Elektrik Elektronik Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1941

Browse

Now showing 1 - 20 of 49

Citation - WoS: 2
Citation - Scopus: 5
Compositional Neural Network Language Models for Agglutinative Languages
(2016) Saraçlar, Murat; Arısoy, Ebru
Continuous space language models (CSLMs) have been proven to be successful in speech recognition. With proper training of the word embeddings, words that are semantically or syntactically related are expected to be mapped to nearby locations in the continuous space. In agglutinative languages, words are made up of concatenation of stems and suffixes and, as a result, compositional modeling is important. However, when trained on word tokens, CSLMs do not explicitly consider this structure. In this paper, we explore compositional modeling of stems and suffixes in a long short-term memory neural network language model. Our proposed models jointly learn distributed representations for stems and endings (concatenation of suffixes) and predict the probability for stem and ending sequences. Experiments on the Turkish Broadcast news transcription task show that further gains on top of a state-of-theart stem-ending-based n-gram language model can be obtained with the proposed models.
Language Modeling for Turkish Text and Speech Processing
(Springer, 2018) Arısoy, Ebru; Saraçlar, Murat
This chapter presents an overview of language modeling followed by a discussion of the challenges in Turkish language modeling. Sub-lexical units are commonly used to reduce the high out-of-vocabulary (OOV) rates of morphologically rich languages. These units are either obtained by morphological analysis or by unsupervised statistical techniques. For Turkish, the morphological analysis yields word segmentations both at the lexical and surface forms which can be used as sub-lexical language modeling units. Discriminative language models, which outperform generative models for various tasks, allow for easy integration of morphological and syntactic features into language modeling. The chapter provides a review of both generative and discriminative approaches for Turkish language modeling.
Citation - WoS: 3
Citation - Scopus: 5
Single-Slice Microwave Imaging of Breast Cancer by Reverse Time Migration
(Wiley, 2022) Bilgin, Egemen; Cansız, Gökhan; Akduman, İbrahim; Cayoren, Mehmet; Joof, Sulayman; Yılmaz, Tuba
Purpose Microwave imaging of breast cancer is considered and a new microwave imaging prototype including the imaging algorithm, the antenna array, and the measurement configuration is presented. The prototype aims to project the geometrical features of the anomalies inside the breast to a single-slice image at the coronal plane depending on the complex dielectric permittivity variation among the tissues to aid the diagnosis . Methods The imaging prototype uses a solid cylindrical dielectric platform, where a total of 24 optimized Vivaldi antennas are embedded inside to form a uniform circular antenna array. The center of the platform is carved to create a hollow part for placement of the breast and the multistatic, microwave scattering parameters are collected with the antenna array around the hollow center. The dielectric platform further enhances the microwave impedance matching against the breast fat tissue and preserves the vertical polarization during the measurements. In the imaging phase, a computationally efficient inverse electromagnetic scattering method-reverse time migration (RTM)-is considered and adapted in terms of scattering parameters to comply with the actual measurements. Results The prototype system is experimentally tested against tissue-mimicking breast phantoms with realistic dielectric permittivity profiles. The reconstructed single-slice images accurately determined the locations and the geometrical extents of the tumor phantoms. These experiments not only verified the microwave imaging prototype but also provided the first experimental results of the imaging algorithm. Conclusions The presented prototype system implementing the RTM method is capable of reconstructing single-slice, nonanatomical images, where the hotspots correspond to the geometrical projections of the anomalies inside the breast.
Parameters Effects Study on Pulse Laser for the Generation of Surface Acoustic Waves in Human Skin Detection Applications
(2015) Chen, Kun; Wu, Sen; Li, Yanning; Li, Tingting; Fu, Xing; Dorantes-Gonzalez, Dante Jorge
Laser-induced Surface Acoustic Waves (LSAWs) has been promisingly and widely used in recent years due to its rapid, high accuracy and non-contact evaluation potential of layered and thin film materials. For now, researchers have applied this technology on the characterization of materials' physical parameters, like Young's Modulus, density, and Poisson's ratio; or mechanical changes such as surface cracks and skin feature like a melanoma. While so far, little research has been done on providing practical guidelines on pulse laser parameters to best generate SAWs. In this paper finite element simulations of the thermos-elastic process based on human skin model for the generation of LSAWs were conducted to give the effects of pulse laser parameters have on the generated SAWs. And recommendations on the parameters to generate strong SAWs for detection and surface characterization without cause any damage to skin are given.
Citation - WoS: 1
Citation - Scopus: 2
Improving the Usage of Subword-Based Units for Turkish Speech Recognition
(IEEE, 2020) Çetinkaya, Gözde; Saraçlar, Murat; Arısoy, Ebru
Subword units are often utilized to achieve better performance in speech recognition because of the high number of observed words in agglutinative languages. In this study, the proper use of subword units is explored in recognition by a reconsideration of details such as silence modeling and position-dependent phones. A modified lexicon by finite-state transducers is implemented to represent the subword units correctly. Also, we experiment with different types of word boundary markers and achieve the best performance by adding a marker both to the left and right side of a subword unit. In our experiments on a Turkish broadcast news dataset, the subword models do outperform word-based models and naive subword implementations. Results show that using proper subword units leads to a relative word error rate (WER) reductions, which is 2.4%, compared with the word level automatic speech recognition (ASR) system for Turkish.
Citation - WoS: 1
Citation - Scopus: 1
Domain Adaptation Approaches for Acoustic Modeling
(IEEE, 2020) Arısoy, Ebru; Fakhan, Enver
In the recent years, with the development of neural network based models, ASR systems have achieved a tremendous performance increase. However, this performance increase mostly depends on the amount of training data and the computational power. In a low-resource data scenario, publicly available datasets can be utilized to overcome data scarcity. Furthermore, using a pre-trained model and adapting it to the in-domain data can help with computational constraint. In this paper we have leveraged two different publicly available datasets and investigate various acoustic model adaptation approaches. We show that 4% word error rate can be achieved using a very limited in-domain data.
Citation - WoS: 41
Citation - Scopus: 49
Adaptive Human Force Scaling Via Admittance Control for Physical Human-Robot Interaction
(IEEE, 2021) Başdoğan, Çağatay; Aydın, Yusuf; Hamad, Yahya M.
The goal of this article is to design an admittance controller for a robot to adaptively change its contribution to a collaborative manipulation task executed with a human partner to improve the task performance. This has been achieved by adaptive scaling of human force based on her/his movement intention while paying attention to the requirements of different task phases. In our approach, movement intentions of human are estimated from measured human force and velocity of manipulated object, and converted to a quantitative value using a fuzzy logic scheme. This value is then utilized as a variable gain in an admittance controller to adaptively adjust the contribution of robot to the task without changing the admittance time constant. We demonstrate the benefits of the proposed approach by a pHRI experiment utilizing Fitts’ reaching movement task. The results of the experiment show that there is a) an optimum admittance time constant maximizing the human force amplification and b) a desirable admittance gain profile which leads to a more effective co-manipulation in terms of overall task performance.
Differential Microwave Imaging of Cerebral Hemorrhage Via Dort Method
(IEEE, 2023) Dilman, İsmail; Bilgin, Egemen; Doğu, Semih
Bleeding in the brain tissues may cause fatal health conditions and continuous monitoring of the change in this blood accumulation becomes important in the first few hours after the incident. The continuous post-event monitoring aims to detect the variations in the size and the shape of the hemorrhage regions. To this end, the human head is illuminated by non-ionizing electromagnetic radiation, and the scattered field is measured in different time instants. The decomposition of the time-reversal (DORT) method is then used as the microwave imaging algorithm to produce an indicator function. The performance of the proposed technique is assessed via numerical simulations involving a realistic human head phantom. The results suggest that the DORT method is capable of detecting the changes in multiple simultaneous cerebral hemorrhage regions successfully.
Citation - WoS: 1
Citation - Scopus: 5
Uncertainty-Aware Representations for Spoken Question Answering
(Institute of Electrical and Electronics Engineers Inc., 2021) Ünlü, Merve; Arısoy, Ebru
This paper describes a spoken question answering system that utilizes the uncertainty in automatic speech recognition (ASR) to mitigate the effect of ASR errors on question answering. Spoken question answering is typically performed by transcribing spoken con-tent with an ASR system and then applying text-based question answering methods to the ASR transcriptions. Question answering on spoken documents is more challenging than question answering on text documents since ASR transcriptions can be erroneous and this degrades the system performance. In this paper, we propose integrating confusion networks with word confidence scores into an end-to-end neural network-based question answering system that works on ASR transcriptions. Integration is performed by generating uncertainty-aware embedding representations from confusion networks. The proposed approach improves F1 score in a question answering task developed for spoken lectures by providing tighter integration of ASR and question answering.
Citation - WoS: 8
Citation - Scopus: 8
Performance Maximization of Network Assisted Mobile Data Offloading With Opportunistic Device-To Communications
(2018) Zeydan, Engin; Tan, A. Serdar
Mobile data traffic inside mobile operator's infrastructure is increasing exponentially every year. This increasing demand forces mobile network operators (MNOs) to seek for alternative communication methods in order to relieve the traffic load in base stations, especially in highly populated and crowded environments. Network assisted data offload and Device-to-Device(D2D) communications are two prominent methods to help MNOs solve this problem. In this study, a data offload framework is developed that incorporates network assisted multiple attribute decision making (MADM) for best network selection and D2D communications for exploiting user proximity in crowded environments. The performance of the framework is evaluated with simulation results as well as analytic solutions and performance bounds. The simulation results indicate the superiority of incorporating network-based information besides user-based information in offloading decisions and demonstrates the significant benefits of D2D communications when the density of D2D users is properly adjusted. The simulation results depict that up to 168% and 200% increase in user satisfaction and throughput can be achieved under high network load scenarios at optimal D2D density. (C) 2018 Elsevier B.V. All rights reserved.
Citation - Scopus: 1
Cnn-Based Emotion Recognition Using Data Augmentation and Preprocessing Methods
(Institute of Electrical and Electronics Engineers Inc., 2023) Toktaş, Tolga; Kırbız, Serap; Kayaoğlu, Bora
In this paper, a system that recognizes emotion from human faces is designed using Convolutional Neural Networks (CNN). CNN is known to perform well when trained with a large database. The lack of large and balanced publicly available databases that can be used by deep learning methods for emotion recognition is still a challenge. To overcome this problem, the number of data is increased by merging FER+, CK+ and KDEF databases; and preprocessing is applied to the face images in order to reduce the variations in the database. Data augmentation methods are used to reduce the imbalance in the data distribution that still remains despite the increasing number of data in the merged database. The CNN-based method developed using database merging, image preprocessing and data augmentation, achieved emotion recognition with 80% accuracy.
Regression Analysis of Stock Exchanges During the Ramadan Period: Analysis of 16 Countries
(2016) Tan, A. Serdar; Özlem S.
...
Turkish Speech Recognition
(2018) Arısoy, Ebru; Saraçlar, Murat
Automatic speech recognition (ASR) is one of the most important applications of speech and language processing, as it forms the bridge between spoken and written language processing. This chapter presents an overview of the foundations of ASR, followed by a summary of Turkish language resources for ASR and a review of various Turkish ASR systems. Language resources include acoustic and text corpora as well as linguistic tools such as morphological parsers, morphological disambiguators, and dependency parsers, discussed in more detail in other chapters. Turkish ASR systems vary in the type and amount of data used for building the models. The focus of most of the research for Turkish ASR is the language modeling component covered in Chap. 4.
Citation - WoS: 17
Citation - Scopus: 18
Microwave Imaging of Breast Cancer With Factorization Method: Spions as Contrast Agent
(Wiley, 2020) Çayӧren, Mehmet; Coşğun, Sema; Bilgin, Egemen
Female breast at macroscopic scale is a non-magnetic medium, which eliminates the possibility of realizing microwave imaging of the breast cancer based on magnetic permeability variations. However, by administering functionalized, superparamagnetic iron-oxide nanoparticles (SPION) as a contrast material to modulate magnetic permeability of cancer cells, a small variation on the scattered electric field from the breast is achievable under an external, polarizing magnetic field. PURPOSE: We demonstrate an imaging technique that can locate cancerous tumors inside the breast due to electric field variations caused by SPION tracers under different magnetic field intensities. Furthermore, we assess the feasibility of SPION enhanced microwave imaging for breast cancer with simulations performed on a multi-static imaging configuration. METHODS: The imaging procedure is realized as the factorization method of qualitative inverse scattering theory, which is essentially a shape retrieval algorithm for inaccessible objects. The formulation is heuristically modified to accommodate the scattering parameters instead of the electric field to comply with the requirements of experimental microwave imaging systems. RESULTS:With full-wave electromagnetic simulations performed on an anthropomorphically realistic breast phantom, which is excited with a cylindrical imaging prototype of 18 dipole antenna arranged as a single row, the technique is able to locate cancerous tumors for a experimentally achievable doses. CONCLUSIONS: The technique generates non-anatomic microwave images, which maps the cancerous tumors depending on concentration of SPION tracers, to aid the diagnosis of the breast cancer.
Quality-Aware Wi-Fi Offload: Analysis, Design and Integration Perspectives
(2018) Mester, Yavuz; Buyruk, Hasan; Zeydan, Engin; Tan, A. Serdar
The rapid spread of smart wireless devices and expansion of mobile data traffic have increased the interest for efficient traffic offloading techniques in next-generation communication technologies. Wi-Fi offloading uses ubiquitous Wi-Fi technology in order to satisfy the ever increasing demand for mobile bandwidth and therefore is an appropriate methodology for mobile operators. As a matter of fact, design and integration of an offloading technology inside mobile network operators' infrastructures is a challenging task due to convergence issues between the The 3rd Generation Partnership Project (3GPP) and non-3GPP networks. Therefore, a connectivity management platform is a key element for integrated heterogeneous mobile network operators in order to enable smart and effective offloading. In this paper, analysis, design and integration of a connectivity management platform that uses a Multiple Attribute Decision Making (MADM) algorithm for efficient Wi-Fi Offloading in heterogeneous wireless networks is presented. In order to enhance the end-user's quality-of-experience (QoE), we have especially concentrated on the benefits that can be achieved by exploiting the presence of integrated service provider platform. Hence, the proposed platform can collect several User Equipment (UE) and network-based attributes via infrastructure and client Application Programming Interfaces (APIs) and decides on the best network access technology (i.e. 3GPP and non-3GPP) to connect to for requested users. We have also proposed multi-user extensions of the MADM algorithms for offloading. Through simulations and experiments, we provide details of the comparisons of the proposed algorithms as well as the sensitivity analysis of the MADM algorithm through an experimental set-up.
Citation - Scopus: 1
A Ran/Sdn Controller Based Connectivity Management Platform for Mobile Service Providers
(Institute of Electrical and Electronics Engineers Inc., 2017) Ayhan, Gökhan; Koca, Melih; Zeydan, Engin; Tan, A. Serdar
In this demo, we demonstrate the integration of radio access network (RAN)/Software-Defined Networking (SDN) controller with a connectivity management platform designed for mobile wireless networks. This is an architecture designed throughout the EU Celtic-Plus project SIGMONA1. OpenDaylight based RAN/SDN controller and the application server are capable of collecting infrastructure and client related parameters from OpenFlow enabled switches and Android based phones respectively. The decision on the best access network selection is computed at the application server using a Multiple Attribute Decision Making (MADM) algorithm and instructed back to Android-based mobile client for execution of access network selection. © 2017 IFIP.
Citation - WoS: 4
Citation - Scopus: 4
Multi-Stream Long Short-Term Memory Neural Network Language Model
(2015) Saraçlar, Murat; Arısoy, Ebru
Long Short-Term Memory (LSTM) neural networks are recurrent neural networks that contain memory units that can store contextual information from past inputs for arbitrary amounts of time. A typical LSTM neural network language model is trained by feeding an input sequence. i.e., a stream of words, to the input layer of the network and the output layer predicts the probability of the next word given the past inputs in the sequence. In this paper we introduce a multi-stream LSTM neural network language model where multiple asynchronous input sequences are fed to the network as parallel streams while predicting the output word sequence. For our experiments, we use a sub-word sequence in addition to a word sequence as the input streams, which allows joint training of the LSTM neural network language model using both information sources.
Live Demo: Design and Fpga Implementation of a Component Level Uav Simulator
(IEEE, 2023) Aydın, Yusuf; Ayhan, Tuba; Akyavaş , İrfan
In this work, we introduce a fast, component based simulation environment for UAVs. The simulator framework is proposed as combination of three sub-models: i. battery, ii. BLDC and propeller, iii. dynamic model. The model parameters are extracted for a particular UAV for testing the simulator. The simulator is implemented on an FPGA to increase simulation speed. The simulator calculates battery SOC, position, velocity and acceleration of the UAV with gravity, drag, propeller air inflow velocity. The simulator runs on the FPGA fabric of XilinxXCKU13P with simulation steps of 1 ms.
Citation - WoS: 22
Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
(Institute of Electrical and Electronics Engineers (IEEE), 2019) Kırbız, Serap; Karamatlı, Ertuğ; Cemgil, Ali Taylan
In this letter, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isolated sources. Since our method does not require source class labels for every time-frequency bin but only a single label for each source constituting the mixture signal, we call this scenario as weak class supervision. We associate a variational autoencoder (VAE) with each source class within a non negative (compositional) model. Each VAE provides a prior model to identify the signal from its associated class in a sound mixture. After training the model on mixtures, we obtain a generative model for each source class and demonstrate our method on one-second mixtures of utterances of digits from 0 to 9. We show that the separation performance obtained by source class supervision is as good as the performance obtained by source signal supervision.
Citation - WoS: 4
Citation - Scopus: 5
Monitoring of Intracerebral Hemorrhage With a Linear Microwave Imaging Algorithm
(Springer, 2022) Dilman, Ismail; Dogu, Semih; Bilgin, Egemen; Akinci, Mehmet Nuri; Cosgun, Sema; Çayören, Mehmet; Akduman, Ibrahim
Intracerebral hemorrhage is a life-threatening condition where conventional imaging modalities such as CT and MRI are indispensable in diagnosing. Nevertheless, monitoring the evolution of intracerebral hemorrhage still poses a technological challenge. We consider continuous monitoring of intracerebral hemorrhage in this context and present a differential microwave imaging scheme based on a linearized inverse scattering. Our aim is to reconstruct non-anatomical maps that reveal the volumetric evolution of hemorrhage by using the differences between consecutive electric field measurements. This approach can potentially allow the monitoring of intracerebral hemorrhage in a real-time and cost-effective manner. Here, we devise an indicator function, which reveals the position, volumetric growth, and shrinkage of hemorrhage. Later, the method is numerically tested via a 3D anthropomorphic dielectric head model. Through several simulations performed for different locations of intracerebral hemorrhage, the indicator function-based technique is demonstrated to be capable of detecting the changes accurately. Finally, the robustness under noisy conditions is analyzed to assess the feasibility of the method. This analysis suggests that the method can be used to monitor the evolution of intracerebral hemorrhage in real-world scenarios. Graphical abstract: [Figure not available: see fulltext.]. © 2022, International Federation for Medical and Biological Engineering.

Browse

Browsing Elektrik Elektronik Mühendisliği Bölümü Koleksiyonu by Department "Mühendislik Fakültesi, Elektrik Elektronik Mühendisliği Bölümü"