• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.1
• /
• pp.30-41
• /
• 2023

With the aggressive down-scaling of advanced integrated circuits (ICs), electronic packages have become the bottleneck of both reliability and performance of whole electronic systems. In order to resolve the reliability issues, Institute of Electrical and Electronics Engineers (IEEE) laid down a roadmap on fault detection and diagnosis (FDD), thrusting the digital twin: a combination of reliability physics and artificial intelligence (AI). In this paper, we especially review research works regarding the signal-based FDD approaches on the electronic packages. We also discuss the research trend of FDD utilizing AI techniques.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.395-401
• /
• 2023

Sound Event Detection (SED) aims to identify not only sound category but also time interval for target sounds in an audio waveform. It is a critical technique in field of acoustic surveillance system and monitoring system. Recently, various models have introduced through Detection and Classification of Acoustic Scenes and Events (DCASE) Task 4. This paper explored how to design optimal parameters of DenseNet based model, which has led to outstanding performance in other recognition system. In experiment, DenseRNN as an SED model consists of DensNet-BC and bi-directional Gated Recurrent Units (GRU). This model is trained with Mean teacher model. With an event-based f-score, evaluation is performed depending on parameters, related to model architecture as well as model training, under the assessment protocol of DCASE task4. Experimental result shows that the performance goes up and has been saturated to near the best. Also, DenseRNN would be trained more effectively without dropout technique.

• The KIPS Transactions:PartC
• /
• v.11C no.1
• /
• pp.89-98
• /
• 2004

AQM (Active Queue Management) techniques such as RED (Random Early Detection) which be proposed to solve the congestion of internet perform congestion control effectively for TCP data. However, in the situation where TCP and UDP share the bottleneck link, they can not solve the problems of the unfairness and long queueing delay. In this paper, we proposed an simple queue management algorithm, called PSRED (Protocol Sensitive RED), that improves fairness and decreases queueing delay. PSRED algorithm improves fairness and decreases average queue length by distinguishes each type of flow in using protocol field of packets and applies different drop functions to them respectively.

• 한국HCI학회:학술대회논문집
• /
• 2008.02c
• /
• pp.224-224
• /
• 2008

Recent advances in model acquisition, computer-aided design, and simulation technologies have resulted in massive databases of complex geometric data occupying multiple gigabytes and even terabytes. In various graphics/geometric applications, the major performance bottleneck is typically in accessing these massive geometric data due to the high complexity of such massive geometric data sets. However, there has been a consistent lower growth rate of data access speed compared to that of computational processing speed. Moreover, recent multi-core architectures aggravate this phenomenon. Therefore, it is expected that the current architecture improvement does not offer the solution to the problem of dealing with ever growing massive geometric data, especially in the case of using commodity hardware. In this tutorial, I will focus on two orthogonal approaches--multi-resolution and cache-coherent layout techniques--to design scalable graphics/geometric algorithms. First, I will discuss multi-resolution techniques that reduce the amount of data necessary for performing geometric methods within an error bound. Second, I will explain cache-coherent layouts that improve the cache utilization of runtime geometric applications. I have applied these two techniques into rendering, collision detection, and iso-surface extractions and, thereby, have been able to achieve significant performance improvement. I will show live demonstrations of view-dependent rendering and collision detection between massive models consisting of tens of millions of triangles on a laptop during the talk.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.43-46
• /
• 2023

호흡기 관련 전염병의 주된 증상인 기침은 공기 중에 감염된 병원균을 퍼트리며 비감염자가 해당 병원균에 노출된 경우 높은 확률로 해당 전염병에 감염될 위험이 있다. 또한 사람들이 많이 모이는 공공장소 및 실내 공간에서의 기침 탐지 및 조치는 전염병의 대규모 유행을 예방할 수 있는 효율적인 방법이다. 따라서 본 논문에서는 탐지해야 하는 기침 소리 및 일상생활 속 발생할 수 있는 기침과 유사한 배경 소리 들을 Mel-Spectrogram으로 변환한 후 시각화된 특징을 CNN 모델에 학습시켜 기침 탐지를 진행하며, 일반적으로 사용되는 사전 학습된 CNN 모델에 제안된 Attention 모듈의 적용이 기침 탐지 성능 향상에 도움이 됨을 입증하였다.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.200-214
• /
• 2024

Amid the flood of data, social network analysis is beneficial in searching for its hidden context and verifying several pieces of information. This can be used for detecting the spread model of infectious diseases, methods of preventing infectious diseases, mining of small groups and so forth. In addition, community detection is the most studied topic in social network analysis using graph analysis methods. The objective of this study is to examine signed attributed social networks and identify the maximal balanced cliques that are both absolute and fair. In the same vein, the purpose is to ensure fairness in complex networks, overcome the "information cocoon" bottleneck, and reduce the occurrence of "group polarization" in social networks. Meanwhile, an empirical study is presented in the experimental section, which uses the personal information of 77 employees of a research company and the trust relationships at the professional level between employees to mine some small groups with the possibility of "group polarization." Finally, the study provides suggestions for managers of the company to align and group new work teams in an organization.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.979-993
• /
• 2021

Acoustic scene classification (ASC) categorizes an audio file based on the environment in which it has been recorded. This has long been studied in the detection and classification of acoustic scenes and events (DCASE). In this study, we considered the problem that ASC faces in real-world applications that the model used should have low-complexity. We compared several models that apply light-weight techniques. First, a base CNN model was proposed using log mel-spectrogram, deltas, and delta-deltas features. Second, depthwise separable convolution, linear bottleneck inverted residual block was applied to the convolutional layer, and Quantization was applied to the models to develop a low-complexity model. The model considering low-complexity was similar or slightly inferior to the performance of the base model, but the model size was significantly reduced from 503 KB to 42.76 KB.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.21-26
• /
• 2024

The one of the famous deep learning models for object detection task is you only look once version 5 (YOLOv5) framework based on the one stage architecture. In addition, YOLOv5 model indicated high performance for accurate lesion detection using the bottleneck CSP layer and skip connection function. The purpose of this study was to evaluate the performance of YOLOv5 framework according to various hyperparameters in position emission tomogrpahy (PET) phantom images. The dataset was obtained from QIN PET segmentation challenge in 500 slices. We set the bounding box to generate ground truth dataset using labelImg software. The hyperparameters for network train were applied by changing optimization function (SDG, Adam, and AdamW), activation function (SiLU, LeakyRelu, Mish, and Hardwish), and YOLOv5 model size (nano, small, large, and xlarge). The intersection over union (IOU) method was used for performance evaluation. As a results, the condition of outstanding performance is to apply AdamW, Hardwish, and nano size for optimization function, activation function and model version, respectively. In conclusion, we confirmed the usefulness of YOLOv5 network for object detection performance in nuclear medicine images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1146-1165
• /
• 2022

A huge amount of data in the form of videos and images is being produced owning to advancements in sensor technology. Use of low performance commodity hardware coupled with resource heavy image processing and analyzing approaches to infer and extract actionable insights from this data poses a bottleneck for timely decision making. Current approach of GPU assisted and cloud-based architecture video analysis techniques give significant performance gain, but its usage is constrained by financial considerations and extremely complex architecture level details. In this paper we propose a data pipeline system that uses open-source tools such as Apache Spark, Kafka and OpenCV running over commodity hardware for video stream processing and image processing in a distributed environment. Experimental results show that our proposed approach eliminates the need of GPU based hardware and cloud computing infrastructure to achieve efficient video steam processing for face detection with increased throughput, scalability and better performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.1012-1015
• /
• 2008

The packet capturing becomes a bottleneck in the network intrusion detection and monitoring system as the network performance developing. Many approaches, zero copy, interrupt coalescing and NAPI which attempt to improve packet capturing performance of Linux, are inefficient. PF_RING is a new type of network socket that dramatically improves the packet capture speed, but not perfect. This paper proposes some solutions which can improve the memory utilization and save some data copy time based on the commodity network adapters rather than on the commercial network adapters.