Deok-Hwan Kim's research while affiliated with Inha University and other places

Publications (110)

Article
Full-text available
Abstract The human inner perception is the core technology for human‐robot interactions. Emotion recognition has been established as a representative study for recognising the internal state of human beings in addition to research regarding intention recognition. In the study of emotion recognition using EEG signals, emotion evaluation is categoris...
Article
Full-text available
Edge computing represents the future of computing paradigms that perform tasks near the user plane. The integration of blockchain with edge computing provides the added advantage of secured and trusted communication. In this paper, we propose a blockchain-based service migration by developing edge clusters using NVIDIA Jetson boards in an embedded...
Article
Full-text available
Federated learning (FL) is a distributed machine learning paradigm in which multiple clients collaboratively learn a global model without sharing local training data. This study presents an adaptive model selection algorithm to enhance existing aggregation for FL. The proposed method uses sparsely learned local models and adaptively selects the bes...
Article
Full-text available
Currently, the existing vehicle-centric semi-autonomous driving modules do not consider the driver's situation and emotions. In an autonomous driving environment, when changing to manual driving, human–machine interface and advanced driver assistance systems (ADAS) are essential to assist vehicle driving. This study proposes a human–machine interfa...
Article
This study aims to propose a novel approach for gender recognition using best feature subset based on recursive feature elimination (RFE) in normal walking. This study has focused on the analysis of gait characteristics by distinguishing the gait phases as initial contact (IC), Mid-stance (MS), Pre-swing, and swing (SW), and collected the large num...
Article
In cloud storage scenarios, each chunk with multiple symbols of a coding strip resides in a different node and, hence, on a different disk. Existing STAIR and sector-disk (SD) scheduling techniques are not scalable because the performance of existing STAIR and SD encoding and decoding schedulers decreases sharply as the number of parity disks incre...
Article
Full-text available
Recently, emerging edge computing technology has been proposed as a new paradigm that compensates for the disadvantages of the current cloud computing. In particular, edge computing is used for service applications with low latency while using local data. For this emerging technology, a neural network approach is required to run large-scale machine...
Article
In cloud storage scenarios, each chunk with multiple symbols of a coding strip resides in a different node and, hence, on a different disk. Existing STAIR and sector-disk (SD) scheduling techniques are not scalable because the performance of existing STAIR and SD encoding and decoding schedulers decreases sharply as the number of parity disks incre...
Article
Full-text available
The gradual increase in latency-sensitive, real-time applications for embedded systems encourages users to share sensor data simultaneously. Streamed sensor data have deficient performance. In this paper, we propose a new edge-based scheduling method with high-bandwidth for decreasing driver-profiling latency. The proposed multi-level memory schedu...
Conference Paper
Full-text available
This paper aims to propose a novel approach for gait phase recognition using an optimal feature subset based on recursive feature elimination. This study has collected a large number of gait data to improve the reliability of quantitative assessment of natural variability associated with muscle activity during free walking. The gait system was desi...
Article
Full-text available
Emotional awareness is vital for advanced interactions between humans and computer systems. This paper introduces a new multimodal dataset called MERTI-Apps based on Asian physiological signals and proposes a genetic algorithm (GA)—long short-term memory (LSTM) deep learning model to derive the active feature groups for emotion recognition. This st...
Article
Full-text available
This study focuses on driver-behavior identification and its application to finding embedded solutions in a connected car environment. We present a lightweight, end-to-end deep-learning framework for performing driver-behavior identification using in-vehicle controller area network (CAN-BUS) sensor data. The proposed method outperforms the state-of...
Article
Full-text available
Key-value stores based on a log-structured merge (LSM) tree have emerged in big data systems because of their scalability and reliability. An LSM-tree offers a multilevel data structure with a simple interface. However, it performs file rewrites at the disk level, which causes write amplification. This study is concerned with this problem in relati...
Article
Full-text available
Emotion recognition is a very important technique for ultimate interactions between human beings and artificial intelligence systems. For effective emotion recognition in a continuous-time domain, this article presents a multimodal fusion network which integrates video modality and electroencephalogram (EEG) modality networks. To calculate the atte...
Article
Long‐term electroencephalography (EEG) monitoring is time‐consuming, and re- quires experts to interpret EEG signals to detect seizures in patients. In this paper, we propose a novel automated method called adaptive slope of wavelet coefficient counts over various thresholds (ASCOT) to classify patient episodes as seizure wave- forms. ASCOT involve...
Article
Full-text available
A dynamic power management (DPM) method makes power-mode-related decisions based on the information available at runtime (online) or before (offline). This paper proposes energy-aware RAID scheduling methods to reduce energy consumption for distributed storage applications using both online and offline DPM strategies. The proposed energy-aware redu...
Article
This paper presents a gait sub-phase detection and prediction approach using surface electromyogram (sEMG) signals, pressure sensors, and the knee angle for a lower-limb power-assist robot. Pattern recognition and machine learning models using sEMG signals have several inherent problems for gait sub-phase detection. These problems are due to recogn...
Article
This paper presents a new method to remove baseline drift and noise by using a differential electrooculography (EOG) signal based on a fixation curve (DOSbFC) and a new electrode positioning scheme based on eyeglasses for user convenience. In addition, a desktop application and mobile applications to control the human–computer interface were implem...
Article
Full-text available
This paper proposes new GPU-accelerated high-performance encoding and decoding for hierarchical RAID in a multiple virtual machine environment. Pass-through GPU technology is used to provide dedicated access to GPU cores for each virtual machine, and for a virtual desktop, it also enables higher encoding and decoding performance than traditional vG...
Article
This study presents a gait subphase recognition method using an electromyogram (EMG) with a signal graph matching (ESGM) algorithm. Existing pattern recognition and machine learning using EMG signals has several innate problems in gait subphase detection. With respect to time domain features, their feature values may be analogous because two differ...
Article
Full-text available
With the recent big-data processing in multimedia devices becoming a popular application, a fast and energy efficient storage area network system for smart classroom is required. Traditional storage management system for smart classroom show low performance when small read and write operations are executed. This paper proposes a smart classroom sto...
Article
This letter presents lower-limb human motion detection using an surface electromyogram (sEMG) with a top and slope (TAS) feature extraction algorithm. Lower-limb human motion detection using sEMG signal is generally divided into gait sub-phase detection, locomotion mode recognition, and mode change detection. Existing feature extraction algorithms...
Conference Paper
According to the growth of the utilization of cloud computing, the required storage capacity is also increasing. The cloud computing services can allocate immediately storage volume according to user requirements, and cloud storage should be scalable. At the same time, cloud service providers have to minimize expenses by maximizing server resource...
Conference Paper
This paper presents a gait phase recognition method using an electromyogram (EMG) with a gait phase EMG signal (GPES) library and an integrated spectral matching filter (ISMF). Existing pattern recognition using an EMG signal has several innate problems in trying to control a gait assistant robot. The GPES library is robust against amplitude bias o...
Article
Object-based storage is an efficient storage solution that can handle unstructured data and shows better security and scalability than traditional block-based storage. However, in terms of power management, Object-based storage writes multiple copies in storage cluster, hence many servers consume unnecessary power in idle state. In order to resolve...
Article
This paper proposes a high-performance graphics processing unit (GPU)-based parity computing scheduler, which we call GPU-redundant array of inexpensive disks (RAID), to reduce the encoding and decoding time for storage applications. The proposed GPU-RAID differs from existing RAID in that it performs additional pairwise-parallel XOR operations bet...
Article
In recent years, the need to build solid state drive (SSD)-based cloud storage systems has been increasing in order to process the big data generated by lots of Internet of Things devices and Internet users. Because these kinds of cloud systems require high performance and reliable storage, the use of flash-based Redundant Array of Independent Disk...
Article
Recently, human identification using various biological signals has been studied and human identification based on the gait has been actively studied. In this paper, we propose a human identification based on the EMG(Electromyography) signal of the thigh muscles that are used when walking. Various features such as RMS, MAV, VAR, WAMP, ZC, SSC, IEMG...
Article
In this paper, we propose Korean monophthong recognition method optimizing muscle mixing based on facial surface EMG signals. We observed that EMG signal patterns and muscle activity may vary according to Korean monophthong pronunciation. We use RMS, VAR, MMAV1, MMAV2 which were shown high recognition accuracy in previous study and Cepstral Coeffic...
Article
Powered prosthesis is used to assist walking of people with an amputated lower limb and/or weak leg strength. The accurate gait phase classification is indispensable in smooth movement control of the powered prosthesis. In previous gait phase classification using physical sensors, there is limitation that powered prosthesis should be simulated as s...
Chapter
In this paper, we propose a new GPGPU based erasure codes encoding method using non-sparse coding vector. The proposed method can be applied to various erasure codes and efficiently utilize GPU cores and GPU memory by using non-sparse coding vector instead of large sparse coding matrix, and erasing multiplication operation and reducing unnecessary...
Article
User adaptive broadcasting service is a critical factor to implement ubiquitous computing for many clients and smart devices in the mobile environment. Service providers apply the user's preference to supply the user adaptive broadcasting service. However, in an error-prone environment, such as wireless networks, faults due to diverse conditions we...
Article
Cloud storage system uses a distributed file system for storing and managing data. Traditional distributed file system makes a triplication of data in order to restore data loss in disk failure. However, enforcing data replication method increases storage utilization and causes extra I/O operations during replication process. In this paper, we prop...
Article
This paper presents a new locomotion mode recognition method based on a transformed correlation feature analysis using an electromyography (EMG) pattern. Each movement is recognized using six weighted subcorrelation filters, which are applied to the correlation feature analysis through the use of six time-domain features. The proposed method has a...
Article
The identification of a certain input signal, f, starts with computing G by element-wise multiplication of F and H*. After this identification, the peak-to-sidelobe ratio (PSR) is applied to g, which is the inverse fast Fourier transform (FFT) of G. Variable PSR represents a simple measurement of peak strength, and the bigger its value is, the clos...
Conference Paper
Recently, there have been many studies to bionic leg to help rehabilitation of lower limb amputees. These powered artificial prosthesis uses physical sensors and repeats trained gait movements in correction process. Therefore, existing methods have to use equal gait speed and movement regardless of person's intention. To solve this problem, in this...
Conference Paper
This paper proposes an energy-aware XRM erasure codes for SSD based RAID storage systems. It removes many small random read and write operations and reduces the number of CPU cycles for encoding and decoding data. For doing this, we use adaptive chunking strategy and XRM(XOR Reference Matrix) rules. The preliminary experimental results show that th...
Conference Paper
Due to wide spread of smart devices, adopting video contents service to the diverse clients' device requirements is essential process. Accordingly, transcoding which is a lossy process is required and degrading video quality is inevitable. In such circumstances, minimizing perceptible quality loss is a key issue, while minimizing service cost is ke...
Article
In the recent cloud storage environment, the amount of SSD (Solid-State Drive) replacing with the traditional hard disk drive is increasing. Management of SSD for its space efficiency has become important since SSD provides fast IO performance due to no mechanical movement whereas it has wearable characteristics and does not provide in place update...
Article
NAND flash-based SSDs (Solid State Drive) have advantages of fast input/output performance and low power consumption so that they could be widely used as storages on tablet, desktop PC, smart-phone, and server. But, SSD has the disadvantage of wear-leveling due to increase of the number of writes. In order to improve the lifespan of the SSD, a vari...
Article
Smart home technologies are getting considerable attentions nowadays for better care of the residents, especially the elderly. One of the key technologies is the human activity recognition (HAR) system which automatically recognizes various indoor activities of a resident and reacts upon the needs of the resident, known as a proactive system. In th...
Article
RAID systems have been widely used by connecting several disks in parallel structure. to resolve the delay and bottleneck of data I/O. Recently, SSD based RAID systems are emerging since SSDs have better I/O performance than HDD. However, endurance and power consumption problems due to frequent write operation in SSD based RAID system should be res...
Article
SSD is a storage device of having high-performance controller and cache buffer and consists of many NAND flash memories. Because NAND flash memory does not support in-place update, valid pages are invalidated when update and erase operations are issued in file system and then invalid pages are completely deleted via garbage collection. However, gar...
Article
Original spectral features contain information pertinent to certain target spectral features. Without an efficient spectral feature extraction method, the target detection performance might be degraded. We present spectral feature extraction techniques based on the Fourier domain for use in target detection. These feature extraction methods are the...
Article
Adaptive services in pervasive environments are based on the correct detection of context. However, sensor malfunctions and inappropriate inference in regards to dynamic environments can lead to incorrect context detection that is unintended by the user. In addition, an appropriate context-aware method needs to be accurate even when environmental c...
Article
A new method of prefetching data blocks from the NVCache to the page cache in main memory and cascading prefetching n-blocks from a hard disk to the NVCache together was proposed to reduce the spin-up frequency of a hybrid hard disk drive and thus enhance I/O performance. The proposed method consists of three steps: 1) Analyzing the pattern of read...
Article
Multimedia devices are becoming smaller to enhance mobility, while users' demands for better Quality of Experience (QoE) are also increasing. In this paper, we present a method to increase QoE in small hand-held devices during the enjoyment of sports videos. Static objects are superimposed graphics such as score boxes, expository comments, or logos...
Article
In this paper we use the concept of co-design and human information system to suggest the doctors, colleagues and patients (DCP) social network that enables communication between clinics, doctors and patients; and among the doctors to improve the standard. We propose a DCP social network architecture based on the cloud computing and two algorithms....
Article
This paper presents an improved approach for periodic estimating the reliability and energy consumption of SSDs. The reliability estimation has been considered to enhance the energy efficiency on the SSD based RAID-6 system. We also present additional layered architecture for reliable energy-aware RAID-6 system. The proposed method mainly differs f...
Article
According to dissemination of appliance such as 3D TV and 3D games, visual fatigue estimation of 3D contents has been focused. EOG(Electro-ocular gram) is one of popular methods to measure the movement of the eye for visual fatigue estimation. However, voltage of EOG signal is depending on the eye shape or physiological state of the subject and its...
Article
In this paper, we propose a method to reduce spectral dimension based on the phase of integrated bispectrum. Because of the excellent and robust information extracted from the bispectrum, the proposed method can achieve high spectral classification accuracy even with low dimensional feature. The classification accuracy of bispectrum with one dimens...
Article
To evaluate the cardiac hypertrophy from chest radiograph images, radiologists usually examine the cardiothoracic ratio (frequently called CTR) which is a standard diagnostic index. The CTR is computed by the maximum transverse diameter of the heart shadow divided by the maximum transverse diameter of right and left lung boundaries. In this paper,...
Article
This paper proposes a novel descriptor, referred to as the localized angular phase (LAP), which is robust to illumination, scaling, and image blurring. LAP utilizes the phase information from the Fourier transform of the pixels in localized polar space with a fixed radius. The application examples of LAP are presented in terms of content-based imag...
Conference Paper
Rotation invariant texture descriptor plays an important role in texture-based object classification. However the classification accuracy may decrease due to the inconsistent performance of texture descriptor with respect to various rotated angles. In this paper we propose a consistent rotation invariant texture descriptor named Sorted Neighborhood...
Article
Recently, databases have been used to store multimedia data such as images, maps, video clips, and music clips. In order to search them, they should be represented by various features, which are composed of high-dimensional vectors. As a result, the dimensionality of data is increased considerably, which causes ‘the curse of dimensionality’. The in...
Article
Texture feature is one of most important feature analysis methods in the computer-aided diagnosis (CAD) systems for disease diagnosis. In this paper, we propose a Uniformity Estimation Method (UEM) for local brightness and structure to detect the pathological change in the chest CT images. Based on the characteristics of the chest CT images, we ext...
Conference Paper
This paper proposes an interest point detector based on wavelet transform as well as a descriptor based on image variation and log-polar coordinate. Taking advantage of the wavelet properties, the proposed method detects a small number of interest points that are distinctive and robust to the illumination changes, scale changes and affine transform...
Article
Defect inspection of polarised films is a crucial process in TFT-LCD (thin film transistor–liquid crystal display) production. In this paper we propose a defect inspection system for TFT-LCD film images that detects film defects in a real-time production environment and classifies them based on the type of a defect. The proposed system is designed...
Article
This paper describes a visual shape descriptor based on the sectors and shape context of contour lines to represent the image local features used for image matching. The proposed descriptor consists of two-component feature vectors. First, the local region is separated into sectors and their gradient magnitude and orientation values are extracted;...
Conference Paper
Full-text available
Recently solid state drive (SSD) based on NAND flash memory chips becomes popular in the consumer electronics market because it is tough on shock and its I/O performance is better than that of conventional hard disk drive. However, as the density of the semiconductor grows higher, the distance between its wires narrows down, their interferences are...
Article
As the multimedia contents market continues its rapid expansion, the amount of image contents used in mobile phone services, digital libraries, and catalog service is increasing remarkably. In spite of this rapid growth, users experience high levels of frustration when searching for the desired image. Even though new images are profitable to the se...
Conference Paper
In this paper, we propose an effective defect classification system for FDP (flat display panel) film images which are acquired in real production lines. A film image is segmented into a binary image with two non-overlapping regions: defect and non-defect regions. From the defect regions, various features are extracted such as brightness distributi...
Article
The flash memory has many advantages such as low power consumption, strong shock resistance, fast I/O and non-volatility. And it is increasingly used in the mobile storage device. The YAFFS, one of the NAND flash file system, is widely used in the embedded device. However, the existing YAFFS takes long time to mount the file system because it scans...
Article
Recently, NAND flash memory has emerged as a next generation storage device because it has several advantages, such as low power consumption, shock resistance, and so on. However, it is necessary to use a flash translation layer (FTL) to intermediate between NAND flash memory and conventional file systems because of the unique hardware characterist...
Article
The detection of the stable local image features is one of the most critical tasks for many object recognition algorithms. The Scale Invariant Feature Transform (SIFT) has been shown to be effective to the image matching or object recognition. However, the large number of features generated by the SIFT is a disadvantage for the real time applicatio...
Article
The gradient descent algorithms like backpropagation (BP) or its variations on multi-layered feed-forward networks are widely used in many applications. However, the most serious problem associated with the BP is local minima problem. Especially, an exceeding number of hidden nodes make the corresponding network deepen the local minima problem. We...
Article
We propose an effective voice-based gender identification method using a support vector machine (SVM). The SVM is a binary classification algorithm that classifies two groups by finding the voluntary nonlinear boundary in a feature space and is known to yield high classification performance. In the present work, we compare the identification perfor...
Conference Paper
This paper proposes a new document summarization method using relevance feedback (RF) and non-negative matrix factorization (NMF) to distill the contents of the documents with respect to a given query. The proposed method expands the query through relevance feedback to reflect user's requirement and extract meaningful sentences using the cosine sim...
Article
A new region filtering and region weighting method, which filters out unnecessary regions from images and learns region importance from the region size and the spatial location of regions in an image, is proposed based on region representations. It weights the regions optimally and improves the performance of the region-based retrieval system based...
Article
The advancement of information technology and the popularization of Internet has explosively increased the amount of multimedia contents. Therefore, the requirement of multimedia recommendation to satisfy a user's needs increases fastly. Up to now, CF is used to recommend general items and multimedia contents. However, general CF doesn't reflect vi...
Conference Paper
This paper presents a novel flash translation layer design that uses clustered hash tables and two-level software cache technique to adaptively switch logical address from the host system to physical address in flash memory. The experimental results show that the proposed address translation mechanism provides good performance in address mapping an...