Işık Üniversitesi Kurumsal Akademik Bellek
Işık Üniversitesi tarafından doğrudan ve dolaylı olarak yayınlanan; kitap, makale, tez, bildiri, rapor, araştırma verisi gibi tüm akademik kaynakları uluslararası standartlarda dijital ortamda depolar, Üniversitenin akademik performansını izlemeye aracılık eder, kaynakları uzun süreli saklar ve telif haklarına uygun olarak Açık Erişime sunar.
Güncel Gönderiler
Integrating the focusing neuron model with N-BEATS and N-HiTS
(Institute of Electrical and Electronics Engineers Inc., 2024) Özçelik, Şuayb Talha; Tek, Faik Boray
The N-BEATS (Neural Basis Expansion Analysis for Time Series) model is a robust deep learning architecture designed specifically for time series forecasting. Its foundational idea lies in the use of a generic, interpretable architecture that leverages backward and forward residual links to predict time series data effectively. N - BEATS influenced the development of N-HiTS (Neural Hierarchical Interpretable Time Series), which builds upon and extends the foundational ideas of N-BEATS. This paper introduces new integrations to enhance these models using the Focusing Neuron model in blocks of N-BEATS and N-HiTS instead of Fully Connected (Dense) Neurons. The integration aims to improve the forward and backward forecasting processes in the blocks by facilitating the learning of parametric local receptive fields. Preliminary results indicate that this new usage can significantly improve model performances on datasets that have longer sequences, providing a promising direction for future advancements in N-BEATS and N-HiTS.
Machine learning-driven adaptive modulation for VLC-enabled medical body sensor networks
(Iran University of Science and Technology, 2024-12) Rizi, Reza Bayat; Forouzan, Amir R.; Miramirkhani, Farshad; Sabahi, Mohamad F.
Visible Light Communication, a key optical wireless technology, offers reliable, high-bandwidth, and secure communication, making it a promising solution for a variety of applications. Despite its many advantages, optical wireless communication faces challenges in medical environments due to fluctuating signal strength caused by patient movement. Smart transmitter structures can improve system performance by adjusting system parameters to the fluctuating channel conditions. The purpose of this research is to examine how adaptive modulation performs in a medical body sensor network system that uses visible light communication. The analysis focuses on various medical situations and investigates machine learning algorithms. The study compares adaptive modulation based on supervised learning with that based on reinforcement learning. The findings indicate that both approaches greatly improve spectral efficiency, emphasizing the significance of implementing link adaptation in visible light communication-based medical body sensor networks. The use of the Q-learning algorithm in adaptive modulation enables real-time training and enables the system to adjust to the changing environment without any prior knowledge about the environment. A remarkable improvement is observed for photodetectors on the shoulder and wrist since they experience more DC gain.
On the theory of single aspheric lenses
(Institute of Electrical and Electronics Engineers Inc., 2024) Hasanoğlu, Elman
Aspheric lenses play a pivotal role in a myriad of applications, including antenna theory, communication systems, sophisticated optical systems etc. These lenses, unlike their spherical counterparts, possess an infinite number of free parameters and by utilizing these parameters it is possible to achieve optical and antenna systems with very high and sophisticated performances. However, the lack of a rigorous mathematical theory essentially limits possibility to utilize their full potential in the related fields. In our days, the design process relies heavily on elementary mathematical principles and empirical methods [1-2]. Even a single thick aspheric lens lacks a comprehensive mathematical theory. In this paper a new mathematical approach to the theory of single lenses is proposed. Surprisingly, even in this seemingly straightforward case, the serious mathematical theory of a single aspherical lens relies on rather nontrivial mathematical principles as partial differential equations, differential geometry, Riemann geometry.
Exploring the acoustic identity of Derinkuyu Underground City
(Society of Acoustics, 2024) Nas, Sezin; Şaher, Konca; Mıhçı, Gürkan; Aytıs, Saadet
Sounds play a significant role in shaping the identity of spaces and places, yet the acoustic environment of underground cities remains relatively unexplored in the existing literature. Derinkuyu Underground City stands as a prominent cultural heritage site, boasting a capacity of 20,000 people and serving as one of the largest underground cities globally. While geological and structural studies have been conducted on such sites, investigations into indoor acoustics, a crucial aspect of the physical environment, are notably lacking. This study initiates an initial examination of the sound environment within Derinkuyu Underground City, aiming to analyse its features acoustically. Undertaking a PhD study, our research endeavours to gather essential data essential for the preservation of the site's current acoustic environment as a cultural heritage site while also generating valuable insights for the design and construction of future underground cities. In this paper, we present a preliminary assessment of the typologies of various spaces within Derinkuyu Underground City, exploring their unique acoustic features. By characterizing and understanding the acoustic properties of diverse spaces within the underground city, we seek to understand how acoustic might contribute to the identity of these spaces and provide foundational knowledge for both preservation efforts and future underground urban design initiatives.
Reflections on the International Noise Awareness Day 2023 activities
(Society of Acoustics, 2024) Şaher, Konca; Dümen, Ayça Şentop; Sezgin, Hakika; Nas, Sezin; Kelle, Dilara; Demiral, Yücel
This paper presents an overview of the experiences and outcomes derived from the activities organized for International Noise Awareness Day 2023 in Turkey with the theme “Keep your hearing, keep your health”. Collaboratively organized by Turkish Acoustical Society, and Occupational Hygienists Society, the initiatives aimed to explore the role of sound in educational facilities, with a particular focus on the perspectives of students and teachers. These activities were a student drawing competition, an online International Symposium, a research project titled "Assessment of Acoustic Conditions in Schools and Health Effects on School," and an "Acoustics Workshop in Educational Buildings" conducted at the Izmir BLX Acoustics Laboratory. Drawing from our experiences and findings, we highlight the significance of actively involving researchers, acoustic consultants, occupational hygienists, teachers, students, and designers in such endeavours. Our findings indicate that inclusive approaches not only boost public engagement but also enhance awareness of behavioural, emotional, educational, administrative and design aspects related to sound. By promoting collaboration and participation in knowledge exchange, such activities significantly improve understanding of sound-related issues in schools.
