Yazar "Boyaci, Ali" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Automatic food recognition system for middle-eastern cuisines
    (INST ENGINEERING TECHNOLOGY-IET, 2020) Qaraqe, Marwa; Usman, Muhammad; Ahmad, Kashif; Sohail, Amir; Boyaci, Ali
    The 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.
  • Küçük Resim
    Öğe
    Detection of involuntary movement with wearable technology
    (Institute of Electrical and Electronics Engineers Inc., 2022) Koseoglu, Yasin; Boyaci, Ali
    Nowadays, 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%.
  • Küçük Resim
    Öğe
    The Internet of Things: a domain-specific security requirement classification
    (Institute of Electrical and Electronics Engineers Inc., 2022) Mukalazi, Arafat; Boyaci, Ali
    Worldwide, 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.
  • Küçük Resim Yok
    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, Serhan
    Next 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.