A5003655177- Energy Efficient Wireless Sensor Networks
- Indoor and Outdoor Localization Technologies
- Data Management and Algorithms
- Optical Wireless Communication Technologies
- Smart Parking Systems Research
- Robotic Path Planning Algorithms
- Context-Aware Activity Recognition Systems
- Mobile Ad Hoc Networks
- Network Traffic and Congestion Control
- Parallel Computing and Optimization Techniques
- Building Energy and Comfort Optimization
- Energy Harvesting in Wireless Networks
- Water Quality Monitoring Technologies
- Advanced Wireless Network Optimization
- Internet of Things and Social Network Interactions
- Underwater Vehicles and Communication Systems
- Image Retrieval and Classification Techniques
- Wireless Networks and Protocols
- Opportunistic and Delay-Tolerant Networks
- Error Correcting Code Techniques
- Mobile and Web Applications
- Traffic Prediction and Management Techniques
- Advanced Neural Network Applications
- Advanced Wireless Communication Techniques
- Image Enhancement Techniques
Sangmyung University
2014-2025
Samsung (South Korea)
2003-2021
Incheon National University
2015
Sookmyung Women's University
2011-2012
Sungkyunkwan University
2008
University of California, Los Angeles
2002-2007
Embedded Systems (United States)
2003-2007
The recent advances in MEMS, embedded systems and wireless communication technologies are making the realization deployment of networked microsensors a tangible task. Vital to success microsensor networks is ability ``collectively perform sensing computation''. In this paper, we study one fundamental challenges sensor networks, node localization. collaborative multilateration presented here, enables ad-hoc deployed nodes accurately estimate their locations by using known beacon that several...
Recognizing and classifying traffic signs is a challenging task that can significantly improve road safety. Deep neural networks have achieved impressive results in various applications, including object identification automatic recognition of signs. These deep network-based sign systems may limitations practical applications due to their computational requirements resource consumption. To address this issue, paper presents lightweight network for achieves high accuracy precision with fewer...
In the domain of radiological diagnostics, accurately detecting and classifying brain tumors from magnetic resonance imaging (MRI) scans presents significant challenges, primarily due to complex diverse manifestations in these scans. this paper, a convolutional-block-based architecture has been proposed for detection multiclass using MRI Leveraging strengths CNNs, our framework demonstrates robustness efficiency distinguishing between different tumor types. Extensive evaluations on three...
We present the design and implementation of Illuminator, a preliminary sensor network-based intelligent light control system for entertainment media production. Unlike most network applications, which focus on sensing alone, distinctive aspect Illuminator is that it closes loop from to lighting control. describe Illuminator's requirements, architecture, algorithms, experimental results. To satisfy high-performance requirements production uses Illumimote, multi-modal high fidelity module...
Traffic Sign Recognition (TSR) plays a vital role in intelligent transportation systems (ITS) to improve road safety and optimize traffic management. While existing TSR models perform well challenging scenarios, their lack of transparency interpretability hinders reliability, trustworthiness, validation, bias identification. To address this issue, we propose Convolutional Neural Network (CNN)-based model for evaluate its performance on three benchmark datasets: German Benchmark (GTSRB),...
Due to the fact that all services today are transmitted over internet, they have become easier use and more affordable. One such service is VoIP. This research focuses on statistical analysis of VoIP user traffic with G.711 codec its variants (G.723, G.729). Data was provided by Intelligent Technology Partner LLC, a company offering in Mongolia. The results this compared theoretical distribution inter-arrival time (the between packets). Additionally, other parameters for simulation defined...
Accurately detecting and classifying brain tumors in magnetic resonance imaging (MRI) scans poses formidable challenges, stemming from the heterogeneous presentation of need for reliable, real-time diagnostic outputs. In this paper, we propose a novel multi-path convolutional architecture enhanced with channel-wise attention mechanisms, evaluated on comprehensive four-class tumor dataset. Specifically: (i) design parallel feature extraction strategy that captures nuanced morphologies, while...
The recent advances in MEMS, embedded systems and wireless communication technologies are making the realization deployment of networked microsensors a tangible task. Vital to success microsensor networks is ability “collectively perform sensing computation”. In this paper, we study one fundamental challenges sensor networks, node localization. collaborative multilateration presented here, enables ad-hoc deployed nodes accurately estimate their locations by using known beacon that several...
The early detection of wildfires is a crucial challenge in environmental monitoring, pivotal for effective disaster management and ecological conservation. Traditional methods often fail to detect fires accurately timely manner, resulting significant adverse consequences. This paper presents FireXplainNet, Convolutional Neural Network (CNN) base model, designed specifically address these limitations through enhanced efficiency precision wildfire detection. We optimized data input via...
As pixel size of image sensors shrinks down rapidly, we are reaching technical barrier to get the required low light performance. In this paper, recent advanced technologies such as backside illumination, new color filter array, F-number with extended depth field technologies, etc. introduced overcome a barrier. It is shown that integration these sensor can make shrink toward 1.0 mum
We present the design and implementation of Illuminator, a preliminary sensor network-based intelligent light control system for entertainment media production. Unlike most network applications, which focus on sensing alone, distinctive aspect Illuminator is that it closes loop from to lighting control. describe Illuminator's requirements, architecture, algorithms, experimental results. To satisfy high-performance requirements production uses Illumimote, multi-modal high fidelity module...
We present the design and implementation of a unique sensing actuation application --the Illuminator: sensor network-based intelligent light control system for entertainment media production.Unlike most network applications, which focus on alone, distinctive aspect Illuminator is that it closes loop from to lighting control.We describe Illuminator's requirements, architecture, algorithms, experimental results.The uses Illumimote, multi-modal high fidelity module well-suited wireless...
We explored the problems which are soon to be faced while parking autonomous cars in lots. Like where is closest slot available car? How navigate that location? What kind of structures could good for cars? also provide an initial solution uses a central server and graph lot guide slots. With experiments, we have shown our proposed method should effective controlled self-driving cars.
We present a long-term and cross-sectional study of vibration-based water flow rate monitoring system in practical environments scenarios. In our earlier research, we proved that with vibration sensors is feasible by deploying evaluating it small-scale laboratory setting. To validate the proposed system, was deployed existing environments—two houses public restroom—and two different test settings. With collected data, first demonstrate various aspects system's performance, including sensing...
We describe the system requirements, design, integration, and performance evaluation of Illumimote, a new light-sensing module for wireless sensor networks. The Illumimote supports three different modalities: incident light intensity, color intensities, angle (the ray arrival from strongest source); two situational sensing attitude temperature. achieves high performance, comparable to commercial meters, while conforming size energy constraints imposed by its application in evaluated our...
Air pollution has become a global issue due to its widespread impact on the environment, economy, civilization and human health. Owing this, lot of research studies have been done tackle this issue. However, most existing methodologies several issues such as high cost, low deployment, maintenance capabilities uni-or bi-variate concentration air pollutants. In paper, hybrid CNN-LSTM model is presented forecast multivariate pollutant for Internet Things (IoT) enabled smart city design. The...
Energy consumption of sensor networks are largely affected by task assignments to the nodes in network. In this paper, a assignment method improve performance wireless networks, which exploits decompositions and transformation, is presented. The formulated as an optimization problem providing cost function incorporating decomposition transformation at same time. To show feasibility our proposed method, simulated annealing approach adopted. simulation results that elaborate can significantly...
In this paper, we present design and implementation of a New FAT file system (NFAT) for mobile multimedia devices. Conventional which has been used personal computers is the it still adopted most current portable The major problem overhead due to cluster switching involves retrieving updating connection information saved on allocation table. Because overhead, response time read write operation cannot be guaranteed in FAT. This paper proposes NFAT guarantees expected by reducing when reads...
The Baculovirus Expression Vector System (BEVS) is a very popular expression vector system in gene engineering. An effective host cell line cultivation protocol can facilitate the baculovirus preparation and following experiments. However, counting of number cells usually performed by manual observation with microscopy, which time consuming labor intensive work, prone to errors for one person or between different individuals. This study aims at giving bright field insect help improve...