Computer Engineering Commons^™

Speech Emotion Recognition Using Semi-Nmf Feature Optimization, Surekha Reddy Bandela, T Kishore Kumar

Turkish Journal of Electrical Engineering and Computer Sciences

In recent times, much research is progressing forward in the field of speech emotion recognition (SER). Many SER systems have been developed by combining different speech features to improve their performances. As a result, the complexity of the classifier increases to train this huge feature set. Additionally, some of the features could be irrelevant in emotion detection and this leads to a decrease in the emotion recognition accuracy. To overcome this drawback, feature optimization can be performed on the feature sets to obtain the most desirable emotional feature set before classifying the features. In this paper, semi-nonnegative matrix factorization (semi-NMF) …

Scale-Invariant Mfccs For Speech/Speaker Recognition, Zekeri̇ya Tüfekci̇, Gökay Di̇şken

Turkish Journal of Electrical Engineering and Computer Sciences

The feature extraction process is a fundamental part of speech processing. Mel frequency cepstral coefficients (MFCCs) are the most commonly used feature types in the speech/speaker recognition literature. However, the MFCC framework may face numerical issues or dynamic range problems, which decreases their performance. A practical solution to these problems is adding a constant to filter-bank magnitudes before log compression, thus violating the scale-invariant property. In this work, a magnitude normalization and a multiplication constant are introduced to make the MFCCs scale-invariant and to avoid dynamic range expansion of nonspeech frames. Speaker verification experiments are conducted to show the effectiveness …

A Novel Randomized Recurrent Artificial Neural Network Approach: Recurrent Random Vector Functional Link Network, Ömer Faruk Ertuğrul

Turkish Journal of Electrical Engineering and Computer Sciences

The random vector functional link (RVFL) has successfully been employed in many applications since 1989. RVFL has a single hidden layer feedforward structure that also has direct links between the input layer and the output layer. Although nonlinearity, high generalization capacity, and fast training ability can be provided in RVFL, it can be found from the literature that higher nonlinearity can be obtained by adding recurrent feedback to an artificial neural network. In this paper, the recurrent type of RVFL (R-RVFL), which has both outer feedbacks and also inner feedbacks, is proposed. In order to evaluate and validate the proposed …

A Fine-Grain And Scalable Set-Based Cache Partitioning Through Thread Classification, İsa Ahmet Güney, Gürhan Küçük

Turkish Journal of Electrical Engineering and Computer Sciences

As contemporary processors utilize more and more cores, cache partitioning algorithms tend to preserve cache associativity with a finer-grain of control to achieve higher throughput and fairness goals. In this study, we propose a scalable set-based cache partitioning mechanism, which welds an allocation policy and an enforcement scheme together. We also propose a set-based classifier to better allocate partitions to more deserving threads, a fast set redirection logic to map accesses to dedicated cache sets, and a double access mechanism to overcome the performance penalty due to a repartitioning phase. We compare our work to the best line-grain cache partitioning …

High-Efficiency Design Of A Grid-Connected Pv Inverter Based On Interleaved Flyback Converter Topology, Bünyami̇n Tamyürek, Bi̇lgehan Kirimer

Turkish Journal of Electrical Engineering and Computer Sciences

The importance of efficiency in photovoltaic (PV) inverter applications makes the topology selection as the critical first step. Due to the low efficiency concern, flyback converter is not the preferred topology in kilowatt range in spite of its galvanic isolation, low cost, and small size advantages. Therefore, the objective of this research is to change the perception in favor of flyback converter by designing a flyback-topology-based PV inverter at 2.5 kW with high efficiency. The enhancement in efficiency is achieved mainly by using silicon carbide switching devices, designing ultrahigh-efficiency flyback transformers with extremely low leakage inductance and by implementing a …

Mobility And Traffic-Aware Resource Scheduling For Downlink Transmissions In Lte-A Systems, Önem Yildiz, Radosveta İvanova Sokullu

Turkish Journal of Electrical Engineering and Computer Sciences

As new cellular networks support not only voice services but also many multimedia applications, the requirements for reliable data transmission at high speeds create heavy load on the system. Even though LTE/LTE-A technology takes action towards alleviating this load, it is still necessary to manage resources effectively because of the inadequacy of the available radio resources. Thus, the scheduler at the MAC layer of the base station plays a very important role in resource allocation to the user. In this study a novel algorithm for resource allocation in mobile environments is presented, with two variations addressing different input traffic. The …

A Beaconing-Based Roadside Services Discovery Protocol For Vehicular Ad Hoc Networks, Kifayat Ullah, Ali Sayyed, Muhammad Aziz, Edson Moreira

Turkish Journal of Electrical Engineering and Computer Sciences

Recently, research on vehicular ad hoc networks (VANETs) has gained momentum all over the world. These emerging networks promise to make our driving experience more efficient, safer, comfortable, and enjoyable. VANETs have the potential to support a wide range of interesting applications. One such promising application area is the discovery of roadside services on the highways. Drivers need an efficient way to find these services during their journeys. However, due to the unique features of VANETs, the design and implementation of such applications is a challenging task. In this paper, we propose an application layer beaconing-based roadside services discovery protocol …

Energy And Economic Assessment Of Major Free Cooling Retrofits For Data Centers In Turkey, Ozan Gözcü, Hamza Sali̇h Erden

Turkish Journal of Electrical Engineering and Computer Sciences

Mechanical cooling is responsible for a significant fraction of the energy consumption of data centers (DCs). Free cooling systems take advantage of ambient conditions to reduce the need for compressor-based cooling. This study utilizes thermodynamic models of major free cooling systems such as the direct air-side economizer (ASE), indirect air-side economizer (IASE), indirect evaporative cooler (IEC), and indirect water-side economizer (WSE) integrated with the existing cooling infrastructure of a typical 1 MW IT load DC. Proposed models utilize hourly weather data of various cities in Turkey to compute annual energy consumption and cost-saving potentials of each free cooling method with …

An Adaptive Scheduling Scheme For Inhomogeneously Distributed Wireless Ad Hocnetworks, Adnan Fazil, Aamir Hasan, Muhammad Atique Ur Rehman, Ijaz Mansoor Qureshi

Turkish Journal of Electrical Engineering and Computer Sciences

An efficient scheduling strategy guarantees the simultaneous transmission and successful reception by the scheduled nodes even inside a congested wireless ad hoc network. Owing to the dispersed nature of ad hoc networks, the node packing algorithm needs to be implementable without having network-wide channel state information and should additionally be able to pack the optimum number of successful transmissions. The proposed algorithm, for a network with nonhomogeneously distributed nodes, makes the decision to either inhibit or permit an active interferer around an active receiver based on the interferer?s transmission power. The analysis evidenced that the suggested scheme provides an estimated …

Qpsk-Dual Carrier Modulation For Ultra-Wideband Communication In Body Areanetwork Channels, Yasi̇n Karan, Sali̇m Kahveci̇

Turkish Journal of Electrical Engineering and Computer Sciences

Dual carrier modulation (DCM) using orthogonal frequency-division multiplexing (OFDM) improves the performance in multipath fading channels. In the literature DCM is proposed with 16-quadrature amplitude modulation (16QAM) for ultra-wideband (UWB) communication, with four bits per symbol to keep reliable high date transmission over longer distances. Body area network (BAN) standards address transmission reliability more than data rate. UWB is one of the physical layers proposed in BAN standards. In this study, DCM is used with quadrature phase shift keying (QPSK) instead of 16QAM to have better performance in reliable transmission. The performance of QPSK-DCM is analyzed and compared with 16QAM-DCM, …

Optimized Modeling Of Ni-Mh Batteries Primarily Based On Taguchi Approach And Evaluation Of Used Ni-Mh Batteries, Hani Muhsen, Ahmad Al-Muhtady

Turkish Journal of Electrical Engineering and Computer Sciences

This paper aims to generate an optimized model of the Ni-MH battery based on the Taguchi method and it further aims to evaluate used Ni-MH batteries that served in hybrid electric vehicles and electric vehicles. The status of twelve used Ni-MH batteries is studied to determine their usefulness after their life cycle in automotive applications. The status of used batteries is evaluated by investigating their state of charge, remaining useful life, and degradation in performance. Accordingly, the tested batteries are classified into four categories and they are proposed to serve in different applications. The novelty of the work lies in …

Determination Of Distance Between Dc Traction Power Centers In A 1500-V Dc Subway Line With Artificial Intelligence Methods, Mehmet Taci̇ddi̇n Akçay, İlhan Kocaarslan

Turkish Journal of Electrical Engineering and Computer Sciences

The electrification system in rail systems is designed with regard to the operating data and design parameters. While the electrification system is formed, the minimum voltage rating that the traction force requires during the operation needs to be provided. The highest value of the voltage drop occurring on the line is determined by the distance between power centers. This value needs to be kept within certain limits for the continuity of operation. In this study, the determination of the distance between DC traction power centers for a 1500-V DC-fed rail system is done by means of the adaptive neuro-fuzzy inference …

Fuzzy-Logic-Based Robust Speed Control Of Switched Reluctance Motor For Low And High Speeds, Zeki̇ Omaç

Turkish Journal of Electrical Engineering and Computer Sciences

Switched reluctance motor (SRM) is operated at high magnetic saturation to generate large torque. The flux linkage of SRM is a nonlinear function with phase current and rotor position because of the high magnetic saturation. Also, the performance of the speed controller for the SRM driver system can be negatively affected by noise, disturbances, and inertia of load torque. Therefore, the fuzzy speed controller for the SRM driver system was developed in this study. In addition, a dynamic model of SRM was simulated in Matlab/Simulink software. Based on the results obtained in this study, the speed of the SRM was …

Fitting A Recurrent Dynamical Neural Network To Neural Spiking Data: Tackling The Sigmoidal Gain Function Issues, Reşat Özgür Doruk

Turkish Journal of Electrical Engineering and Computer Sciences

This is a continuation of a recent study (Doruk RO, Zhang K. Fitting of dynamic recurrent neural network models to sensory stimulus-response data. J Biol Phys 2018; 44: 449-469), where a continuous time dynamical recurrent neural network is fitted to neural spiking data. In this research, we address the issues arising from the inclusion of sigmoidal gain function parameters to the estimation algorithm. The neural spiking data will be obtained from the same model as that of Doruk and Zhang, but we propose a different model for identification. This will also be a continuous time recurrent neural network, but with …

Robust Compressed Domain Watermarking Algorithm For Video Protection And Authentication In Noisy Channels, Naveen Cheggoju, Vishal Satpute

Turkish Journal of Electrical Engineering and Computer Sciences

This paper introduces a robust and noise-resilient compressed domain video watermarking technique for data authentication and copyright protection. In recent years, watermarking has emerged as an essential technique to be equipped with data transmission. The main challenge pertaining to transmission is to protect the watermark from noise introduced by the channel. Here, we address this issue by watermark replication and by using the independent pass coding (INPAC) algorithm for compression. A replicated watermark is embedded into the video by the proposed blind video watermarking algorithm and then the watermarked video is compressed by the INPAC algorithm. The compressed video is …

Speech Enhancement Using Adaptive Thresholding Based On Gamma Distribution Of Teager Energy Operated Intrinsic Mode Functions, Özkan Arslan, Erkan Zeki̇ Engi̇n

Turkish Journal of Electrical Engineering and Computer Sciences

This paper introduces a new speech enhancement algorithm based on the adaptive threshold of intrinsic mode functions (IMFs) of noisy signal frames extracted by empirical mode decomposition. Adaptive threshold values are estimated by using the gamma statistical model of Teager energy operated IMFs of noisy speech and estimated noise based on symmetric Kullback--Leibler divergence. The enhanced speech signal is obtained by a semisoft thresholding function, which is utilized by threshold IMF coefficients of noisy speech. The method is tested on the NOIZEUS speech database and the proposed method is compared with wavelet-shrinkage and EMD-shrinkage methods in terms of segmental SNR …

A Novel Hybrid Teaching-Learning-Based Optimization Algorithm For The Classification Of Data By Using Extreme Learning Machines, Ender Sevi̇nç, Tansel Dökeroğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Data classification is the process of organizing data by relevant categories. In this way, the data can be understood and used more efficiently by scientists. Numerous studies have been proposed in the literature for the problem of data classification. However, with recently introduced metaheuristics, it has continued to be riveting to revisit this classical problem and investigate the efficiency of new techniques. Teaching-learning-based optimization (TLBO) is a recent metaheuristic that has been reported to be very effective for combinatorial optimization problems. In this study, we propose a novel hybrid TLBO algorithm with extreme learning machines (ELM) for the solution of …

Comprehending The Safety Paradox And Privacy Concerns With Medical Device Remote Patient Monitoring, Marc Doyle

CCAC Theses and Dissertations

Medical literature identifies a number of technology-driven improvements in disease management such as implantable medical devices (IMDs) that are a standard treatment for candidates with specific diseases. Among patients using implantable cardiac defibrillators (ICD), for example, problems and issues are being discovered faster compared to patients without monitoring, improving safety. What is not known is why patients report not feeling safer, creating a safety paradox, and why patients identify privacy concerns in ICD monitoring.

There is a major gap in the literature regarding the factors that contribute to perceived safety and privacy in remote patient monitoring (RPM). To address this …

Multi-Objective Design Optimization Of A Permanent Magnet Axial Flux Eddy Current Brake, Rasul Tarvirdilu Asl, Hüseyi̇n Murat Yüksel, Ozan Keysan

Turkish Journal of Electrical Engineering and Computer Sciences

The main aim of this study is to optimize an axial flux eddy current damper to be used in a specific aviation application. Eddy current dampers are more advantageous compared to conventional mechanical dampers as they are maintenance-free due to contactless structure and have higher reliability, which is very desirable in aerospace applications. An initial eddy current brake prototype is manufactured and the test results are used to verify the 3-D finite element simulations. The effect of temperature on the brake performance is investigated. Finally, a multiobjective genetic algorithm optimization is applied to find the optimum pole number and geometric …

Extraction And Selection Of Statistical Harmonics Features For Electrical Appliancesidentification Using K-Nn Classifier Combined With Voting Rules Method, Fateh Ghazali, Abdenour Hacine-Gharbi, Philippe Ravier, Tayeb Mohamadi

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, we propose a novel framework for electrical appliances identification using statistical harmonic features of current signals and the use of the k-NN classifier combined with a voting rule strategy. Harmonic coefficients are computed over time using short-time Fourier series of the current signals. From these sequences of coefficients, the mean, standard deviation, skewness, and kurtosis are computed, which provide the statistical harmonic features. This framework has three novelties: (i) selecting the best combination of statistical measures in the sense of classification rate (CR); (ii) combining the k-NN classifier with the voting rule method in order to search …

Softswitch: A Centralized Honeypot-Based Security Approach Using Software-Defined Switching For Secure Management Of Vlan Networks, Muhammet Baykara, Resul Daş

Turkish Journal of Electrical Engineering and Computer Sciences

Honeypot systems are traps for intruders which simulate real systems such as web, application, and database servers used in information systems. Using these systems, unauthorized and malicious access can be efficiently detected. Honeypot is an entity which acts as a source of valued information and its behavior can be monitored. The inability or difficulty of intrusion detection is a serious security problem in networks including virtual local area network (VLAN). According to the literature, the use of honeypots for intrusion detection and prevention in networks including VLAN is strongly recommended. In this paper, in order to provide security and to …

Efficient Detection Of Diseases By Feature Engineering Approach From Chest Radiograph, Avishek Mukherjee

Legacy Theses & Dissertations (2009 - 2024)

Deep Learning is the new state-of-the-art technology in Image Processing. We applied Deep Learning techniques for identification of diseases from Radiographs made publicly available by NIH. We applied some Feature Engineering approach to augment the data from Anterior-Posterior position to Posterior-Anterior position and vice-versa for all the diseases, at the same point we suppressed ‘No Finding’ radiographs which contributed to more than 50% (approximately 60,000) of the dataset to top 1000 images. We also prepared a model by adding a huge amount of noise to the augmented data, which if need be can be deployed at rural locations which lack …

Autonomous Spectrum Enforcement : A Blockchain Approach, Maqsood Ahamed Abdul Careem

Legacy Theses & Dissertations (2009 - 2024)

A core limitation in existing wireless technologies is the scarcity of spectrum, to support the exponential increase in Internet-connected and multimedia-capable mobile devices and the increasing demand for bandwidth-intensive services. As a solution, Dynamic Spectrum Access policies are being ratified to promote spectrum sharing for various spectrum bands and to improve the spectrum utilization. This poses an equally challenging problem of enforcing these spectrum policies. The distributed and dynamic nature of policy violations necessitates the use of autonomous agents to implement efficient and agile enforcement systems. The design of such a fully autonomous enforcement system is complicated due to the …

Emotion Forecasting In Dyadic Conversation : Characterizing And Predicting Future Emotion With Audio-Visual Information Using Deep Learning, Sadat Shahriar

Legacy Theses & Dissertations (2009 - 2024)

Emotion forecasting is the task of predicting the future emotion of a speaker, i.e., the emotion label of the future speaking turn–based on the speaker’s past and current audio-visual cues. Emotion forecasting systems require new problem formulations that differ from traditional emotion recognition systems. In this thesis, we first explore two types of forecasting windows(i.e., analysis windows for which the speaker’s emotion is being forecasted): utterance forecasting and time forecasting. Utterance forecasting is based on speaking turns and forecasts what the speaker’s emotion will be after one, two, or three speaking turns. Time forecasting forecasts what the speaker’s emotion will …

Ieee Access Special Section Editorial: Wirelessly Powered Networks, And Technologies, Theofanis P. Raptis, Nuno B. Carvalho, Diego Masotti, Lei Shu, Cong Wang, Yuanyuan Yang

Computer Science Faculty Publications

Wireless Power Transfer (WPT) is, by definition, a process that occurs in any system where electrical energy is transmitted from a power source to a load without the connection of electrical conductors. WPT is the driving technology that will enable the next stage in the current consumer electronics revolution, including battery-less sensors, passive RF identification (RFID), passive wireless sensors, the Internet of Things and 5G, and machine-to-machine solutions. WPT-enabled devices can be powered by harvesting energy from the surroundings, including electromagnetic (EM) energy, leading to a new communication networks paradigm, the Wirelessly Powered Networks.

A Novel Resource Clustering Model To Develop An Efficient Wireless Personal Cloud Environment, Kowsigan Mohan, Balasubramanie Palanisamy

Turkish Journal of Electrical Engineering and Computer Sciences

In the current era, cloud computing is the major focus of distributed computing and it helps in satisfying the requirements of the business world. It provides facilities on demand under all the parameters of the computing, such as infrastructure, platform, and software, across the globe. One of the major challenges in the cloud environment is to cluster the resources and schedule the jobs among the resource clusters. Many existing approaches failed to provide an optimal solution for job scheduling due to inefficient clustering of resources. In the proposed system, a novel algorithm called resource differentiation based on equivalence node potential …

Evaluation Of Losses In A Secondary-Side Controlled Wireless Battery Charging System, Fahri̇ Gürbüz, Tolga Sürgevi̇l, Mutlu Boztepe

Turkish Journal of Electrical Engineering and Computer Sciences

Secondary-side controlled inductive power transfer (IPT) systems are easy to control compared to primary and dual-side control methods, and more importantly, they do not require wireless communication between primary and secondary sides. In this paper, a wireless battery charging system based on secondary-side controlled IPT is analyzed and presented in detail. The proposed control method relies on the detection of the secondary coil current and the transferred power can be fully controlled by the secondary-side active rectifier with reduced number of power switching devices. The steady-state performance of the IPT system is evaluated using a fundamental harmonic analysis method for …

Vibration Analysis Of A Novel Magnetic-Viscous Nonlinear Passive Isolator Via Finite Element Simulation, Ahmad Partovi Meran, Ümi̇t Önen

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, the design and the finite element simulation of a novel magnetic-viscous vibration isolator have been presented. The proposed isolator consists of permanent magnets axially aligned in repulsion position and a viscous damper in parallel with them. The nonlinear spring characteristic of the permanent magnets provides a good damping property with this configuration. Explicit finite element analyses have been conducted to examine the dynamic behavior of the isolator. Output displacements and transmissibility ratios were measured for various magnet configurations, dashpot coefficients, and input displacement excitation frequencies to determine the best damping properties. The results of the finite element …

Investigation Of Control Of Power Flow By Using Phase Shifting Transformers: Turkey Case Study, Erdi̇ Doğan, Nuran Yörükeren

Turkish Journal of Electrical Engineering and Computer Sciences

Transmission systems are needed to be upgraded based on expected/unexpected load growth factor by years. However, it is not so easy to install and upgrade the transmission system, which requires transmission planning calculation ahead of time. Traditionally, transmission companies built extra transmission lines to meet that load growth, but it is not easy and cost-effective to upgrade the system every time loads increase. Some unexpected load growth may occur for some load points that is not in the part of planning calculation. For those situations, the transmission system may face serious congestion problems. Transmission companies have been looking for a …

Optimal Rescheduling Of Real Power To Mitigate Congestion Using Gravitational Search Algorithm, Kaushik Paul, Niranjan Kumar, Shaligram Agrawal, Kamalendu Paul

Turkish Journal of Electrical Engineering and Computer Sciences

The initiative to manage congestion has gained interest in the current deregulated scenario. The principle commitment of the work in this article is to extend the gravitational search algorithm (GSA) as an efficient metaheuristic optimizing algorithm to diminish the rescheduling cost and efficiently attenuate the overloading of the line with the minimal deviation in the active power generation. The congestion management drive is accomplished by prioritizing the generators based on their sensitivity values. Thereafter, the GSA is introduced to optimally minimize the rescheduling cost along with the minimization of the total amount of active power output and system losses. The …