Kamiş, S. | Goularas, D.
Conference Object | 2019 | Proceedings - 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications, Deep-ML 2019 , pp.12 - 17
This study presents a comparison of different deep learning methods used for sentiment analysis in Twitter data. In this domain, deep learning (DL) techniques, which contribute at the same time to the solution of a wide range of problems, gained popularity among researchers. Particularly, two categories of neural networks are utilized, convolutional neural networks(CNN), which are especially performant in the area of image processing and recurrent neural networks (RNN) which are applied with success in natural language processing (NLP) tasks. In this work we evaluate and compare ensembles and combinations of CNN and a category of RN . . .N the long short-term memory (LSTM) networks. Additionally, we compare different word embedding systems such as the Word2Vec and the global vectors for word representation (GloVe) models. For the evaluation of those methods we used data provided by the international workshop on semantic evaluation (SemEval), which is one of the most popular international workshops on the area. Various tests and combinations are applied and best scoring values for each model are compared in terms of their performance. This study contributes to the field of sentiment analysis by analyzing the performances, advantages and limitations of the above methods with an evaluation procedure under a single testing framework with the same dataset and computing environment. © 2019 IEEE Daha fazlası Daha az
Kose, A. | Masazade, E.
Conference Object | 2015 | IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems2015-October , pp.31 - 36
In this paper, the considered task of the wireless sensor network is to track a target emitting energy. Each sensor measures received signal strength from the target, and sends binary decisions directly to the fusion center. We assume that at each time step of tracking, the local decision thresholds of sensors are updated optimally and dynamically as a result from a Multiobjective Optimization Problem (MOP). The MOP considered in this paper jointly maximizes the Fisher Information for decreasing the error on estimation and minimizes the sum of sensor transmission probabilities. Simulation results show that solutions obtained from th . . .e Pareto-optimal front provides good target tracking performance while significantly reducing the average number of sensors transmitting to the fusion center at each time step of tracking. © 2015 IEEE Daha fazlası Daha az
Yoner, S.I. | Ertas, G.
Conference Object | 2017 | 2016 20th National Biomedical Engineering Meeting, BIYOMUT 2016 , pp.31 - 36
In pulse oximeter devices, the most important issue is the generation of appropriate light intensity by the light source according to the color and the composition of the target tissue. For this purpose, these devices are equipped with dedicated driver circuits that transfer different levels of DC current levels to the LEDs acting as the light sources. The current level is typically ranging from 5mA to 20mA and automatically adjusted so as to increase gradually. In this study, three different transistor based and microcontroller-controlled DC current sources for use in pulse oximeter devices have been designed, simulation and practi . . .cal implementations have been performed and results have been analyzed. © 2016 IEEE Daha fazlası Daha az
Ertaş, G. | Keskin, A.U.
Conference Object | 2014 | 2014 18th National Biomedical Engineering Meeting, BIYOMUT 2014 , pp.31 - 36
2014 18th National Biomedical Engineering Meeting, BIYOMUT 2014 -- 16 October 2014 through 17 October 2014 -- -- 110485
Seneler, C. | Dabic, M. | Owaishiz, A. | Daim, T.
Conference Object | 2019 | PICMET 2019 - Portland International Conference on Management of Engineering and Technology: Technology Management in the World of Intelligent Systems, Proceedings , pp.31 - 36
The entrepreneurial university has taken a prodigious influence globally and studies show the expedient value of entrepreneurship in education. Universities are performing various entrepreneurship activities alongside their main objectives of teaching and research. This study evaluates university faculty of different work experiences and positions of their perceptions toward the entrepreneurial university. Analysis of Variances (ANOVA) and Least Significant Difference (LSD) comparisons were performed on participants work experience by evaluating certain factors of the entrepreneurship university. Independent sample t-tests were cond . . .ucted to reveal faculty's awareness of entrepreneurship in their universities. The results help in understanding the interpersonal dynamics within academic organizations. Universities worldwide are adopting entrepreneurship in education by introducing models, methods, and collaboration on all levels of industry and government to fulfill innovative systems in academia. © 2019 PICMET Daha fazlası Daha az
Gokay, R. | Masazade, E. | Aydin, C. | Erol-Barkana, D.
Conference Object | 2015 | IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems2015-October , pp.178 - 183
In this paper, our goal is to map the psychophysiological signal features obtained from Blood Volume Pulse (BVP) and Skin Conductance (SC) sensors to each subjects emotional state and cognitive load. The psychophysiological signals are collected under tests (Stroop test, math test, and event recall test) targeting different levels of emotional state and cognitive load. We use the SC and BVP features as skin conductance response (SCR), heart rate (HR), and the spectral power in the low frequency (LF) band of the heart rate variability (HRV) spectrum for emotional state and cognitive load analysis. Our results show that HR and SCR are . . . indicative features for determining the emotional state, and LF and SCR are indicative features for determining the cognitive load. © 2015 IEEE Daha fazlası Daha az
Demirkanli, S.A. | Kadioglu, D. | Tuna, B.G. | Etemoglu, S. | Kiratll, B. | Şahin, Fikrettin | Utku, F.S.
Conference Object | 2018 | 2017 21st National Biomedical Engineering Meeting, BIYOMUT 2017 , pp.178 - 183
Regenerative Medicine and Tissue Engineering has been gaining critical importance in the medical sector, specifically in cancer and organ-tissue losses. Laboratory studies have been conducted on tissue and organ generation using whole organ decellularization and recellularization techniques. In this study, whole rat pancreas has been decellularized by perfusion and imaged using confocal microscopy. Whole rat pancreas tissue has been divided into control and exerimental groups and decellularized using hypotonic, hypertonic and detergent solutions. The tissues, imbedded in Tissue Tech and frozen at -20 , have been prepared as 30 micro . . .meter sections, dyed using DAPI for confocal microscopic imaging of the cell nuclei. It has been demonstrated that the cell nuclei imaged in the control group have been removed as a result of the decellularization process. These findings indicate that the collagenous tissue has been preserved to a large extent. With the imaging of the serial sections, 3D reconstruction of decellularized pancreas can be obtained. © 2017 IEEE Daha fazlası Daha az
Şenay, S. | Akan, A. | Chaparro, L.F.
Conference Object | 2005 | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - ProceedingsIII , pp.178 - 183
In wireless communications, the channel is typically modeled as a random linear time-varying system that spreads the transmitted signal in both time and frequency due to multi-path and Doppler effects. In this paper, we show how time-frequency analysis can be used to model and estimate the channel of a multi-carrier spread spectrum (MC-SS) system with a complex quadratic spreading sequence. We will show that in this case the effects of time delays and Doppler frequency shifts can be characterized effectively as time-shifts. Using the discrete evolutionary transform (DET) we are able to estimate these effective time shifts via a spre . . .ading function and use them to equalize the channel. To illustrate the performance of the proposed method we perform several simulations with different levels of channel noise, jammer and Doppler frequency shifts. © 2005 IEEE Daha fazlası Daha az
Yigit, E. | Ucak, C.
Conference Object | 2018 | 2017 10th International Conference on Electrical and Electronics Engineering, ELECO 20172018-January , pp.100 - 104
Power transformers are crucial components of electric power systems for continuity of electricity. The reliability of power system depends greatly on the operational performance of the power transformers under different operating conditions. The most important indicator of the operating performance of oil-immersed transformers is the top-oil and the hottest-spot temperature values. Therefore, different thermal models have been developed in the literature to estimate temperature changes of power transformers. In this study, thermal models developed by IEC Loading guide for oil and winding temperatures of power transformers are studie . . .d. To the best of our knowledge, description of IEC models in the literature have some ambiguous points. Thus, ambiguous points have been clarified and some modification to IEC models has been introduced to have better estimates of top-oil and hottest-spot temperatures of power transformers. With these modifications, top-oil and hottest-spot temperatures, which are given for 250MVA ONAF transformer unit in IEC Annex-b, are presented during different load variations as an example. © 2017 EMO (Turkish Chamber of Electrical Enginners) Daha fazlası Daha az
Ve Gokhan Ertas, I.H.
Conference Object | 2017 | 2017 Medical Technologies National Conference, TIPTEKNO 20172017-January , pp.1 - 4
Advanced smart pillboxes are needed for use with the heart rate regulating drugs. The most important component of these pillboxes is the heart beat rate sensor. In this study, experimental analyses have been performed with different optical sensors namely HRM-2511B transmissive sensor, TCRT1000 reflective sensor and PulseSensor reflective sensor in heartbeat sensing. All of the sensors provide very similar frequency signals captured from the left index finger. All the sensors give quite similar and correct measurement results when compared with the reference device. However, the measurement consistency is highly dependent on the pla . . .cement of the fingertip on the sensor. TCRT1000 and PulseSensor sensors require additional mechanical setup while HRM-2511B sensor is already equipped with a robust fingertip fixing mechanism. In the future, we are planning to develop an advanced smart pillbox based on the HRM-2511B sensor. © 2017 IEEE Daha fazlası Daha az
Ovant, B.S. | Güney, I.A. | Savaş, M.E. | Küçük, G.
Conference Object | 2016 | 2016 International Conference on High Performance Computing and Simulation, HPCS 2016 , pp.204 - 212
Last Level Caches (LLCs) are among the most common processor resources that are shared by multiple threads in simultaneous multithreaded (SMT) and chip multi processors (CMP). In an unmanaged cache organization, threads might not get along well and steal cache lines from each other. This type of thread interaction prevents effective utilization of this precious resource. Cache partitioning is one of the well-studied methods that target improved system performance through isolation of cache lines dedicated to each thread. In this study, we propose a new allocation policy that chooses the amount of cache partitions through thread clas . . .sification and auxiliary cache structures, which we call Parallel Universe Tag Directories (PUTDs). Each thread maintains a PUTD structure, which enables collecting statistics from another execution dimension, where the dedicated thread receives more cache resources. Our test results show that our proposed mechanism gives better performance and fairness results with negligible hardware requirements compared to the current state of the art, in all studied processor configurations. © 2016 IEEE Daha fazlası Daha az
Goularas, D. | Cinar, K.
Conference Object | 2019 | 2019 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019 , pp.204 - 212
This paper presents a method for the recognition of music notes from the Hamparsum music notation system. This notation was widely used during the last two centuries of the Ottoman Empire and it is still in use today. The Hamparsum notation presents significant differences compared to the European music notation, in terms of symbols and structure. Moreover, the notes can consist of more than one individual symbols. The proposed recognition method comprises several steps and algorithms, including a feature extraction based on Gabor Filters, recognition of symbols using a Support Vector Machine classifier, a method for assigning recog . . .nized symbols to a candidate Hamparsum note and a final recognition system based on template matching. This work will help to popularize this unique cultural heritage by providing Hamparsum scores in a machine-readable format. © 2019 IEEE Daha fazlası Daha az