Search results for: Fuzzy Analytical Network Process (FANP)

Authors: Meng Koon Lee, Mohammad Hosseini Fouladi, Satesh Narayana Namasivayam

Abstract:

Research is focused on the response of soundboards of Classical guitars at frequencies up to 5 kHz as the soundboard is a major contributor to acoustic radiation at high frequencies when compared to the bridge and sound hole. A thin rectangular plate of variable thickness that is simply-supported on all sides is used as an analytical model of the research. This model is used to study the response of the guitar soundboard as the latter can be considered as a modified form of a rectangular plate. Homotopy Perturbation Method (HPM) is selected as a mathematical method to obtain an analytical solution of the 4th-order parabolic partial differential equation of motion of the rectangular plate of constant thickness viewed as a linear problem. This procedure is generalized to the nonlinear problem of the rectangular plate with variable thickness and an analytical solution can also be obtained. Sound power is used as a parameter to investigate the acoustic radiation of soundboards made from spruce using various bracing patterns. The sound power of soundboards made from Malaysian softwood such as damar minyak, sempilor or podo are investigated to determine the viability of replacing spruce as future materials for soundboards of Classical guitars.

Keywords: rectangular plates, analytical solution, homotopy perturbation, natural frequencies

Procedia PDF Downloads 386

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 181

Authors: Guezouli Larbi, Belkacem Soundes

Abstract:

The automation of the text detection process can help the human in his driving task. Its application can be very useful to help drivers to have more information about their environment by facilitating the reading of road signs such as directional signs, events, stores, etc. In this paper, a system consisting of two stages has been proposed. In the first one, we used pseudo-Zernike moments to pinpoint areas of the image that may contain text. The architecture of this part is based on three main steps, region of interest (ROI) detection, text localization, and non-text region filtering. Then, in the second step, we present a convolutional neural network architecture (On-Road Text Detection Network - ORTDN) which is considered a classification phase. The results show that the proposed framework achieved ≈ 35 fps and an mAP of ≈ 90%, thus a low computational time with competitive accuracy.

Keywords: text detection, CNN, PZM, deep learning

Procedia PDF Downloads 78

Authors: Ana L. Martins, Rita S. Saraiva, João C. Ferreira

Abstract:

Much effort has been placed on the assessment of perceived service quality. Several models can be found in literature, but these are mainly focused on business-to-consumer (B2C) relationships. Literature on how to assess perceived quality in business-to-business (B2B) contexts is scarce both conceptually and in terms of its application. This research aims at filling this gap in literature by applying INDSERV to a case study situation. Under this scope, this research aims at analyzing the adequacy of the proposed assessment tool to other context besides the one where it was developed and by doing so analyzing the perceive quality of the advertisement service provided by a specific television network to its B2B customers. The INDSERV scale was adopted and applied to a sample of 33 clients, via questionnaires adapted to interviews. Data was collected in person or phone. Both quantitative and qualitative data collection was performed. Qualitative data analysis followed content analysis protocol. Quantitative analysis used hypotheses testing. Findings allowed to conclude that the perceived quality of the television service provided by television network is very positive, being the Soft Process Quality the parameter that reveals the highest perceived quality of the service as opposed to Potential Quality. To this end, some comments and suggestions were made by the clients regarding each one of these service quality parameters. Based on the hypotheses testing, it was noticed that only advertisement clients that maintain a connection to the television network from 5 to 10 years do show a significant different perception of the TV advertisement service provided by the company in what the Hard Process Quality parameter is concerned. Through the collected data content analysis, it was possible to obtain the percentage of clients which share the same opinions and suggestions for improvement. Finally, based on one of the four service quality parameter in a B2B context, managerial suggestions were developed aiming at improving the television network advertisement perceived quality service.

Keywords: B2B, case study, INDSERV, perceived service quality

Procedia PDF Downloads 203

Authors: Ahmed Hamzi, Bryan Norman

Abstract:

Having scribes help document patient records in electronic health record systems can improve hospitalists’ productivity. But hospitals need to determine the optimum number of scribes to hire to maximize scribe cost effectiveness. Scribe attendance uncertainty due to planned and unplanned absences is a primary challenge. This paper presents simulation and analytical models to determine the optimum number of scribes for a hospital to hire. Scribe staffing practices vary from one context to another; different staffing scenarios are considered where having extra attending scribes provides or does not provide additional value and utilizing on-call scribes to fill in for potentially absent scribes. These staffing scenarios are assessed for different scribe revenue ratios (ratio of the value of the scribe relative to scribe costs) ranging from 100% to 300%. The optimum solution depends on the absenteeism rate, revenue ratio, and desired service level. The analytical model obtains solutions easier and faster than the simulation model, but the simulation model is more accurate. Therefore, the analytical model’s solutions are compared with the simulation model’s solutions regarding both the number of scribes hired and cost-effectiveness. Additionally, an Excel tool has been developed to facilitate decision-makers in easily obtaining solutions using the analytical model.

Keywords: hospitalists, workload, optimization cost, economic analysis

Procedia PDF Downloads 38

Authors: Aref Aasi, Sadegh Mehdi Aghaei, Balaji Panchapakesan

Abstract:

This work aims to evaluate the free and forced vibration of a beam with two end joints subjected to a concentrated moving mass and a load using the Euler-Bernoulli method. The natural frequency is calculated for different locations of the concentrated mass and load on the beam. The analytical results are verified by the experimental data. The variations of natural frequency as a function of the location of the mass, the effect of the forced frequency on the vibrational amplitude, and the displacement amplitude versus time are investigated. It is discovered that as the concentrated mass moves toward the center of the beam, the natural frequency of the beam and the relative error between experimental and analytical data decreases. There is a close resemblance between analytical data and experimental observations.

Keywords: Euler-Bernoulli beam, natural frequency, forced vibration, experimental setup

Procedia PDF Downloads 261

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 331

Authors: Sharad Shrivastava, Arun Jalan

Abstract:

In this study tensile testing was performed on randomly oriented short glass fiber/epoxy resin composite specimens which were prepared using hand lay-up method. Samples were tested over a wide range of strain rate/loading rate from 2mm/min to 40mm/min to see the effect on ultimate tensile strength of the composite. A multi layered 'back propagation artificial neural network of supervised learning type' was used to analyze and predict the tensile properties with strain rate and temperature as given input and output as UTS to predict. Various network structures were designed and investigated with varying parameters and network sizes, and an optimized network structure was proposed to predict the UTS of short glass fiber/epoxy resin composite specimens with reasonably good accuracy.

Keywords: glass fiber composite, mechanical properties, strain rate, artificial neural network

Procedia PDF Downloads 436

Authors: José Luis Carrillo-Medina, Roberto Latorre

Abstract:

Experimental evidence has revealed that different living neural systems can sign their output signals with some specific neural signature. Although experimental and modeling results suggest that neural signatures can have an important role in the activity of neural networks in order to identify the source of the information or to contextualize a message, the functional meaning of these neural fingerprints is still unclear. The existence of cellular mechanisms to identify the origin of individual neural signals can be a powerful information processing strategy for the nervous system. We have recently built different models to study the ability of a neural network to process information based on the emission and recognition of specific neural fingerprints. In this paper we further analyze the features that can influence on the information processing ability of this kind of networks. In particular, we focus on the role that the duration of a refractory period in each neuron after emitting a signed message can play in the network collective dynamics.

Keywords: neural signature, neural fingerprint, processing based on signal identification, self-organizing neural network

Procedia PDF Downloads 484

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 283

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 350

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 263

Authors: Alireza Keshmiri, Shahriar Bagheri, Nan Wu

Abstract:

This research presents an analytical model for the development of an energy harvester with piezoelectric rings stacked at the boundary of the structure based on the Adomian decomposition method. The model is applied to geometrically non-uniform beams to derive the steady-state dynamic response of the structure subjected to base motion excitation and efficiently harvest the subsequent vibrational energy. The in-plane polarization of the piezoelectric rings is employed to enhance the electrical power output. A parametric study for the proposed energy harvester with various design parameters is done to prepare the dataset required for optimization. Finally, simulation-based optimization technique helps to find the optimum structural design with maximum efficiency. To solve the optimization problem, an artificial neural network is first trained to replace the simulation model, and then, a genetic algorithm is employed to find the optimized design variables. Higher geometrical non-uniformity and length of the beam lowers the structure natural frequency and generates a larger power output.

Keywords: piezoelectricity, energy harvesting, simulation-based optimization, artificial neural network, genetic algorithm

Procedia PDF Downloads 116

Authors: Yazhou Zhou, Yong Huang, Guoqin Ge

Abstract:

In the process of human social development, the coupling and coordinated development among the ecological environment(E), production(P), and living functions(L) is of great significance for sustainable development. This study uses an improved coupling coordination degree model (CCDM) to discover the coordination conflict between E and human settlement environment. The main work of this study is as follows: (1) It is found that in the process of urbanization development of Ya 'an city from 2014 to 2018, the degree of coupling (DOC) value between E, P, and L is high, but the coupling coordination degree (CCD) of the three is low, especially the DOC value of E and the other two has the biggest decline. (2) A more objective weight value is obtained, which can avoid the analysis error caused by subjective judgment weight value.

Keywords: ecological environment, coupling coordination degree, neural network, sustainable development

Procedia PDF Downloads 68

Authors: Samia Dardouri, Ridha Bouallegue

Abstract:

Scheduling is the process of dynamically allocating physical resources to User Equipment (UE) based on scheduling algorithms implemented at the LTE base station. Various algorithms have been proposed by network researchers as the implementation of scheduling algorithm which represents an open issue in Long Term Evolution (LTE) standard. This paper makes an attempt to study and compare the performance of PF, MLWDF and EXP/PF scheduling algorithms. The evaluation is considered for a single cell with interference scenario for different flows such as Best effort, Video and VoIP in a pedestrian and vehicular environment using the LTE-Sim network simulator. The comparative study is conducted in terms of system throughput, fairness index, delay, packet loss ratio (PLR) and total cell spectral efficiency.

Keywords: LTE, multimedia flows, scheduling algorithms, mobile computing

Procedia PDF Downloads 378

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 137

Authors: Radouane Elbahjaoui, Hamid El Qarnia

Abstract:

The present work aims to investigate numerically the thermal and flow characteristics of a rectangular latent heat storage unit (LHSU) during the melting process of a phase change material (PCM). The LHSU consists of a number of vertical and identical plates of PCM separated by rectangular channels. The melting process is initiated when the LHSU is heated by a heat transfer fluid (HTF: water) flowing in channels in a downward or upward direction. The proposed study is motivated by the need to optimize the thermal performance of the LHSU by accelerating the charging process. A mathematical model is developed and a fixed-grid enthalpy formulation is adopted for modeling the melting process coupling with convection-conduction heat transfer. The finite volume method was used for discretization. The obtained numerical results are compared with experimental, analytical and numerical ones found in the literature and reasonable agreement is obtained. Thereafter, the numerical investigations were carried out to highlight the effects of the HTF flow direction and the aspect ratio of the PCM slabs on the heat transfer characteristics and thermal performance enhancement of the LHSU.

Keywords: PCM, TES, LHSU, melting

Procedia PDF Downloads 254

Authors: Gülay Dalgıç, Gildis Tachir

Abstract:

Architectural design studios are ambiencein where architecture design is realized as a palpable product in architectural education. In the design studios that the architect candidate will use in the design processthe information, the methods of approaching the design problem, the solution proposals, etc., are set uptogetherwith the studio coordinators. The architectural design process, on the other hand, is complex and uncertain.Candidate architects work in a process that starts with abstre and ill-defined problems. This process starts with the generation of alternative solutions with the help of representation tools, continues with the selection of the appropriate/satisfactory solution from these alternatives, and then ends with the creation of an acceptable design/result product. In the studio ambience, many designs and thought relationships are evaluated, the most important step is the early design phase. In the early design phase, the first steps of converting the information are taken, and converted information is used in the constitution of the first design decisions. This phase, which positively affects the progress of the design process and constitution of the final product, is complex and fuzzy than the other phases of the design process. In this context, the aim of the study is to investigate the effects of face-to-face learning model and e-learning model on the early design phase. In the study, the early design phase was defined by literature research. The data of the defined early design phase criteria were obtained with the feedback graphics created for the architect candidates who performed e-learning in the first year of architectural education and continued their education with the face-to-face learning model. The findings of the data were analyzed with the common graphics program. It is thought that this research will contribute to the establishment of a contemporary architectural design education model by reflecting the evaluation of the data and results on architectural education.

Keywords: education modeling, architecture education, design education, design process

Procedia PDF Downloads 131

Authors: Murat Oral, Seda Bostancı, Sadık Ata, Kevser Dincer

Abstract:

When evaluating the aesthetics of cities, an analysis of the urban form development depending on design properties with a variety of factors is performed together with a study of the effects of this appearance on human beings. Different methods are used while making an aesthetical evaluation related to a city. Entropy, in its preliminary meaning, is the mathematical representation of thermodynamic results. Measuring the entropy is related to the distribution of positional figures of a message or information from the probabilities standpoint. In this study, analysis of evaluation the urban skylines by the entropy approach was modelled with Rule-Based Mamdani-Type Fuzzy (RBMTF) modelling technique. Input-output parameters were described by RBMTF if-then rules. Numerical parameters of input and output variables were fuzzificated as linguistic variables: Very Very Low (L1), Very Low (L2), Low (L3), Negative Medium (L4), Medium (L5), Positive Medium (L6), High (L7), Very High (L8) and Very Very High (L9) linguistic classes. The comparison between application data and RBMTF is done by using absolute fraction of variance (R2). The actual values and RBMTF results indicated that RBMTF can be successfully used for the analysis of evaluation the urban skylines by the entropy approach. As a result, RBMTF model has shown satisfying relation with experimental results, which suggests an alternative method to evaluation of the urban skylines by the entropy approach.

Keywords: urban skylines, entropy, rule-based Mamdani type, fuzzy logic

Procedia PDF Downloads 277

Authors: Mayada Mazher, Ahmed Moustafa, Ahmed Abdellatif

Abstract:

Background: Autophagy is a eukaryotic, highly conserved catabolic process implicated in many pathophysiologies such as wound healing. Autophagy-associated genes serve as a scaffolding platform for signal transduction of macrophage polarization during the inflammatory phase of wound healing and tissue repair process. In the current study, we report a model for the interplay between autophagy-associated genes and macrophages polarization associated genes. Methods: In silico analysis was performed on 249 autophagy-related genes retrieved from the public autophagy database and gene expression data retrieved from Gene Expression Omnibus (GEO); GSE81922 and GSE69607 microarray data macrophages polarization 199 DEGS. An integrated protein-protein interaction network was constructed for autophagy and macrophage gene sets. The gene sets were then used for GO terms pathway enrichment analysis. Common transcription factors for autophagy and macrophages' polarization were identified. Finally, microRNAs enriched in both autophagy and macrophages were predicated. Results: In silico prediction of common transcription factors in DEGs macrophages and autophagy gene sets revealed a new role for the transcription factors, HOMEZ, GABPA, ELK1 and REL, that commonly regulate macrophages associated genes: IL6,IL1M, IL1B, NOS1, SOC3 and autophagy-related genes: Atg12, Rictor, Rb1cc1, Gaparab1, Atg16l1. Conclusions: Autophagy and macrophages' polarization are interdependent cellular processes, and both autophagy-related proteins and macrophages' polarization related proteins coordinate in tissue remodelling via transcription factors and microRNAs regulatory network. The current work highlights a potential new role for transcription factors HOMEZ, GABPA, ELK1 and REL in wound healing.

Keywords: autophagy related proteins, integrated network analysis, macrophages polarization M1 and M2, tissue remodelling

Procedia PDF Downloads 143

Authors: Hamid Reza Behnood, Esmaeel Ayati, Tom Brijs, Mohammadali Pirayesh Neghab

Abstract:

Investment projects in road safety planning can benefit from an effectiveness evaluation regarding their expected safety outcomes. The objective of this study is to develop a decision support system (DSS) to support policymakers in taking the right choice in road safety planning based on the efficiency of previously implemented safety measures in a set of regions in Iran. The measures considered for each region in the study include performance indicators about (1) police operations, (2) treated black spots, (3) freeway and highway facility supplies, (4) speed control cameras, (5) emergency medical services, and (6) road lighting projects. To this end, inefficiency measure is calculated, defined by the proportion of fatality rates in relation to the combined measure of road safety performance indicators (i.e., road safety measures) which should be minimized. The relative inefficiency for each region is modeled by the Data Envelopment Analysis (DEA) technique. In a next step, a fuzzy decision-making system is constructed to convert the information obtained from the DEA analysis into a rule-based system that can be used by policy makers to evaluate the expected outcomes of certain alternative investment strategies in road safety.

Keywords: performance indicators, road safety, decision support system, data envelopment analysis, fuzzy reasoning

Procedia PDF Downloads 344

Authors: Ashish Payal, C. S. Rai, B. V. R. Reddy

Abstract:

With the increasing use and application of Wireless Sensor Networks (WSN), need has arisen to explore them in more effective and efficient manner. An important area which can bring efficiency to WSNs is the localization process, which refers to the estimation of the position of wireless sensor nodes in an ad hoc network setting, in reference to a coordinate system that may be internal or external to the network. In this paper, we have done comparison and analysed Sigmoidal Feedforward Artificial Neural Networks (SFFANNs) and Radial Basis Function (RBF) networks for developing localization framework in WSNs. The presented work utilizes the Received Signal Strength Indicator (RSSI), measured by static node on 100 x 100 m² grid from three anchor nodes. The comprehensive evaluation of these approaches is done using MATLAB software. The simulation results effectively demonstrate that FFANNs based sensor motes will show better localization accuracy as compared to RBF.

Keywords: localization, wireless sensor networks, artificial neural network, radial basis function, multi-layer perceptron, backpropagation, RSSI, GPS

Procedia PDF Downloads 328

Authors: Priyesh Kumar Pandey, Zakir Husain, R. K. Jarial

Abstract:

Condition monitoring and diagnostic is important for testing of power transformer in order to estimate the remnant life. Concentration of furan content in transformer oil can be a promising indirect measurement of the aging of transformer insulation. The oil gets contaminated mainly due to ageing. The present paper introduces adaptive neuro fuzzy technique to correlate furanic compounds obtained by high performance liquid chromatography (HPLC) test and remnant life of the power transformer. The results are obtained by conducting HPLC test at TIFAC-CORE lab, NIT Hamirpur on thirteen power transformer oil samples taken from Himachal State Electricity Board, India.

Keywords: adaptive neuro fuzzy technique, furan compounds, remnant life, transformer oil

Procedia PDF Downloads 456

Authors: Mehdi Ameur, Ahmed Essadki, Tamou Nasser

Abstract:

The purpose of this paper is the evaluation of photovoltaic system with MPPT techniques. This system is developed by combining the models of established solar module and DC-DC converter with the algorithms of perturbing and observing (P&O), incremental conductance (INC) and fuzzy logic controller (FLC). The system is simulated under different climate conditions and MPPT algorithms to determine the influence of these conditions on characteristic power-voltage of PV system. According to the comparisons of the simulation results, the photovoltaic system can extract the maximum power with precision and rapidity using the MPPT algorithms discussed in this paper.

Keywords: fuzzy logic controller, FLC, hill climbing, HC, incremental conductance (INC), perturb and observe (P&O), maximum power point, MPP, maximum power point tracking, MPPT

Procedia PDF Downloads 505

Authors: Rodrigo S. Moreira, Nelson F. F. Ebecken

Abstract:

This paper proposes a maritime vessel tracker composed of an ensemble of WiSARD weightless neural network classifiers. A failure detector analyzes vessel movement with a Kalman filter and corrects the tracking, if necessary, using FFT matching. The use of the WiSARD neural network to track objects is uncommon. The additional contributions of the present study include a performance comparison with four state-of-art trackers, an experimental study of the features that improve maritime vessel tracking, the first use of an ensemble of classifiers to track maritime vessels and a new quantization algorithm that compares the values of pixel pairs.

Keywords: ram memory, WiSARD weightless neural network, object tracking, quantization

Procedia PDF Downloads 304

Authors: Rosdyana Mangir Irawan Kusuma, Wei-Chun Kao, Ho-Thi Trang, Yu-Yen Ou, Kai-Lung Hua

Abstract:

Stock market prediction is still a challenging problem because there are many factors that affect the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment, and economic factors. This work explores the predictability in the stock market using deep convolutional network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. Finally, these candlestick charts will be feed as input for training a convolutional neural network model. This convolutional neural network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of the stock market. The effectiveness of our method is evaluated in stock market prediction with promising results; 92.2% and 92.1 % accuracy for Taiwan and Indonesian stock market dataset respectively.

Keywords: candlestick chart, deep learning, neural network, stock market prediction

Procedia PDF Downloads 435

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 144

Authors: Chih-Chieh Yang, Chung-Neng Huang

Abstract:

In power system, how to improve the fault diagnosis technology of transmission line has always been the primary goal of power grid operators. In recent years, due to the rise of green energy, the addition of all kinds of distributed power also has an impact on the stability of the power system. Because the smart meters are with the function of data recording and bidirectional transmission, the adaptive Fuzzy Neural inference system, ANFIS, as well as the artificial intelligence that has the characteristics of learning and estimation in artificial intelligence. For transmission network, in order to avoid misjudgment of the fault type and location due to the input of these unstable power sources, combined with the above advantages of smart meter and ANFIS, a method for identifying fault types and location of faults is proposed in this study. In ANFIS training, the bus voltage and current information collected by smart meters can be trained through the ANFIS tool in MATLAB to generate fault codes to identify different types of faults and the location of faults. In addition, due to the uncertainty of distributed generation, a wind power system is added to the transmission network to verify the diagnosis correctness of the study. Simulation results show that the method proposed in this study can correctly identify the fault type and location of fault with more efficiency, and can deal with the interference caused by the addition of unstable power sources.

Keywords: ANFIS, fault diagnosis, power system, smart meter

Procedia PDF Downloads 130

Authors: Ga Ye Kim, Hee Sun Kim, Yeong Soo Shin

Abstract:

Many studies have been done on the repair and strengthening method of concrete structure, so far. The traditional retrofit method was to attach fiber sheet such as CFRP (Carbon Fiber Reinforced Polymer), GFRP (Glass Fiber Reinforced Polymer) and AFRP (Aramid Fiber Reinforced Polymer) on the concrete structure. However, this method had many downsides in that there are a risk of debonding and an increase in displacement by a shortage of structure section. Therefore, it is effective way to enlarge the structural member with polymer mortar or Ultra-High Performance Fiber Reinforced Concrete (UHPFRC) as a means of strengthening concrete structure. This paper intends to investigate structural performance of reinforced concrete (RC) beams enlarged with polymer mortar and compare the experimental results with analytical results. Nonlinear finite element analyses were conducted to compare the experimental results and predict structural behavior of retrofitted RC beams accurately without cost consuming experimental process. In addition, this study aims at comparing differences of retrofit material between commonly used material (polymer mortar) and recently used material (UHPFRC) by conducting nonlinear finite element analyses. In the first part of this paper, the RC beams having different cover type were fabricated for the experiment and the size of RC beams was 250 millimeters in depth, 150 millimeters in width and 2800 millimeters in length. To verify the experiment, nonlinear finite element models were generated using commercial software ABAQUS 6.10-3. From this study, both experimental and analytical results demonstrated good strengthening effect on RC beam and showed similar tendency. For the future, the proposed analytical method can be used to predict the effect of strengthened RC beam. In the second part of the study, the main parameters were type of retrofit materials. The same nonlinear finite element models were generated to compare the polymer mortar with UHPFRCC. Two types of retrofit material were evaluated and retrofit effect was verified by analytical results.

Keywords: retrofit material, polymer mortar, UHPFRC, nonlinear finite element analysis

Procedia PDF Downloads 411

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 133