Hyunjin Kim

Total Energy Minimization of Real-Time Tasks in an On-Chip Multiprocessor Using Dynamic Voltage Scaling Efficiency Metric

This paper proposes an algorithm that provides both dynamic voltage scaling and power shutdown to minimize the total energy consumption of an application executed on an on-chip multiprocessor. The proposed algorithm provides an extended schedule and stretch method, where task computations are iteratively stretched within the slack of a time-constrained dependent task set. In addition, the break-even threshold interval for amortizing the shutdown overhead is considered. By evaluating each set of stretched task computations, an energy-efficient set is obtained. The proposed dynamic voltage scaling efficiency metric is the ratio of the reduced energy to the increased cycle time when the supply voltage is scaled, which can be used to determine the task computation cycle to be stretched. Experimental results show that the proposed algorithm outperforms the traditional schedule and stretch method in the various evaluations of target real applications.

Communication-aware task scheduling and voltage selection for total energy minimization in a multiprocessor system using Ant Colony Optimization

Energy consumption is a key parameter when highly computational tasks should be performed in a multiprocessor system. In this case, in order to reduce total energy consumption, task scheduling and low-power methodology should be combined in an efficient way. This paper proposes an algorithm for off-line communication-aware task scheduling and voltage selection using Ant Colony Optimization. The proposed algorithm minimizes total energy consumption of an application executing on a homogeneous multiprocessor system. The artificial agents explore the search space based on stochastic decision-making using global heuristic information with total energy consumption and local heuristic information with interprocessor communication volume. In search space exploration, both voltage selection and the dependencies between tasks are considered. The pheromone trails are updated by normalizing the total energy consumption. The pheromone trails represent the global heuristic information in order to utilize all entire energy consumption information from previous evaluated solutions. Experimental results show that the proposed algorithm outperforms traditional communication-aware task scheduling and task scheduling using genetic algorithms in terms of total energy consumption.

LGscore: A method to identify disease-related genes using biological literature and Google data

Since the genome project in 1990s, a number of studies associated with genes have been conducted and researchers have confirmed that genes are involved in disease. For this reason, the identification of the relationships between diseases and genes is important in biology. We propose a method called LGscore, which identifies disease-related genes using Google data and literature data. To implement this method, first, we construct a disease-related gene network using text-mining results. We then extract gene-gene interactions based on co-occurrences in abstract data obtained from PubMed, and calculate the weights of edges in the gene network by means of Z-scoring. The weights contain two values: the frequency and the Google search results. The frequency value is extracted from literature data, and the Google search result is obtained using Google. We assign a score to each gene through a network analysis. We assume that genes with a large number of links and numerous Google search results and frequency values are more likely to be involved in disease. For validation, we investigated the top 20 inferred genes for five different diseases using answer sets. The answer sets comprised six databases that contain information on disease-gene relationships. We identified a significant number of disease-related genes as well as candidate genes for Alzheimers disease, diabetes, colon cancer, lung cancer, and prostate cancer. Our method was up to 40% more accurate than existing methods.

A memory-efficient parallel string matching for intrusion detection systems

As the variety of hazardous packet payload contents increases, the intrusion detection system (IDS) should be able to detect numerous patterns in real time. For this reason, this paper proposes an Aho-Corasick algorithm based parallel string matching. In order to balance memory usage between homogeneous finite-state machine (FSM) tiles for each string matcher, an optimal set of bit position groups is determined. Target patterns are sorted by binary-reflected gray code (BRGC), which reduces bit transitions in patterns mapped onto a string matcher. In the evaluations of Snort rules, the proposed string matching outperforms the existing bit-split string matching.

A Lossless Color Image Compression Architecture Using a Parallel Golomb-Rice Hardware CODEC

In this paper, a high performance lossless color image compression and decompression architecture to reduce both memory requirement and bandwidth is proposed. The proposed architecture consists of differential-differential pulse coded modulation (DDPCM) and Golomb-Rice coding. The original image frame is organized as m by n sub-window arrays, to which DDPCM is applied to produce one seed and m × n - 1 pieces of differential data. Then the differential data are encoded using the Golomb-Rice algorithm to produce losslessly compressed data. According to the experimental results on benchmark images, the proposed architecture can guarantee high enough compression rate and throughput to perform real-time lossless CODEC operations with a reasonable hardware area.

Integrative gene network construction to analyze cancer recurrence using semi-supervised learning.

Background The prognosis of cancer recurrence is an important research area in bioinformatics and is challenging due to the small sample sizes compared to the vast number of genes. There have been several attempts to predict cancer recurrence. Most studies employed a supervised approach, which uses only a few labeled samples. Semi-supervised learning can be a great alternative to solve this problem. There have been few attempts based on manifold assumptions to reveal the detailed roles of identified cancer genes in recurrence. Results In order to predict cancer recurrence, we proposed a novel semi-supervised learning algorithm based on a graph regularization approach. We transformed the gene expression data into a graph structure for semi-supervised learning and integrated protein interaction data with the gene expression data to select functionally-related gene pairs. Then, we predicted the recurrence of cancer by applying a regularization approach to the constructed graph containing both labeled and unlabeled nodes. Conclusions The average improvement rate of accuracy for three different cancer datasets was 24.9% compared to existing supervised and semi-supervised methods. We performed functional enrichment on the gene networks used for learning. We identified that those gene networks are significantly associated with cancer-recurrence-related biological functions. Our algorithm was developed with standard C++ and is available in Linux and MS Windows formats in the STL library. The executable program is freely available at: http://embio.yonsei.ac.kr/~Park/ssl.php.

A hardware-efficent multi-character string matching architecture using brute-force algorithm

Due to the growth of network environment complexity, the necessity of packet payload inspection at application layer is increased. String matching, which is critical to network intrusions detection systems, inspects packet payloads and detects malicious network attacks using a set of rules. Because string matching is a computationally intensive task, hardware based string matching is required. In this paper, we propose a hardware-efficient string matching architecture using the brute-force algorithm. A process element that organizes the proposed architecture is optimized by reducing the number of the comparators. The performance of the proposed architecture is nearly equal to a previous work. The experimental results show that the proposed architecture with any process width reduces the comparator requirements in comparison with the previous work.

At-speed boundary-scan interconnect testing in a board with multiple system clocks

As an at-speed solution to board-level interconnect testing, an enhanced boundary-scan architecture utilizing a combination of slightly modified boundary-scan cells and a user-defined register is proposed. Test methods based on the new architecture can accomplish cost-effective at-speed testing and propagation delay measurements on board-level interconnects. Particularly when the board under test has multiple domains of interconnects controlled by different clock speeds, our at-speed solution is much more efficient than other previous works.

A Pipelined Non-Deterministic Finite Automaton-Based String Matching Scheme Using Merged State Transitions in an FPGA

This paper proposes a pipelined non-deterministic finite automaton (NFA)-based string matching scheme using field programmable gate array (FPGA) implementation. The characteristics of the NFA such as shared common prefixes and no failure transitions are considered in the proposed scheme. In the implementation of the automaton-based string matching using an FPGA, each state transition is implemented with a look-up table (LUT) for the combinational logic circuit between registers. In addition, multiple state transitions between stages can be performed in a pipelined fashion. In this paper, it is proposed that multiple one-to-one state transitions, called merged state transitions, can be performed with an LUT. By cutting down the number of used LUTs for implementing state transitions, the hardware overhead of combinational logic circuits is greatly reduced in the proposed pipelined NFA-based string matching scheme.

Relationship between theta-phase gamma-amplitude coupling and attention-deficit/hyperactivity behavior in children

The Continuous Performance Test (CPT) is a valuable tool for assessing behavior in attention-deficit/hyperactivity disorder (ADHD). Quantitative electroencephalography (QEEG) is a promising tool for the diagnosis of ADHD. Recently, theta-phase gamma-amplitude coupling (TGC) measurement has received attention because it is a feasible method of assessing brain function. We investigated the relationship between CPT performance and EEG measures such as TGC and theta and gamma activity. EEGs were recorded from 68 volunteers from a camp for hyperactive children using a 19-electrode system. Their TGC, theta and 40 Hz gamma activity were estimated and compared with results obtained on the Korean ADHD Rating Scale (KARS) and the Intermediate Visual and Auditory (IVA) CPT. The results demonstrated significant negative partial correlations between TGC and the IVA CPT, such as the Response Control Quotient (RCQ) and Attention Quotient (AQ). TGC successfully identified the level of dysfunctional interaction of the attention/arousal system at a multi-scale large network level. It is thought that as the TGC increases, the efficacy of the system is very low or dysfunctional. Compensatory hyper-arousal patterns of the dysfunctional attention/arousal system may account for this effect. TGC is a promising neurophysiological marker for ADHD behavior in children.