Search results for: train passenger

Authors: Anum Ali, Kashaf ad Dooja, Asif Saleem

Abstract:

The future smart cities trend will be towards Internet of Things (IoT); IoT creates dynamic connections in a ubiquitous manner. Smart cities offer ease and flexibility for daily life matters. By using small devices that are connected to cloud servers based on IoT, network traffic between these devices is growing exponentially, whose security is a concerned issue, since ratio of cyber attack may make the network traffic vulnerable. This paper discusses the latest machine learning approaches in related work further to tackle the increasing rate of cyber attacks, machine learning algorithm is applied to IoT-based network traffic data. The proposed algorithm train itself on data and identify different sections of devices interaction by using supervised learning which is considered as a classifier related to a specific IoT device class. The simulation results clearly identify the attacks and produce fewer false detections.

Keywords: IoT, traffic security, deep learning, classification

Procedia PDF Downloads 130

Authors: Maedeh Pourmajidian, Joseph R. McDermid

Abstract:

Advanced High Strength Steels are revolutionizing both the steel and automotive industries due to their high specific strength and ability to absorb energy during crash events. This allows manufacturers to design vehicles with significantly increased fuel efficiency without compromising passenger safety. To maintain the structural integrity of the fabricated parts, they must be protected from corrosion damage through continuous hot-dip galvanizing process, which is challenging due to selective oxidation of Mn and Si on the surface of this AHSSs. The effects of process atmosphere oxygen partial pressure and small additions of Sn on the selective oxidation of a medium-Mn C-6Mn-2Si advanced high strength steel was investigated. Intercritical annealing heat treatments were carried out at 690˚C in an N2-5%H2 process atmosphere under dew points ranging from –50˚C to +5˚C. Surface oxide chemistries, morphologies, and thicknesses were determined at a variety of length scales by several techniques, including SEM, TEM+EELS, and XPS. TEM observations of the sample cross-sections revealed the transition to internal oxidation at the +5˚C dew point. EELS results suggested that the internal oxides network was composed of a multi-layer oxide structure with varying chemistry from oxide core towards the outer part. The combined effect of employing a known surface active element as a function of process atmosphere on the surface structure development and the possible impact on reactive wetting of the steel substrates by the continuous galvanizing zinc bath will be discussed.

Keywords: 3G AHSS, hot-dip galvanizing, oxygen partial pressure, selective oxidation

Procedia PDF Downloads 377

Authors: Yuanjin Liu

Abstract:

Retirement withdrawal strategies are very important to minimize the probability of ruin in retirement. The ruin probability is modeled as a function of initial withdrawal age, gender, asset allocation, inflation rate, and initial withdrawal rate. The ruin probability is obtained based on the 2019 period life table for the Social Security, IRS Required Minimum Distribution (RMD) Worksheets, US historical bond and equity returns, and inflation rates using simulation. Several popular machine learning algorithms of the generalized additive model, random forest, support vector machine, extreme gradient boosting, and artificial neural network are built. The model validation and selection are based on the test errors using hyperparameter tuning and train-test split. The optimal model is recommended for retirees to monitor the ruin probability. The optimal withdrawal strategy can be obtained based on the optimal predictive model.

Keywords: ruin probability, retirement withdrawal strategies, predictive models, optimal model

Procedia PDF Downloads 52

Authors: Safayat Ali Shaikh

Abstract:

Software has been developed for optimal cropping pattern in an irrigation project considering land constraint, water availability constraint and pick up flow constraint using modified Simplex Algorithm. Artificial Neural Network Models (ANN) have been developed to predict rainfall. AR (1) model used to generate 1000 years rainfall data to train the ANN. Simulation has been done with expected rainfall data. Eight number crops and three types of soil class have been considered for optimization model. Area under each crop and each soil class have been quantified using Modified Simplex Algorithm to get optimum net return. Efficacy of the software has been tested using data of large irrigation project in India.

Keywords: artificial neural network, large irrigation project, modified simplex algorithm, optimal cropping pattern

Procedia PDF Downloads 184

Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca

Abstract:

Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.

Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks

Procedia PDF Downloads 173

Authors: Lopamudra Bakshi Basu

Abstract:

Transport is one of the most important characteristic features of Indian cities. The physical and societal requirements determine the selection of a particular transport system along with the uniqueness of road networks. Kolkata has a mixed traffic of which Paratransit system plays a crucial role. It is an indispensable transport system in Kolkata mainly because of its size and service flexibility which has led to a unique network character. The paratransit system, mainly the autorickshaws, is the most favoured mode of transport in the city. Its fast movement and comfortability make it a vital transport system of the city. Since the inception of the autorickshaws in Kolkata in 1981, this mode has gained popularity and presently serves nearly 80 to 90 percent of the total passenger trips. This employment generating mode of transport has increased its number rapidly affecting the city’s traffic. Minimal check on their growth by the authority has led to traffic snarls along many streets of Kolkata. Indiscipline behavior, violation of traffic rules and rash driving make situations even worse. The rise in the number and increasing popularity of the autorickshaws make it an interesting study area. Autorickshaws as a paratransit mode play its role as a leader or a follower. However, it is informal in its planning and operations, which makes it a problem area for the city. The entire research work deals with the growth and expansion of the number of vehicles and the routes within the city. The development of transport system has been interesting in the city, which has been studied. The growth of the paratransit modes in the city has been rapid. The network pattern of the paratransit mode within Kolkata has been analysed.

Keywords: growth, informal, network characteristics, paratransit, service flexibility

Procedia PDF Downloads 213

Authors: Lara Bettinelli, Bernhard Glatz, Josef Fink

Abstract:

Planning engineers and researchers use various calculation models with different levels of complexity, calculation efficiency and accuracy in dynamic calculations of railway bridges under high-speed traffic. When choosing a vehicle model to depict the dynamic loading on the bridge structure caused by passing high-speed trains, different goals are pursued: On the one hand, the selected vehicle models should allow the calculation of a bridge’s vibrations as realistic as possible. On the other hand, the computational efficiency and manageability of the models should be preferably high to enable a wide range of applications. The commonly adopted and straightforward vehicle model is the moving load model (MLM), which simplifies the train to a sequence of static axle loads moving at a constant speed over the structure. However, the MLM can significantly overestimate the structure vibrations, especially when resonance events occur. More complex vehicle models, which depict the train as a system of oscillating and coupled masses, can reproduce the interaction dynamics between the vehicle and the bridge superstructure to some extent and enable the calculation of more realistic bridge accelerations. At the same time, such multi-body models require significantly greater processing capacities and precise knowledge of various vehicle properties. The European standards allow for applying the so-called additional damping method when simple load models, such as the MLM, are used in dynamic calculations. An additional damping factor depending on the bridge span, which should take into account the vibration-reducing benefits of the vehicle-bridge interaction, is assigned to the supporting structure in the calculations. However, numerous studies show that when the current standard specifications are applied, the calculation results for the bridge accelerations are in many cases still too high compared to the measured bridge accelerations, while in other cases, they are not on the safe side. A proposal to calculate the additional damping based on extensive dynamic calculations for a parametric field of simply supported bridges with a ballasted track was developed to address this issue. In this contribution, several different approaches to determine the additional damping of the supporting structure considering the vehicle-bridge interaction when using the MLM are compared with one another. Besides the standard specifications, this includes the approach mentioned above and two additional recently published alternative formulations derived from analytical approaches. For a bridge catalogue of 65 existing bridges in Austria in steel, concrete or composite construction, calculations are carried out with the MLM for two different high-speed trains and the different approaches for additional damping. The results are compared with the calculation results obtained by applying a more sophisticated multi-body model of the trains used. The evaluation and comparison of the results allow assessing the benefits of different calculation concepts for the additional damping regarding their accuracy and possible applications. The evaluation shows that by applying one of the recently published redesigned additional damping methods, the calculation results can reflect the influence of the vehicle-bridge interaction on the design-relevant structural accelerations considerably more reliable than by using normative specifications.

Keywords: Additional Damping Method, Bridge Dynamics, High-Speed Railway Traffic, Vehicle-Bridge-Interaction

Procedia PDF Downloads 150

Authors: S. Mousavian, A. Abedianpour, A. Khanmohammadi, S. Hematian, Gh. Eidi Veisi

Abstract:

Ionic liquids are finding a wide range of applications from reaction media to separations and materials processing. In these applications, Vapor–Liquid equilibrium (VLE) is the most important one. VLE for six systems at 353 K and activity coefficients at infinite dilution 〖(γ〗_i^∞) for various solutes (alkanes, alkenes, cycloalkanes, cycloalkenes, aromatics, alcohols, ketones, esters, ethers, and water) in the ionic liquids (1-ethyl-3-methylimidazolium bis (trifluoromethylsulfonyl)imide [EMIM][BTI], 1-hexyl-3-methyl imidazolium bis (trifluoromethylsulfonyl) imide [HMIM][BTI], 1-octyl-3-methylimidazolium bis(trifluoromethylsulfonyl) imide [OMIM][BTI], and 1-butyl-1-methylpyrrolidinium bis (trifluoromethylsulfonyl) imide [BMPYR][BTI]) have been used to train neural networks in the temperature range from (303 to 333) K. Densities of the ionic liquids, Hildebrant constant of substances, and temperature were selected as input of neural networks. The networks with different hidden layers were examined. Networks with seven neurons in one hidden layer have minimum error and good agreement with experimental data.

Keywords: ionic liquid, neural networks, VLE, dilute solution

Procedia PDF Downloads 275

Authors: Ajoy Kumar Das, Prasenjit Dey

Abstract:

Heat transfer due to forced convection of copper water based nanofluid has been predicted by Artificial Neural network (ANN). The present nanofluid is formed by mixing copper nano particles in water and the volume fractions are considered here are 0% to 15% and the Reynolds number are kept constant at 100. The back propagation algorithm is used to train the network. The present ANN is trained by the input and output data which has been obtained from the numerical simulation, performed in finite volume based Computational Fluid Dynamics (CFD) commercial software Ansys Fluent. The numerical simulation based results are compared with the back propagation based ANN results. It is found that the forced convection heat transfer of water based nanofluid can be predicted correctly by ANN. It is also observed that the back propagation ANN can predict the heat transfer characteristics of nanofluid very quickly compared to standard CFD method.

Keywords: forced convection, square cylinder, nanofluid, neural network

Procedia PDF Downloads 305

Authors: Ci Lin, Tet Yeap, Iluju Kiringa

Abstract:

This paper introduces the subspace rotation algorithm (SRA) to train the Restricted Hopfield Network (RHN) as an auto-associative memory. Subspace rotation algorithm is a gradient-free subspace tracking approach based on the singular value decomposition (SVD). In comparison with Backpropagation Through Time (BPTT) on training RHN, it is observed that SRA could always converge to the optimal solution and BPTT could not achieve the same performance when the model becomes complex, and the number of patterns is large. The AUTS case study showed that the RHN model trained by SRA could achieve a better structure of attraction basin with larger radius(in general) than the Hopfield Network(HNN) model trained by Hebbian learning rule. Through learning 10000 patterns from MNIST dataset with RHN models with different number of hidden nodes, it is observed that an several components could be adjusted to achieve a balance between recovery accuracy and noise resistance.

Keywords: hopfield neural network, restricted hopfield network, subspace rotation algorithm, hebbian learning rule

Procedia PDF Downloads 96

Authors: Yang Zhang, Jian He

Abstract:

Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper introduces sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for coronary heart disease prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.

Keywords: Bi-LSTM, CHD, ECG, ResNet, sliding window

Procedia PDF Downloads 65

Authors: Bulus Kpame, Mukhtar Mohammed Alhaji, Garba Jibril

Abstract:

In any team sport, the most important variables that should be used to measure performance are physical condition, and technical and tactical performance. In a complex game like football, it is extremely difficult to measure the relative importance of each of these variables. However, physical fitness itself has been shown to consist of several components, like endurance, strength, flexibility, agility, coordination and speed. Each of these components has been shown to consist of several subcomponents. This paper attempts to describe a test battery to assess and evaluate physical performance in football players. This battery comprises a functional, structured training session of about 2.5hrs. it consists of quality rating of the warm-up procedure, tests of flexibility, football skills, power, speed, and endurance. Acceptable values for performance in each of the tests are also presented under each test. It is hoped that this battery of tests will be helpful to the coach in determining the effect of a specific training program. It would also be helpful to train physician and trainer, to monitor progress during rehabilitation after sustaining any injury.

Keywords: assessment, evaluation, performance, programs

Procedia PDF Downloads 379

Authors: Cyril Kaplan, Nikola Jajcay

Abstract:

We developed purely sonic, musical based, highly customizable EEG neurofeedback environment designed to administer a new neurofeedback training protocol. The training protocol concentrates on improving the ability to switch between several mental states characterized by different levels of arousal, each of them correlated to specific brain wave activity patterns in several specific regions of neocortex. This paper describes the neurofeedback training environment we developed and its specificities, thus can be helpful as a manual to guide other neurofeedback users (both researchers and practitioners) interested in our editable open source program (available to download and usage under CC license). Responses and reaction of first trainees that used our environment are presented in this article. Combination of qualitative methods (thematic analysis of neurophenomenological insights of trainees and post-session semi-structured interviews) and quantitative methods (power spectra analysis of EEG recorded during the training) were employed to obtain a multifaceted view on our new training protocol.

Keywords: EEG neurofeedback, mixed methods, self-regulation, switch-between-states training

Procedia PDF Downloads 193

Authors: Christoph Linse, Thomas Martinetz

Abstract:

Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.

Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets

Procedia PDF Downloads 66

Authors: Tanish Mittal, Preyansh Agrawal, Esha Pahwa, Aarya Makwana

Abstract:

Multi-Scale and U-shaped Networks are widely used in various image restoration problems, including deblurring. Keeping in mind the wide range of applications, we present a comparison of these architectures and their effects on image deblurring. We also introduce a new block called as NFResblock. It consists of a Fast Fourier Transformation layer and a series of modified Non-Linear Activation Free Blocks. Based on these architectures and additions, we introduce NFResnet and NFResnet+, which are modified multi-scale and U-Net architectures, respectively. We also use three differ-ent loss functions to train these architectures: Charbonnier Loss, Edge Loss, and Frequency Reconstruction Loss. Extensive experiments on the Deep Video Deblurring dataset, along with ablation studies for each component, have been presented in this paper. The proposed architectures achieve a considerable increase in Peak Signal to Noise (PSNR) ratio and Structural Similarity Index (SSIM) value.

Keywords: multi-scale, Unet, deblurring, FFT, resblock, NAF-block, nfresnet, charbonnier, edge, frequency reconstruction

Procedia PDF Downloads 101

Authors: Shehret Tilvaldyev, Jorge Flores-Garay, Alfredo Villanueva, Erwin Martinez, Lazaro Rico

Abstract:

The efficiency of modern transportation is severely compromised by the prevalence of turbulent drag. The high level of turbulent skin-friction occurring, e.g., on the surface of an aircraft, automobiles or the carriage of a high-speed train, is responsible for excess fuel consumption and increased carbon emissions. The environmental, political, and economic pressure to improve fuel efficiency and reduce carbon emissions associated with transportation means that reducing turbulent skin-friction drag is a pressing engineering problem. The dynamic pressure of subsonic airflow around solid objects creates lift, but also induces drag force. This paper is presenting the results of laboratory experiments, investigating appearance and magnitude of dynamic pressure in micro scale of subsonic air flow around right cylinder and symmetrical airfoil.

Keywords: airflow, dynamic pressure, micro scale, symmetric object

Procedia PDF Downloads 359

Authors: Ting (Grace) Lin, Jianhong (Cecilia) Xia, Todd Robinson

Abstract:

Accessibility analysis, examining people’s ability to access facilities and destinations, is a fundamental assessment for transport planning, policy making, and social exclusion research. Dynamic accessibility which measures accessibility in real-time traffic environment has been an advanced accessibility indicator in transport research. It is also a useful indicator to help travelers to understand travel time daily variability, assists traffic engineers to monitor traffic congestions, and finally develop effective strategies in order to mitigate traffic congestions. This research involved real-time traffic information by collecting travel time data with 15-minute interval via the TomTom^® API. A framework for measuring dynamic accessibility was then developed based on the gravity theory and accessibility dichotomy theory through space and time interpolation. Finally, the dynamic accessibility can be derived at any given time and location under dynamic accessibility spatial analysis framework.

Keywords: dynamic accessibility, hot spot, transport research, TomTom® API

Procedia PDF Downloads 363

Authors: Sadeem A. Alolayan

Abstract:

The purpose of early intervention (EI) programs and services is to minimize the impact of disability on children ages 0-5 and to reduce future special education costs. This literature review identifies the status of families of children with special needs. Four major themes emerged from this literature review. The first was the family’s needs and the expressed desire for services to be obtained or outcomes to be achieved. The second was family support, meaning any information or skills needed to facilitate parents’ role as professionals in order to enable them to train and provide their child with the best quality of life. The third theme, barriers, was defined as parents’ actions or life circumstances that hindered families in obtaining appropriate EI services. The conclusions derived from the recommendations are that effective parent participation involves careful planning, establishing and maintaining a trusted rapport between parents, and EI providers that understand parents’ individual needs and interests, thus motivating effective parent involvement in early intervention programs.

Keywords: early intervention, individuals with disabilities education act, parents, recommendations

Procedia PDF Downloads 166

Authors: Hasnun Wara Khondker, M. Tarek Morad

Abstract:

Bangladesh is one of the most populous countries of the world in terms of density. Dhaka, the capital of Bangladesh currently has a population of approximately 15-16 million of which around 9 million people are accommodated in Dhaka South City Corporation (DSCC) within around 109 square kilometer area. Despite having various urban issues, country is at its pick of economic progress and Dhaka is the core of this economic growth. To ensure the proper economic development and citizens wellbeing, city needs an ingenious, congestion-free public transportation network. Bus stop/bus bay is an essential infrastructure for ensuring efficient public transportation flow within the city along with enhancing accessibility, user comfort, and safety through public amenities. At present, there is no established Mass Rapid Transit or Bus Rapid Transit network within the city and therefore these private owned buses are the only major mode of mass transportation of Dhaka city. DSCC has undertaken a project to re-design several bus stops and bus bays according to the universal standard for better urban mobility and user satisfaction. This paper will analyze the design approach of the bus stop/bay infrastructure within Dhaka South, putting the research lens on sustainable urban mobility with case studies of similar kind of urban context. The paper will also study the design process with setting several parameters, i.e., accessibility, passenger safety, comfort, sustainability, etc. Moreover, this research will recommend a guideline for designing a bus stop based on the analysis of the design methods.

Keywords: bus stop, Dhaka, public transportation, sustainable urban mobility, universal accessibility, user safety

Procedia PDF Downloads 351

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su

Abstract:

Deep reinforcement learning has been applied to address various problems in robotics, such as autonomous driving and unmanned aerial vehicle. However, because of the sparse reward penalty for a collision with obstacles during the navigation mission, the agent fails to learn the optimal policy or requires a long time for convergence. Therefore, using obstacles and enemy agents, in this paper, we present a curriculum-based boost learning method to effectively train compound skills during multi-agent reinforcement learning. First, to enable the agents to solve challenging tasks, we gradually increased learning difficulties by adjusting reward shaping instead of constructing different learning environments. Then, in a benchmark environment with static obstacles and moving enemy agents, the experimental results showed that the proposed curriculum learning strategy enhanced cooperative navigation and compound collision avoidance skills in uncertain environments while improving learning efficiency.

Keywords: curriculum learning, hard exploration, multi-agent reinforcement learning, robotic navigation, sparse reward

Procedia PDF Downloads 69

Authors: Wichian Sriprachan, Chutikarn Sriviboon

Abstract:

The objectives of this research were to study the management of local towns and to develop a better model of town management according to the Philosophy of Sufficiency Economy. This study utilized qualitative research, field research, as well as documentary research at the same time. A total of 10 local towns or Tambons of Supanburi province, Thailand were selected for an in-depth interview. The findings revealed that the model of local town management according to Philosophy of Sufficient Economy was in a level of “good” and the model of management has the five basic guidelines: 1) ability to manage budget information and keep it up-to-date, 2) ability to decision making according to democracy rules, 3) ability to use check and balance system, 4) ability to control, follow, and evaluation, and 5) ability to allow the general public to participate. In addition, the findings also revealed that the human resource management according to Philosophy of Sufficient Economy includes obeying laws, using proper knowledge, and having integrity in five areas: plan, recruit, select, train, and maintain human resources.

Keywords: management, local town (Tambon), principles of sufficiency economy, marketing management

Procedia PDF Downloads 324

Authors: Yihao Kuang, Bowen Ding

Abstract:

With the increasing scale and complexity of knowledge graph, modern knowledge graph contains more and more types of entity, relationship, and attribute information. Therefore, in recent years, it has been a trend for knowledge graph inference to use reinforcement learning to deal with large-scale, incomplete, and noisy knowledge graphs and improve the inference effect and interpretability. The Proximal Policy Optimization (PPO) algorithm utilizes a near-end strategy optimization approach. This allows for more extensive updates of policy parameters while constraining the update extent to maintain training stability. This characteristic enables PPOs to converge to improved strategies more rapidly, often demonstrating enhanced performance early in the training process. Furthermore, PPO has the advantage of offline learning, effectively utilizing historical experience data for training and enhancing sample utilization. This means that even with limited resources, PPOs can efficiently train for reinforcement learning tasks. Based on these characteristics, this paper aims to obtain a better and more efficient inference effect by introducing PPO into knowledge inference technology.

Keywords: reinforcement learning, PPO, knowledge inference

Procedia PDF Downloads 214

Authors: Bitewulign Mekonnen

Abstract:

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

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

Procedia PDF Downloads 68

Authors: Jorge Sandoval Lezama, Arturo Ivan Sandoval Rodriguez, Jose Arturo Correa Arredondo

Abstract:

This work aims to share innovative educational experiences at IPN Mexico, that involve collaborative learning at institutional and global level through course competition and global collaboration projects. Students from universities in China, USA, South Korea, Canada and Mexico collaborate to design electric vehicles to solve global urban mobility problems. The participation of IPN students in the 2015-2016 global competition (São Paolo, Brazil and Cincinnati, USA) Reconfigurable Shared-Use Mobility Systems allowed to apply pedagogical strategies of groups of collaboration and of learning based on projects where they shared activities, commitments and goals, demonstrating that students were motivated to develop / self-generate their knowledge with greater meaning and understanding. One of the most evident achievements is that the students are self-managed, so the most advanced students train the students who join the project with CAD, CAE, CAM tools. Likewise, the motivation achieved is evident since in 2014 there were 12 students involved in the project, and there are currently more than 70 students.

Keywords: collaboration projects, global competency, course competition, active learning

Procedia PDF Downloads 252

Authors: Ashkan Zakaryazad, Ekrem Duman

Abstract:

A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.

Keywords: neural network, profit-based neural network, sum of squared errors (SSE), MBO, gradient descent

Procedia PDF Downloads 450

Authors: Abdul Azarrudin M. A., Pothiraj K., Kandasamy Satish

Abstract:

In the current automobile scenario, there comes a demand on more sophistication and comfort drive feel on passenger segments. The clutch pedal effort is one such customer touch feels in manual transmission vehicles, where the driver continuous to operate the clutch pedal in his entire the driving maneuvers. Hence optimum pedal efforts at green condition and over mileage to be ensured for fatigue free the driving. As friction is one the predominant factor and its tendency to challenge the technicality by causing the function degradation. One such semi-hydraulic systems shows load efficiency of about 70-75% over lifetime only due to the increase in friction which leads to the increase in pedal effort and cause fatigue to the vehicle driver. This work deals with the study of friction with different interfaces and its influence in the fulcrum points over mileage, with the objective of understanding the trend over mileage and determining the alternative ways of resolving it. In that one way of methodology is the reduction of friction by experimental investigation of various friction reduction interfaces like metal-to-metal interface and it has been tried out and is detailed further. Also, the specific attention has been put up considering the fulcrum load and its contact interfaces to move on with this study. The main results of the experimental data with the influence of three different contact interfaces are being presented with an ultimate intention of ending up into less fatigue with longer consistent pedal effort, thus smoothens the operation of the end user. The Experimental validation also has been done through rig-level test setup to depict the performance at static condition and in-parallel vehicle level test has also been performed to record the additional influences if any.

Keywords: automobile, clutch, friction, fork

Procedia PDF Downloads 99

Authors: David F. Nettleton, Elodie Bugnicourt, Christian Wasiak, Alejandro Rosales

Abstract:

In this presentation, preliminary results are given for the modeling and calibration of two different industrial winding MIMO (Multiple Input Multiple Output) processes using machine learning techniques. In contrast to previous approaches which have typically used ‘black-box’ linear statistical methods together with a definition of the mechanical behavior of the process, we use non-linear machine learning algorithms together with a ‘white-box’ rule induction technique to create a supervised model of the fitting error between the expected and real force measures. The final objective is to build a precise model of the winding process in order to control de-tension of the material being wound in the first case, and the friction of the material passing through the die, in the second case. Case 1, Tension Control of a Winding Process. A plastic web is unwound from a first reel, goes over a traction reel and is rewound on a third reel. The objectives are: (i) to train a model to predict the web tension and (ii) calibration to find the input values which result in a given tension. Case 2, Friction Force Control of a Micro-Pullwinding Process. A core+resin passes through a first die, then two winding units wind an outer layer around the core, and a final pass through a second die. The objectives are: (i) to train a model to predict the friction on die2; (ii) calibration to find the input values which result in a given friction on die2. Different machine learning approaches are tested to build models, Kernel Ridge Regression, Support Vector Regression (with a Radial Basis Function Kernel) and MPART (Rule Induction with continuous value as output). As a previous step, the MPART rule induction algorithm was used to build an explicative model of the error (the difference between expected and real friction on die2). The modeling of the error behavior using explicative rules is used to help improve the overall process model. Once the models are built, the inputs are calibrated by generating Gaussian random numbers for each input (taking into account its mean and standard deviation) and comparing the output to a target (desired) output until a closest fit is found. The results of empirical testing show that a high precision is obtained for the trained models and for the calibration process. The learning step is the slowest part of the process (max. 5 minutes for this data), but this can be done offline just once. The calibration step is much faster and in under one minute obtained a precision error of less than 1x10-3 for both outputs. To summarize, in the present work two processes have been modeled and calibrated. A fast processing time and high precision has been achieved, which can be further improved by using heuristics to guide the Gaussian calibration. Error behavior has been modeled to help improve the overall process understanding. This has relevance for the quick optimal set up of many different industrial processes which use a pull-winding type process to manufacture fibre reinforced plastic parts. Acknowledgements to the Openmind project which is funded by Horizon 2020 European Union funding for Research & Innovation, Grant Agreement number 680820

Keywords: data model, machine learning, industrial winding, calibration

Procedia PDF Downloads 220

Authors: Vijaya Yuvaram Singh V M, Kameshwar Rao J V

Abstract:

The challenge with development of neural network based methods for medical is the availability of data. Anatomical landmark detection in the medical domain is a process to find points on the x-ray scan report of the patient. Most of the time this task is done manually by trained professionals as it requires precision and domain knowledge. Traditionally object detection based methods are used for landmark detection. Here, we utilize reinforcement learning and query based method to train a single agent capable of detecting multiple landmarks. A deep Q network agent is trained to detect single and multiple landmarks present on hip and shoulder from x-ray scan of a patient. Here a single agent is trained to find multiple landmark making it superior to having individual agents per landmark. For the initial study, five images of different patients are used as the environment and tested the agents performance on two unseen images.

Keywords: reinforcement learning, medical landmark detection, multi target detection, deep neural network

Procedia PDF Downloads 124

Authors: Sean Paulsen, Michael Casey

Abstract:

In this work we present a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.

Keywords: transfer learning, fMRI, self-supervised, brain decoding, transformer, multitask training

Procedia PDF Downloads 65

Authors: Josselyn Mata Calidonio, Arianna I. Maddox, Kimberly Hamad-Schifferli

Abstract:

Rapid diagnostics are critical infectious disease tools that are designed to detect a known biomarker using antibodies specific to that biomarker. However, a way to detect unknown viruses has not yet been achieved in a paper test format. We describe here a route to make an adaptable paper immunoassay that can detect an unknown biomarker, demonstrating it on SARS-CoV-2 variants. The immunoassay repurposes cross-reactive antibodies raised against the alpha variant. Gold nanoparticles of two different colors conjugated to two different antibodies create a colorimetric signal, and machine learning of the resulting colorimetric pattern is used to train the assay to discriminate between variants of alpha and Omicron BA.5. By using principal component analysis, the colorimetric test patterns can pick up and discriminate an unknown that it has not encountered before, Omicron BA.1. The test has an accuracy of 100% and a potential calculated discriminatory power of 900. We show that it can be used adaptively and that it can be used to pick up emerging variants without the need to raise new antibodies.

Keywords: adaptive immunoassay, detecting unknown viruses, gold nanoparticles, paper immunoassay, repurposing antibodies

Procedia PDF Downloads 90