- Chaos-based Image/Signal Encryption
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Complex Network Analysis Techniques
- Indoor and Outdoor Localization Technologies
- Cryptographic Implementations and Security
- Gaze Tracking and Assistive Technology
- Digital Communication and Language
- Chaos control and synchronization
- Spam and Phishing Detection
- COVID-19 diagnosis using AI
- AI in cancer detection
- Numerical Methods and Algorithms
- Internet Traffic Analysis and Secure E-voting
- ECG Monitoring and Analysis
- Corneal surgery and disorders
- Cellular Automata and Applications
- Radiomics and Machine Learning in Medical Imaging
- Urinary Tract Infections Management
- Multiple Sclerosis Research Studies
- Network Packet Processing and Optimization
- Smart Parking Systems Research
- Physical Unclonable Functions (PUFs) and Hardware Security
- Biometric Identification and Security
- Systemic Sclerosis and Related Diseases
Fırat University
2015-2024
Turgut Özal University
2020
Abstract Today, corneal refraction, height, and thickness data, which are required in the diagnosis of keratoconus, can be obtained with tomography devices. Pentacam four map display presenting this data is one most basic options keratoconus. In article, an artificial intelligence‐based method using images proposed to distinguish keratoconus from healthy eyes. Axial/sagittal curvature, back elevation, front a total 341 corneas İnönü University ophthalmology clinic as set were given input...
The most important function of a sensor network is to collect information from the environment. For many applications, it that location or originates collected ascertained. This article presents detection mobile sensor's in an indoor environment with help known sensors (anchors) placed Anchor measure temperature, which sent phone via Bluetooth. can RSSI values incoming signals as well temperature coming each anchor sensors. Artificial Neural Network(ANN) model presented this was developed...
Random numbers have a wide range of usage area such as simulation, games chance, sampling and computer science (cryptography, game programming, data transmission). In order to use random in science, they must three basic requirements. First, the generated be unpredictable. Second, should good statistical properties. Finally, number streams not reproduced. generators (RNGs) been developed obtain with these These are classified into true (TRNG) pseudo (PRNG). One PRNGs used for generate is...
Denial of Service attacks are one the major type problems in computer network security. Because they include many other most frequently used attack methods.. In general, DoS to block access networks or personal computers. SYN flooding is widespread attacks. these normal packets can not be distinguished from packets. this paper, we propose a fuzzy logic based system for detecting Performance proposed has been compared with Cumulative Sum (CUSUM) algorithm. The simulation results show that...
It is critical in terms of security that numbers used cryptographic systems are generated by hardware such as Field Programmable Gate Array (FPGA). The most common method to develop high-quality and fast True Random Number Generators (TRNGs) use Ring Oscillator (RO). Jitter mostly an approach provide randomness source clock signals RO so random can be generated. Numbers based TRNGs because jitter random. However, it a disadvantage these do not have good statistical properties....
For many of the applications in which wireless sensor networks are used, it is important to know from nodes or what location useful information acquired.The Global Positioning System (GPS) conventionally used determine location.However, GPS systems not ideal for due their excessive power consumption and high cost.As an alternative GPS, distance can be estimated through usage at least 3 with known locations.Received Signal Strength Indication (RSSI) simplest most inexpensive technique...
This article considers methodological approaches to determine and prevent social media manipulation specific Twitter. Behavioral analyses of Twitter users were performed by using their profile structures interaction types, classified according effect size values determining asset values. User profiles into three different categories, namely popular-active, observer-passive, spam-bot-malicious k-nearest neighbor (K-NN), support vector machine (SVM), artificial neural network (ANN) algorithms....
Abstract Urine sediment examination (USE) is an important issue in the detection of urinary system diseases and a prerequisite, especially diagnosis kidney diseases. The low‐contrast urine images contain many particles, these particles are superimposed or adherent, making it difficult to detect interpret particles. In this paper, YOLOv5‐based analysis system, which one fastest most successful architectures used for object detection, presented identify urine. artificial intelligence‐based can...
Obstructive sleep apnea (OSAS), which is one of the leading disorders and can result in death if not diagnosed treated early, most often confused with snoring. OSAS disease, prevalence varies between 0.9% 1.9% Turkey, a serious health problem that occurs as complete or partial obstruction respiratory tract during sleep, resulting disruption, poor quality paralysis even sleep. Polysomnography signal recordings (PSG) obtained from laboratories are used for diagnosis OSAS, related to factors...
The quality of randomness in numbers generated by true random number generators (TRNGs) depends on the source entropy. However, TRNGs, sources entropy are affected environmental changes and this creates a correlation between bit sequences. Postprocessing is required to remove problem created TRNGs. In study, an S-box-based postprocessing structure proposed as alternative structures seen published literature. A ring oscillator (RO)-based TRNG used demonstrate use S-box for removal...
Random numbers constitute the most important part of many applications and have a vital importance in security these applications, especially cryptography. Therefore, there is need for secure random to provide their security. This study concerned with development efficient number generator that primarily intended cryptographic applications. The consists two subsystems. first algorithmic structure, Keccak, which latest standard hash functions. structure provides generate numbers. second...
The present study aims to accurately classify estrus cycle by using images of the uterus from female rats.Convolutional neural network-based deep learning techniques were utilized for classification process.While human menstrual spans 28 days, in rats, it completes within 4-5 days.Female rats are particularly preferred studies related reproductive system due being a model organism.In study, sections stained with Hematoxylin and Eosin uterine tissue examined under light microscope, their...
Abstract Urine sediment examination (USE) is an essential aspect in detecting urinary system diseases, and it a prerequisite for diagnostic procedures. images are complex, containing numerous particles, which makes detailed analysis interpretation challenging. It crucial both patients medical professionals to conduct urine automatically, quickly inexpensively, without compromising reliability. In this paper, we present deep multi-modal fusion system, commonly employed artificial...
Nail capillaroscopic examination is an inexpensive and easily applicable method to identify capillary morphological changes in patients with conditions such as systemic sclerosis Raynaud's. The detection of capillaries makes important contribution diagnosing these diseases. Capillary morphology the symptoms diseases, diameter, visibility, distribution, length, microbleeds, blood flow, density are indicators evaluation. Manual determine parameters subjective, causes inconsistent results,...
Wireless sensor networks consist of many sensors designed to provide information flow from a specific area. Sensors communicate with each other and receive the environment. The obtained physical environment is carried into network In recent years, improvements in wireless have necessitated control, observation, data collection storage large areas. Especially crowded cities, it compulsory collect process on infrastructure, air pollution, traffic similar issues. Therefore, cities become smart...
Wireless sensor networks consist of many sensors designed to provide an information flow from a specific area.Sensors communicate with each other receive the physical environment they are in and transfer results electronic environment.In recent years, advances wireless have made it necessary control monitor large fields, collect store resulting data.In particular, is very important process data on infrastructure, air pollution, traffic similar issues crowded cities.The smart city structure...
By examining the change of eye movements during reading, it is possible to determine type document read.Returning previous position (negative saccade), blink, fixation, and are important indicators in determining being read.In this paper, a hybrid deep learning model proposed read.The MPIIDPEye dataset, which includes movement data 10-minute comic, newspaper text readings from 20 participants, was used.First, obtained over time were augmented by non-linear interpolation technique.In order...
Linear Feedback Shift Register (LFSR) is mostly used in the implementation of Pseudo Random Number Generator (PRNG). LFSR based on PRNG techniques are for many applications such as generating data, encryption keys and padding bits. Although a majority random number generators have been implemented software level, hardware becoming more popular due to advent faster high density Field Programmable Gate Arrays (FPGA). In this paper, we propose implementations FPGA Shrinking (SG) Alternating...
Random numbers are important parameters for the security of cryptographic applications. In this study, a secure and efficient generator is proposed to generate random numbers. The first part true number that consists chaotic systems implemented on FPGA. second post-processing algorithm used overcome problems emerge from or environmental factors. As algorithm, Keccak, latest standard hash was rearranged used. with approach meet requirements Furthermore, NIST 800-22 test suite autocorrelation...