• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.213-221
• /
• 2012

In this paper, a dynamic power management system is proposed to reduce energy consumption for multiple clients in cloud computing environments. The proposed system monitors both keyboard and mouse input from the user, available memory, and CPU usage in the virtual machine. If the system detects no keyboard and mouse input for a certain amount of time and both available memory and CPU usage reach predefined threshold value, the manager in the virtual machine orders the client to shutdown the client machine, which results in significant power save. The developed system is applied to the real university computer lab and the performance of the system is evaluated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.7
• /
• pp.2914-2935
• /
• 2016

With the increasing popularization of cloud computing, how to reduce physical energy consumption and increase resource utilization while maintaining system performance has become a research hotspot of virtual machine deployment in cloud platform. Although some related researches have been reported to solve this problem, most of them used the traditional heuristic algorithm based on greedy algorithm and only considered effect of single-dimensional resource (CPU or Memory) on energy consumption. With considerations to multi-dimensional resource utilization, this paper analyzed impact of multi-dimensional resources on energy consumption of cloud computation. A multi-dimensional resource constraint that could maintain normal system operation was proposed. Later, a novel virtual machine deployment method (NVMDM) based on improved particle swarm optimization (IPSO) and Euclidean distance was put forward. It deals with problems like how to generate the initial particle swarm through the improved first-fit algorithm based on resource constraint (IFFABRC), how to define measure standard of credibility of individual and global optimal solutions of particles by combining with Bayesian transform, and how to define fitness function of particle swarm according to the multi-dimensional resource constraint relationship. The proposed NVMDM was proved superior to existing heuristic algorithm in developing performances of physical machines. It could improve utilization of CPU, memory, disk and bandwidth effectively and control task execution time of users within the range of resource constraint.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.85-91
• /
• 2021

In our daily life, artificial intelligence performs simple and complicated tasks like us, including operating mobile phones and working at homes and workplaces. Artificial intelligence is used in industrial technology for diagnosing various types of equipment using the machine learning technology. This study presents a fault mode effect analysis (FMEA) of start motors using machine learning and big data. Through multiple data collection, we observed that the primary failure of the start motor was caused by the melting of the magnetic switch inside the start motor causing it to fail. Long-short-term memory (LSTM) was used to diagnose the condition of the magnetic locations, and synthetic data were generated using the synthetic minority oversampling technique (SMOTE). This technique has the advantage of increasing the data accuracy. LSTM can also predict a start motor failure.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.281-287
• /
• 2008

Data transfers occur during the execution time of a Java program, from constant to variable, from variable to other variable and so on. Data are located in memory and hence data transfer requires access to memory. As memory access generates both time delay and energy consumption it is absolutely necessary to know the data transfer overheads incurred among different paths not only to write an efficient program but also to build a high-performance Java virtual machine. In this paper we classify Java memory into three different regions, constant, local variable, and field, and then investigate data transfer overheads among these regions. The result says that the transfer between local variables incur the least overhead usually, while the transfer between fields incur the most. The difference of overheads reaches up to a double. Optimization techniques like JIT reduces the data transfer overhead dramatically. It is observed that the overhead is reduced from 14 to 27 times for the case of Hotspot JVM.

• Journal of KIISE:Software and Applications
• /
• v.34 no.6
• /
• pp.562-571
• /
• 2007

Various researches had been devoted in purpose of improving memory management in terms of performance, efficiency, ease of use, and safety. One of these approaches is a region-based memory management. Each allocation site selects a specific region, after that allocated objects are placed in this region. Memory is reclaimed by destroying the region, freeing all the objects allocated therein. In this paper, we propose reusing of local regions to reduce heap memory usage in memory-limited environments. The basic idea of this proposal is reusing of upper local regions where objects that are allocated to these regions are not accessed until the current method is finished. We believe our method of reusing local regions is able to overcome memory constraints in memory-limited environments.

• The KIPS Transactions:PartA
• /
• v.10A no.4
• /
• pp.397-404
• /
• 2003

Dedicated-purpose embedded Java system usually takes such model that all class files are converted into a single ROM Image by the ROMizer in the host computer, and then the Java virtual machine in the embedded system executes the image. Defining the ROM Image is a very important issue for embedded system with limited memory resource and low-performance processor since the format directly influences on the memory usage and effectiveness of accessing entries in classes. In this paper we have analyzed the ROMizer and especially the format of the ROM image implemented in the simpleRTJ embedded Jana virtual machine. The analysis says that memory space can be saved up to 50% compared to the original class file and access speed exceeds up to six times with the use of the ROMizer. The result of this study will be applied to develop a more efficient ROMizer for a ROM-based embedded Java system.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.581-594
• /
• 2021

Purpose: The purpose of this study is to compare machine learning models for anomaly detection of mechanical facility equipment and suggest an anomaly detection system for mechanical facility equipment in subway stations. It helps to predict failures and plan the maintenance of facility. Ultimately it aims to improve the quality of facility equipment. Methods: The data collected from Daejeon Metropolitan Rapid Transit Corporation was used in this experiment. The experiment was performed using Python, Scikit-learn, tensorflow 2.0 for preprocessing and machine learning. Also it was conducted in two failure states of the equipment. We compared and analyzed five unsupervised machine learning models focused on model Long Short-Term Memory Variational Autoencoder(LSTM-VAE). Results: In both experiments, change in vibration and current data was observed when there is a defect. When the rotating body failure was happened, the magnitude of vibration has increased but current has decreased. In situation of axis alignment failure, both of vibration and current have increased. In addition, model LSTM-VAE showed superior accuracy than the other four base-line models. Conclusion: According to the results, model LSTM-VAE showed outstanding performance with more than 97% of accuracy in the experiments. Thus, the quality of mechanical facility equipment will be improved if the proposed anomaly detection system is established with this model used.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• Proceedings of the KIPE Conference
• /
• 1998.11a
• /
• pp.5-8
• /
• 1998

The adaptation to vector control theory is so generalized that it is widely used for implementing the high-performance of AC machine. Nowadays, One-Chip microprocessors or DSP chips are being well-used to implement Vector Control algorithm. DSP Chip have less flexibility for memory decoding and I/O rather than One-Chip microprocessor so that is requires more additional circuit and high cost. And the past One-Chip micro processors have difficult of implementation the complex algorithm because of small memory capacity and low arithmetic performance. Therefore we implemented the vector control algorithm of PMSM(Permanent Magnetic Synchronous Motors) using 80296SA form intel , which have many features as 6M memory space, 500MHz clock frequency, including memory decoding circuit and general I/O, Special I/O(EPA, Interrupt controller, Timer/Count, PWM generator) which is proper controller for the complex algorithm or operation program requiring so much memory capacity, So in this paper we fully digitized the vector control of PMSM included SVPWM Voltage controller using the intel 80296SA

• Journal of Information Technology Services
• /
• v.8 no.4
• /
• pp.129-140
• /
• 2009

The accurate estimation of software reliability is important to a successful development in software engineering. Until recent days, the models using regression analysis based on statistical algorithm and machine learning method have been used. However, this paper estimates the software reliability using support vector regression, a sort of machine learning technique. Also, it finds the best set of optimized parameters applying immune algorithm, changing the number of generations, memory cells, and allele. The proposed IA-SVR model outperforms some recent results reported in the literature.