A5014148140- Quantum Computing Algorithms and Architecture
- Anomaly Detection Techniques and Applications
- Stock Market Forecasting Methods
- Smart Grid Security and Resilience
- Electricity Theft Detection Techniques
- Advancements in Semiconductor Devices and Circuit Design
- Machine Fault Diagnosis Techniques
- Neural Networks and Reservoir Computing
- Sensor Technology and Measurement Systems
- Visual Attention and Saliency Detection
- Machine Learning and ELM
- Magnetic Field Sensors Techniques
- Non-Destructive Testing Techniques
- Image Enhancement Techniques
- Machine Learning in Materials Science
- Energy Harvesting in Wireless Networks
- Advanced Image and Video Retrieval Techniques
- Advanced Battery Technologies Research
- Network Security and Intrusion Detection
Pukyong National University
2022-2024
Convergence
2022
Image denoising is essential for removing noise in images caused by electric device malfunctions or other factors during image acquisition. It helps preserve quality and interpretation. Many convolutional autoencoder algorithms have proven effective denoising. Owing to their promising efficiency, quantum computers gained popularity. This study introduces a (QCAE) method improved was developed substituting the representative latent space of with circuit. To enhance we leveraged advantages...
Portfolio optimization is a primary component of the decision-making process in finance, aiming to tactfully allocate assets achieve optimal returns while considering various constraints. Herein, we proposed method that uses knapsack-based portfolio problem and incorporates quantum computing capabilities walk mixer with approximate algorithm (QAOA) address challenges presented by NP-hard problem. Additionally, present sequential procedure our suggested approach demonstrate empirical proof...
Electric power steering (EPS) has emerged as a valuable driver-assistance system. In an EPS system, extensive amount of data collected from various sensors is analyzed to enhance the driving experience. Anomaly detection techniques have shown potential in ensuring integrity patterns and detecting abnormalities prevent adverse incidents, thus improving vehicle safety. However, traditional centralized anomaly methods require collection all sensors, resulting high communication network...
As anomaly detection for electrical power steering (EPS) systems has been centralized using model- and knowledge-based approaches, EPS system have become complex more sophisticated, thereby requiring enhanced reliability safety. Since most current methods rely on prior knowledge, it is difficult to identify new or previously unknown anomalies. In this paper, we propose a deep learning approach that consists of two-stage process an autoencoder long short-term memory (LSTM) detect anomalies in...
The growing use of Internet-of-Things devices in electric power systems has resulted increased complexity and flexibility, making monitoring usage critical for effective system maintenance detecting abnormal behavior. However, traditional anomalous consumption detection methods struggle to handle the vast amounts data generated by these devices. While deep learning machine are anomaly detection, they require significant training collected on centralized servers. This approach results high...
The electric vehicle (EV) industry is currently afflicted with inefficient charging systems. Considering the growing adoption of EVs, optimization strategies for efficient charging, and overcoming constraints such as limited power supply extended waiting times, are required. knapsack algorithm, a classical technique that maximizes value capacity, enables utilization available while minimizing times in EV scenarios. However, problem notoriously NP-hard, making it difficult to find solutions...
Image denoising is essential for removing noise in images caused by electric device malfunctions or other factors during image acquisition. It helps preserve quality and interpretation. Many convolutional autoencoder algorithms have proven effective denoising. Owing to their promising efficiency, quantum computers gained popularity. This study introduces a (QCAE) method improved was developed substituting the representative latent space of with circuit. To enhance we leveraged advantages...
The stock markets have become a popular topic within machine learning (ML) communities, with one particular application being price prediction. However, accurately predicting the market is challenging task due to various factors financial markets. With introduction of ML, prediction techniques more efficient but computationally demanding for classical computers. Given rise quantum computing (QC), which holds great promise exponentially faster than current computers, it natural explore ML QC...
Foveated rendering emulates human vision by prioritizing sharpness at the center while introducing peripheral blur outside this central area. We explore its potential for enhancing object detection performance integrating it into various methods. Our investigation demonstrates that foveated effectively reduces time and false alarm detections, thus showcasing utility in improving performance. Experimental results indicate a reduction of up to 20% compared with using conventional techniques.
This paper presents a magnetic Hall sensor for current sensing in standard CMOS process, which that does not include any special fabrication process steps the implementation. Based on measurement results previously fabricated device, we employ square-shaped plate as device and design novel bridge instrumentation amplifier with chopping auto-zero functions. The prototype of is implemented 180 nm die area <tex xmlns:mml="http://www.w3.org/1998/Math/MathML"...