Search results for: BP neural network model

Authors: Sathapath Kilaso

Abstract:

Nowadays, Today, wireless sensor networks are an important technology that works with Internet of Things. It is receiving various data from many sensor. Then sent to processing or storing. By wireless network or through the Internet. The devices around us are intelligent, can receiving/transmitting and processing data and communicating through the system. There are many applications of wireless sensor networks, such as smart city, smart farm, environmental management, weather. This article will explore the use of wireless sensor networks in Thailand and collect data from Thai Thesis database in 2012-2017. How to Implementing Wireless Sensor Network Technology. Advantage from this study To know the usage wireless technology in many fields. This will be beneficial for future research. In this study was found the most widely used wireless sensor network in agriculture field. Especially for smart farms. And the second is the adoption of the environment. Such as weather stations and water inspection.

Keywords: wireless sensor network, smart city, survey, Adhoc Network

Procedia PDF Downloads 207

Authors: Madhawa Basnayaka, Jouni Paltakari

Abstract:

Fully passive backscattering chipless RFID tags are an emerging wireless technology with low cost, higher reading distance, and fast automatic identification without human interference, unlike already available technologies like optical barcodes. The design optimization of chipless RFID tags is crucial as it requires replacing integrated chips found in conventional RFID tags with printed geometric designs. These designs enable data encoding and decoding through backscattered electromagnetic (EM) signatures. The applications of chipless RFID tags have been limited due to the constraints of data encoding capacity and the ability to design accurate yet efficient configurations. The traditional approach to accomplishing design parameters for a desired EM response involves iterative adjustment of design parameters and simulating until the desired EM spectrum is achieved. However, traditional numerical simulation methods encounter limitations in optimizing design parameters efficiently due to the speed and resource consumption. In this work, a deep learning neural network (DNN) is utilized to establish a correlation between the EM spectrum and the dimensional parameters of nested centric rings, specifically square and octagonal. The proposed bi-directional DNN has two simultaneously running neural networks, namely spectrum prediction and design parameters prediction. First, spectrum prediction DNN was trained to minimize mean square error (MSE). After the training process was completed, the spectrum prediction DNN was able to accurately predict the EM spectrum according to the input design parameters within a few seconds. Then, the trained spectrum prediction DNN was connected to the design parameters prediction DNN and trained two networks simultaneously. For the first time in chipless tag design, design parameters were predicted accurately after training bi-directional DNN for a desired EM spectrum. The model was evaluated using a randomly generated spectrum and the tag was manufactured using the predicted geometrical parameters. The manufactured tags were successfully tested in the laboratory. The amount of iterative computer simulations has been significantly decreased by this approach. Therefore, highly efficient but ultrafast bi-directional DNN models allow rapid and complicated chipless RFID tag designs.

Keywords: artificial intelligence, chipless RFID, deep learning, machine learning

Procedia PDF Downloads 50

Authors: Yinggang Guo, Zongchun Li

Abstract:

In order to decrease the accumulated survey error of tunnel installation control network of particle accelerator, a sectional control method is proposed. Firstly, the accumulation rule of positional error with the length of the control network is obtained by simulation calculation according to the shape of the tunnel installation-control-network. Then, the RMS of horizontal positional precision of tunnel backbone control network is taken as the threshold. When the accumulated error is bigger than the threshold, the tunnel installation control network should be divided into subsections reasonably. On each segment, the middle survey station is taken as the datum for independent adjustment calculation. Finally, by taking the backbone control points as faint datums, the weighted partial parameters adjustment is performed with the adjustment results of each segment and the coordinates of backbone control points. The subsections are jointed and unified into the global coordinate system in the adjustment process. An installation control network of the linac with a length of 1.6 km is simulated. The RMS of positional deviation of the proposed method is 2.583 mm, and the RMS of the difference of positional deviation between adjacent points reaches 0.035 mm. Experimental results show that the proposed sectional control method can not only effectively decrease the accumulated survey error but also guarantee the relative positional precision of the installation control network. So it can be applied in the data processing of tunnel installation control networks, especially for large particle accelerators.

Keywords: alignment, tunnel installation control network, accumulated survey error, sectional control method, datum

Procedia PDF Downloads 191

Authors: Muhammad Zubair Khan, Yugyung Lee

Abstract:

Deep learning has recently achieved enormous response in semantic image segmentation. The previously developed U-Net inspired architectures operate with continuous stride and pooling operations, leading to spatial data loss. Also, the methods lack establishing long-term pixels connection to preserve context knowledge and reduce spatial loss in prediction. This article developed encoder-decoder architecture with bi-directional LSTM embedded in long skip-connections and densely connected convolution blocks. The network non-linearly combines the feature maps across encoder-decoder paths for finding dependency and correlation between image pixels. Additionally, the densely connected convolutional blocks are kept in the final encoding layer to reuse features and prevent redundant data sharing. The method applied batch-normalization for reducing internal covariate shift in data distributions. The empirical evidence shows a promising response to our method compared with other semantic segmentation techniques.

Keywords: deep learning, semantic segmentation, image analysis, pixels connection, convolution neural network

Procedia PDF Downloads 103

Authors: Ksheeraj Sai Vepuri, Nada Attar

Abstract:

We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.

Keywords: facial expression recognittion, image preprocessing, deep learning, CNN

Procedia PDF Downloads 143

Authors: Gholba Niranjan Dilip, Anil Kumar

Abstract:

Conduct of accurate reliable mapping of oil palm plantations and census of individual palm trees is a huge challenge. This study addresses this challenge and developed an optimized solution implemented deep learning techniques on remote sensing data. The oil palm is a very important tropical crop. To improve its productivity and land management, it is imperative to have accurate census over large areas. Since, manual census is costly and prone to approximations, a methodology for automated census using panchromatic images from Cartosat-2, SkySat and World View-3 satellites is demonstrated. It is selected two different study sites in Indonesia. The customized set of training data and ground-truth data are created for this study from Cartosat-2 images. The pre-trained model of Single Shot MultiBox Detector (SSD) Lite MobileNet V2 Convolutional Neural Network (CNN) from the TensorFlow Object Detection API is subjected to transfer learning on this customized dataset. The SSD model is able to generate the bounding boxes for each oil palm and also do the counting of palms with good accuracy on the panchromatic images. The detection yielded an F-Score of 83.16 % on seven different images. The detections are buffered and dissolved to generate polygons demarcating the boundaries of the oil palm plantations. This provided the area under the plantations and also gave maps of their location, thereby completing the automated census, with a fairly high accuracy (≈100%). The trained CNN was found competent enough to detect oil palm crowns from images obtained from multiple satellite sensors and of varying temporal vintage. It helped to estimate the increase in oil palm plantations from 2014 to 2021 in the study area. The study proved that high-resolution panchromatic satellite image can successfully be used to undertake census of oil palm plantations using CNNs.

Keywords: object detection, oil palm tree census, panchromatic images, single shot multibox detector

Procedia PDF Downloads 160

Authors: Utkarsh A. Mishra, Ankit Bansal

Abstract:

At high temperature, radiative heat transfer is the dominant mode of heat transfer. It is governed by various phenomena such as photon emission, absorption, and scattering. The solution of the governing integrodifferential equation of radiative transfer is a complex process, more when the effect of participating medium and wavelength properties are taken into consideration. Although a generic formulation of such radiative transport problem can be modeled for a wide variety of problems with non-gray, non-diffusive surfaces, there is always a trade-off between simplicity and accuracy of the problem. Recently, solutions of complicated mathematical problems with statistical methods based on randomization of naturally occurring phenomena have gained significant importance. Photon bundles with discrete energy can be replicated with random numbers describing the emission, absorption, and scattering processes. Photon Monte Carlo (PMC) is a simple, yet powerful technique, to solve radiative transfer problems in complicated geometries with arbitrary participating medium. The method, on the one hand, increases the accuracy of estimation, and on the other hand, increases the computational cost. The participating media -generally a gas, such as CO₂, CO, and H₂O- present complex emission and absorption spectra. To model the emission/absorption accurately with random numbers requires a weighted sampling as different sections of the spectrum carries different importance. Importance sampling (IS) was implemented to sample random photon of arbitrary wavelength, and the sampled data provided unbiased training of MC estimators for better results. A better replacement to uniform random numbers is using deterministic, quasi-random sequences. Halton, Sobol, and Faure Low-Discrepancy Sequences are used in this study. They possess better space-filling performance than the uniform random number generator and gives rise to a low variance, stable Quasi-Monte Carlo (QMC) estimators with faster convergence. An optimal supervised learning scheme was further considered to reduce the computation costs of the PMC simulation. A one-dimensional plane-parallel slab problem with participating media was formulated. The history of some randomly sampled photon bundles is recorded to train an Artificial Neural Network (ANN), back-propagation model. The flux was calculated using the standard quasi PMC and was considered to be the training target. Results obtained with the proposed model for the one-dimensional problem are compared with the exact analytical and PMC model with the Line by Line (LBL) spectral model. The approximate variance obtained was around 3.14%. Results were analyzed with respect to time and the total flux in both cases. A significant reduction in variance as well a faster rate of convergence was observed in the case of the QMC method over the standard PMC method. However, the results obtained with the ANN method resulted in greater variance (around 25-28%) as compared to the other cases. There is a great scope of machine learning models to help in further reduction of computation cost once trained successfully. Multiple ways of selecting the input data as well as various architectures will be tried such that the concerned environment can be fully addressed to the ANN model. Better results can be achieved in this unexplored domain.

Keywords: radiative heat transfer, Monte Carlo Method, pseudo-random numbers, low discrepancy sequences, artificial neural networks

Procedia PDF Downloads 223

Authors: Shweta Singh, Sudaman Katti

Abstract:

The most well-known sequence models make use of complex recurrent neural networks in an encoder-decoder configuration. The model used in this research makes use of a transformer, which is based purely on a self-attention mechanism, without relying on recurrence at all. More specifically, encoders and decoders which make use of self-attention and operate based on a memory, are used. In this research work, results for various 3D visual and non-visual reinforcement learning tasks designed in Unity software were obtained. Convolutional neural networks, more specifically, nature CNN architecture, are used for input processing in visual tasks, and comparison with standard long short-term memory (LSTM) architecture is performed for both visual tasks based on CNNs and non-visual tasks based on coordinate inputs. This research work combines the transformer architecture with the proximal policy optimization technique used popularly in reinforcement learning for stability and better policy updates while training, especially for continuous action spaces, which are used in this research work. Certain tasks in this paper are long horizon tasks that carry on for a longer duration and require extensive use of memory-based functionalities like storage of experiences and choosing appropriate actions based on recall. The transformer, which makes use of memory and self-attention mechanism in an encoder-decoder configuration proved to have better performance when compared to LSTM in terms of exploration and rewards achieved. Such memory based architectures can be used extensively in the field of cognitive robotics and reinforcement learning.

Keywords: convolutional neural networks, reinforcement learning, self-attention, transformers, unity

Procedia PDF Downloads 136

Authors: Dylan Santos De Pinho, Nabil Ouerhani

Abstract:

Energy consumption of machine-tools is becoming critical for machine-tool builders and end-users because of economic, ecological and legislation-related reasons. Many machine-tool builders are seeking for solutions that allow the reduction of energy consumption of machine-tools while preserving the same productivity rate and the same quality of machined parts. In this paper, we present the first results of a project conducted jointly by academic and industrial partners to reduce the energy consumption of a Swiss-Type lathe. We employ genetic algorithms to find optimal machining parameters – the set of parameters that lead to the best trade-off between energy consumption, part quality and tool lifetime. Three main machining process parameters are considered in our optimization technique, namely depth of cut, spindle rotation speed and material feed rate. These machining process parameters have been identified as the most influential ones in the configuration of the Swiss-type machining process. A state-of-the-art multi-objective genetic algorithm has been used. The algorithm combines three fitness functions, which are objective functions that permit to evaluate a set of parameters against the three objectives: energy consumption, quality of the machined parts, and tool lifetime. In this paper, we focus on the investigation of the fitness function related to energy consumption. Four different energy consumption related fitness functions have been investigated and compared. The first fitness function refers to the Kienzle cutting force model. The second fitness function uses the Material Removal Rate (RMM) as an indicator of energy consumption. The two other fitness functions are non-deterministic, learning-based functions. One fitness function uses a simple Neural Network to learn the relation between the process parameters and the energy consumption from experimental data. Another fitness function uses Lasso regression to determine the same relation. The goal is, then, to find out which fitness functions predict best the energy consumption of a Swiss-Type machining process for the given set of machining process parameters. Once determined, these functions may be used for optimization purposes – determine the optimal machining process parameters leading to minimum energy consumption. The performance of the four fitness functions has been evaluated. The Tornos DT13 Swiss-Type Lathe has been used to carry out the experiments. A mechanical part including various Swiss-Type machining operations has been selected for the experiments. The evaluation process starts with generating a set of CNC (Computer Numerical Control) programs for machining the part at hand. Each CNC program considers a different set of machining process parameters. During the machining process, the power consumption of the spindle is measured. All collected data are assigned to the appropriate CNC program and thus to the set of machining process parameters. The evaluation approach consists in calculating the correlation between the normalized measured power consumption and the normalized power consumption prediction for each of the four fitness functions. The evaluation shows that the Lasso and Neural Network fitness functions have the highest correlation coefficient with 97%. The fitness function “Material Removal Rate” (MRR) has a correlation coefficient of 90%, whereas the Kienzle-based fitness function has a correlation coefficient of 80%.

Keywords: adaptive machining, genetic algorithms, smart manufacturing, parameters optimization

Procedia PDF Downloads 147

Authors: Subodh Chandra Shakya, Badal Shrestha, Suni Thapa, Ashutosh Chauhan, Saugat Adhikari

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: inception ResNet, convolutional neural net, deep learning, confusion matrix, data augmentation, data preprocessing

Procedia PDF Downloads 187

Authors: YingWei Tan, XueFeng Ding

Abstract:

Attention-based voice activity detection models have gained significant attention in recent years due to their fast training speed and ability to capture a wide contextual range. The inclusion of multi-head style and position embedding in the attention architecture are crucial. Having multiple attention heads allows for differential focus on different parts of the sequence, while position embedding provides guidance for modeling dependencies between elements at various positions in the input sequence. In this work, we propose an approach by considering each head as a node, enabling the application of graph neural networks (GNN) to identify correlations among the different nodes. In addition, we adopt an implementation named rotary position embedding (RoPE), which encodes absolute positional information into the input sequence by a rotation matrix, and naturally incorporates explicit relative position information into a self-attention module. We evaluate the effectiveness of our method on a synthetic dataset, and the results demonstrate its superiority over the baseline CRNN in scenarios with low signal-to-noise ratio and noise, while also exhibiting robustness across different noise types. In summary, our proposed framework effectively combines the strengths of CNN and RNN (LSTM), and further enhances detection performance through the integration of graph neural networks and rotary position embedding.

Keywords: voice activity detection, CRNN, graph neural networks, rotary position embedding

Procedia PDF Downloads 72

Authors: Linh Nguyen Tung, Anh Truong Viet, Nghien Nguyen Ba, Chuong Trinh Trong

Abstract:

This paper proposes a reconfiguration methodology based on a continuous genetic algorithm (CGA) and particle swarm optimization (PSO) for minimizing active power loss and minimizing voltage deviation. Both algorithms are adapted using graph theory to generate feasible individuals, and the modified crossover is used for continuous variable of CGA. To demonstrate the performance and effectiveness of the proposed methods, a comparative analysis of CGA with PSO for network reconfiguration, on 33-node and 119-bus radial distribution system is presented. The simulation results have shown that both CGA and PSO can be used in the distribution network reconfiguration and CGA outperformed PSO with significant success rate in finding optimal distribution network configuration.

Keywords: distribution network reconfiguration, particle swarm optimization, continuous genetic algorithm, power loss reduction, voltage deviation

Procedia PDF Downloads 188

Authors: Soheila Sadeghi

Abstract:

Construction projects are complex and often subject to significant cost overruns due to the multifaceted nature of the activities involved. Accurate cost estimation is crucial for effective budget planning and resource allocation. Traditional methods for predicting overruns often rely on expert judgment or analysis of historical data, which can be time-consuming, subjective, and may fail to consider important factors. However, with the increasing availability of data from construction projects, machine learning techniques can be leveraged to improve the accuracy of overrun predictions. This study applied machine learning algorithms to enhance the prediction of cost overruns in a case study of a construction project. The methodology involved the development and evaluation of two machine learning models: Random Forest and Neural Networks. Random Forest can handle high-dimensional data, capture complex relationships, and provide feature importance estimates. Neural Networks, particularly Deep Neural Networks (DNNs), are capable of automatically learning and modeling complex, non-linear relationships between input features and the target variable. These models can adapt to new data, reduce human bias, and uncover hidden patterns in the dataset. The findings of this study demonstrate that both Random Forest and Neural Networks can significantly improve the accuracy of cost overrun predictions compared to traditional methods. The Random Forest model also identified key cost drivers and risk factors, such as changes in the scope of work and delays in material delivery, which can inform better project risk management. However, the study acknowledges several limitations. First, the findings are based on a single construction project, which may limit the generalizability of the results to other projects or contexts. Second, the dataset, although comprehensive, may not capture all relevant factors influencing cost overruns, such as external economic conditions or political factors. Third, the study focuses primarily on cost overruns, while schedule overruns are not explicitly addressed. Future research should explore the application of machine learning techniques to a broader range of projects, incorporate additional data sources, and investigate the prediction of both cost and schedule overruns simultaneously.

Keywords: cost prediction, machine learning, project management, random forest, neural networks

Procedia PDF Downloads 56

Authors: Tao Feng, Xiaomei Ma, Xian Guo, Jing Wang

Abstract:

Named Data Network (NDN) is one of the future Internet architecture, all nodes (i.e., hosts, routers) are allowed to have a local cache, used to satisfy incoming requests for content. However, depending on caching allows an adversary to perform attacks that are very effective and relatively easy to implement, such as content pollution attack. In this paper, we use a method of secure network coding based on homomorphic signature system to solve this problem. Firstly ,we use a dynamic public key technique, our scheme for each generation authentication without updating the initial secret key used. Secondly, employing the homomorphism of hash function, intermediate node and destination node verify the signature of the received message. In addition, when the network topology of NDN is simple and fixed, the code coefficients in our scheme are generated in a pseudorandom number generator in each node, so the distribution of the coefficients is also avoided. In short, our scheme not only can efficiently prevent against Intra/Inter-GPAs, but also can against the content poisoning attack in NDN.

Keywords: named data networking, content polloution attack, network coding signature, internet architecture

Procedia PDF Downloads 337

Authors: Niroshan K. Walgama Wellalage, Tieling Zhang, Richard Dwight

Abstract:

State-based Markov deterioration models (SMDM) sometimes fail to find accurate transition probability matrix (TPM) values, and hence lead to invalid future condition prediction or incorrect average deterioration rates mainly due to drawbacks of existing nonlinear optimization-based algorithms and/or subjective function types used for regression analysis. Furthermore, a set of separate functions for each condition state with age cannot be directly derived by using Markov model for a given bridge element group, which however is of interest to industrial partners. This paper presents a new approach for generating Homogeneous SMDM model output, namely, the Modified Weibull approach, which consists of a set of appropriate functions to describe the percentage condition prediction of bridge elements in each state. These functions are combined with Bayesian approach and Metropolis Hasting Algorithm (MHA) based Markov Chain Monte Carlo (MCMC) simulation technique for quantifying the uncertainty in model parameter estimates. In this study, factors contributing to rail bridge deterioration were identified. The inspection data for 1,000 Australian railway bridges over 15 years were reviewed and filtered accordingly based on the real operational experience. Network level deterioration model for a typical bridge element group was developed using the proposed Modified Weibull approach. The condition state predictions obtained from this method were validated using statistical hypothesis tests with a test data set. Results show that the proposed model is able to not only predict the conditions in network-level accurately but also capture the model uncertainties with given confidence interval.

Keywords: bridge deterioration modelling, modified weibull approach, MCMC, metropolis-hasting algorithm, bayesian approach, Markov deterioration models

Procedia PDF Downloads 727

Authors: Imam Muthohar, Budi Hartono, Sigit Priyanto, Hardiansyah Hardiansyah

Abstract:

The eruption of Merapi Volcano in Yogyakarta, Indonesia in 2010 caused many casualties due to minimum preparedness in facing disaster. Increasing population capacity and evacuating to safe places become very important to minimize casualties. Regional government through the Regional Disaster Management Agency has divided disaster-prone areas into three parts, namely ring 1 at a distance of 10 km, ring 2 at a distance of 15 km and ring 3 at a distance of 20 km from the center of Mount Merapi. The success of the evacuation is fully supported by road network infrastructure as a way to rescue in an emergency. This research attempts to model evacuation process based on the rise of refugees in ring 1, expanded to ring 2 and finally expanded to ring 3. The model was developed using SATURN (Simulation and Assignment of Traffic to Urban Road Networks) program version 11.3. 12W, involving 140 centroid, 449 buffer nodes, and 851 links across Yogyakarta Special Region, which was aimed at making a preliminary identification of road networks considered vulnerable to disaster. An assumption made to identify vulnerability was the improvement of road network performance in the form of flow and travel times on the coverage of ring 1, ring 2, ring 3, Sleman outside the ring, Yogyakarta City, Bantul, Kulon Progo, and Gunung Kidul. The research results indicated that the performance increase in the road networks existing in the area of ring 2, ring 3, and Sleman outside the ring. The road network in ring 1 started to increase when the evacuation was expanded to ring 2 and ring 3. Meanwhile, the performance of road networks in Yogyakarta City, Bantul, Kulon Progo, and Gunung Kidul during the evacuation period simultaneously decreased in when the evacuation areas were expanded. The results of preliminary identification of the vulnerability have determined that the road networks existing in ring 1, ring 2, ring 3 and Sleman outside the ring were considered vulnerable to the evacuation of Mount Merapi eruption. Therefore, it is necessary to pay a great deal of attention in order to face the disasters that potentially occur at anytime.

Keywords: model, evacuation, SATURN, vulnerability

Procedia PDF Downloads 170

Authors: H. Zormati, J. Chebil, J. Bel Hadj Taher

Abstract:

The goal of this paper is to present an addressing scheme that allows for assigning a unique IPv6 address to each node in the Internet of Things (IoT) network. This scheme guarantees uniqueness by extracting the clock skew of each communication device and converting it into an IPv6 address. Simulation analysis confirms that the presented scheme provides reductions in terms of energy consumption, communication overhead and response time as compared to four studied addressing schemes Strong DAD, LEADS, SIPA and CLOSA.

Keywords: addressing, IoT, IPv6, network, nodes

Procedia PDF Downloads 293

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 101

Authors: R. Venkatesan, A. Sabari

Abstract:

Developments of social networking internet scenario are recommended for the requirements of scalable, authentic, secure group communication model like multicasting. Multicasting is an inter network service that offers efficient delivery of data from a source to multiple destinations. Even though multicast has been very successful at providing an efficient and best-effort data delivery service for huge groups, it verified complex process to expand other features to multicast in a scalable way. Separately, the requirement for secure electronic information had become gradually more apparent. Since multicast applications are deployed for mainstream purpose the need to secure multicast communications will become significant.

Keywords: multicasting, scalability, security, social network

Procedia PDF Downloads 292

Authors: Adekunle Taiwo Adenike, I. K. Ogundoyin

Abstract:

Lassa fever is a neglected tropical virus that has become a significant public health issue in Nigeria, with the country having the greatest burden in Africa. This paper presents a Geo-Computational Model for Analysis and Prediction of Lassa Fever Dynamics and Outbreaks in Nigeria. The model investigates the dynamics of the virus with respect to environmental factors and human populations. It confirms the role of the rodent host in virus transmission and identifies how climate and human population are affected. The proposed methodology is carried out on a Linux operating system using the OSGeoLive virtual machine for geographical computing, which serves as a base for spatial ecology computing. The model design uses Unified Modeling Language (UML), and the performance evaluation uses machine learning algorithms such as random forest, fuzzy logic, and neural networks. The study aims to contribute to the control of Lassa fever, which is achievable through the combined efforts of public health professionals and geocomputational and machine learning tools. The research findings will potentially be more readily accepted and utilized by decision-makers for the attainment of Lassa fever elimination.

Keywords: geo-computational model, lassa fever dynamics, lassa fever, outbreak prediction, nigeria

Procedia PDF Downloads 94

Authors: Zhifeng Kong

Abstract:

Over-parameterized neural networks have attracted a great deal of attention in recent deep learning theory research, as they challenge the classic perspective of over-fitting when the model has excessive parameters and have gained empirical success in various settings. While a number of theoretical works have been presented to demystify properties of such models, the convergence properties of such models are still far from being thoroughly understood. In this work, we study the convergence properties of training two-hidden-layer partially over-parameterized fully connected networks with the Rectified Linear Unit activation via gradient descent. To our knowledge, this is the first theoretical work to understand convergence properties of deep over-parameterized networks without the equally-wide-hidden-layer assumption and other unrealistic assumptions. We provide a probabilistic lower bound of the widths of hidden layers and proved linear convergence rate of gradient descent. We also conducted experiments on synthetic and real-world datasets to validate our theory.

Keywords: over-parameterization, rectified linear units ReLU, convergence, gradient descent, neural networks

Procedia PDF Downloads 142

Authors: Virender Ranga, Mayank Dave, Anil Kumar Verma

Abstract:

Recently wireless sensor networks (WSNs) are used in many real life applications like environmental monitoring, habitat monitoring, health monitoring etc. Due to power constraint cheaper devices used in these applications, the energy consumption of each device should be kept as low as possible such that network operates for longer period of time. One of the techniques to prolong the network lifetime is an intelligent grouping of sensor nodes such that they can perform their operation in cooperative and energy efficient manner. With this motivation, we propose a novel approach by organize the sensor nodes in cooperative multihop mini-groups so that the total global energy consumption of the network can be reduced and network lifetime can be improved. Our proposed approach also reduces the number of transmitted messages inside the WSNs, which further minimizes the energy consumption of the whole network. The experimental simulations show that our proposed approach outperforms over the state-of-the-art approach in terms of stability period and aggregated data.

Keywords: clustering, cluster-head, mini-group, stability period

Procedia PDF Downloads 357

Authors: Hamdi Beji, Toufik Kanit, Tanguy Messager

Abstract:

This study aims to construct a predictive model proficient in foreseeing the linear elastic and thermal characteristics of composite materials, drawing on a multitude of influencing parameters. These parameters encompass the shape of inclusions (circular, elliptical, square, triangle), their spatial coordinates within the matrix, orientation, volume fraction (ranging from 0.05 to 0.4), and variations in contrast (spanning from 10 to 200). A variety of machine learning techniques are deployed, including decision trees, random forests, support vector machines, k-nearest neighbors, and an artificial neural network (ANN), to facilitate this predictive model. Moreover, this research goes beyond the predictive aspect by delving into an inverse analysis using genetic algorithms. The intent is to unveil the intrinsic characteristics of composite materials by evaluating their thermomechanical responses. The foundation of this research lies in the establishment of a comprehensive database that accounts for the array of input parameters mentioned earlier. This database, enriched with this diversity of input variables, serves as a bedrock for the creation of machine learning and genetic algorithm-based models. These models are meticulously trained to not only predict but also elucidate the mechanical and thermal conduct of composite materials. Remarkably, the coupling of machine learning and genetic algorithms has proven highly effective, yielding predictions with remarkable accuracy, boasting scores ranging between 0.97 and 0.99. This achievement marks a significant breakthrough, demonstrating the potential of this innovative approach in the field of materials engineering.

Keywords: machine learning, composite materials, genetic algorithms, mechanical and thermal proprieties

Procedia PDF Downloads 54

Authors: Chiao-Chen Chang, Yang-Chieh Chin

Abstract:

Social media has created a change in the way the network community is clustered, especially from the location of the community, from the original virtual space to the intertwined network, and thus the communication between people will change from face to face communication to social media-based communication model. However, social media users who have had a fixed engagement may have an intention to switch to another service provider because of the emergence of new forms of social media. For example, some of Facebook or Twitter users switched to Instagram in 2014 because of social media messages or image overloads, and users may seek simpler and instant social media to become their main social networking tool. This study explores the impact of system features overload, information overload, social monitoring concerns, problematic use and privacy concerns as the antecedents on social media fatigue, dissatisfaction, and alternative attractiveness; further influence social media switching. This study also uses the online questionnaire survey method to recover the sample data, and then confirm the factor analysis, path analysis, model fit analysis and mediating analysis with the structural equation model (SEM). Research findings demonstrated that there were significant effects on multiple paths. Based on the research findings, this study puts forward the implications of theory and practice.

Keywords: social media, switching, social media fatigue, alternative attractiveness

Procedia PDF Downloads 140

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 148

Authors: Yousra Hadj Hassen, Walid Ayedi, Tarek Ouni, Mohamed Jallouli

Abstract:

To re-identify a person is to check if he/she has been already seen over a cameras network. Recently, re-identifying people over large public cameras networks has become a crucial task of great importance to ensure public security. The vision community has deeply investigated this area of research. Most existing researches rely only on the spatial appearance information from either one or multiple person images. Actually, the real person re-id framework is a multi-shot scenario. However, to efficiently model a person’s appearance and to choose the best samples to remain a challenging problem. In this work, an extensive comparison of descriptors of state of the art associated with the proposed frame selection method is studied. Specifically, we evaluate the samples selection approach using multiple proposed descriptors. We show the effectiveness and advantages of the proposed method by extensive comparisons with related state-of-the-art approaches using two standard datasets PRID2011 and iLIDS-VID.

Keywords: camera network, descriptor, model, multi-shot, person re-identification, selection

Procedia PDF Downloads 278

Authors: Shahram Jamali, Samira Hamed

Abstract:

One of the open issues in Random Early Detection (RED) algorithm is how to set its parameters to reach high performance for the dynamic conditions of the network. Although original RED uses fixed values for its parameters, this paper follows a model-based approach to upgrade performance of the RED algorithm. It models the routers queue behavior by using the Markov model and uses this model to predict future conditions of the queue. This prediction helps the proposed algorithm to make some tunings over RED's parameters and provide efficiency and better performance. Widespread packet level simulations confirm that the proposed algorithm, called Markov-RED, outperforms RED and FARED in terms of queue stability, bottleneck utilization and dropped packets count.

Keywords: active queue management, RED, Markov model, random early detection algorithm

Procedia PDF Downloads 539

Authors: Walailak Atthirawong

Abstract:

By the end of 2015, the Association of Southeast Asian Nations (ASEAN) countries proclaim to transform into the next stage of an economic era by having a single market and production base called ASEAN Economic Community (AEC). One objective of the AEC is to establish ASEAN as a single market and one production base making ASEAN highly competitive economic region and competitive with new mechanisms. As a result, it will open more opportunities to enterprises in both trade and investment, which offering a competitive market of US$ 2.6 trillion and over 622 million people. Location decision plays a key role in achieving corporate competitiveness. Hence, it may be necessary for enterprises to redesign their supply chains via enlarging a new production base which has low labor cost, high labor skill and numerous of labor available. This strategy will help companies especially for apparel industry in order to maintain a competitive position in the global market. Therefore, in this paper a generic model for location selection decision for Thai apparel industry using Fuzzy Analytical Network Process (FANP) is proposed. Myanmar, Vietnam and Cambodia are referred for alternative location decision from interviewing expert persons in this industry who have planned to enlarge their businesses in AEC countries. The contribution of this paper lies in proposing an approach model that is more practical and trustworthy to top management in making a decision on location selection.

Keywords: apparel industry, ASEAN Economic Community (AEC), Fuzzy Analytical Network Process (FANP), location decision

Procedia PDF Downloads 236

Authors: Lin Dong, Fei Shi

Abstract:

Based on the railway network and the principles of space syntax, the study attempts to reconstruct the spatial relationship of the passenger network connections from space and time perspective. According to the travel time data of main stations in the Yangtze River Delta urban agglomeration obtained by the Internet, the topological drawing of railway network under different time sections is constructed. With the comprehensive index composed of connection and integration, the accessibility and network operation efficiency of the railway network in different time periods is calculated, while the fairness of the network is analyzed by the fairness indicators constructed with the integration and location entropy from the perspective of horizontal and vertical fairness respectively. From the analysis of the efficiency and fairness of the railway passenger transport network, the study finds: (1) There is a strong regularity in regional system accessibility change; (2) The problems of efficiency and fairness are different in different time periods; (3) The improvement of efficiency will lead to the decline of horizontal fairness to a certain extent, while from the perspective of vertical fairness, the supply-demand situation has changed smoothly with time; (4) The network connection efficiency of Shanghai, Jiangsu and Zhejiang regions is higher than that of the western regions such as Anqing and Chizhou; (5) The marginalization of Nantong, Yancheng, Yangzhou, Taizhou is obvious. The study explores the application of spatial syntactic theory in regional traffic analysis, in order to provide a reference for the development of urban agglomeration transportation network.

Keywords: spatial syntax, the Yangtze River Delta, railway passenger time, efficiency and fairness

Procedia PDF Downloads 136

Authors: Adeolu O. Dairo

Abstract:

Getting the consumer marketing strategy right is a crucial and complex task for firms with a large customer base such as mobile operators in a competitive mobile market. While empirical studies have made efforts to identify key constructs, no geospatial model has been developed to comprehensively assess the viability and interdependency of ground realities regarding the customer, competition, channel and the network quality of mobile operators. With this research, a geo-analytic framework is proposed for strategy formulation and allocation for mobile operators. Firstly, a fuzzy analytic network using a self-organizing feature map clustering technique based on inputs from managers and literature, which depicts the interrelationships amongst ground realities is developed. The model is tested with a mobile operator in the Nigeria mobile market. As a result, a customer-centric geospatial and visualization solution is developed. This provides a consolidated and integrated insight that serves as a transparent, logical and practical guide for strategic, tactical and operational decision making.

Keywords: geospatial, geo-analytics, self-organizing map, customer-centric

Procedia PDF Downloads 183