Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- China Simulation Federation (3880)
- TÜBİTAK (3106)
- Wright State University (1776)
- Washington University in St. Louis (698)
- Singapore Management University (449)
-
- Embry-Riddle Aeronautical University (440)
- Old Dominion University (402)
- University of Nebraska - Lincoln (256)
- Chulalongkorn University (234)
- University of Dayton (164)
- Air Force Institute of Technology (130)
- Portland State University (122)
- Universitas Negeri Malang (104)
- Chapman University (97)
- University of Nevada, Las Vegas (90)
- University of Arkansas, Fayetteville (86)
- Purdue University (84)
- University of South Florida (74)
- University of New Haven (71)
- University for Business and Technology in Kosovo (70)
- Technological University Dublin (68)
- California Polytechnic State University, San Luis Obispo (52)
- University of South Carolina (45)
- University of New Mexico (39)
- Edith Cowan University (35)
- New Jersey Institute of Technology (34)
- Journal of Soft Computing and Computer Applications (32)
- University of Malaya (32)
- University of Texas at El Paso (31)
- San Jose State University (30)
- Keyword
-
- Computer Science (312)
- Department of Computer Science and Engineering (284)
- Engineering (239)
- Machine learning (197)
- Deep learning (193)
-
- Simulation (182)
- College of Engineering and Computer Science (157)
- Newsletters (157)
- Science news (157)
- Technical writing (157)
- Classification (109)
- Genetic algorithm (107)
- Optimization (101)
- Computer Engineering (100)
- Machine Learning (90)
- Particle swarm optimization (85)
- Path planning (85)
- Security (76)
- Artificial intelligence (72)
- Computer Sciences (68)
- Physical Sciences and Mathematics (64)
- Cybersecurity (62)
- Robotics (61)
- Virtual reality (60)
- Reinforcement learning (59)
- Clustering (57)
- Deep Learning (57)
- Modeling (57)
- Digital forensics (56)
- Support vector machine (55)
- Publication Year
- Publication
-
- Journal of System Simulation (3880)
- Turkish Journal of Electrical Engineering and Computer Sciences (3106)
- Computer Science & Engineering Syllabi (1312)
- All Computer Science and Engineering Research (683)
- Research Collection School Of Computing and Information Systems (431)
-
- Browse all Theses and Dissertations (307)
- Journal of Digital Forensics, Security and Law (298)
- Chulalongkorn University Theses and Dissertations (Chula ETD) (234)
- Electrical and Computer Engineering Faculty Publications (164)
- Theses and Dissertations (160)
- BITs and PCs Newsletter (157)
- School of Computing: Dissertations, Theses, and Student Research (152)
- Electrical & Computer Engineering Theses & Dissertations (143)
- Annual ADFSL Conference on Digital Forensics, Security and Law (104)
- Knowledge Engineering and Data Science (104)
- Faculty Publications (87)
- Dissertations (85)
- Computer Science Faculty Publications and Presentations (81)
- Electrical & Computer Engineering and Computer Science Faculty Publications (70)
- Engineering Faculty Articles and Research (69)
- USF Tampa Graduate Theses and Dissertations (65)
- UNLV Theses, Dissertations, Professional Papers, and Capstones (57)
- Computer Science Faculty Publications (55)
- Electronic Theses and Dissertations (54)
- UBT International Conference (51)
- School of Computing: Conference and Workshop Papers (45)
- Computer Science Theses & Dissertations (42)
- Dissertations and Theses (35)
- Graduate Theses and Dissertations (34)
- Journal of Soft Computing and Computer Applications (32)
- Publication Type
- File Type
Articles 6661 - 6690 of 13574
Full-Text Articles in Computer Engineering
Virtual Reality And Analysis Framework For Studying Different Layout Designs, Madison Glines
Virtual Reality And Analysis Framework For Studying Different Layout Designs, Madison Glines
Browse all Theses and Dissertations
This thesis describes the tools for studying different design prototypes. The goal was to develop effective tools to study these designs using a data-driven approach. “Proof of concept” experiments were conducted, in which participants were allowed to interact with a virtual environment depicting different designs as data pertaining to their virtual location and orientation was recorded for later analysis. The designs included “flat” store racks, as opposed to racks with more varied shapes, as well as “curved” racks. Focus of the design studies was to assist in identifying optimal locations for different product types. The automated data collection mechanisms required …
Securing Modern Cyberspace Using A Multi-Faceted Approach, Yu Li
Securing Modern Cyberspace Using A Multi-Faceted Approach, Yu Li
Browse all Theses and Dissertations
Security has become one of the most significant concerns for our cyberspace. Securing the cyberspace, however, becomes increasingly challenging. This can be attributed to the rapidly growing diversities and complexity of the modern cyberspace. Specifically, it is not any more dominated by connected personal computers (PCs); instead, it is greatly characterized by cyber-physical systems (CPS), embedded systems, dynamic services, and human-computer interactions. Securing modern cyberspace therefore calls for a multi-faceted approach capable of systematically integrating these emerging characteristics. This dissertation presents our novel and significant solutions towards this direction. Specifically, we have devised automated, systematic security solutions to three critical …
Neutrosophic Set Is A Generalization Of Intuitionistic Fuzzy Set, Inconsistent Intuitionistic Fuzzy Set (Picture Fuzzy Set, Ternary Fuzzy Set), Pythagorean Fuzzy Set, Q-Rung Orthopair Fuzzy Set, Spherical Fuzzy Set, And N-Hyperspherical Fuzzy Set, While Neutrosophication Is A Generalization Of Regret Theory, Grey System Theory, And Three-Ways Decision (Revisited), Florentin Smarandache
Branch Mathematics and Statistics Faculty and Staff Publications
In this paper we prove that Neutrosophic Set (NS) is an extension of Intuitionistic Fuzzy Set (IFS) no matter if the sum of single-valued neutrosophic components is < 1, or > 1, or = 1. For the case when the sum of components is 1 (as in IFS), after applying the neutrosophic aggregation operators one gets a different result from that of applying the intuitionistic fuzzy operators, since the intuitionistic fuzzy operators ignore the indeterminacy, while the neutrosophic aggregation operators take into consideration the indeterminacy at the same level as truth-membership and falsehood-nonmembership are taken. NS is also more flexible and effective because it …
Improvement Of The Material’S Mechanical Characteristics Using Intelligent Real Time Control Interfaces In Hfc Hardening Process, Florentin Smarandache, Luige Vladareanu, Mihaiela Iliescu, Victor Vladareanu, Alexandru Gal, Octavian Melinte, Adrian Margean
Improvement Of The Material’S Mechanical Characteristics Using Intelligent Real Time Control Interfaces In Hfc Hardening Process, Florentin Smarandache, Luige Vladareanu, Mihaiela Iliescu, Victor Vladareanu, Alexandru Gal, Octavian Melinte, Adrian Margean
Branch Mathematics and Statistics Faculty and Staff Publications
The paper presents Intelligent Control (IC) Interfaces for real time control of mechatronic systems applied to Hardening Process Control (HPC) in order to improvement of the material’s mechanical characteristics. Implementation of IC laws in the intelligent real time control interfaces depends on the particular circumstances of the models characteristics used and the exact definition of optimization problem. The results led to the development of the IC interfaces in real time through Particle Swarm Optimization (PSO) and neural networks (NN) using off- line the regression methods.
Channel And Carrier Frequency Offset Estimation Based On Projection Onto Abidimensional Basis, Roberto Carrasco Alvarez, Ramon Parra Michel, Aldo Gustavo Orozco Lugo, Marco Antonio Gurrola Navarro
Channel And Carrier Frequency Offset Estimation Based On Projection Onto Abidimensional Basis, Roberto Carrasco Alvarez, Ramon Parra Michel, Aldo Gustavo Orozco Lugo, Marco Antonio Gurrola Navarro
Turkish Journal of Electrical Engineering and Computer Sciences
Two of the most counterproductive effects that must be dealt with in communication systems in realistic environments are carrier frequency offset (CFO) and time-varying channels. These problems are usually addressed by using independent approaches for each one. This paper introduces an algorithm that attacks both of these effects in a joint fashion. It is based on a rough compensation of CFO, and after considering that the remaining CFO uncertainty can be seen as part of the time-varying channel a channel estimation that includes that composite channel is performed. Particularly, the channel estimation based on projection onto a bidimensional basis is …
Robust Power System State Estimation By Appropriate Selection Of Tolerance Forthe Least Measurement Rejected Algorithm, Mohammad Shoaib Shahriar, Ibrahim Omar Habiballah
Robust Power System State Estimation By Appropriate Selection Of Tolerance Forthe Least Measurement Rejected Algorithm, Mohammad Shoaib Shahriar, Ibrahim Omar Habiballah
Turkish Journal of Electrical Engineering and Computer Sciences
Modern power systems are highly complicated and nonlinear in nature. Accurate estimation of the power system states (voltage-magnitude and phase-angle) is required for the secure operation of the power system. The presence of bad-data measurements in meters has made this estimation process challenging. An efficient estimator should detect and eliminate the effect of bad data during the estimation process. Least measurement rejected (LMR) is a robust estimator that has been found successful in dealing with various categories of bad data. The performance of LMR depends upon the proper selection of a tolerance for each measurement. This paper presents a novel …
A New Approach For Parameter Estimation Of The Single-Diode Model Forphotovoltaic Cells/Modules, Bi̇lge Kaan Atay, Ulaş Emi̇noğlu
A New Approach For Parameter Estimation Of The Single-Diode Model Forphotovoltaic Cells/Modules, Bi̇lge Kaan Atay, Ulaş Emi̇noğlu
Turkish Journal of Electrical Engineering and Computer Sciences
Solar energy has become a popular renewable energy source, leading to wide use of photovoltaic (PV) cells/modules in energy production. For this reason, realistic modeling of PVs and determining the equivalent circuit parameters is of great importance in terms of planning and operation. Hence, in this study, an analytical model for identifying the single-diode equivalent circuit parameters; series resistance (Rs ), shunt resistance (Rp ), diode ideality factor (a), diode reverse-saturation current (Io ), and photon current (Ipv ) for PV cells/modules is developed without neglecting any term. In order to test the accuracy of the model, a number of …
Effect Of Orientation Of Rf Sources Maintained Within The Enclosures On Electricalshielding Effectiveness Performance, İbrahi̇m Bahadir Başyi̇ği̇t, Abdullah Genç, Selçuk Helhel
Effect Of Orientation Of Rf Sources Maintained Within The Enclosures On Electricalshielding Effectiveness Performance, İbrahi̇m Bahadir Başyi̇ği̇t, Abdullah Genç, Selçuk Helhel
Turkish Journal of Electrical Engineering and Computer Sciences
The effect of single aperture metallic enclosures on electrical shielding effectiveness (ESE) has been investigated. Simulations and measurements have been obtained for comparison. The effects of orientation of transmitting antenna (source orientation) with respect to aperture length have been studied at 2.60?9 GHz as a novelty, and this gives details of IC RF source orientation in an enclosure. In the case of square apertures on an enclosure, a higher ESE value is obtained with respect to a rectangular aperture. As a case study, when the aperture width of the enclosure is decreased from 75 to 18.75 mm, the frequency bandwidth …
Adaptive Switching Gain Sliding Mode Control For Speed Regulation In Pmsms, Yanwei Huang, Yuqing Xie, Zheyi Liu
Adaptive Switching Gain Sliding Mode Control For Speed Regulation In Pmsms, Yanwei Huang, Yuqing Xie, Zheyi Liu
Turkish Journal of Electrical Engineering and Computer Sciences
To suppress uncertainties caused by parametric variations or disturbances, an adaptive switching gain (ASG) is proposed for integral sliding mode control (ISMC) to regulate speed in permanent magnet synchronous motors (PMSMs). According to system uncertainties, the ASG is designed to adjust the switching gain to suppress the chattering. The adaptive law is a positive value resulting in an increment of the switching gain when the tracking trajectory is outside the boundary layer. Conversely, it is negative with a decrement of the gain. Further, it improves a convergent rate by the function of the reciprocal of the tracking error when the …
Particle Swarm Optimization Approach To Optimal Design Of An Afpm Tractionmachine For Different Driving Conditions, Naghi Rostami
Particle Swarm Optimization Approach To Optimal Design Of An Afpm Tractionmachine For Different Driving Conditions, Naghi Rostami
Turkish Journal of Electrical Engineering and Computer Sciences
Axial flux permanent magnet (AFPM) machines can be employed as the traction motor of electric vehicles due to their high torque capability, high efficiency, modular and compact construction, and capability of integration with other mechanical components in integrated systems. Besides, the system efficiency can be further improved by optimal design of the selected electric machine. In this paper, an AFPM machine is optimized against two well-known driving cycles called the New European Drive Cycle (NEDC) and US06 and the influence of the driving cycle on the obtained machine parameters is evaluated. US06 is the more demanding driving cycle and thus …
Empirical Single Frequency Network Threshold For Dvb-T2 Based On Laboratory Experiments, Bundit Ruckveratham, Sathaporn Promwong
Empirical Single Frequency Network Threshold For Dvb-T2 Based On Laboratory Experiments, Bundit Ruckveratham, Sathaporn Promwong
Turkish Journal of Electrical Engineering and Computer Sciences
DVB-T2 broadcasting with a single frequency network (SFN) allows an efficient management of frequency utilization and extends the coverage area, which will enable more people to view a broadcast. The SFN mode also increases the concentration of the signal in overlap areas. However, some difference of overlap areas in actual use of SFN networks may have some degradation of the received signal due to the effect of the SFN. In this research, we analyze SFN broadcasting in SISO mode. This paper represents the effects of delays on the SFN signal over different delay times within the guard interval (GI) by …
A Robust Ensemble Feature Selector Based On Rank Aggregation For Developing New Vo\Textsubscript{2}Max Prediction Models Using Support Vector Machines, Fatih Abut, Mehmet Fati̇h Akay, James George
A Robust Ensemble Feature Selector Based On Rank Aggregation For Developing New Vo\Textsubscript{2}Max Prediction Models Using Support Vector Machines, Fatih Abut, Mehmet Fati̇h Akay, James George
Turkish Journal of Electrical Engineering and Computer Sciences
This paper proposes a new ensemble feature selector, called the majority voting feature selector (MVFS), for developing new maximal oxygen uptake (VO2max) prediction models using a support vector machine (SVM). The approach is based on rank aggregation, which meaningfully utilizes the correlation among the relevance ranks of predictor variables given by three state-of-the-art feature selectors: Relief-F, minimum redundancy maximum relevance (mRMR), and maximum likelihood feature selection (MLFS). By applying the SVM combined with MVFS on a self-created dataset containing maximal and submaximal exercise data from 185 college students, several new hybrid (VO2max) prediction models have been created. To compare the …
A Modified Gravitational Search Algorithm And Its Application In Lifetime Maximization Of Wireless Sensor Networks, Sepehr Ebrahimi Mood, Mohammad Masoud Javidi
A Modified Gravitational Search Algorithm And Its Application In Lifetime Maximization Of Wireless Sensor Networks, Sepehr Ebrahimi Mood, Mohammad Masoud Javidi
Turkish Journal of Electrical Engineering and Computer Sciences
Recently, academic communities and industrial sectors have been affected by significant advancements in wireless sensor networks (WSNs). Employing clustering methods is the dominant method to maximize the WSN's lifetime, which is considered to be a major issue. Metaheuristic algorithms have attracted wide attention in the research area of clustering. In this paper, first a novel nature-inspired optimization algorithm based on the gravitational search algorithm (GSA) is defined. To control the exploitation and exploration capabilities of this algorithm, along with calculating the masses value, the tournament selection method is employed. Tournament size, the parameter of this method, is computed automatically using …
Evaluating The Attributes Of Remote Sensing Image Pixels For Fast K-Means Clustering, Ali̇ Sağlam, Nurdan Baykan
Evaluating The Attributes Of Remote Sensing Image Pixels For Fast K-Means Clustering, Ali̇ Sağlam, Nurdan Baykan
Turkish Journal of Electrical Engineering and Computer Sciences
Clustering process is an important stage for many data mining applications. In this process, data elements are grouped according to their similarities. One of the most known clustering algorithms is the k-means algorithm. The algorithm initially requires the number of clusters as a parameter and runs iteratively. Many remote sensing image processing applications usually need the clustering stage like many image processing applications. Remote sensing images provide more information about the environments with the development of the multispectral sensor and laser technologies. In the dataset used in this paper, the infrared (IR) and the digital surface maps (DSM) are also …
Parallel Algorithms For Computing Sparse Matrix Permanents, Kamer Kaya
Parallel Algorithms For Computing Sparse Matrix Permanents, Kamer Kaya
Turkish Journal of Electrical Engineering and Computer Sciences
The permanent is an important characteristic of a matrix and it has been used in many applications. Unfortunately, it is a hard to compute and hard to approximate the immanant. For dense/full matrices, the fastest exact algorithm, Ryser, has O($2^{n-1}$n) complexity. In this work, a parallel algorithm, SkipPer, is proposed to exploit the sparsity within the input matrix as much as possible. SkipPer restructures the matrix to reduce the overall work, skips the unnecessary steps, and employs a coarse-grain, shared-memory parallelization with dynamic scheduling. The experiments show that SkipPer increases the performance of exact permanent computation up to 140 compared …
Possible Effects Of Dielectrophoretic Fields In The Brains Of Mri Operators And Ms Patients: A Radiologically Isolated Syndrome Evaluation, Cahi̇t Canbay
Turkish Journal of Electrical Engineering and Computer Sciences
Frequent use of magnetic resonance imaging (MRI) devices, which are major contributors in understanding health problems in the human body, is a subject that needs to be taken into consideration both for patients and for operators who are constantly in the vicinity of devices. In this context, electromagnetic impact assessment of an MRI device was performed at the point where the patient entered the device. Dielectrophoretic fields induced by radio frequency (RF) coils of an MRI scanner on male and female operator brain models were computed by using dispersive electrical medium parameters. The main cause of induced secondary dielectrophoretic fields …
Compact Metal-Plate Slotted Wlan-Wimax Antenna Design With Usb Wi-Fi Adapter Application, Cem Baytöre, Cem Göçen, Meri̇h Palandöken, Adnan Kaya, Emi̇ne Yeşi̇m Zoral
Compact Metal-Plate Slotted Wlan-Wimax Antenna Design With Usb Wi-Fi Adapter Application, Cem Baytöre, Cem Göçen, Meri̇h Palandöken, Adnan Kaya, Emi̇ne Yeşi̇m Zoral
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, a compact antenna design, which operates in the 2.4, 5.2, and 5.8 GHz (WLAN) and 3.5 and 5.5 GHz (WiMAX) frequency bands, has been implemented to be compatible with the 802.11.ac/n standards. The proposed metal antenna is made of a copper plate of thickness 0.5 mm with a compact overall physical size of 20 mm $\times$ 30 mm. Although it is low-profile, it can work with high efficiency because it has a cheap planar metal structure and it does not contain any expensive dielectric material. The antenna is investigated in terms of S parameters, input impedance, efficiency, …
Improving Word Embeddings Projection For Turkish Hypernym Extraction, Savaş Yildirim
Improving Word Embeddings Projection For Turkish Hypernym Extraction, Savaş Yildirim
Turkish Journal of Electrical Engineering and Computer Sciences
Corpus-driven approaches can automatically explore is-a relations between the word pairs from corpus. This problem is also called hypernym extraction. Formerly, lexico-syntactic patterns have been used to solve hypernym relations. The language-specific syntactic rules have been manually crafted to build the patterns. On the other hand, recent studies have applied distributional approaches to word semantics. They extracted the semantic relations relying on the idea that similar words share similar contexts. Former distributional approaches have applied one-hot bag-of-word (BOW) encoding. The dimensionality problem of BOW has been solved by various neural network approaches, which represent words in very short and dense …
Assessment Of Techno-Economic Benefits For Smart Charging Scheme Of Electric Vehicles In Residential Distribution System, Kumari Kasturi, Manas Ranjan Nayak
Assessment Of Techno-Economic Benefits For Smart Charging Scheme Of Electric Vehicles In Residential Distribution System, Kumari Kasturi, Manas Ranjan Nayak
Turkish Journal of Electrical Engineering and Computer Sciences
Connecting multiple electric vehicles (EVs) to a power system network for the purpose of charging has major setbacks like decrease in power quality, instability in voltage profile, and increase in power losses and thus electricity price. This paper focuses on devising an optimal charging scheme to reduce the negative impacts of EVs' presence in the distribution network by limiting the charging process to only off-peak demand periods when the electricity price is comparatively lower. The salp swarm algorithm, an efficient, fast, and reliable optimization technique, is used to obtain the optimal locations for the EVs and their charging schedule in …
Tapu: Test And Pick Up-Based $K$-Connectivity Restoration Algorithm For Wireless Sensor Networks, Vahi̇d Khali̇lpour Akram, Orhan Dağdevi̇ren
Tapu: Test And Pick Up-Based $K$-Connectivity Restoration Algorithm For Wireless Sensor Networks, Vahi̇d Khali̇lpour Akram, Orhan Dağdevi̇ren
Turkish Journal of Electrical Engineering and Computer Sciences
A $k$-connected wireless sensor network remains connected if any $k$-1 arbitrary nodes stop working. The aim of movement-assisted $k$-connectivity restoration is to preserve the $k$-connectivity of a network by moving the nodes to the necessary positions after possible failures in nodes. This paper proposes an algorithm named TAPU for $k$-connectivity restoration that guarantees the optimal movement cost. Our algorithm improves the time and space complexities of the previous approach (MCCR) in both best and worst cases. In the proposed algorithm, the nodes are classified into safe and unsafe groups. Failures of safe nodes do not change the $k$ value of …
The Biobjective Multiarmed Bandit: Learning Approximate Lexicographic Optimal Allocations, Cem Teki̇n
The Biobjective Multiarmed Bandit: Learning Approximate Lexicographic Optimal Allocations, Cem Teki̇n
Turkish Journal of Electrical Engineering and Computer Sciences
We consider a biobjective sequential decision-making problem where an allocation (arm) is called $\epsilon$ lexicographic optimal if its expected reward in the first objective is at most $\epsilon$ smaller than the highest expected reward, and its expected reward in the second objective is at least the expected reward of a lexicographic optimal arm. The goal of the learner is to select arms that are $\epsilon$ lexicographic optimal as much as possible without knowing the arm reward distributions beforehand. For this problem, we first show that the learner's goal is equivalent to minimizing the $\epsilon$ lexicographic regret, and then, propose a …
Power Quality Improvement Of Smart Microgrids Using Ems-Based Fuzzy Controlled Upqc, Ahmed A. Hossam-Eldin, Ahmed A. Mansour, Mohammed El-Gamal, Karim H. Youssef
Power Quality Improvement Of Smart Microgrids Using Ems-Based Fuzzy Controlled Upqc, Ahmed A. Hossam-Eldin, Ahmed A. Mansour, Mohammed El-Gamal, Karim H. Youssef
Turkish Journal of Electrical Engineering and Computer Sciences
The prevalent power quality problems in smart microgrids and power distribution systems are voltage sag, voltage swell, and harmonic distortion. The achievement of pure sinusoidal waveform with proper magnitude and phase is currently a great research and development concern. The aim of this paper is to evaluate and mitigate the smart microgrid harmonics, voltage sag, and voltage swell throughout a 24-h cycle, taking into consideration the variation in solar power generation due to changes in irradiation received by photovoltaic cells, the variation in wind power generation due to changes in wind speed, and the variation of linear and nonlinear load …
Optimized Bilevel Classifier For Brain Tumor Type And Grade Discrimination Using Evolutionary Fuzzy Computing, Kavitha Srinivasan, Mohanavalli Subramaniam, Bharathi Bhagavathsingh
Optimized Bilevel Classifier For Brain Tumor Type And Grade Discrimination Using Evolutionary Fuzzy Computing, Kavitha Srinivasan, Mohanavalli Subramaniam, Bharathi Bhagavathsingh
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, an optimized bilevel brain tumor diagnostic system for identifying the tumor type at the first level and grade of the identified tumor at the second level is proposed using genetic algorithm, decision tree, and fuzzy rule-based approach. The dataset is composed of axial MRI of brain tumor types and grades. From the images, various features such as first and second order statistical and textural features are extracted (26 features). In the first level, tumor type classification was done using decision tree constructed with all features. Further evolutionary computing using genetic algorithms (GA) was applied to select the …
Selective Word Encoding For Effective Text Representation, Savaş Özkan, Akin Özkan
Selective Word Encoding For Effective Text Representation, Savaş Özkan, Akin Özkan
Turkish Journal of Electrical Engineering and Computer Sciences
Determining the category of a text document from its semantic content is highly motivated in the literature and it has been extensively studied in various applications. Also, the compact representation of the text is a fundamental step in achieving precise results for the applications and the studies are generously concentrated to improve its performance. In particular, the studies which exploit the aggregation of word-level representations are the mainstream techniques used in the problem. In this paper, we tackle text representation to achieve high performance in different text classification tasks. Throughout the paper, three critical contributions are presented. First, to encode …
Word Sense Disambiguation Using Semantic Kernels With Class-Based Term Values, Ayşe Berna Altinel, Murat Can Gani̇z, Bi̇lge Şi̇pal, Eren Can Erkaya, Onur Can Yücedağ, Muhammed Ali̇ Doğan
Word Sense Disambiguation Using Semantic Kernels With Class-Based Term Values, Ayşe Berna Altinel, Murat Can Gani̇z, Bi̇lge Şi̇pal, Eren Can Erkaya, Onur Can Yücedağ, Muhammed Ali̇ Doğan
Turkish Journal of Electrical Engineering and Computer Sciences
In this study, we propose several semantic kernels for word sense disambiguation (WSD). Our approaches adapt the intuition that class-based term values help in resolving ambiguity of polysemous words in WSD. We evaluate our proposed approaches with experiments, utilizing various sizes of training sets of disambiguated corpora (SensEval). With these experiments we try to answer the following questions: 1.) Do our semantic kernel formulations yield higher classification performance than traditional linear kernel?, 2.) Under which conditions a kernel design performs better than others?, 3.) Does the addition of class labels into standard term-document matrix improve the classification accuracy?, 4.) Is …
Predicting Violent Crime Reports From Geospatial And Temporal Attributes Of Us 911 Emergency Call Data, Vincent Corcoran
Predicting Violent Crime Reports From Geospatial And Temporal Attributes Of Us 911 Emergency Call Data, Vincent Corcoran
Dissertations
The aim of this study is to create a model to predict which 911 calls will result in crime reports of a violent nature. Such a prediction model could be used by the police to prioritise calls which are most likely to lead to violent crime reports. The model will use geospatial and temporal attributes of the call to predict whether a crime report will be generated. To create this model, a dataset of characteristics relating to the neighbourhood where the 911 call originated will be created and combined with characteristics related to the time of the 911 call. Geospatial …
Enhancing Partially Labelled Data: Self Learning And Word Vectors In Natural Language Processing, Eamon Mcentee
Enhancing Partially Labelled Data: Self Learning And Word Vectors In Natural Language Processing, Eamon Mcentee
Dissertations
There has been an explosion in unstructured text data in recent years with services like Twitter, Facebook and WhatsApp helping drive this growth. Many of these companies are facing pressure to monitor the content on their platforms and as such Natural Language Processing (NLP) techniques are more important than ever. There are many applications of NLP ranging from spam filtering, sentiment analysis of social media, automatic text summarisation and document classification.
Performance Comparison Of Hybrid Cnn-Svm And Cnn-Xgboost Models In Concrete Crack Detection, Sahana Thiyagarajan
Performance Comparison Of Hybrid Cnn-Svm And Cnn-Xgboost Models In Concrete Crack Detection, Sahana Thiyagarajan
Dissertations
Detection of cracks mainly has been a sort of essential step in visual inspection involved in construction engineering as it is the commonly used building material and cracks in them is an early sign of de-basement. It is hard to find cracks by a visual check for the massive structures. So, the development of crack detecting systems generally has been a critical issue. The utilization of contextual image processing in crack detection is constrained, as image data usually taken under real-world situations vary widely and also includes the complex modelling of cracks and the extraction of handcrafted features. Therefore the …
Computational Modeling Of Trust Factors Using Reinforcement Learning, C. M. Kuzio, A. Dinh, C. Stone, L. Vidyaratne, K. M. Iftekharuddin
Computational Modeling Of Trust Factors Using Reinforcement Learning, C. M. Kuzio, A. Dinh, C. Stone, L. Vidyaratne, K. M. Iftekharuddin
Electrical & Computer Engineering Faculty Publications
As machine-learning algorithms continue to expand their scope and approach more ambiguous goals, they may be required to make decisions based on data that is often incomplete, imprecise, and uncertain. The capabilities of these models must, in turn, evolve to meet the increasingly complex challenges associated with the deployment and integration of intelligent systems into modern society. Historical variability in the performance of traditional machine-learning models in dynamic environments leads to ambiguity of trust in decisions made by such algorithms. Consequently, the objective of this work is to develop a novel computational model that effectively quantifies the reliability of autonomous …
Recurrent Residual U-Net For Medical Image Segmentation, Md Zahangir Alom, Christopher Yakopcic, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari
Recurrent Residual U-Net For Medical Image Segmentation, Md Zahangir Alom, Christopher Yakopcic, Mahmudul Hasan, Tarek M. Taha, Vijayan K. Asari
Electrical and Computer Engineering Faculty Publications
Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep …