Search results for: neural interface

Authors: Abdulaziz Afandi

Abstract:

Minimizing the inventory cost, optimizing the inventory quantities, and increasing system operational availability are the main motivations to enhance forecasting demand of spare parts in a major power utility company in Medina. This paper reports in an effort made to optimize the orders quantities of spare parts by improving the method of forecasting the demand. The study focuses on equipment that has frequent spare parts purchase orders with uncertain demand. The pattern of the demand considers a lumpy pattern which makes conventional forecasting methods less effective. A comparison was made by benchmarking various methods of forecasting based on experts’ criteria to select the most suitable method for the case study. Three actual data sets were used to make the forecast in this case study. Two neural networks (NN) approaches were utilized and compared, namely long short-term memory (LSTM) and multilayer perceptron (MLP). The results as expected, showed that the NN models gave better results than traditional forecasting method (judgmental method). In addition, the LSTM model had a higher predictive accuracy than the MLP model.

Keywords: neural network, LSTM, MLP, forecasting demand, inventory management

Procedia PDF Downloads 131

Authors: Peter K. Galenko, Stefanie Koch, Markus Rettenmayr, Robert Wonneberger, Evgeny V. Kharanzhevskiy, Maria Zamoryanskaya, Vladimir Ankudinov

Abstract:

We analyze the structure of undercooled melts, crystal growth kinetics and amorphous/crystalline microstructure of rapidly solidifying glass-forming Pd-based and CuZr-based alloys. A dendrite growth model is developed using a combination of the kinetic phase-field model and mesoscopic sharp interface model. The model predicts features of crystallization kinetics in alloys from thermodynamically controlled growth (governed by the Gibbs free energy change on solidification) to the kinetically limited regime (governed by atomic attachment-detachment processes at the solid/liquid interface). Comparing critical undercoolings observed in the crystallization kinetics with experimental data on melt viscosity, atomistic simulation's data on liquid microstructure and theoretically predicted dendrite growth velocity allows us to conclude that the dendrite growth kinetics strongly depends on the cluster structure changes of the melt. The obtained data of theoretical and experimental investigations are used for interpretation of microstructure of samples processed in electro-magnetic levitator on board International Space Station in the frame of the project "MULTIPHAS" (European Space Agency and German Aerospace Center, 50WM1941) and "KINETIKA" (ROSKOSMOS).

Keywords: dendrite, kinetics, model, solidification

Procedia PDF Downloads 125

Authors: Simon R. Melchioly, Ibrahimu C. Mjemah, Isaac M. Marobhe

Abstract:

The main objective of this research was to identify new potential sources of groundwater resources using geophysical methods and also to demarcate the saltwater - freshwater interface. Kilwa Kisiwani Island geologically is covered mostly by Quaternary alluvial sediments, sand, and gravel. The geophysical techniques employed during the research include Vertical Electrical Sounding (VES), Earth Resistivity Tomography (ERT), and Transient Electromagnetics (TEM). Two-dimensional interpolated geophysical results show that there exist freshwater lenses formations that are potential aquifers on the Island with resistivity values ranging from 11.68 Ωm to 46.71 Ωm. These freshwater lenses are underlain by formation with brackish water in which the resistivity values are varying between 3.89 Ωm and 1.6 Ωm. Saltwater with resistivity less than 1 Ωm is found at the bottom being overlaid by brackish saturated formation. VES resistivity results show that 89% (16 out of 18) of the VES sites are potential for groundwater resources drilling while TEM results indicate that 75% (12 out of 16) of TEM sites are potential for groundwater borehole drilling. The recommended drilling depths for potential sites in Kilwa Kisiwani Island show that the maximum depth is 25 m and the minimum being 10 m below ground surface. The aquifer structure in Kilwa Kisiwani Island is a shallow, unconfined freshwater lenses floating above the seawater and the maximum thickness of the aquifer is 25 m for few selected VES and TEM sites while the minimum thickness being 10 m.

Keywords: groundwater, hydrogeophysical, Kilwa Kisiwani, freshwater, saltwater, resistivity

Procedia PDF Downloads 204

Authors: Reena Murali, David Peter S.

Abstract:

The small interfering RNA (siRNA) alters the regulatory role of mRNA during gene expression by translational inhibition. Recent studies shows that up regulation of mRNA cause serious diseases like Cancer. So designing effective siRNA with good knockdown effects play an important role in gene silencing. Various siRNA design tools had been developed earlier. In this work, we are trying to analyze the existing good scoring second generation siRNA predicting tools and to optimize the efficiency of siRNA prediction by designing a computational model using Artificial Neural Network and whole stacking energy (ΔG), which may help in gene silencing and drug design in cancer therapy. Our model is trained and tested against a large data set of siRNA sequences. Validation of our results is done by finding correlation coefficient of experimental versus observed inhibition efficacy of siRNA. We achieved a correlation coefficient of 0.727 in our previous computational model and we could improve the correlation coefficient up to 0.753 when the threshold of whole tacking energy is greater than or equal to -32.5 kcal/mol.

Keywords: artificial neural network, double stranded RNA, RNA interference, short interfering RNA

Procedia PDF Downloads 527

Authors: Zheng Zhihao

Abstract:

Recently, Knowledge Graph Framework Network (KGCN) has developed powerful capabilities in knowledge representation and reasoning tasks. However, traditional KGCN often uses a fixed weight mechanism when aggregating information, failing to make full use of rich structural information, resulting in a certain expression ability of node representation, and easily causing over-smoothing problems. In order to solve these challenges, the paper proposes an new graph neural network model called KGCN-STAR (Knowledge Graph Convolutional Network with Structural Adaptive Receptive Fields). This model dynamically adjusts the perception of each node by introducing a structural adaptive receptive field. wild range, and a subgraph aggregator is designed to capture local structural information more effectively. Experimental results show that KGCN-STAR shows significant performance improvement on multiple knowledge graph data sets, especially showing considerable capabilities in the task of representation learning of complex structures.

Keywords: knowledge graph, graph neural networks, structural adaptive receptive fields, information aggregation

Procedia PDF Downloads 41

Authors: Mustafa Sahin, İlkay Yavrucuk

Abstract:

This paper presents a wind turbine envelope protection control algorithm that protects Variable Speed Variable Pitch (VSVP) wind turbines from damage during operation throughout their below and above rated regions, i.e. from cut-in to cut-out wind speed. The proposed approach uses a neural network that can adapt to turbines and their operating points. An algorithm monitors instantaneous wind and turbine states, predicts a wind speed that would push the turbine to a pre-defined envelope limit and, when necessary, realizes an avoidance action. Simulations are realized using the MS Bladed Wind Turbine Simulation Model for the NREL 5 MW wind turbine equipped with baseline controllers. In all simulations, through the proposed algorithm, it is observed that the turbine operates safely within the allowable limit throughout the below and above rated regions. Two example cases, adaptations to turbine operating points for the below and above rated regions and protections are investigated in simulations to show the capability of the proposed envelope protection system (EPS) algorithm, which reduces excessive wind turbine loads and expectedly increases the turbine service life.

Keywords: adaptive envelope protection control, limit detection and avoidance, neural networks, ultimate load reduction, wind turbine power control

Procedia PDF Downloads 139

Authors: Luis Amador Jimenez, Md. Shohel Amin

Abstract:

Pavement performance models are based on projections of observed traffic loads, which makes uncertain to study funding strategies in the long run if history does not repeat. Neural networks can be used to estimate deterioration rates but the learning rate and momentum have not been properly investigated, in addition, economic evolvement could change traffic flows. This study addresses both issues through a case study for roads of Montreal that simulates traffic for a period of 50 years and deals with the measurement error of the pavement deterioration model. Travel demand models are applied to simulate annual average daily traffic (AADT) every 5 years. Accumulated equivalent single axle loads (ESALs) are calculated from the predicted AADT and locally observed truck distributions combined with truck factors. A back propagation Neural Network (BPN) method with a Generalized Delta Rule (GDR) learning algorithm is applied to estimate pavement deterioration models capable of overcoming measurement errors. Linear programming of lifecycle optimization is applied to identify M&R strategies that ensure good pavement condition while minimizing the budget. It was found that CAD 150 million is the minimum annual budget to good condition for arterial and local roads in Montreal. Montreal drivers prefer the use of public transportation for work and education purposes. Vehicle traffic is expected to double within 50 years, ESALS are expected to double the number of ESALs every 15 years. Roads in the island of Montreal need to undergo a stabilization period for about 25 years, a steady state seems to be reached after.

Keywords: pavement management system, traffic simulation, backpropagation neural network, performance modeling, measurement errors, linear programming, lifecycle optimization

Procedia PDF Downloads 461

Authors: Massimo Miccoli, Luca Marangoni, Alberto Aniello Scaringi, Alessandro Marceddu, Alessandro Amicone

Abstract:

The susceptibility of deep neural networks (DNNs) to adversarial manipulations is a recognized challenge within the computer vision domain. Adversarial examples, crafted by adding subtle yet malicious alterations to benign images, exploit this vulnerability. Various defense strategies have been proposed to safeguard DNNs against such attacks, stemming from diverse research hypotheses. Building upon prior work, our approach involves the utilization of autoencoder models. Autoencoders, a type of neural network, are trained to learn representations of training data and reconstruct inputs from these representations, typically minimizing reconstruction errors like mean squared error (MSE). Our autoencoder was trained on a dataset of benign examples; learning features specific to them. Consequently, when presented with significantly perturbed adversarial examples, the autoencoder exhibited high reconstruction errors. The architecture of the autoencoder was tailored to the dimensions of the images under evaluation. We considered various image sizes, constructing models differently for 256x256 and 512x512 images. Moreover, the choice of the computer vision model is crucial, as most adversarial attacks are designed with specific AI structures in mind. To mitigate this, we proposed a method to replace image-specific dimensions with a structure independent of both dimensions and neural network models, thereby enhancing robustness. Our multi-modal autoencoder reconstructs the spectral representation of images across the red-green-blue (RGB) color channels. To validate our approach, we conducted experiments using diverse datasets and subjected them to adversarial attacks using models such as ResNet50 and ViT_L_16 from the torch vision library. The autoencoder extracted features used in a classification model, resulting in an MSE (RGB) of 0.014, a classification accuracy of 97.33%, and a precision of 99%.

Keywords: adversarial attacks, malicious images detector, binary classifier, multimodal transformer autoencoder

Procedia PDF Downloads 117

Authors: Kaining Zhang, Lang Chen, Danyang Liu, Jianying Lu, Kun Yang, Junying Wu

Abstract:

In order to solve the problem of a large amount of simulation and limited simulation scale in the first-principle molecular dynamics simulation of energetic material detonation reaction, we established an artificial intelligence model for analyzing and predicting the detonation reaction mechanism of CL-20 based on the first-principle molecular dynamics simulation of the multiscale shock technique (MSST). We employed principal component analysis to identify the dominant charge features governing molecular reactions. We adopted the K-means clustering algorithm to cluster the reaction paths and screen out the key reactions. We introduced the neural network algorithm to construct the mapping relationship between the charge characteristics of the molecular structure and the key reaction characteristics so as to establish a calculation method for predicting detonation reactions based on the charge characteristics of CL-20 and realize the rapid analysis of the reaction mechanism of energetic materials.

Keywords: energetic material detonation reaction, first-principle molecular dynamics simulation of multiscale shock technique, neural network, CL-20

Procedia PDF Downloads 119

Authors: Boce Zhang

Abstract:

Strategic innovation of nanotechnology to promote food safety has drawn tremendous attentions among research groups, which includes the need for research support during the implementation of the Food Safety Modernization Act (FSMA) in the United States. There are urgent demands and knowledge gaps to the understanding of a) food-water-bacteria interface as for how pathogens persist and transmit during food processing and storage; b) minimum processing requirement needed to prevent pathogen cross-contamination in the food system. These knowledge gaps are of critical importance to the food industry. However, the lack of knowledge is largely hindered by the limitations of research tools. Our groups recently endeavored two novel engineering systems with biomimetics and microfluidics as a holistic approach to hazard analysis and risk mitigation, which provided unprecedented research opportunities to study pathogen behavior, in particular, contamination, and cross-contamination, at the critical food-water-pathogen interface. First, biomimetically-patterned surfaces (BPS) were developed to replicate the identical surface topography and chemistry of a natural food surface. We demonstrated that BPS is a superior research tool that empowers the study of a) how pathogens persist through sanitizer treatment, b) how to apply fluidic shear-force and surface tension to increase the vulnerability of the bacterial cells, by detaching them from a protected area, etc. Secondly, microfluidic devices were designed and fabricated to study the bactericidal kinetics in the sub-second time frame (0.1~1 second). The sub-second kinetics is critical because the cross-contamination process, which includes detachment, migration, and reattachment, can occur in a very short timeframe. With this microfluidic device, we were able to simulate and study these sub-second cross-contamination scenarios, and to further investigate the minimum sanitizer concentration needed to sufficiently prevent pathogen cross-contamination during the food processing. We anticipate that the findings from these studies will provide critical insight on bacterial behavior at the food-water-cell interface, and the kinetics of bacterial inactivation from a broad range of sanitizers and processing conditions, thus facilitating the development and implementation of science-based food safety regulations and practices to mitigate the food safety risks.

Keywords: biomimetic materials, microbial food safety, microfluidic device, nanotechnology

Procedia PDF Downloads 361

Authors: Ruxandra Barbulescu, Daniel Ioan, Gabriela Ciuprina

Abstract:

The saltatory conduction is the way the action potential is transmitted along a myelinated axon. The potential diffuses along the myelinated compartments and it is regenerated in the Ranvier nodes due to the ion channels allowing the flow across the membrane. For an efficient simulation of populations of neurons, it is important to use reduced order models both for myelinated compartments and for Ranvier nodes and to have control over their accuracy and inner parameters. The paper presents a reduced order model of this neural system which allows an efficient simulation method for the saltatory conduction in myelinated axons. This model is obtained by concatenating reduced order linear models of 1D myelinated compartments and nonlinear 0D models of Ranvier nodes. The models for the myelinated compartments are selected from a series of spatially distributed models developed and hierarchized according to their modeling errors. The extracted model described by a nonlinear PDE of hyperbolic type is able to reproduce the saltatory conduction with acceptable accuracy and takes into account the finite propagation speed of potential. Finally, this model is again reduced in order to make it suitable for the inclusion in large-scale neural circuits.

Keywords: action potential, myelinated segments, nonlinear models, Ranvier nodes, reduced order models, saltatory conduction

Procedia PDF Downloads 164

Authors: Yassamina Berkane, Leila Kloul, Yoann Demoli

Abstract:

Quality of life, environmental impact, congestion of mobility means, and infrastructures remain significant challenges for urban mobility. Solutions like car sharing, spatial redesign, eCommerce, and autonomous vehicles will likely increase the unit veh-km and the density of cars in urban traffic, thus reducing congestion. However, the impact of such solutions is not clear for researchers. Congestion arises from growing populations that must travel greater distances to arrive at similar locations (e.g., workplaces, schools) during the same time frame (e.g., rush hours). This paper first reviews the research and application cases of urban congestion methods through recent years. Rethinking the question of time, it then investigates people’s willingness and flexibility to adapt their arrival and departure times from workplaces. We use neural networks and methods of supervised learning to apply a new methodology for predicting peoples' intentions from their responses in a questionnaire. We created and distributed a questionnaire to more than 50 companies in the Paris suburb. Obtained results illustrate that our methodology can predict peoples' intentions to reschedule their activities (work, study, commerce, etc.).

Keywords: urban mobility, decongestion, machine learning, neural network

Procedia PDF Downloads 197

Authors: P. S. Jagadeesh Kumar, Yang Yung, Mingmin Pan, Xianpei Li, Wenli Hu

Abstract:

Glaucoma is impelled by optic nerve mutilation habitually represented as cupping and visual field injury frequently with an arcuate pattern of mid-peripheral loss, subordinate to retinal ganglion cell damage and death. Glaucoma is the second foremost cause of blindness and the chief cause of permanent blindness worldwide. Consequently, all-embracing study into the analysis and empathy of glaucoma is happening to escort deep learning based neural network intrusions to deliberate this substantial optic neuropathy. This paper advances an ophthalmic hashing based supervision of glaucoma and corneal disorders preeminent on deep graphical model. Ophthalmic hashing is a newly proposed method extending the efficacy of visual hash-coding to predict glaucoma corneal disorder matching, which is the faster than the existing methods. Deep graphical model is proficient of learning interior explications of corneal disorders in satisfactory time to solve hard combinatoric incongruities using deep Boltzmann machines.

Keywords: corneal disorders, deep Boltzmann machines, deep graphical model, glaucoma, neural networks, ophthalmic hashing

Procedia PDF Downloads 255

Authors: A. Basu, A. A. Purohit, M. M. Vaidya, M. D. Kudale

Abstract:

Mumbai, being traditionally the epicenter of India's trade and commerce, the existing major ports such as Mumbai and Jawaharlal Nehru Ports (JN) situated in Thane estuary are also developing its waterfront facilities. Various developments over the passage of decades in this region have changed the tidal flux entering/leaving the estuary. The intake at Pir-Pau is facing the problem of shortage of water in view of advancement of shoreline, while jetty near Ulwe faces the problem of ship scheduling due to existence of shallower depths between JN Port and Ulwe Bunder. In order to solve these problems, it is inevitable to have information about tide levels over a long duration by field measurements. However, field measurement is a tedious and costly affair; application of artificial intelligence was used to predict water levels by training the network for the measured tide data for one lunar tidal cycle. The application of two layered feed forward Artificial Neural Network (ANN) with back-propagation training algorithms such as Gradient Descent (GD) and Levenberg-Marquardt (LM) was used to predict the yearly tide levels at waterfront structures namely at Ulwe Bunder and Pir-Pau. The tide data collected at Apollo Bunder, Ulwe, and Vashi for a period of lunar tidal cycle (2013) was used to train, validate and test the neural networks. These trained networks having high co-relation coefficients (R= 0.998) were used to predict the tide at Ulwe, and Vashi for its verification with the measured tide for the year 2000 & 2013. The results indicate that the predicted tide levels by ANN give reasonably accurate estimation of tide. Hence, the trained network is used to predict the yearly tide data (2015) for Ulwe. Subsequently, the yearly tide data (2015) at Pir-Pau was predicted by using the neural network which was trained with the help of measured tide data (2000) of Apollo and Pir-Pau. The analysis of measured data and study reveals that: The measured tidal data at Pir-Pau, Vashi and Ulwe indicate that there is maximum amplification of tide by about 10-20 cm with a phase lag of 10-20 minutes with reference to the tide at Apollo Bunder (Mumbai). LM training algorithm is faster than GD and with increase in number of neurons in hidden layer and the performance of the network increases. The predicted tide levels by ANN at Pir-Pau and Ulwe provides valuable information about the occurrence of high and low water levels to plan the operation of pumping at Pir-Pau and improve ship schedule at Ulwe.

Keywords: artificial neural network, back-propagation, tide data, training algorithm

Procedia PDF Downloads 486

Authors: Shwetha B. S., Sirisha M., Vachana U., Aditya Kadlimatti, Manjushree N. S.

Abstract:

Braille script holds significant importance in bridging the communication gap for visually impaired individuals. However, the challenge of interpreting Braille for non-experts creates barriers in education and day-to-day interactions. This paper aims to develop a system that translates Braille text into multilingual speech using advanced Convolutional Neural Networks (CNNs) and Google Text-to-Speech (GTTS) technology. The proposed system employs image recognition techniques powered by CNNs to accurately identify and decode Braille characters from captured images. The deep learning model undergoes training on a diverse dataset of Braille symbols to ensure high accuracy and robustness. Among the models evaluated, AlexNet demonstrated the highest accuracy in decoding Braille characters. Once recognized, the decoded text is converted into speech in the user’s preferred language using the GTTS API. This system possesses the ability to greatly improve inclusivity by enabling real-time Braille interpretation for visually impaired individuals, educators, and caregivers.

Keywords: convolutional neural networks, Braille image, image-to-speech, GTTS, AlexNet, VGG16, DenseNet121, ResNet50

Procedia PDF Downloads 4

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 205

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 164

Authors: Kaiying Lai, Suiping Wang, Luodi Yu, Yang Zhang, Pengmin Qin

Abstract:

Abnormalities in auditory processing are one of the most commonly reported sensory processing impairments in children with Autism Spectrum Disorder (ASD). Tonal language speaker with autism has enhanced neural sensitivity to pitch changes in pure tone. However, not all children with ASD exhibit the same performance in pitch processing due to different auditory sensitivity. The current study aimed to examine auditory change detection in ASD with different auditory sensitivity. K-means clustering method was adopted to classify ASD participants into two groups according to the auditory processing scores of the Sensory Profile, 11 autism with hypersensitivity (mean age = 11.36 ; SD = 1.46) and 18 with hypo-sensitivity (mean age = 10.64; SD = 1.89) participated in a passive auditory oddball paradigm designed for eliciting mismatch negativity (MMN) under the pure tone condition. Results revealed that compared to hypersensitive autism, the children with hypo-sensitivity showed smaller MMN responses to pure tone stimuli. These results suggest that ASD with auditory hypersensitivity and hypo-sensitivity performed differently in processing pure tone, so neural responses to pure tone hold promise for predicting the auditory sensitivity of ASD and targeted treatment in children with ASD.

Keywords: ASD, sensory profile, pitch processing, mismatch negativity, MMN

Procedia PDF Downloads 395

Authors: Abebe Mulugojam Negash, Yongbin Yu, Ekong Favour, Bekalu Nigus Dawit, Molla Woretaw Teshome, Aynalem Birtukan Yirga

Abstract:

Breast cancer remains a significant health concern, necessitating advancements in diagnostic methodologies. Addressing this, our paper confronts the notable challenges in breast cancer classification, particularly the imbalance in datasets and the constraints in the accuracy and interpretability of prevailing deep learning approaches. We proposed an attention-based residual neural network (ResNet), which effectively combines the robust features of ResNet with an advanced attention mechanism. Enhanced through strategic data augmentation and positive weight adjustments, this approach specifically targets the issue of data imbalance. The proposed model is tested on the BreakHis dataset and achieved accuracies of 99.00%, 99.04%, 98.67%, and 98.08% in different magnifications (40X, 100X, 200X, and 400X), respectively. We evaluated the performance by using different evaluation metrics such as precision, recall, and F1-Score and made comparisons with other state-of-the-art methods. Our experiments demonstrate that the proposed model outperforms existing approaches, achieving higher accuracy in breast cancer classification.

Keywords: residual neural network, attention mechanism, positive weight, data augmentation

Procedia PDF Downloads 111

Authors: Tomas Berhanu Bekele

Abstract:

Traffic congestion is one of the main problems related to transportation in developed as well as developing countries. Traffic control systems are based on the idea of avoiding traffic instabilities and homogenizing traffic flow in such a way that the risk of accidents is minimized and traffic flow is maximized. Lately, Intelligent Transport Systems (ITS) has become an important area of research to solve such road traffic-related issues for making smart decisions. It links people, roads and vehicles together using communication technologies to increase safety and mobility. Moreover, accurate prediction of road traffic is important to manage traffic congestion. The aim of this study is to develop an ANN model for the prediction of traffic flow and to compare the ANN model with the linear regression model of traffic flow predictions. Data extraction was carried out in intervals of 15 minutes from the video player. Video of mixed traffic flow was taken and then counted during office work in order to determine the traffic volume. Vehicles were classified into six categories, namely Car, Motorcycle, Minibus, mid-bus, Bus, and Truck vehicles. The average time taken by each vehicle type to travel the trap length was measured by time displayed on a video screen.

Keywords: intelligent transport system (ITS), traffic flow prediction, artificial neural network (ANN), linear regression

Procedia PDF Downloads 72

Authors: Rakesh Namdeti

Abstract:

Toxic dyes found in industrial effluent must be treated before being disposed of due to their harmful impact on human health and aquatic life. Thus, Musa acuminata (Banana Leaves) was employed in the role of a biosorbent in this work to get rid of methylene blue derived from a synthetic solution. The effects of five process parameters, such as temperature, pH, biosorbent dosage, and initial methylene blue concentration, using a central composite design (CCD), and the percentage of dye clearance were investigated. The response was modelled using a quadratic model based on the CCD. The analysis of variance revealed the most influential element on experimental design response (ANOVA). The temperature of 44.30C, pH of 7.1, biosorbent dose of 0.3 g, starting methylene blue concentration of 48.4 mg/L, and 84.26 percent dye removal were the best conditions for Musa acuminata (Banana leave powder). At these ideal conditions, the experimental percentage of biosorption was 76.93. The link between the estimated results of the developed ANN model and the experimental results defined the success of ANN modeling. As a result, the study's experimental results were found to be quite close to the model's predicted outcomes.

Keywords: Musa acuminata, central composite design, methylene blue, artificial neural network

Procedia PDF Downloads 82

Authors: Shimaa Nagro, Russell Campion

Abstract:

Mobile devices are becoming ever more widely available, with growing functionality, and they are increasingly used as enabling technology to give students access to educational material anytime and anywhere. However, the design of educational material's user interfaces for mobile devices is beset by many unresolved research problems such as those arising from constraints associated with mobile devices or from issues linked to effective learning. The proposed research aims to produce: (i) a method framework for the design and evaluation of educational material’s interfaces to be delivered on mobile devices, in multimedia form based on Human Computer Interaction strategies; and (ii) a software tool implemented as a fast-track alternative to use the method framework in full. The investigation will combine qualitative and quantitative methods, including interviews and questionnaires for data collection and three case studies for validating the method framework. The method framework is a framework to enable an educational designer to effectively and efficiently create educational multimedia interfaces to be used on mobile devices by following a particular methodology that contains practical and usable tools and techniques. It is a method framework that accepts any educational material in its final lesson plan and deals with this plan as a static element, it will not suggest any changes in any information given in the lesson plan but it will help the instructor to design his final lesson plan in a multimedia format to be presented in mobile devices.

Keywords: mobile learning, M-Learn, HCI, educational multimedia, interface design

Procedia PDF Downloads 378

Authors: Sabahat Nadeem, Farman Ali Khan

Abstract:

Emotions are considered as a vital factor affecting the process of information handling, level of attention, memory capacity and decision making. Latest e-Learning systems are therefore taking into consideration the effective state of learners to make the learning process more effective and enjoyable. One such use of user’s affective information is in the systems that tend to regulate users’ emotions to a state optimally desirable for learning. So for, this objective has been tried to be achieved with the help of teaching strategies, background music, guided imagery, video clips and odors. Nevertheless, we know that colors can affect human emotions. Relationship between color and emotions has a strong influence on how we perceive our environment. Similarly, the colors of the interface can also affect the user positively as well as negatively. This affective behavior of color and its use as emotion regulation agent is not yet exploited. Therefore, this research proposes a Color-based Emotion Regulation Model (CERM), a new framework that can automatically adapt its colors according to user’s emotional state and her personality type and can help in producing a desirable emotional effect, aiming at providing an unobtrusive emotional support to the users of e-learning environment. The evaluation of CERM is carried out by comparing it with classical non-adaptive, static colored learning management system. Results indicate that colors of the interface, when carefully selected has significant positive impact on learner’s emotions.

Keywords: effective learning, e-learning, emotion regulation, emotional design

Procedia PDF Downloads 308

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 135

Authors: Mouli Banga, Chaya Ravindra

Abstract:

Wound classification is a crucial step in wound diagnosis. An effective classifier can aid wound specialists in identifying wound types with reduced financial and time investments, facilitating the determination of optimal treatment procedures. This study presents a deep neural network-based classifier that leverages wound images and their corresponding locations to categorize wounds into various classes, such as diabetic, pressure, surgical, and venous ulcers. By incorporating a developed body map, the process of tagging wound locations is significantly enhanced, providing healthcare specialists with a more efficient tool for wound analysis. We conducted a comparative analysis between two prominent convolutional neural network models, ResNet50 and MobileNetV2, utilizing a dataset of 730 images. Our findings reveal that the RestNet50 outperforms MovileNetV2, achieving an accuracy of approximately 90%, compared to MobileNetV2’s 83%. This disparity highlights the superior capability of ResNet50 in the context of this dataset. The results underscore the potential of integrating deep learning with spatial data to improve the precision and efficiency of wound diagnosis, ultimately contributing to better patient outcomes and reducing healthcare costs.

Keywords: wound classification, MobileNetV2, ResNet50, multimodel

Procedia PDF Downloads 38

Authors: Noah Emil Glisik

Abstract:

Multiple sclerosis (MS) is a chronic, immune-mediated disorder characterized by neurodegenerative processes and a highly variable disease course. Recent research highlights a complex interplay between psychological stress and MS progression, with both acute and chronic stressors linked to heightened inflammatory activity, increased relapse risk, and accelerated disability. This review synthesizes findings from systematic analyses, cohort studies, and neuroimaging investigations to examine how stress contributes to disease dynamics in MS. Evidence suggests that psychological stress influences MS progression through neural and physiological pathways, including dysregulation of the hypothalamic-pituitary-adrenal (HPA) axis and heightened activity in specific brain regions, such as the insular cortex. Notably, functional MRI studies indicate that stress-induced neural activity may predict future atrophy in gray matter regions implicated in motor and cognitive function, thus supporting a neurobiological link between stress and neurodegeneration in MS. Longitudinal studies further associate chronic stress with reduced quality of life and higher relapse frequency, emphasizing the need for a multifaceted therapeutic approach that addresses both the physical and psychological dimensions of MS. Evidence from intervention studies suggests that stress management strategies, such as cognitive-behavioral therapy and mindfulness-based programs, may reduce relapse rates and mitigate lesion formation in MS patients. These findings underscore the importance of integrating stress-reducing interventions into standard MS care, with potential to improve disease outcomes and patient well-being. Further research is essential to clarify the causal pathways and develop targeted interventions that could modify the stress response in MS, offering an avenue to address disease progression and enhance quality of life.

Keywords: multiple sclerosis, psychological stress, disease progression, neuroimaging, stress management

Procedia PDF Downloads 18

Authors: Monireh Ahmadi Bani, Adel Khorramrouz, Lalenoor Morvarid, Bagheri Mahtab

Abstract:

Background:- Foot disorders are common in musculoskeletal problems. Plantar pressure distribution measurement is one the most important part of foot disorders diagnosis for quantitative analysis. However, the association of plantar pressure and foot disorders is not clear. With the growth of dataset and machine learning methods, the relationship between foot disorders and plantar pressures can be detected. Significance of the study:- The purpose of this study was to predict the probability of common foot disorders based on peak plantar pressure distribution and center of pressure during walking. Methodologies:- 2323 participants were assessed in a foot therapy clinic between 2015 and 2021. Foot disorders were diagnosed by an experienced physician and then they were asked to walk on a force plate scanner. After the data preprocessing, due to the difference in walking time and foot size, we normalized the samples based on time and foot size. Some of force plate variables were selected as input to a deep neural network (DNN), and the probability of any each foot disorder was measured. In next step, we used support vector machine (SVM) and run dataset for each foot disorder (classification of yes or no). We compared DNN and SVM for foot disorders prediction based on plantar pressure distributions and center of pressure. Findings:- The results demonstrated that the accuracy of deep learning architecture is sufficient for most clinical and research applications in the study population. In addition, the SVM approach has more accuracy for predictions, enabling applications for foot disorders diagnosis. The detection accuracy was 71% by the deep learning algorithm and 78% by the SVM algorithm. Moreover, when we worked with peak plantar pressure distribution, it was more accurate than center of pressure dataset. Conclusion:- Both algorithms- deep learning and SVM will help therapist and patients to improve the data pool and enhance foot disorders prediction with less expense and error after removing some restrictions properly.

Keywords: deep neural network, foot disorder, plantar pressure, support vector machine

Procedia PDF Downloads 361

Authors: Touil Issam, Bouraghda Skander

Abstract:

This paper elaborates on the comprehensive design, development, and evaluation of an Arduino-powered robot car operated through an Android-based application. The system is built upon an Arduino UNO microcontroller, leveraging Bluetooth technology to facilitate seamless communication between the robot and the Android control interface. The primary objective of the project is to provide users with an intuitive and interactive means to control autonomous systems while ensuring simplicity, cost-efficiency, and reliability. The architecture of the system encompasses hardware and software integration, where the microcontroller acts as the central processing unit, handling signals received via Bluetooth and translating them into precise motor commands. The Android application serves as a user-friendly interface, enabling real-time control of the robot's movement and functionality. This paper delves into the technical aspects of system architecture, including the hardware components, wiring schematics, and Bluetooth module integration. Additionally, it highlights the software development process, emphasizing the programming logic, algorithm design, and debugging techniques employed. Testing and validation phases are thoroughly documented, showcasing the system's performance under various conditions, including speed, maneuverability, and Bluetooth signal range. The results confirm the project's success in achieving its goals, offering a robust and accessible solution for educational and practical applications in robotics.

Keywords: Arduino Robot, car, microcontroller, Bluetooth communication

Procedia PDF Downloads 14

Authors: R. Ramesh, K. K. Shivaraman

Abstract:

The main aim of this paper is to handle the energy requirement in an efficient manner by merging the advanced digital communication and control technologies for smart grid applications. In order to reduce user home load during peak load hours, utility applies several incentives such as real-time pricing, time of use, demand response for residential customer through smart meter. However, this method provides inconvenience in the sense that user needs to respond manually to prices that vary in real time. To overcome these inconvenience, this paper proposes a convolutional neural network (CNN) with k-means clustering machine learning model which have ability to forecast energy requirement in short term, i.e., hour of the day or day of the week. By integrating our proposed technique with home energy management based on Bluetooth low energy provides predicted value to user for scheduling appliance in advanced. This paper describes detail about CNN configuration and k-means clustering algorithm for short-term energy forecasting.

Keywords: convolutional neural network, fuzzy logic, k-means clustering approach, smart home energy management

Procedia PDF Downloads 310

Authors: M. S. Gadala, Khaled Ahmed, Elasadig Mahdi

Abstract:

In this paper, we introduced a gradient-based inverse solver to obtain the missing boundary conditions based on the readings of internal thermocouples. The results show that the method is very sensitive to measurement errors, and becomes unstable when small time steps are used. The artificial neural networks are shown to be capable of capturing the whole thermal history on the run-out table, but are not very effective in restoring the detailed behavior of the boundary conditions. Also, they behave poorly in nonlinear cases and where the boundary condition profile is different. GA and PSO are more effective in finding a detailed representation of the time-varying boundary conditions, as well as in nonlinear cases. However, their convergence takes longer. A variation of the basic PSO, called CRPSO, showed the best performance among the three versions. Also, PSO proved to be effective in handling noisy data, especially when its performance parameters were tuned. An increase in the self-confidence parameter was also found to be effective, as it increased the global search capabilities of the algorithm. RPSO was the most effective variation in dealing with noise, closely followed by CRPSO. The latter variation is recommended for inverse heat conduction problems, as it combines the efficiency and effectiveness required by these problems.

Keywords: inverse analysis, function specification, neural net works, particle swarm, run-out table

Procedia PDF Downloads 241