Yazar "Boyaci, Ali" seçeneğine göre listele
Listeleniyor 1 - 10 / 10
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Automatic food recognition system for middle-eastern cuisines(INST ENGINEERING TECHNOLOGY-IET, 2020) Qaraqe, Marwa; Usman, Muhammad; Ahmad, Kashif; Sohail, Amir; Boyaci, AliThe concerns for a healthier diet are increasing day by day, especially in diabetics wherein the aim of healthier diet can only be achieved by keeping a track of daily food intake and glucose-level. As a consequence, there is an ever-increasing need for automatic tools able to help diabetics to manage their diet and also help physicians to better analyse the effects of various types of food on the glucose-level of diabetics. In this paper, we propose an intelligent food recognition and tracking system for diabetics, which is potentially an essential part of a mobile application that we propose to couple food intake with the blood glucose-level using glucose measuring sensors. For food recognition, we rely on several feature extraction and classification techniques individually and jointly using an early and three different late fusion techniques, namely (i) Particle Swarm Optimisation (PSO), (ii) Genetic Algorithms (GA) based fusion and (iii) simple averaging. Moreover, we also evaluate the performance of several handcrafted and deep features and compare the results against state-of-the-art. In addition, we collect a large-scale dataset containing images from several types of local Middle-Eastern food, which is intended to become a powerful support tool for future research in the domain.Öğe Detection of involuntary movement with wearable technology(Institute of Electrical and Electronics Engineers Inc., 2022) Koseoglu, Yasin; Boyaci, AliNowadays, wearable accelerometers have improved the popularity of smartwatches, and physical activity measurements. This article aims to use a smartwatch as a stimulant against hair pulling obsession (Trichotillomania). Data were collected for 4 hours with a user who pulls out his beard at indefinite intervals, and machine learning models were applied to the collected data. A Watch X is preferred as a programmable watch. This smartwatch is programmed to create an alert when the user makes the beard plucking action. Based on this, it is aimed to prevent Trichotillomania obsession by applying positive punishment with an alert (stimulant). CNN and LSTM models were compared to find the most suitable model and it was seen that LSTM had better accuracy than CNN. However, in terms of speed performance, CNN gave better results. As a result of all comparisons, the LSTM model was observed as the most suitable model with an accuracy rate of 91%.Öğe High-Resolution Multi-band Spectrum Occupancy Measurements and Evaluations at 900MHz Downlink Band for Istanbul Metropolitan(IEEE, 2015) Aki, Fatma Nur; Boyaci, Ali; Yarkan, SerhanRadio frequency spectrum is one of the most important resources for both contemporary and next generation wireless communications (NGWC) systems. Therefore, utilization of the radio frequency spectrum is a critical task. Reliable occupancy statistics are key to such utilization. Considering the fact that Turkey will migrate to digital terrestrial TV broadcast in the near future, a specific portion of the radio frequency spectrum will be available. Hence, occupancy statistics and relevant analyses are mandatory for both contemporary and NGWC systems. Results of high-resolution multi-band spectrum occupancy measurements at 900MHz downlink band for Istanbul metropolitan are presented. Two of the prominent evaluation methods and corresponding occupancy statistics are given in a comparative manner. It is observed that parameters of the evaluation methods affect the occupancy statistics drastically.Öğe The Internet of Things: a domain-specific security requirement classification(Institute of Electrical and Electronics Engineers Inc., 2022) Mukalazi, Arafat; Boyaci, AliWorldwide, societies are rapidly becoming more connected, owing primarily to the growing number of intelligent things and smart applications (e.g, smart automobiles, smart wearable devices, etc.) These have occurred in tandem with the Internet Of Things, a new method of connecting the physical and virtual worlds. It is a new promising paradigm whereby every 'thing' can connect to anything via the Internet. However, with IoT systems being deployed even on large-scale, security concerns arise amongst other challenges. Hence the need to allocate appropriate protection of resources. The realization of secure IoT systems could only be accomplished with a comprehensive understanding of the particular needs of a specific system. How-ever, this paradigm lacks a proper and exhaustive classification of security requirements. This paper presents an approach towards understanding and classifying the security requirements of IoT devices. This effort is expected to play a role in designing cost-efficient and purposefully secured future IoT systems. During the coming up with and the classification of the requirements, We present a variety of set-ups and define possible attacks and threats within the scope of IoT. Considering the nature of IoT and security weaknesses as manifestations of unrealized security requirements, We put together possible attacks and threats in categories, assessed the existent IoT security requirements as seen in literature, added more in accordance with the applied domain of the IoT and then classified the security requirements. An IoT system can be secure, scalable, and flexible by following the proposed security requirement classification.Öğe A low-cost, high-precision signal generation algorithm and prototype implementation for software-defined radios(Institute of Electrical and Electronics Engineers Inc., 2017) Alaca, Ozgur; Boyaci, Ali; Yarkan, SerhanNext generation wireless communications systems are built on highly-adaptive components in order to meet the ever-increasing requirements and to keep up with the dynamically changing environmental conditions. Software-defined radio (SDR) is considered among vital components of next generation wireless communications due to its capabilities such as spectrum monitoring and sensing along with application-specific waveform generation as well as fast switching between several standards. Therefore, it is expected from SDR that it fulfills fundamental communications operations and functionalities of high-precision with the lowest computational complexity. In this study, a low-computational complexity and high-precision signal generation algorithm operating on digital signal processor (DSP) is proposed for SDR and implemented. Its performance results are compared with those of several algorithms. Results are discussed along with future directions. © 2016 The Chamber of Turkish Electrical Engineers.Öğe A Low-cost, High-precision Signal Generation Algorithm and Prototype Implementation for Software-Defined Radios(IEEE, 2016) Alaca, Ozgur; Boyaci, Ali; Yarkan, SerhanNext generation wireless communications systems are built on highly-adaptive components in order to meet the ever-increasing requirements and to keep up with the dynamically changing environmental conditions. Software-defined radio (SDR) is considered among vital components of next generation wireless communications due to its capabilities such as spectrum monitoring and sensing along with application-specific waveform generation as well as fast switching between several standards. Therefore, it is expected from SDR that it fulfills fundamental communications operations and functionalities of high-precision with the lowest computational complexity. In this study, a low-computational complexity and high-precision signal generation algorithm operating on digital signal processor (DSP) is proposed for SDR and implemented. Its performance results are compared with those of several algorithms. Results are discussed along with future directions.Öğe Privacy-Preserving Real-Time Action Detection in Intelligent Vehicles Using Federated Learning-Based Temporal Recurrent Network(Mdpi, 2024) Gokcen, Alpaslan; Boyaci, AliThis study introduces a privacy-preserving approach for the real-time action detection in intelligent vehicles using a federated learning (FL)-based temporal recurrent network (TRN). This approach enables edge devices to independently train models, enhancing data privacy and scalability by eliminating central data consolidation. Our FL-based TRN effectively captures temporal dependencies, anticipating future actions with high precision. Extensive testing on the Honda HDD and TVSeries datasets demonstrated robust performance in centralized and decentralized settings, with competitive mean average precision (mAP) scores. The experimental results highlighted that our FL-based TRN achieved an mAP of 40.0% in decentralized settings, closely matching the 40.1% in centralized configurations. Notably, the model excelled in detecting complex driving maneuvers, with mAPs of 80.7% for intersection passing and 78.1% for right turns. These outcomes affirm the model's accuracy in action localization and identification. The system showed significant scalability and adaptability, maintaining robust performance across increased client device counts. The integration of a temporal decoder enabled predictions of future actions up to 2 s ahead, enhancing the responsiveness. Our research advances intelligent vehicle technology, promoting safety and efficiency while maintaining strict privacy standards.Öğe A secure communications prototype implementation for PSTNs operating on physical layer(Institute of Electrical and Electronics Engineers Inc., 2017) Tokgoz, Sezer Can; Boyaci, Ali; Yarkan, SerhanWidespread use of data communications applications along with recently emerging high-performance telecommunication techniques enforce people, organizations, and even countries to rely on the infrastructures with which these communication services are provided. It is clear that dependence on infrastructure leads to critical concerns about security, reliability, authenticity, and integrity of the data carried over the same infrastructure. Therefore, a prototype based on digital signal processor (DSP) is implemented, which operates on public switched telephone network (PSTN) lines in accordance with the regional (ITU-R, European) standards, supports stegano-graphic information exchange, and allows both analog and digital data transfer in several security levels. In addition, statistical characteristics of the physical layer channel are identified via measurements and communication between two end nodes is established with the use of DSPs by taking into account the behaviors of the switching center. Future directions are provided in light of the results and relevant discussions as well. © 2016 The Chamber of Turkish Electrical Engineers.Öğe A Secure Communications Prototype Implementation for PSTNs operating on Physical Layer(IEEE, 2016) Tokgoz, Sezer Can; Boyaci, Ali; Yarkan, SerhanWidespread use of data communications applications along with recently emerging high-performance telecommunication techniques enforce people, organizations, and even countries to rely on the infrastructures with which these communication services are provided. It is clear that dependence on infrastructure leads to critical concerns about security, reliability, authenticity, and integrity of the data carried over the same infrastructure. Therefore, a prototype based on digital signal processor (DSP) is implemented, which operates on public switched telephone network (PSTN) lines in accordance with the regional (ITU-R, European) standards, supports steganographic information exchange, and allows both analog and digital data transfer in several security levels. In addition, statistical characteristics of the physical layer channel are identified via measurements and communication between two end nodes is established with the use of DSPs by taking into account the behaviors of the switching center. Future directions are provided in light of the results and relevant discussions as well.Öğe A Symmetric U-Slot Microstrip Patch Antenna Design(IEEE, 2015) Boyaci, Ali; Imeci, TahaIn this paper a U-shaped slotted microstrip patch antenna that aims to work in 8.86-8.98GHz frequencies was designed and simulated. First antenna design was in shape of U-slot, then it was changed into [] shaped slot. Sonnet Suites version 13.56 was used as simulation program [ 1]. Air thickness is 20mm and the distance between ground ant the patch is 5mm. S11 is nearly -11.20dB. Antenna has 7.55dB gain at resonance frequency.
