during the cultivation. The proposed feeding strategy consists of two phases – biomass growth phase and recombinant protein production phase. In the first process phase, substrate-limited process is recommended when the specific growth rate of biomass is about 90-95% of its maximum value. This ensures reduction of glucose concentration in the medium, improves process repeatability, reduces the development of secondary metabolites and other unwanted by-products. The substrate limitation can be enhanced to satisfy restriction on maximum oxygen transfer rate in the bioreactor and to guarantee necessary dissolved carbon dioxide concentration in culture media. In the recombinant protein production phase, the level of substrate limitation and specific growth rate are selected within the range to enable optimal target protein synthesis rate. To account for complex process dynamics, to efficiently exploit the oxygen transfer capability of the bioreactor, and to maintain the required dissolved oxygen concentration, adaptive control algorithms for dissolved oxygen control have been proposed. The developed model-based control strategies are useful in scale-up of cultivation processes and accelerate implementation of innovative biotechnological processes for industrial applications.

Keywords: adaptive algorithms, model-based control, recombinant E. coli, scale-up of bioprocesses

Procedia PDF Downloads 258

Authors: Zhifei Hu, Feng Xia

Abstract:

In recent years, Graph neural network has been widely used in knowledge graph recommendation. The existing recommendation methods based on graph neural network extract information from knowledge graph through entity and relation, which may not be efficient in the way of information extraction. In order to better propose useful entity information for the current recommendation task in the knowledge graph, we propose an end-to-end Neural network Model based on multi-stream graph attentional Mechanism (MSGAT), which can effectively integrate the knowledge graph into the recommendation system by evaluating the importance of entities from both users and items. Specifically, we use the attention mechanism from the user's perspective to distil the domain nodes information of the predicted item in the knowledge graph, to enhance the user's information on items, and generate the feature representation of the predicted item. Due to user history, click items can reflect the user's interest distribution, we propose a multi-stream attention mechanism, based on the user's preference for entities and relationships, and the similarity between items to be predicted and entities, aggregate user history click item's neighborhood entity information in the knowledge graph and generate the user's feature representation. We evaluate our model on three real recommendation datasets: Movielens-1M (ML-1M), LFM-1B 2015 (LFM-1B), and Amazon-Book (AZ-book). Experimental results show that compared with the most advanced models, our proposed model can better capture the entity information in the knowledge graph, which proves the validity and accuracy of the model.

Keywords: graph attention network, knowledge graph, recommendation, information propagation

Procedia PDF Downloads 121

Authors: Keyvan Kashkouli Nejad, Motoaki Sugiura, Atsushi Sato, Takayuki Nozawa, Hyeonjeong Jeong, Sugiko Hanawa , Yuka Kotozaki, Ryuta Kawashima

Abstract:

The perception of agency/control is altered with presence of discrepancies in the environment or mismatch of predictions (of possible results) and actual results the sense of agency might become altered. Synofzik et al. proposed a two layer model of agency: In the first layer, the Feeling of Agency (FoA) is not directly available to awareness; a slight mismatch in the environment/outcome might cause alterations in FoA, while the agent still feels in control. If the discrepancy passes a threshold, it becomes available to consciousness and alters Judgment of Agency (JoA), which is directly available in the person’s awareness. Most experiments so far only investigate subjects rather conscious JoA, while FoA has been neglected. In this experiment we target FoA by using subliminal discrepancies that can not be consciously detectable by the subjects. Here, we explore whether we can detect this two level model in the subjects behavior and then try to map this in their brain activity. To do this, in a fMRI study, we incorporated both consciously detectable mismatching between action and result and also subliminal discrepancies in the environment. Also, unlike previous experiments where subjective questions from the participants mainly trigger the rather conscious JoA, we also tried to measure the rather implicit FoA by asking participants to rate their performance. We compared behavioral results and also brain activation when there were conscious discrepancies and when there were subliminal discrepancies against trials with no discrepancies and against each other. In line with our expectations, conditions with consciously detectable incongruencies triggered lower JoA ratings than conditions without. Also, conditions with any type of discrepancies had lower FoA ratings compared to conditions without. Additionally, we found out that TPJ and angular gyrus in particular to have a role in coding of JoA and also FoA.

Keywords: agency, fMRI, TPJ, two layer model

Procedia PDF Downloads 471

Authors: Mirijam Vrabec, Marian Janak, Bojan Ambrozic, Angelja K. Surca, Nastja Rogan Smuc, Nina Zupancic, Saso Sturm

Abstract:

Natural microdiamonds and moissanite (SiC) can form during the orogenic events under ultrahigh-pressure metamorphic conditions (UHP), when parts of Earth’s crust are subducted to extreme depths. So far, such processes were identified only in few places on the Earth, and therefore, represent unique opportunity to study the evolution of the Earth’s deep interior. An important discovery of microdiamonds and moissanite was reported from Pohorje, (Slovenia), where they occurred as single or polyphase inclusions in garnets. Metasedimentary rocks from Pohorje are predominantly gneisses representing parts of the Austroalpine metamorphic units of the Eastern Alps. During Cretaceous orogeny, (ca. 95–92 Ma) continental crustal rocks were deeply subducted to the mantle depths (below 100 km) and metamorphosed at pressures exceeding 3.5 GPa and temperatures between 800–850 °C. Microstructural and phase analysis of the inclusions as well as detailed elemental analysis of host garnets were carried out combining several analytical techniques: optical microscope in plane polarized transmitted light, electron probe microanalysis (EPMA) with wavelength-dispersive x-ray spectrometry (WDS) and field-emission scanning microscope (FEG-SEM) with energy-dispersive x-ray spectroscopy (EDS). Micro-Raman analysis revealed sharp, first order diamond bands sometimes accompanied by graphite bands implying that transformation of diamond back to graphite occurred. To study the chemical and crystallographic relationship between microdiamonds and co-inclusions, advanced techniques of transmission electron microscopy (TEM) were applied, which included high-angle annular dark-field scanning transmission electron microscopy (HAADF-STEM), combined with EDS and electron energy-loss spectroscopy (EELS). To prepare electron transparent TEM lamellae selectively a dual-beam Focused Ion Beam/SEM (FIB/SEM) was employed. Detailed study of TEM lamellae, which was cross-sectioned from the highly faceted inclusion body located within the host garnet crystal matrix, revealed rich and rather complex internal structure. Namely, the negative crystal facets of the main inclusion body were typically decorated with up to 1 μm thick amorphous layer, reflecting the general garnet composition with slight variations in Fe/Ca content. Within these layers, ELNES analysis revealed the presence of a 28–30 nm thick layer of amorphous carbon. The very last section of this layer corresponds to composition of SiO2. Within the inclusion, besides diamond and moissanite alumosilicate mineral with pronounced layered structure, iron sulfides and chlorine were identified under TEM and CO2 and CH4 using Raman. Moissanite is found as single crystal or composed from numerous highly textured nano-crystals with the average size of 10 nm. Moissanite inclusions were found embedded inside the amorphous crust implying that moissanite crystalized well before the deposition of the amorphous layer. From the microstructural, crystallographic and chemical observations so far we can deduce, that polyphase inclusions in diamond bearing garnets from Pohorje most probably crystallized from reduced supercritical fluids. Based on layered interface structure of the host mineral multiphase process of crystallization is possible. The presence of microdiamonds and moissanite in rocks from Pohorje demonstrates that these parts of the Eastern Alps were subducted to extreme depths, and were subsequently exhumed back to the Earth's surface without complete breakdown of UHP mineral phases, allowing a rear and exceptional opportunity to study them in-situ.

Keywords: diamond, fluid inclusions, moissanite, TEM, UHP metamorphism.

Procedia PDF Downloads 306

Authors: Rabia Korkmaz Tan, Şebnem Bora

Abstract:

The major problem encountered when modeling complex systems with agent-based modeling and simulation techniques is the existence of large parameter spaces. A complex system model cannot be expected to reflect the whole of the real system, but by specifying the most appropriate parameters, the actual system can be represented by the model under certain conditions. When the studies conducted in recent years were reviewed, it has been observed that there are few studies for parameter tuning problem in agent based simulations, and these studies have focused on tuning parameters of a single model. In this study, an approach of parameter tuning is proposed by using metaheuristic algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Artificial Bee Colonies (ABC), Firefly (FA) algorithms. With this hybrid structured study, the parameter tuning problems of the models in the different fields were solved. The new approach offered was tested in two different models, and its achievements in different problems were compared. The simulations and the results reveal that this proposed study is better than the existing parameter tuning studies.

Keywords: parameter tuning, agent based modeling and simulation, metaheuristic algorithms, complex systems

Procedia PDF Downloads 230

Authors: Katerina Kormusheva

Abstract:

Pricing plays a pivotal role in the marketing discipline as it directly influences consumer perceptions, purchase decisions, and overall market positioning of a product or service. This paper seeks to expand current knowledge in the area of discriminatory and differential pricing, a main area of marketing research. The methodology includes developing a framework and a model for determining how many price points to implement in differential pricing. We focus on choosing the levels of differentiation, derive a function form of the model framework proposed, and lastly, test it empirically with data from a large-scale marketing pricing experiment of services in telecommunications.

Keywords: marketing, differential pricing, price points, optimization

Procedia PDF Downloads 94

Authors: Timothée Bligny, Clément Codron, Antoine Estruch, Nicolas Girodet, Clément Ginet

Abstract:

Collateralized Debt Obligations are not as widely used nowadays as they were before 2007 Subprime crisis. Nonetheless there remains an enthralling challenge to optimize cash flows associated with synthetic CDOs. A Gaussian-based model is used here in which default correlation and unconditional probabilities of default are highlighted. Then numerous simulations are performed based on this model for different scenarios in order to evaluate the associated cash flows given a specific number of defaults at different periods of time. Cash flows are not solely calculated on a single bought or sold tranche but rather on a combination of bought and sold tranches. With some assumptions, the simplex algorithm gives a way to find the maximum cash flow according to correlation of defaults and maturities. The used Gaussian model is not realistic in crisis situations. Besides present system does not handle buying or selling a portion of a tranche but only the whole tranche. However the work provides the investor with relevant elements on how to know what and when to buy and sell.

Keywords: synthetic collateralized debt obligation (CDO), credit default swap (CDS), cash flow optimization, probability of default, default correlation, strategies, simulation, simplex

Procedia PDF Downloads 277

Authors: Abdolreza Memari

Abstract:

In this article in order to estimate the viscosity of crude oil,a numerical method has been used. We use this method to measure the crude oil's viscosity for 3 states: Saturated oil's viscosity, viscosity above the bubble point and viscosity under the saturation pressure. Then the crude oil's viscosity is estimated by using KHAN model and roller ball method. After that using these data that include efficient conditions in measuring viscosity, the estimated viscosity by the presented method, a radial based neural method, is taught. This network is a kind of two layered artificial neural network that its stimulation function of hidden layer is Gaussian function and teaching algorithms are used to teach them. After teaching radial based neural network, results of experimental method and artificial intelligence are compared all together. Teaching this network, we are able to estimate crude oil's viscosity without using KHAN model and experimental conditions and under any other condition with acceptable accuracy. Results show that radial neural network has high capability of estimating crude oil saving in time and cost is another advantage of this investigation.

Keywords: viscosity, Iranian crude oil, radial based, neural network, roller ball method, KHAN model

Procedia PDF Downloads 503

Authors: J. K. Adedeji, M. O. Oyekanmi

Abstract:

This paper has critically examined the use of Machine Learning procedures in curbing unauthorized access into valuable areas of an organization. The use of passwords, pin codes, user’s identification in recent times has been partially successful in curbing crimes involving identities, hence the need for the design of a system which incorporates biometric characteristics such as DNA and pattern recognition of variations in facial expressions. The facial model used is the OpenCV library which is based on the use of certain physiological features, the Raspberry Pi 3 module is used to compile the OpenCV library, which extracts and stores the detected faces into the datasets directory through the use of camera. The model is trained with 50 epoch run in the database and recognized by the Local Binary Pattern Histogram (LBPH) recognizer contained in the OpenCV. The training algorithm used by the neural network is back propagation coded using python algorithmic language with 200 epoch runs to identify specific resemblance in the exclusive OR (XOR) output neurons. The research however confirmed that physiological parameters are better effective measures to curb crimes relating to identities.

Keywords: biometric characters, facial recognition, neural network, OpenCV

Procedia PDF Downloads 258

Authors: Anung Style Bukhori, Ani Dijah Rahajoe

Abstract:

Poverty poses a significant challenge in Indonesia, requiring an effective analytical approach to understand and address this issue. In this research, we applied the Naïve Bayes classification method to examine and classify poverty data in Indonesia. The main focus is on classifying data using RapidMiner, a powerful data analysis platform. The analysis process involves data splitting to train and test the classification model. First, we collected and prepared a poverty dataset that includes various factors such as education, employment, and health..The experimental results indicate that the Naïve Bayes classification model can provide accurate predictions regarding the risk of poverty. The use of RapidMiner in the analysis process offers flexibility and efficiency in evaluating the model's performance. The classification produces several values to serve as the standard for classifying poverty data in Indonesia using Naive Bayes. The accuracy result obtained is 40.26%, with a moderate recall result of 35.94%, a high recall result of 63.16%, and a low recall result of 38.03%. The precision for the moderate class is 58.97%, for the high class is 17.39%, and for the low class is 58.70%. These results can be seen from the graph below.

Keywords: poverty, classification, naïve bayes, Indonesia

Procedia PDF Downloads 63

Authors: Anastasios Papathanasiou, George Liontos, Athanasios Katsouras, Vasiliki Liagkou, Euripides Glavas

Abstract:

Email remains a crucial communication tool due to its efficiency, accessibility and cost-effectiveness, enabling rapid information exchange across global networks. However, the global adoption of email has also made it a prime target for cyber threats, including phishing, malware and Business Email Compromise (BEC) attacks, which exploit its integral role in personal and professional realms in order to perform fraud and data breaches. To combat these threats, this research advocates for a multi-layered defense strategy incorporating advanced technological tools such as anti-spam and anti-malware software, machine learning algorithms and authentication protocols. Moreover, we developed an artificial intelligence model specifically designed to analyze email headers and assess their security status. This AI-driven model examines various components of email headers, such as "From" addresses, ‘Received’ paths and the integrity of SPF, DKIM and DMARC records. Upon analysis, it generates comprehensive reports that indicate whether an email is likely to be malicious or benign. This capability empowers users to identify potentially dangerous emails promptly, enhancing their ability to avoid phishing attacks, malware infections and other cyber threats.

Keywords: email security, artificial intelligence, header analysis, threat detection, phishing, DMARC, DKIM, SPF, ai model

Procedia PDF Downloads 62

Authors: Jayesh Mahitkar, V. K. Singh, Surendra Singh Kachhwaha

Abstract:

Wire Mesh Heat Pipe (WMHP) as an effective component of thermal control system in the payload of spacecraft, utilizing ammonia to transfer efficient amount of heat. One dimensional generic and robust mathematical model with partial-analytical hydraulic approach (PAHA) is developed to study inside behaviour of WMHP. In this model, inside performance during operation is investigated like mass flow rate, and velocity along the wire mesh as well as vapour core is modeled respectively. This numerical model investigate heat flow along length, pressure drop along wire mesh as well as vapour line in axial direction. Furthermore, WMHP is modeled into equivalent resistance network such that total thermal resistance of heat pipe, temperature drop across evaporator end and condenser end is evaluated. This numerical investigation should be carried out for single layer and double layer wire mesh each with heat input at evaporator section is 10W, 20 W and 30 W at condenser temperature maintained at 20˚C.

Keywords: ammonia, heat transfer, modeling, wire mesh

Procedia PDF Downloads 280

Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi, Morvarid Lalenoor

Abstract:

Background: Plantar pressure distribution measurement has been used for a long time to assess foot disorders. Plantar pressure is an important component affecting the foot and ankle function and Changes in plantar pressure distribution could indicate various foot and ankle disorders. Morphologic and mechanical properties of the foot may be important factors affecting the plantar pressure distribution. Accurate and early measurement may help to reduce the prevalence of pes planus. With recent developments in technology, new techniques such as machine learning have been used to assist clinicians in predicting patients with foot disorders. Significance of the study: This study proposes a neural network learning-based flat foot classification methodology using static foot pressure distribution. Methodologies: Data were collected from 895 patients who were referred to a foot clinic due to foot disorders. Patients with pes planus were labeled by an experienced physician based on clinical examination. Then all subjects (with and without pes planus) were evaluated for static plantar pressures distribution. Patients who were diagnosed with the flat foot in both feet were included in the study. In the next step, the leg length was normalized and the network was trained for plantar pressure mapping images. Findings: From a total of 895 image data, 581 were labeled as pes planus. A computational neural network (CNN) ran to evaluate the performance of the proposed model. The prediction accuracy of the basic CNN-based model was performed and the prediction model was derived through the proposed methodology. In the basic CNN model, the training accuracy was 79.14%, and the test accuracy was 72.09%. Conclusion: This model can be easily and simply used by patients with pes planus and doctors to predict the classification of pes planus and prescreen for possible musculoskeletal disorders related to this condition. However, more models need to be considered and compared for higher accuracy.

Keywords: foot disorder, machine learning, neural network, pes planus

Procedia PDF Downloads 366

Authors: Sun Zhe, Ruggero Micheletto

Abstract:

The research of neural network is very important for the development of advanced next generation intelligent devices and the medical treatment. The most important part of the neural network research is the learning. The process of learning in our brain is essentially several adjustment processes of connection strength between neurons. It is very difficult to figure out how this mechanism works in the complex network and how the connection strength influences brain functions. For this reason, we made a model with only two coupled neurons and studied the influence of connection strength between them. To emulate the neuronal activity of realistic neurons, we prefer to use the Izhikevich neuron model. This model can simulate the neuron variables accurately and it’s simplicity is very suitable to implement on computers. In this research, the parameter ρ is used to estimate the correlation coefficient between spike train of two coupling neurons.We think the results is very important for figuring out the mechanism between synchronization of coupling neurons and synaptic plasticity. The result also presented the importance of the spike frequency adaptation in complex systems.

Keywords: neural networks, noise, stochastic processes, coupled neurons, correlation coefficient, synchronization, pacemaker, synaptic plasticity

Procedia PDF Downloads 286

Authors: Hesham Abd Elkhalek, Sherif M. Hafez, Yasser M. El Fahham

Abstract:

Allocating limited budget to maintain bridge networks and selecting effective maintenance strategies for each bridge represent challenging tasks for maintenance managers and decision makers. In Egypt, bridges are continuously deteriorating. In many cases, maintenance works are performed due to user complaints. The objective of this paper is to develop a practical and reliable framework to manage the maintenance, repair, and rehabilitation (MR&R) activities of Bridges network considering performance and budget limits. The model solves an optimization problem that maximizes the average condition of the entire network given the limited available budget using Genetic Algorithm (GA). The framework contains bridge inventory, condition assessment, repair cost calculation, deterioration prediction, and maintenance optimization. The developed model takes into account multiple parameters including serviceability requirements, budget allocation, element importance on structural safety and serviceability, bridge impact on network, and traffic. A questionnaire is conducted to complete the research scope. The proposed model is implemented in software, which provides a friendly user interface. The framework provides a multi-year maintenance plan for the entire network for up to five years. A case study of ten bridges is presented to validate and test the proposed model with data collected from Transportation Authorities in Egypt. Different scenarios are presented. The results are reasonable, feasible and within acceptable domain.

Keywords: bridge management systems (BMS), cost optimization condition assessment, fund allocation, Markov chain

Procedia PDF Downloads 292

Authors: Kaewkarn Phuangsombat, Arthit Phuangsombat, Anupun Terdwongworakul

Abstract:

Hard seeds will not grow and can cause mold in sprouting process. Thus, the hard seeds need to be separated from the normal seeds. Near infrared hyperspectral imaging in a range of 900 to 1700 nm was implemented to develop a model by partial least squares discriminant analysis to discriminate the hard seeds from the normal seeds. The orientation of the seeds was also studied to compare the performance of the models. The model based on hilum-up orientation achieved the best result giving the coefficient of determination of 0.98, and root mean square error of prediction of 0.07 with classification accuracy was equal to 100%.

Keywords: mung bean, near infrared, germinatability, hard seed

Procedia PDF Downloads 306

Authors: Sneha Thakur, Sanjeev Karmakar

Abstract:

This paper proposed hybrid Particle Swarm Optimization (PSO) – Long-Short Term Memory (LSTM) model for groundwater level prediction. The evaluation of the performance is realized using the parameters: root mean square error (RMSE) and mean absolute error (MAE). Ground water level forecasting will be very effective for planning water harvesting. Proper calculation of water level forecasting can overcome the problem of drought and flood to some extent. The objective of this work is to develop a ground water level forecasting model using deep learning technique integrated with optimization technique PSO by applying 29 years data of Chhattisgarh state, In-dia. It is important to find the precise forecasting in case of ground water level so that various water resource planning and water harvesting can be managed effectively.

Keywords: long short-term memory, particle swarm optimization, prediction, deep learning, groundwater level

Procedia PDF Downloads 80

Authors: Xi Gu, Guan Heng Yeoh, Victoria Timchenko

Abstract:

In the current work, a three-dimensional geometry of a 75% stenosed blood vessel is analysed. Large eddy simulation (LES) with the help of a dynamic subgrid scale Smagorinsky model is applied to model the turbulent pulsatile flow. The geometry, the transmural pressure and the properties of the blood and the elastic boundary were based on clinical measurement data. For the flexible wall model, a thin solid region is constructed around the 75% stenosed blood vessel. The deformation of this solid region was modelled as a deforming boundary to reduce the computational cost of the solid model. Fluid-structure interaction is realised via a two-way coupling between the blood flow modelled via LES and the deforming vessel. The information of the flow pressure and the wall motion was exchanged continually during the cycle by an arbitrary lagrangian-eulerian method. The boundary condition of current time step depended on previous solutions. The fluctuation of the velocity in the post-stenotic region was analysed in the study. The axial velocity at normalised position Z=0.5 shows a negative value near the vessel wall. The displacement of the elastic boundary was concerned in this study. In particular, the wall displacement at the systole and the diastole were compared. The negative displacement at the stenosis indicates a collapse at the maximum velocity and the deceleration phase.

Keywords: Large Eddy Simulation, Fluid Structural Interaction, constricted artery, Computational Fluid Dynamics

Procedia PDF Downloads 295

Authors: Fatemeh Jannesarvatan, Ghazaal Parastooei, Jimmy frerejan, Saedeh Mokhtari, Peter Van Rosmalen

Abstract:

Medical and dental education increasingly emphasizes the acquisition, integration, and coordination of complex knowledge, skills, and attitudes that can be applied in practical situations. Instructional design approaches have focused on using real-life tasks in order to facilitate complex learning in both real and simulated environments. The Four component instructional design (4C/ID) model has become a useful guideline for designing instructional materials that improve learning transfer, especially in health profession education. The objective of this study was to apply the 4C/ID model in the creation of virtual patients (VPs) that dental students can use to practice their clinical management and clinical reasoning skills. The study first explored the context and concept of complication factors and common errors for novices and how they can affect the design of a virtual patient program. The study then selected key dental information and considered the content needs of dental students. The design of virtual patients was based on the 4C/ID model's fundamental principles, which included: Designing learning tasks that reflect real patient scenarios and applying different levels of task complexity to challenge students to apply their knowledge and skills in different contexts. Creating varied learning materials that support students during the VP program and are closely integrated with the learning tasks and students' curricula. Cognitive feedback was provided at different levels of the program. Providing procedural information where students followed a step-by-step process from history taking to writing a comprehensive treatment plan. Four virtual patients were designed using the 4C/ID model's principles, and an experimental design was used to test the effectiveness of the principles in achieving the intended educational outcomes. The 4C/ID model provides an effective framework for designing engaging and successful virtual patients that support the transfer of knowledge and skills for dental students. However, there are some challenges and pitfalls that instructional designers should take into account when developing these educational tools.

Keywords: 4C/ID model, virtual patients, education, dental, instructional design

Procedia PDF Downloads 83

Authors: Kim Jin Sup

Abstract:

This paper presents a vertical hall effect device using current-mode. Among different geometries that have been studied and simulated using COMSOL Multiphysics, optimized cross-shaped model displayed the best sensitivity. The cross-shaped model emerged as the optimum plate to fit the lowest noise and residual offset and the best sensitivity. The symmetrical cross-shaped hall plate is widely used because of its high sensitivity and immunity to alignment tolerances resulting from the fabrication process. The hall effect device has been designed using a 0.18-μm CMOS technology. The simulation uses the nominal bias current of 12μA. The applied magnetic field is from 0 mT to 20 mT. Simulation results achieved in COMSOL and validated with respect to the electrical behavior of equivalent circuit for Cadence. Simulation results of the one structure over the 13 available samples shows for the best geometry a current-mode sensitivity of 6.6 %/T at 20mT. Acknowledgment: This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. R7117-16-0165, Development of Hall Effect Semiconductor for Smart Car and Device).

Keywords: vertical hall device, current-mode, crossed-shaped model, CMOS technology

Procedia PDF Downloads 294

Authors: Reza Zakerinejad

Abstract:

Gully erosion is a serious problem that threading the sustainability of agricultural area and rangeland and water in a large part of Iran. This type of water erosion is the main source of sedimentation in many catchment areas in the north of Iran. Since in many national assessment approaches just qualitative models were applied the aim of this study is to predict the spatial distribution of gully erosion processes by means of detail terrain analysis and GIS -based logistic regression in the loess deposition in a case study in the Golestan Province. This study the DEM with 25 meter result ion from ASTER data has been used. The Landsat ETM data have been used to mapping of land use. The TreeNet model as a stochastic modeling was applied to prediction the susceptible area for gully erosion. In this model ROC we have set 20 % of data as learning and 20 % as learning data. Therefore, applying the GIS and satellite image analysis techniques has been used to derive the input information for these stochastic models. The result of this study showed a high accurate map of potential for gully erosion.

Keywords: TreeNet model, terrain analysis, Golestan Province, Iran

Procedia PDF Downloads 538

Authors: Moustafa Osman Mohammed

Abstract:

The modeling of a spatial-economic database is crucial in recitation economic network structure to social development. Sustainability within the spatial-economic model gives attention to green businesses to comply with Earth’s Systems. The natural exchange patterns of ecosystems have consistent and periodic cycles to preserve energy and materials flow in systems ecology. When network topology influences formal and informal communication to function in systems ecology, ecosystems are postulated to valence the basic level of spatial sustainable outcome (i.e., project compatibility success). These referred instrumentalities impact various aspects of the second level of spatial sustainable outcomes (i.e., participant social security satisfaction). The sustainability outcomes are modeling composite structure based on a network analysis model to calculate the prosperity of panel databases for efficiency value, from 2005 to 2025. The database is modeling spatial structure to represent state-of-the-art value-orientation impact and corresponding complexity of sustainability issues (e.g., build a consistent database necessary to approach spatial structure; construct the spatial-economic-ecological model; develop a set of sustainability indicators associated with the model; allow quantification of social, economic and environmental impact; use the value-orientation as a set of important sustainability policy measures), and demonstrate spatial structure reliability. The structure of spatial-ecological model is established for management schemes from the perspective pollutants of multiple sources through the input–output criteria. These criteria evaluate the spillover effect to conduct Monte Carlo simulations and sensitivity analysis in a unique spatial structure. The balance within “equilibrium patterns,” such as collective biosphere features, has a composite index of many distributed feedback flows. The following have a dynamic structure related to physical and chemical properties for gradual prolong to incremental patterns. While these spatial structures argue from ecological modeling of resource savings, static loads are not decisive from an artistic/architectural perspective. The model attempts to unify analytic and analogical spatial structure for the development of urban environments in a relational database setting, using optimization software to integrate spatial structure where the process is based on the engineering topology of systems ecology.

Keywords: ecological modeling, spatial structure, orientation impact, composite index, industrial ecology

Procedia PDF Downloads 69

Authors: Sven Gehrke, Johannes Ruhland

Abstract:

Data is the oil of our time, without them progress would come to a hold [1]. On the other hand, the mistrust of data mining is increasing [2]. The paper at hand shows different aspects of the concept of trust and describes the information asymmetry of the typical stakeholders of a data mining project using the CRISP-DM phase model. Based on the identified influencing factors in relation to trust, problematic aspects of the current approach are verified using various interviews with the stakeholders. The results of the interviews confirm the theoretically identified weak points of the phase model with regard to trust and show potential research areas.

Keywords: trust, data mining, CRISP DM, stakeholder management

Procedia PDF Downloads 95