Vol. 49, No. 5,
May 2022
Digital Library
Design and Implementation of a Concurrency Error Detection Method for Embedded Software Using Machine Learning
Dongeon Lee, Jiwon Kim, Junghun Jin, Kyutae Cho
http://doi.org/10.5626/JOK.2022.49.5.327
Unlike general-purpose software, embedded software is designed by optimizing hardware for a specific purpose, so it is important to satisfy the target performance in a limited environment. Embedded software is increasing significantly in scale and complexity compared to the past. As the scale and complexity increase, the types of errors that occur in the software also diversify. Among them, there are many issues regarding concurrency errors that may occur between complex software modules. To detect concurrency errors in such embedded software, we have previously relied on manual input from the user. However, in this study, we propose a machine learning-based concurrency error detection tool (MCED) using SVM and deep learning.
Current Research Trends in Attacking Deep Learning Using Adversarial Examples
http://doi.org/10.5626/JOK.2022.49.5.339
Despite its great success, deep learning is largely vulnerable to attacks by adversarial examples. An attack by an adversarial example is a technique that deceives a well-trained deep learning model by adding noise to the normal input that is small enough to be invisible to the human eye. Such vulnerabilities in safe-critical systems, such as autonomous cars, can cause catastrophic failures and results such as traffic accidents. Although such attacks using adversarial examples with high potential risk are being actively studied worldwide, there is still a lack of systematic summaries on this in the Korean academic community. Therefore, in this paper, we systematically summarized recent trends in adversarial attacks on deep learning to boost future research.
Information Collection of COVID-19 Pandemic Using Wikipedia Template Network
Danu Kim, Damin Lee, Jaehyeon Myung, Changwook Jung, Inho Hong, Diego Sáez-Trumper, Jinhyuk Yun, Woo-Sung Jung, Meeyoung Cha
http://doi.org/10.5626/JOK.2022.49.5.347
Access to accurate information is essential to reduce the social damage caused by the Coronavirus Disease 2019 (COVID-19) pandemic. Information about ongoing events, such as COVID-19, is quickly updated on Wikipedia, an accessible internet encyclopedia that allows users to edit it themselves. However, the existing Wikipedia information retrieval method has a limitation in collecting information, including relationships between documents. The template format of Wikipedia reflects the structure of information as a link that is selectively applied to documents with high relevance. This study collected information on COVID-19 in 10 languages on Wikipedia using a template and reorganized it into networks. Among the 10 networks with 130,662 nodes and 202,258 edges, languages with a large number of active users had a template network with a large size and depth, and documents highly related to COVID-19 existed within a 3-hop connection structure. This research proposed a new information retrieval method applicable to multiple languages and contributes to the construction of document lists related to specific topics.
An Autism Spectrum Disorder Detection System Based on Learning Dynamic Connectivity of the Superior Temporal Sulcus
Kyoung-Won Park, Seok-Jun Bu, Sung-Bae Cho
http://doi.org/10.5626/JOK.2022.49.5.354
Considering a hypothesis that abnormalities in the superior temporal sulcus (STS) connected with visual cortex regions can be a critical sign of ASD, autism spectrum disorder, a model is required to exploit the brain functional connectivity between the STS and visual cortex to reinforce the neurobiological evidence. This paper proposes a deep learning model comprising attention and convolutional recurrent neural networks that can select and extract the time-series pattern of dynamic connectivity between the two regions within the brain based on observations. By integration of the extracted autism disorder features from dynamic connectivity through attention with the structure containing interlayer connections to preserve the functional connectivity loss within a neural network, the model extracts the connectivity between the STS and visual cortex, leading to an increase in generalization performance. A 10-fold cross-validation to compare the performance shows that the proposed model outperforms the state-of-the-art models by achieving an improvement of 4.90% in the ASD classification. Additionally, we use the proposed method to diagnose ASD by visualizing dynamic brain connectivity of the neural network layers.
SVD-based Cross-Domain Recommendation Using K-means Clustering
http://doi.org/10.5626/JOK.2022.49.5.360
Cross-domain recommendation is a method that shares related user information data and item data in different domains. It is mainly used in online shopping malls with many users or multimedia service contents, such as YouTube or Netflix. Through K-means Clustering, embeddings are created by performing clustering based on user data and ratings. After learning the result through a multi-layer neural network, user satisfaction is predicted. Then, items suitable for the user are recommended using matrix factorization, which is a collaborative filtering technique. Through this study, it was shown through experiments that recommendations can predict cold-start problems at a lesser time cost and increase the user satisfaction.
Radar Signal Processor for High-Resolution Target Detection
http://doi.org/10.5626/JOK.2022.49.5.369
Recently, as the technology of multi-function radar is developed, the radar deception technology of ballistic missiles is also developing. For some ballistic missiles, the propellant explodes in the air after the stage is separated, causing the warhead and many fragments to fly together, which lowers the multi-function radar’s ability to engage ballistic missiles. Thus, there is a need for a radar system capable of operating a broadband waveform to intercept a warhead, by quickly discriminating between a high-speed warhead and fragments while retaining the existing target detection/tracking function. It is possible to find and intercept warhead among fragments by extracting the length of a target, using a broadband waveform and performing warhead classification using this. In this paper, we describe the process of performing the target detection/tracking function using a narrowband waveform such as doppler processing, pulse compression, threshold processing, and target processing and high-resolution target length extraction and phase diffraction correction for accurate length extraction using a wideband waveform to create a radar system that satisfies these requirements. Also, it shows the results of designing and implementing these functions with signal processing software and performing tests.
Motor Imagery Decoding with Residual Dense Network
Permana Deny, Sae Won Cheon, Kae Won Choi
http://doi.org/10.5626/JOK.2022.49.5.380
This article proposes a Residual Dense Network (RDN) framework for brain signals during motor imagery (MI) decoding. We designed a decoding framework including feature extraction and a decoding algorithm built on a deep neural network to perform feature learning and decision making. We analyzed the capability of the RDN to decode a public BCI dataset from BCI Competition IV Dataset 2A. Experiments were conducted to evaluate the capability in terms of the performance accuracy for a given dataset and showed that the RDN framework achieved a result of 0.8290, outperforming the previous study using the same dataset benchmark. In conclusion, the RDN provided a decoding framework in a practical brain-computer interface.
Database Tuning Techniques to Mitigate SSD-internal Interference among Multi-tenant Databases
Seung-Jin Oh, Jong-Hyeok Park, Sang-Won Lee
http://doi.org/10.5626/JOK.2022.49.5.388
In a multi-tenant environment, multi-tenants share an SSD(Solid State Drive) as their storage device. Multi-tenants with different IO characteristics can interfere with each other at the channel level in terms of storage performance. In this paper, to harness the full potential of channel level parallelism of SSD, we proposed two tuning techniques: page size alignment and increasing readahead size. We measured transaction throughput and latency (execution time) while running Linkbench and TPC-H simultaneously in Docker container-based environment. Our evaluation showed that the page size alignment technique reduced unnecessary data padding/division overhead and prevented unnecessary IO requests from occupying the channel to mitigate interference, improving the performance of the Linkbench and the TPC-H. However, increasing readahead size raised SSD internal channel occupancy of sequential read requests and reduced the interference of the Linkbench, whose request size was small and access type was random. Thus, it only improved the TPC-H in terms of query execution performance.
Drunk Driving Detection System Using Wearable Devices
http://doi.org/10.5626/JOK.2022.49.5.397
Drunk driving may cause traffic accidents that result in human casualties. Even though most people are well aware of the danger, many traffic accidents still occur due to poor judgement caused by drinking. In this paper, we propose a drunk driving detection system using wearable devices. First, we use a smart watch, a wearable device, to collect data using only general-purpose sensors and sends the data via a smart phone to a server that performs machine learning to determine if the user is drinking. Then, the driver detection algorithm, which uses in-car beacons, sends a warning to the user to prevent drunk driving. We implemented the system on a smart watch, smart phone, and server, and also developed a practical user mobile app. The results showed that the accuracy of drinking detection and driver detection algorithms were around 92% and 99%, respectively.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr