Computer Sciences Commons^™

Abusive Text Detection Using Neural Networks, Hao Chen, Susan Mckeever, Sarah Jane Delany

Articles

Neurall network models have become increasingly popular for text classification in recent years. In particular, the emergence of word embeddings within deep learning architecture has recently attracted a high level of attention amongst researchers.

A Neural Network Approach To Visibility Range Estimation Under Foggy Weather Conditions, Hazar Chaabani, Faouzi Kamoun, Hichem Bargaoui, Fatma Outay, Ansar Ul Haque Yasar

All Works

© 2017 The Authors. Published by Elsevier B.V. The degradation of visibility due to foggy weather conditions is a common trigger for road accidents and, as a result, there has been a growing interest to develop intelligent fog detection and visibility range estimation systems. In this contribution, we provide a brief overview of the state-of-the-art contributions in relation to estimating visibility distance under foggy weather conditions. We then present a neural network approach for estimating visibility distances using a camera that can be fixed to a roadside unit (RSU) or mounted onboard a moving vehicle. We evaluate the proposed solution …

A Cooperative Neural Network Approach For Enhancing Data Traffic Prediction, Salihu Aish Abdulkarim, Isa Abdullahi Lawal

Turkish Journal of Electrical Engineering and Computer Sciences

This paper addresses the problem of learning a regression model for the prediction of data traffic in a cellular network. We proposed a cooperative learning strategy that involves two Jordan recurrent neural networks (JNNs) trained using the firefly algorithm (FFA) and resilient backpropagation algorithm (Rprop), respectively. While the cooperative capability of the learning process ensures the effectiveness of the regression model, the recurrent nature of the neural networks allows the model to handle temporally evolving data. Experiments were carried out to evaluate the proposed approach using high-speed downlink packet access data demand and throughput measurements collected from different cell sites …

Pairwise Relation Classification With Mirror Instances And A Combined Convolutional Neural Network, Jianfei Yu, Jing Jiang

Research Collection School Of Computing and Information Systems

Relation classification is the task of classifying the semantic relations between entity pairs in text. Observing that existing work has not fully explored using different representations for relation instances, especially in order to better handle the asymmetry of relation types, in this paper, we propose a neural network based method for relation classification that combines the raw sequence and the shortest dependency path representations of relation instances and uses mirror instances to perform pairwise relation classification. We evaluate our proposed models on two widely used datasets: SemEval-2010 Task 8 and ACE-2005. The empirical results show that our combined model together …

Building 3d Shape Primitive Based Object Models From Range Images, Vamsikrishna Gopikrishna

Computer Science and Engineering Dissertations - Archive

Most pattern recognition approaches to object identification work in the image domain. However this is ignoring potential information that can be provided by depth information. Using range images, we can build a set of geometric depth features. These depth features can be used to identify basic three-dimensional shape primitives. There have been many studies regarding object identification in humans that postulate that at least at a primary level object recognition works by breaking down objects into its component parts. To build a similar Recognition-by-component (RBC) system we need a system to identify these shape primitives. We build a depth feature …

Synaptic Annealing: Anisotropic Simulated Annealing And Its Application To Neural Network Synaptic Weight Selection, Justin R. Fletcher

Theses and Dissertations

Machine learning algorithms have become a ubiquitous, indispensable part of modern life. Neural networks are one of the most successful classes of machine learning algorithms, and have been applied to solve problems previously considered to be the exclusive domain of human intellect. Several methods for selecting neural network configurations exist. The most common such method is error back-propagation. Backpropagation often produces neural networks that perform well, but do not achieve an optimal solution. This research explores the effectiveness of an alternative feed-forward neural network weight selection procedure called synaptic annealing. Synaptic annealing is the application of the simulated annealing algorithm …

Self-Organizing Neural Network For Adaptive Operator Selection In Evolutionary Search, Teck Hou Teng, Stephanus Daniel Handoko, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Evolutionary Algorithm is a well-known meta-heuristics paradigm capable of providing high-quality solutions to computationally hard problems. As with the other meta-heuristics, its performance is often attributed to appropriate design choices such as the choice of crossover operators and some other parameters. In this chapter, we propose a continuous state Markov Decision Process model to select crossover operators based on the states during evolutionary search. We propose to find the operator selection policy efficiently using a self-organizing neural network, which is trained offline using randomly selected training samples. The trained neural network is then verified on test instances not used for …

Learning From Minimally Labeled Data With Accelerated Convolutional Neural Networks, Aysegul Dundar

Open Access Dissertations

The main objective of an Artificial Vision Algorithm is to design a mapping function that takes an image as an input and correctly classifies it into one of the user-determined categories. There are several important properties to be satisfied by the mapping function for visual understanding. First, the function should produce good representations of the visual world, which will be able to recognize images independently of pose, scale and illumination. Furthermore, the designed artificial vision system has to learn these representations by itself. Recent studies on Convolutional Neural Networks (ConvNets) produced promising advancements in visual understanding. These networks attain significant …

On The 3d Point Cloud For Human-Pose Estimation, Kai-Chi Chan

Open Access Dissertations

This thesis aims at investigating methodologies for estimating a human pose from a 3D point cloud that is captured by a static depth sensor. Human-pose estimation (HPE) is important for a range of applications, such as human-robot interaction, healthcare, surveillance, and so forth. Yet, HPE is challenging because of the uncertainty in sensor measurements and the complexity of human poses. In this research, we focus on addressing challenges related to two crucial components in the estimation process, namely, human-pose feature extraction and human-pose modeling.

In feature extraction, the main challenge involves reducing feature ambiguity. We propose a 3D-point-cloud feature called …

Application Of A Time Delay Neural Network For Predicting Positive And Negative Links In Social Networks, Saghar Babakhanbak, Kaveh Kavousi, Fardad Farokhi

Turkish Journal of Electrical Engineering and Computer Sciences

No abstract provided.

Reduction Of Torque Ripple In Induction Motor By Artificial Neural Multinetworks, Fati̇h Korkmaz, İsmai̇l Topaloğlu, Hayati̇ Mamur, Murat Ari, İlhan Tarimer

Turkish Journal of Electrical Engineering and Computer Sciences

Direct torque control is used in the high performance control of induction motors. The most frequently faced problem of it is high torque ripples. In this study, a new approach based on artificial neural multinetworks is presented to overcome the problem. Two different artificial neural networks were suggested instead of vector selection and sector determination processes in the conventional direct torque control method. The conventional and the proposed control methods were evaluated on an induction motor through an experimental set. It was observed that the speed and torque responses of the proposed method were better than those of the conventional …

Fpga Implementations Of Scale-Invariant Models Of Neural Networks, Zeinulla Zhanabaev, Yeldos Kozhagulov, Dauren Zhexebay

Turkish Journal of Electrical Engineering and Computer Sciences

Integrated circuit implementations of new models of neural networks with scale-invariant properties are presented. The specifics of such models are necessary in analysis of discrete mappings containing fractional power. We suggest an algorithm for increasing the power of a physical value by using a field-programmable gate array (FPGA). Comparisons between FPGA implementations and numerical results are demonstrated.

Flexc: Protein Flexibility Prediction Using Context-Based Statistics, Predicted Structural Features, And Sequence Information, Ashraf Yaseen, Mais Nijim, Brandon Williams, Lei Qian, Min Li, Jianxin Wang, Yaohang Li

Computer Science Faculty Publications

The fluctuation of atoms around their average positions in protein structures provides important information regarding protein dynamics. This flexibility of protein structures is associated with various biological processes. Predicting flexibility of residues from protein sequences is significant for analyzing the dynamic properties of proteins which will be helpful in predicting their functions.

Deep Models For Brain Em Image Segmentation: Novel Insights And Improved Performance, Ahmed Fakhry, Hanchuan Peng, Shuiwang Ji

Computer Science Faculty Publications

Motivation: Accurate segmentation of brain electron microscopy (EM) images is a critical step in dense circuit reconstruction. Although deep neural networks (DNNs) have been widely used in a number of applications in computer vision, most of these models that proved to be effective on image classification tasks cannot be applied directly to EM image segmentation, due to the different objectives of these tasks. As a result, it is desirable to develop an optimized architecture that uses the full power of DNNs and tailored specifically for EM image segmentation.

Results: In this work, we proposed a novel design of DNNs for …

Why Fuzzy Cognitive Maps Are Efficient, Vladik Kreinovich, Chrysostomos Stylios

Departmental Technical Reports (CS)

In many practical situations, the relation between the experts' degrees of confidence in different related statements is well described by Fuzzy Cognitive Maps (FCM). This empirical success is somewhat puzzling, since from the mathematical viewpoint, each FCM relation corresponds to a simplified one-neuron neural network, and it is well known that to adequately describe relations, we need multiple neurons. In this paper, we show that the empirical success of FCM can be explained if we take into account that human's subjective opinions follow Miller's seven plus minus two law.

Computational Intelligence Based Complex Adaptive System-Of-Systems Architecture Evolution Strategy, Siddharth Agarwal

Doctoral Dissertations

The dynamic planning for a system-of-systems (SoS) is a challenging endeavor. Large scale organizations and operations constantly face challenges to incorporate new systems and upgrade existing systems over a period of time under threats, constrained budget and uncertainty. It is therefore necessary for the program managers to be able to look at the future scenarios and critically assess the impact of technology and stakeholder changes. Managers and engineers are always looking for options that signify affordable acquisition selections and lessen the cycle time for early acquisition and new technology addition. This research helps in analyzing sequential decisions in an evolving …

Short-Term Load Forecasting Using Mixed Lazy Learning Method, Seyed-Masoud Barakati, Ali Akbar Gharaveisi, Seyed-Mohammad Reza Rafiei

Turkish Journal of Electrical Engineering and Computer Sciences

A novel short-term load forecasting method based on the lazy learning (LL) algorithm is proposed. The LL algorithm's input data are electrical load information, daily electricity consumption patterns, and temperatures in a specified region. In order to verify the ability of the proposed method, a load forecasting problem, using the Pennsylvania-New Jersey-Maryland Interconnection electrical load data, is carried out. Three LL models are proposed: constant, linear, and mixed models. First, the performances of the 3 developed models are compared using the root mean square error technique. The best technique is then selected to compete with the state-of-the-art neural network (NN) …

Model-Based Test Case Prioritization Using Cluster Analysis: A Soft-Computing Approach, Ni̇da Gökçe, Fevzi̇ Belli̇, Mübari̇z Emi̇nli̇, Beki̇r Taner Di̇nçer

Turkish Journal of Electrical Engineering and Computer Sciences

Model-based testing is related to the particular relevant features of the software under test (SUT) and its environment. Real-life systems often require a large number of tests, which cannot exhaustively be run due to time and cost constraints. Thus, it is necessary to prioritize the test cases in accordance with their importance as the tester perceives it, usually given by several attributes of relevant events entailed. Based on event-oriented graph models, this paper proposes an approach to ranking test cases in accordance with their preference degrees. For forming preference groups, events are clustered using an unsupervised neural network and fuzzy …

Near Optimal Event-Based Control Of Nonlinear Discrete Time Systems In Affine Form With Measured Input And Output Data, Avimanyu Sahoo, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, an event-based near optimal control of uncertain nonlinear discrete time systems is presented by using input-output data and approximate dynamic programming (ADP). The nonlinear system dynamics in affine form are transformed into an input-output form. Then, three neural networks (NN) with event sampled input-output vector are used, namely, the identifier NN to relax the knowledge of the system dynamics, a critic NN to approximate the value function which is the solution to the Hamilton-Jacobi Bellman (HJB) equation, and an actor NN to approximate the optimal control policy, in an online manner without utilizing value or policy iterations. …

Integrating Self-Organizing Neural Network And Motivated Learning For Coordinated Multi-Agent Reinforcement Learning In Multi-Stage Stochastic Game, Teck-Hou Teng, Ah-Hwee Tan, Janusz A. Starzyk, Yuan-Sin Tan, Loo-Nin Teow

Research Collection School Of Computing and Information Systems

Most non-trivial problems require the coordinated performance of multiple goal-oriented and time-critical tasks. Coordinating the performance of the tasks is required due to the dependencies among the tasks and the sharing of resources. In this work, an agent learns to perform a task using reinforcement learning with a self-organizing neural network as the function approximator. We propose a novel coordination strategy integrating Motivated Learning (ML) and a self-organizing neural network for multi-agent reinforcement learning (MARL). Specifically, we adapt the ML idea of using pain signal to overcome the resource competition issue. Dependency among the agents is resolved using domain knowledge …

Event-Based Optimal Regulator Design For Nonlinear Networked Control Systems, Avimanyu Sahoo, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a novel stochastic event-based near optimal control strategy to regulate a networked control system (NCS) represented as an uncertain nonlinear continuous time system. An online stochastic actor-critic neural network (NN) based approach is utilized to achieve the near optimal regulation in the presence of network constraints, such as, network induced time-varying delays and random packet losses under event-based transmission of the feedback signals. The transformed nonlinear NCS in discrete-time after the incorporation the delays and packet losses are utilized for the actor-critic NN based controller design. To relax the knowledge of the control coefficient matrix, a NN …

Neural Network-Based Adaptive Optimal Consensus Control Of Leaderless Networked Mobile Robots, Haci Mehmet Guzey, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

A novel neural network (NN)-based optimal adaptive consensus control scheme is introduced in this paper for networked mobile robots in the presence of unknown robot dynamics. Throughout the paper, two NNs are used. The unknown formation dynamics of each robot is identified by using the first NN. The second NN is utilized to approximate a novel value function derived in this paper as a function of augmented error vector, which is comprised of the regulation and consensus-based formation errors of each robot. A novel near optimal controller is developed by using approximated value function and identified formation dynamics. The Lyapunov …

Evolutionary Algorithm Based Approach For Modeling Autonomously Trading Agents, Anil Yaman, Stephen Lucci, Izidor Gertner

Publications and Research

The autonomously trading agents described in this paper produce a decision to act such as: buy, sell or hold, based on the input data. In this work, we have simulated autonomously trading agents using the Echo State Network (ESNs) model. We generate a collection of trading agents that use different trading strategies using Evolutionary Programming (EP). The agents are tested on EUR/ USD real market data. The main goal of this study is to test the overall performance of this collection of agents when they are active simultaneously. Simulation results show that using different agents concurrently outperform a single agent …

An Online Outlier Identification And Removal Scheme For Improving Fault Detection Performance, Hasan Ferdowsi, Sarangapani Jagannathan, Maciej Jan Zawodniok

Electrical and Computer Engineering Faculty Research & Creative Works

Measured data or states for a nonlinear dynamic system is usually contaminated by outliers. Identifying and removing outliers will make the data (or system states) more trustworthy and reliable since outliers in the measured data (or states) can cause missed or false alarms during fault diagnosis. In addition, faults can make the system states nonstationary needing a novel analytical model-based fault detection (FD) framework. In this paper, an online outlier identification and removal (OIR) scheme is proposed for a nonlinear dynamic system. Since the dynamics of the system can experience unknown changes due to faults, traditional observer-based techniques cannot be …

Removing Random-Valued Impulse Noise In Images Using A Neural Network Detector, İlke Türkmen

Turkish Journal of Electrical Engineering and Computer Sciences

This paper proposes a new method using an artificial neural network to remove random-valued impulse noise (RVIN) in images. The inputs of the neural model used to detect the RVIN are formed using basic and related gradient values. The detection of the noisy pixels is realized in 3 phases using the proposed neural detector. In order to obtain a more robust detector, 2 different networks, which are trained with an artificial training image corrupted with high and low clutter densities, are used. The extensive simulation results show that the proposed method is significantly better than the compared filters in terms …

Template-Based C8-Scorpion: A Protein 8 State Secondary Structure Prediction Method Using Structural Information And Context-Based Features, Ashraf Yaseen, Yaohang Li

Computer Science Faculty Publications

Background: Secondary structures prediction of proteins is important to many protein structure modeling applications. Correct prediction of secondary structures can significantly reduce the degrees of freedom in protein tertiary structure modeling and therefore reduces the difficulty of obtaining high resolution 3D models.

Methods: In this work, we investigate a template-based approach to enhance 8-state secondary structure prediction accuracy. We construct structural templates from known protein structures with certain sequence similarity. The structural templates are then incorporated as features with sequence and evolutionary information to train two-stage neural networks. In case of structural templates absence, heuristic structural information is incorporated instead. …

Neural Network Topologies, Michael Rimer, Dr. Tony Martinez

Journal of Undergraduate Research

Neural networks are a statistics-based learning paradigm in which specific acquired data samples are studied to form general rules on how to correctly handle new, unseen data. They have been used to make informed decisions in complex systems, such as predicting stock market trends, controlling robots in unpredictable environments, and performing voice or face recognition.

Using Symmetries (Beyond Geometric Symmetries) In Chemical Computations: Computing Parameters Of Multiple Binding Sites, Andres Ortiz, Vladik Kreinovich

Departmental Technical Reports (CS)

We show how group-theoretic ideas can be naturally used to generate efficient algorithms for scientific computations. The general group-theoretic approach is illustrated on the example of determining, from the experimental data, the dissociation constants related to multiple binding sites. We also explain how the general group-theoretic approach is related to the standard (backpropagation) neural networks; this relation justifies the potential universal applicability of the group-theoretic approach.

Role Of Energy Management In Hybrid Renewable Energy Systems: Case Study-Based Analysis Considering Varying Seasonal Conditions, Recep Yumurtaci

Turkish Journal of Electrical Engineering and Computer Sciences

The recent popularity of alternative energy technologies is mainly promoted by the increasing awareness of environmental concerns as well as the economic impacts of the depleting fossil fuel reserves. Among several alternative technologies, wind- and solar-based energy have been given specific importance with government-based support for providing a cost-effective structure to realize better penetration of such environmentally friendly sources in the energy market. Even these sources are advantageous over the conventional means of energy production from many aspects, a main drawback being the total dependence on the meteorological conditions (wind speed, solar radiation, temperature, etc.) of the wind and solar …

Knowledge Extraction From Survey Data Using Neural Networks, Khan Imran, Arun Kulkarni

Computer Science Faculty Publications and Presentations

Surveys are an important tool for researchers. It is increasingly important to develop powerful means for analyzing such data and to extract knowledge that could help in decision-making. Survey attributes are typically discrete data measured on a Likert scale. The process of classification becomes complex if the number of survey attributes is large. Another major issue in Likert-Scale data is the uniqueness of tuples. A large number of unique tuples may result in a large number of patterns. The main focus of this paper is to propose an efficient knowledge extraction method that can extract knowledge in terms of rules. …