Search results for: Bayesian network model

Authors: Kyoung-Jae Kim

Abstract:

Collaborative Filtering (CF) is a popular technique for the personalization in the E-commerce domain to reduce information overload. In general, CF provides recommending items list based on other similar users’ preferences from the user-item matrix and predicts the focal user’s preference for particular items by using them. Many recommender systems in real-world use CF techniques because it’s excellent accuracy and robustness. However, it has some limitations including sparsity problems and complex dimensionality in a user-item matrix. In addition, traditional CF does not consider the emotional interaction between users. In this study, we propose recommender systems using social network and singular value decomposition (SVD) to alleviate some limitations. The purpose of this study is to reduce the dimensionality of data set using SVD and to improve the performance of CF by using emotional information from social network data of the focal user. In this study, we test the usability of hybrid CF, SVD and social network information model using the real-world data. The experimental results show that the proposed model outperforms conventional CF models.

Keywords: recommender systems, collaborative filtering, social network information, singular value decomposition

Procedia PDF Downloads 261

Authors: Trung Hieu Tran, Jesse O'Hanley, Russell Fowler

Abstract:

When in-wheel wireless charging technology for electric vehicles becomes mature, a need for such integrated charging stations network development is essential. In this paper, we thus investigate the optimisation problem of in-wheel wireless electric vehicle charging network design. A mixed-integer linear programming model is formulated to solve into optimality the problem. In addition, a meta-heuristic algorithm is proposed for efficiently solving large-sized instances within a reasonable computation time. A parallel computing strategy is integrated into the algorithm to speed up its computation time. Experimental results carried out on the benchmark instances show that our model and algorithm can find the optimal solutions and their potential for practical applications.

Keywords: electric vehicle, wireless charging station, mathematical programming, meta-heuristic algorithm, parallel computing

Procedia PDF Downloads 55

Authors: Danladi Ali

Abstract:

In this paper, we measured GSM signal strength in the Dnepropetrovsk city in order to predict path loss in study area using nonlinear autoregressive neural network prediction and we also, used neural network clustering to determine average GSM signal strength receive at the study area. The nonlinear auto-regressive neural network predicted that the GSM signal is attenuated with the mean square error (MSE) of 2.6748dB, this attenuation value is used to modify the COST 231 Hata and the Okumura-Hata models. The neural network clustering revealed that -75dB to -95dB is received more frequently. This means that the signal strength received at the study is mostly weak signal

Keywords: one-dimensional multilevel wavelets, path loss, GSM signal strength, propagation, urban environment and model

Procedia PDF Downloads 356

Authors: Bo Yan, Amy Y. M. Chow

Abstract:

Bereavement is recognized as a universal challenging experience. It is important to gather research evidence on protective factors in bereavement. Hope is considered as one of the protective factors in previous coping studies. The present study aims to add knowledge by investigating hope at the first month after death to predict psychological symptoms altogether including complicated grief (CG), anxiety, and depressive symptoms at the seventh month. The data were collected via one-on-one interview survey in a longitudinal project with Hong Kong hospice users (sample size 105). Most participants were at their middle age (49-year-old on average), female (72%), with no religious affiliation (58%). Bayesian Structural Equation Modeling (BSEM) analysis was conducted on the longitudinal dataset. The BSEM findings show that hope at the first month of bereavement negatively predicts both CG and anxiety symptoms at the seventh month but not for depressive symptoms. Age and gender are controlled in the model. The overall model fit is good. The current study findings suggest assessing hope at the first month of bereavement. Hope at the first month after the loss is identified as an excellent predictor for complicated grief and anxiety symptoms at the seventh month. The result from this sample is clear, so it encourages cross-cultural research on replicated modeling and development of further clinical application. Particularly, practical consideration for early intervention to increase the level of hope has the potential to reduce the psychological symptoms and thus to improve the bereaved persons’ wellbeing in the long run.

Keywords: anxiety, complicated grief, depressive symptoms, hope, structural equational modeling

Procedia PDF Downloads 174

Authors: J. K. Alhassan, C. S. Actsu

Abstract:

This study is on the prediction of feature performance of undergraduate students with Artificial Neural Networks (ANN). With the growing decline in the quality academic performance of undergraduate students, it has become essential to predict the students’ feature academic performance early in their courses of first and second years and to take the necessary precautions using such prediction-based information. The feed forward multilayer neural network model was used to train and develop a network and the test carried out with some of the input variables. A result of 80% accuracy was obtained from the test which was carried out, with an average error of 0.009781.

Keywords: academic performance, artificial neural network, prediction, students

Procedia PDF Downloads 431

Authors: Humeyra Bolakar Tosun

Abstract:

The transport sector has an undisputed place in human life. People need transport access to continuous increase day by day with growing population. The number of rail network, urban transport planning, infrastructure improvements, transportation management and other related areas is a key factor affecting our country made it quite necessary to improve the work of transportation. In this context, it plays an important role in domestic rail freight demand planning. Alternatives that the increase in the transportation field and has made it mandatory requirements such as the demand for improving transport quality. In this study generally is known and used in studies by the definition, rail freight transport, railway line length, population, energy consumption. In this study, Iron Road Load Net Demand was modeled by multiple regression and ANN methods. In this study, model dependent variable (Output) is Iron Road Load Net demand and 6 entries variable was determined. These outcome values extracted from the model using ANN and regression model results. In the regression model, some parameters are considered as determinative parameters, and the coefficients of the determinants give meaningful results. As a result, ANN model has been shown to be more successful than traditional regression model.

Keywords: railway load carrying, neural network, modelling transport, transportation

Procedia PDF Downloads 125

Authors: P. Singh, R. M. Banik

Abstract:

Artificial neural network (ANN) was employed to optimize assay parameters viz., time, temperature, pH of reaction mixture, enzyme volume and substrate concentration of L-glutaminase from Bacillus cereus MTCC 1305. ANN model showed high value of coefficient of determination (0.9999), low value of root mean square error (0.6697) and low value of absolute average deviation. A multilayer perceptron neural network trained with an error back-propagation algorithm was incorporated for developing a predictive model and its topology was obtained as 5-3-1 after applying Levenberg Marquardt (LM) training algorithm. The predicted activity of L-glutaminase was obtained as 633.7349 U/l by considering optimum assay parameters, viz., pH of reaction mixture (7.5), reaction time (20 minutes), incubation temperature (35˚C), substrate concentration (40mM), and enzyme volume (0.5ml). The predicted data was verified by running experiment at simulated optimum assay condition and activity was obtained as 634.00 U/l. The application of ANN model for optimization of assay conditions improved the activity of L-glutaminase by 1.499 fold.

Keywords: Bacillus cereus, L-glutaminase, assay parameters, artificial neural network

Procedia PDF Downloads 405

Authors: Ana Staneva, Vessela Stoimenova

Abstract:

A parametric estimation of the MBP with Power Series offspring distribution family is considered in this paper. The MLE for the parameters is obtained in the case when the observable data are incomplete and consist only with the generation sizes of the family tree of MBP. The parameter estimation is calculated by using the Monte Carlo EM algorithm. The estimation for the posterior distribution and for the offspring distribution parameters are calculated by using the Bayesian approach and the Gibbs sampler. The article proposes various examples with bivariate branching processes together with computational results, simulation and an implementation using R.

Keywords: Bayesian, branching processes, EM algorithm, Gibbs sampler, Monte Carlo methods, statistical estimation

Procedia PDF Downloads 393

Authors: Ashok V. Sutagundar, Sunilkumar S. Manvi

Abstract:

Energy, delay and bandwidth are the prime issues of wireless sensor network (WSN). Energy usage optimization and efficient bandwidth utilization are important issues in WSN. Event triggered data aggregation facilitates such optimal tasks for event affected area in WSN. Reliable delivery of the critical information to sink node is also a major challenge of WSN. To tackle these issues, we propose an event driven dynamic clustering and data aggregation scheme for WSN that enhances the life time of the network by minimizing redundant data transmission. The proposed scheme operates as follows: (1) Whenever the event is triggered, event triggered node selects the cluster head. (2) Cluster head gathers data from sensor nodes within the cluster. (3) Cluster head node identifies and classifies the events out of the collected data using Bayesian classifier. (4) Aggregation of data is done using statistical method. (5) Cluster head discovers the paths to the sink node using residual energy, path distance and bandwidth. (6) If the aggregated data is critical, cluster head sends the aggregated data over the multipath for reliable data communication. (7) Otherwise aggregated data is transmitted towards sink node over the single path which is having the more bandwidth and residual energy. The performance of the scheme is validated for various WSN scenarios to evaluate the effectiveness of the proposed approach in terms of aggregation time, cluster formation time and energy consumed for aggregation.

Keywords: wireless sensor network, dynamic clustering, data aggregation, wireless communication

Procedia PDF Downloads 416

Authors: Hounyèmè Romuald, Mama Daouda, Argillier Christine

Abstract:

The present study focused on the use of benthic macrofauna to define the reference state of an anthropized lagoon (Nokoué-Benin) from the responses of relevant metrics to proxies. The approach used is a combination of a joint species distribution model and Bayesian networks. The joint species distribution model was used to select the relevant metrics and generate posterior probabilities that were then converted into posterior response probabilities for each of the quality classes (pressure levels), which will constitute the conditional probability tables allowing the establishment of the probabilistic graph representing the different causal relationships between metrics and pressure proxies. For the definition of the reference thresholds, the predicted responses for low-pressure levels were read via probability density diagrams. Observations collected during high and low water periods spanning 03 consecutive years (2004-2006), sampling 33 macroinvertebrate taxa present at all seasons and sampling points, and measurements of 14 environmental parameters were used as application data. The study demonstrated reliable inferences, selection of 07 relevant metrics and definition of quality thresholds for each environmental parameter. The relevance of the metrics as well as the reference thresholds for ecological assessment despite the small sample size, suggests the potential for wider applicability of the approach for aquatic ecosystem monitoring and assessment programs in developing countries generally characterized by a lack of monitoring data.

Keywords: pressure proxies, bayesian inference, bioindicators, acadjas, functional traits

Procedia PDF Downloads 59

Authors: Hossain A., Chowdhury S. I.

Abstract:

Introduction: The use of a gamma camera is a standard procedure in nuclear medicine facilities or hospitals to diagnose chronic kidney disease (CKD), but the gamma camera does not precisely stage the disease. The authors sought to determine whether they could use an artificial neural network to determine whether CKD was in normal or abnormal stages based on GFR values (ANN). Method: The 250 kidney patients (Training 188, Testing 62) who underwent an ultrasonography test to diagnose a renal test in our nuclear medical center were scanned using a gamma camera. Before the scanning procedure, the patients received an injection of ⁹⁹ᵐTc-DTPA. The gamma camera computes the pre- and post-syringe radioactive counts after the injection has been pushed into the patient's vein. The artificial neural network uses the softmax function with cross-entropy loss to determine whether CKD is normal or abnormal based on the GFR value in the output layer. Results: The proposed ANN model had a 99.20 % accuracy according to K-fold cross-validation. The sensitivity and specificity were 99.10 and 99.20 %, respectively. AUC was 0.994. Conclusion: The proposed model can distinguish between normal and abnormal stages of CKD by using an artificial neural network. The gamma camera could be upgraded to diagnose normal or abnormal stages of CKD with an appropriate GFR value following the clinical application of the proposed model.

Keywords: artificial neural network, glomerular filtration rate, stages of the kidney, gamma camera

Procedia PDF Downloads 73

Authors: Zhifei Hu, Feng Xia

Abstract:

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

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

Procedia PDF Downloads 91

Authors: Frankie Burgos, Emely Munar, Conrado Basa

Abstract:

This paper aimed at developing an artificial neural network (ANN) model specifically for the Philippine Stock Exchange index closing value. The inputs to the ANN are US Dollar and Philippine Peso(USD-PHP) exchange rate, GDP growth of the country, quarterly inflation rate, 10-year bond yield, credit rating of the country, previous open, high, low, close values and volume of trade of the Philippine Stock Exchange Index (PSEi), gold price of the previous day, National Association of Securities Dealers Automated Quotations (NASDAQ), Standard and Poor’s 500 (S & P 500) and the iShares MSCI Philippines ETF (EPHE) previous closing value. The target is composed of the closing value of the PSEi during the 627 trading days from November 3, 2011, to May 30, 2014. MATLAB’s Neural Network toolbox was employed to create, train and simulate the network using multi-layer feed forward neural network with back-propagation algorithm. The results satisfactorily show that the neural network developed has the ability to model the PSEi, which is affected by both internal and external economic factors. It was found out that the inputs used are the main factors that influence the movement of the PSEi closing value.

Keywords: artificial neural networks, artificial intelligence, philippine stocks exchange index, stocks trading

Procedia PDF Downloads 269

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: artificial intelligence, air quality prediction, neural networks, pattern recognition, PM-10

Procedia PDF Downloads 208

Authors: Ren Moses, Emmanuel Kidando, Eren Ozguven, Yassir Abdelrazig

Abstract:

This study applied traffic speed and occupancy to develop clustering models that identify different traffic conditions. Particularly, these models are based on the Dirichlet Process Mixture of Generalized Linear regression (DML) and change-point regression (CR). The model frameworks were implemented using 2015 historical traffic data aggregated at a 15-minute interval from an Interstate 295 freeway in Jacksonville, Florida. Using the deviance information criterion (DIC) to identify the appropriate number of mixture components, three traffic states were identified as free-flow, transitional, and congested condition. Results of the DML revealed that traffic occupancy is statistically significant in influencing the reduction of traffic speed in each of the identified states. Influence on the free-flow and the congested state was estimated to be higher than the transitional flow condition in both evening and morning peak periods. Estimation of the critical speed threshold using CR revealed that 47 mph and 48 mph are speed thresholds for congested and transitional traffic condition during the morning peak hours and evening peak hours, respectively. Free-flow speed thresholds for morning and evening peak hours were estimated at 64 mph and 66 mph, respectively. The proposed approaches will facilitate accurate detection and prediction of traffic congestion for developing effective countermeasures.

Keywords: traffic congestion, multistate speed distribution, traffic occupancy, Dirichlet process mixtures of generalized linear model, Bayesian change-point detection

Procedia PDF Downloads 267

Authors: Kyu Jin Kim, Byung Kwan Oh, Hyo Seon Park

Abstract:

The seismic responses-based structural health monitoring system has been performed to prevent seismic damage. Structural seismic damage of building is caused by the instantaneous stress concentration which is related with dynamic characteristic of earthquake. Meanwhile, seismic response analysis to estimate the dynamic responses of building demands significantly high computational cost. To prevent the failure of structural members from the characteristic of the earthquake and the significantly high computational cost for seismic response analysis, this paper presents an artificial neural network (ANN) based prediction model for dynamic responses of building considering specific time length. Through the measured dynamic responses, input and output node of the ANN are formed by the length of specific time, and adopted for the training. In the model, evolutionary radial basis function neural network (ERBFNN), that radial basis function network (RBFN) is integrated with evolutionary optimization algorithm to find variables in RBF, is implemented. The effectiveness of the proposed model is verified through an analytical study applying responses from dynamic analysis for multi-degree of freedom system to training data in ERBFNN.

Keywords: structural health monitoring, dynamic response, artificial neural network, radial basis function network, genetic algorithm

Procedia PDF Downloads 281

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 149

Authors: Rashi Bhalla, Russel Pears, M. Asif Naeem

Abstract:

In this 'Information Explosion Era' analyzing data 'a critical commodity' and mining knowledge from vertically distributed data stream incurs huge communication cost. However, an effort to decrease the communication in the distributed environment has an adverse influence on the classification accuracy; therefore, a research challenge lies in maintaining a balance between transmission cost and accuracy. This paper proposes a method based on Bayesian inference to reduce the communication volume in a heterogeneous distributed environment while retaining prediction accuracy. Our experimental evaluation reveals that a significant reduction in communication can be achieved across a diverse range of dataset types.

Keywords: big data, bayesian inference, distributed data stream mining, heterogeneous-distributed data

Procedia PDF Downloads 131

Authors: Chuan Yang, Jing Bie, Panagiotis Psimoulis, Zhong Wang

Abstract:

Modelling and understanding vehicle volume distribution over the urban network are essential for urban design and transport planning. The space syntax approach was widely applied as the main conceptual and methodological framework for contemporary vehicle volume models with the help of the statistical method of multiple regression analysis (MRA). However, the MRA model with space syntax variables shows a limitation in vehicle volume predicting in accounting for the crossed effect of the urban configurational characters and socio-economic factors. The aim of this paper is to construct models by interacting with the combined impact of the street network structure and socio-economic factors. In this paper, we present a multilevel linear (ML) and an agent-based (AB) vehicle volume model at an urban scale interacting with space syntax theoretical framework. The ML model allowed random effects of urban configurational characteristics in different urban contexts. And the AB model was developed with the incorporation of transformed space syntax components of the MRA models into the agents’ spatial behaviour. Three models were implemented in the same urban environment. The ML model exhibit superiority over the original MRA model in identifying the relative impacts of the configurational characters and macro-scale socio-economic factors that shape vehicle movement distribution over the city. Compared with the ML model, the suggested AB model represented the ability to estimate vehicle volume in the urban network considering the combined effects of configurational characters and land-use patterns at the street segment level.

Keywords: space syntax, vehicle volume modeling, multilevel model, agent-based model

Procedia PDF Downloads 112

Authors: Divvela Vishnu Sai Kumar, Deepak Arora, Sheenu Rizvi

Abstract:

Forecasting a cyclone through satellite images consists of the estimation of the intensity of the cyclone and predicting it before a cyclone comes. This research work can help people to take safety measures before the cyclone comes. The prediction of the intensity of a cyclone is very important to save lives and minimize the damage caused by cyclones. These cyclones are very costliest natural disasters that cause a lot of damage globally due to a lot of hazards. Authors have proposed five different CNN (Convolutional Neural Network) models that estimate the intensity of cyclones through INSAT-3D IR images. There are a lot of techniques that are used to estimate the intensity; the best model proposed by authors estimates intensity with a root mean squared error (RMSE) of 10.02 kts.

Keywords: estimating cyclone intensity, deep learning, convolution neural network, prediction models

Procedia PDF Downloads 89

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 179

Authors: Hidir S. Nogay

Abstract:

In this study, two systems were created to predict interior temperature in induction motor. One of them consisted of a simple ANN model which has two layers, ten input parameters and one output parameter. The other one consisted of eight ANN models connected each other as cascaded. Cascaded ANN system has 17 inputs. Main reason of cascaded system being used in this study is to accomplish more accurate estimation by increasing inputs in the ANN system. Cascaded ANN system is compared with simple conventional ANN model to prove mentioned advantages. Dataset was obtained from experimental applications. Small part of the dataset was used to obtain more understandable graphs. Number of data is 329. 30% of the data was used for testing and validation. Test data and validation data were determined for each ANN model separately and reliability of each model was tested. As a result of this study, it has been understood that the cascaded ANN system produced more accurate estimates than conventional ANN model.

Keywords: cascaded neural network, internal temperature, inverter, three-phase induction motor

Procedia PDF Downloads 323

Authors: Yayun Hsu, Henry Horng-Shing Lu

Abstract:

This paper proposes a data-driven, biology-inspired neural segmentation method of 3D drosophila Brainbow images. We use Bayesian Sequential Partitioning algorithm for probabilistic modeling, which can be used to detect somas and to eliminate cross talk effects. This work attempts to develop an automatic methodology for neuron image segmentation, which nowadays still lacks a complete solution due to the complexity of the image. The proposed method does not need any predetermined, risk-prone thresholds since biological information is inherently included in the image processing procedure. Therefore, it is less sensitive to variations in neuron morphology; meanwhile, its flexibility would be beneficial for tracing the intertwining structure of neurons.

Keywords: brainbow, 3D imaging, image segmentation, neuron morphology, biological data mining, non-parametric learning

Procedia PDF Downloads 460

Authors: L. Rakesh, T. Y. Heblekar

Abstract:

This study entails the development and optimization of a mathematical model for a floating drum biogas reactor from first principles using thermal and empirical considerations. The model was derived on the basis of mass conservation, lumped mass heat transfer formulations and empirical biogas formation laws. The treatment leads to a system of coupled nonlinear ordinary differential equations whose solution mapped four-time independent controllable parameters to five output variables which adequately serve to describe the reactor performance. These equations were solved numerically using fourth order Runge-Kutta method for a range of input parameter values. Using the data so obtained an Artificial Neural Network with a single hidden layer was trained using Levenberg-Marquardt Damped Least Squares (DLS) algorithm. This network was then fine-tuned for optimal mapping by varying hidden layer size. This fast forward model was then employed as a health score generator in the Bacterial Foraging Optimization code. The optimal operating state of the simplified Biogas reactor was thus obtained.

Keywords: biogas, floating drum reactor, neural network model, optimization

Procedia PDF Downloads 122

Authors: Oleg Vlasovets, Fabian Schaipp, Christian L. Mueller

Abstract:

we conduct a network analysis and predict the sex of 1000 participants based on ”connectome” - pairwise Pearson’s correlation across 436 brain parcels. We solve the non-smooth convex optimization problem, known under the name of Graphical Lasso, where the solution includes a low-rank component. With this solution and machine learning model for a sex prediction, we explain the brain parcels-sex connectivity patterns.

Keywords: network analysis, neuroscience, machine learning, optimization

Procedia PDF Downloads 117

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: distillation, machine learning, neural networks, quantization

Procedia PDF Downloads 293

Authors: Ayman M. Mansour, Bilal Hawashin, Hesham Alsalem

Abstract:

Faster delivery of laboratory test results is one of the most noticeable signs of good laboratory service and is often used as a key performance indicator of laboratory performance. Despite the availability of technology, the delivery time of clinical laboratory test results continues to be a cause of customer dissatisfaction which makes patients feel frustrated and they became careless to get their laboratory test results. The Medical Clinical Laboratory test results are highly sensitive and could harm patients especially with the severe case if they deliver in wrong time. Such results affect the treatment done by physicians if arrived at correct time efforts should, therefore, be made to ensure faster delivery of lab test results by utilizing new trusted, Robust and fast system. In this paper, we proposed a distributed Multi-Agent System to enhance and faster the process of laboratory test results delivery using SMS. The developed system relies on SMS messages because of the wide availability of GSM network comparing to the other network. The software provides the capability of knowledge sharing between different units and different laboratory medical centers. The system was built using java programming. To implement the proposed system we had many possible techniques. One of these is to use the peer-to-peer (P2P) model, where all the peers are treated equally and the service is distributed among all the peers of the network. However, for the pure P2P model, it is difficult to maintain the coherence of the network, discover new peers and ensure security. Also, security is a quite important issue since each node is allowed to join the network without any control mechanism. We thus take the hybrid P2P model, a model between the Client/Server model and the pure P2P model using GSM technology through SMS messages. This model satisfies our need. A GUI has been developed to provide the laboratory staff with the simple and easy way to interact with the system. This system provides quick response rate and the decision is faster than the manual methods. This will save patients life.

Keywords: multi-agent system, delivery process, GSM technology, clinical laboratory results

Procedia PDF Downloads 228

Authors: Yapegue Bayogo, Ahmadou Halassi Dicko, Brahima Songore

Abstract:

In developing countries, the road transportation system occupies an important place because of its flexibility and the low prices of infrastructure and rolling stock. While road transport is necessary for economic development, the movement of people and their goods, it is urgent to use transportation systems that minimize carbon emissions in order to ensure sustainable development. One of the main objectives of OEDC and the Word Bank is to ensure sustainable economic’ development. This paper aims to develop a road transport network taking into account environmental impacts. The methodology adopted consists of formulating a model optimizing the flow of goods and then collecting information relating to the transport of products. Our model was tested with data on product transport in CMDT areas in the Republic of Mali. The results of our study indicate that emissions from the transport sector can be significantly reduced by minimizing the traffic volume. According to our study, optimizing the transportation network, we benefit from a significant amount of tons of CO₂.

Keywords: road transport, transport sustainability, pollution, flexibility, optimized network

Procedia PDF Downloads 124

Authors: M. S. Jimah, A. C. Achuenu, M. Momodu

Abstract:

Group communications over public infrastructure are prone to a lot of security issues. Existing network protocols like Protocol Independent Multicast Sparse Mode (PIM SM) and Protocol Independent Multicast Dense Mode (PIM DM) do not have inbuilt security features. Therefore, any user or node can easily access the group communication as long as the user can send join message to the source nodes, the source node then adds the user to the network group. In this research, a hybrid method of salting and hashing to encrypt information in the source and stub node was designed, and when stub nodes need to connect, they must have the appropriate key to join the group network. Object oriented analysis design (OOAD) was the methodology used, and the result shows that no extra controlled bandwidth overhead cost was added by encrypting and the hybrid model was more securing than the existing PIM SM, PIM DM and Zhang secure PIM SM.

Keywords: group communications, multicast, PIM SM, PIM DM, encryption

Procedia PDF Downloads 138

Authors: Shu-Yu Chung, Ying-Fang Wang, Shih-Min Wang

Abstract:

To conduct long-term exposure assessments are important for workers exposed to chemicals with chronic effects. However, it usually encounters with several constrains, including cost, workers' willingness, and interference to work practice, etc., leading to inadequate long-term exposure data in the real world. In this study, an integrated approach was developed for conducting long-term exposure assessment for welding workers in a shipbuilding factory. A laboratory study was conducted to yield the fume generation rates under various operating conditions. The results and the measured environmental conditions were applied to the near field/far field (NF/FF) model for predicting long term fume exposures via the Monte Carlo simulation. Then, the predicted long-term concentrations were used to determine the prior distribution in Bayesian decision analysis (BDA). Finally, the resultant posterior distributions were used to assess the long-term exposure and serve as basis for initiating control strategies for shipbuilding workers. Results show that the NF/FF model was a suitable for predicting the exposures of metal contents containing in welding fume. The resultant posterior distributions could effectively assess the long-term exposures of shipbuilding welders. Welders' long-term Fe, Mn and Pb exposures were found with high possibilities to exceed the action level indicating preventive measures should be taken for reducing welders' exposures immediately. Though the resultant posterior distribution can only be regarded as the best solution based on the currently available predicting and monitoring data, the proposed integrated approach can be regarded as a possible solution for conducting long term exposure assessment in the field.

Keywords: Bayesian decision analysis, exposure assessment, near field and far field model, shipbuilding industry, welding fume

Procedia PDF Downloads 115