• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2101-2123
• /
• 2023

Recent studies have shown that the neural network-based binary code similarity detection technology performs well in vulnerability mining, plagiarism detection, and malicious code analysis. However, existing cross-architecture methods still suffer from insufficient feature characterization and low discrimination accuracy. To address these issues, this paper proposes a cross-architecture binary function similarity detection method based on composite feature model (SDCFM). Firstly, the binary function is converted into vector representation according to the proposed composite feature model, which is composed of instruction statistical features, control flow graph structural features, and application program interface calling behavioral features. Then, the composite features are embedded by the proposed hierarchical embedding network based on a graph neural network. In which, the block-level features and the function-level features are processed separately and finally fused into the embedding. In addition, to make the trained model more accurate and stable, our method utilizes the embeddings of predecessor nodes to modify the node embedding in the iterative updating process of the graph neural network. To assess the effectiveness of composite feature model, we contrast SDCFM with the state of art method on benchmark datasets. The experimental results show that SDCFM has good performance both on the area under the curve in the binary function similarity detection task and the vulnerable candidate function ranking in vulnerability search task.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1994년도 추계학술발표회 및 정기총회
• /
• pp.32-32
• /
• 1994

In this example, a message passing based multicomputer system with general interdonnedtion network is considered. After multicomputer systems are developed with morm-hole routing network, topologies of interconecting network are not major considertion for process management and resource sharing. Tehre is an independeent operating system kernel oneach node. It communicates with other kernels using message passingmechanism. Based on this architecture, the problem is how mech does performance degradation will occur in the case of processor sharing on multicomputer systems. Processor sharing between application programs is veryimprotant decision on system performance. In almost cases, application programs running on massively parallel computer systems are not so much user-interactive. Thus, the main performance index is system throughput. Each application program has various communication patterns. and the sharing of processors causes serious performance degradation in hte worst case such that one processor is shared by two processes and another processes are waiting the messages from those processes. As a result, considering this problem is improtant since it gives the reason whether the system allows processor sharingor not. Input data has many parameters in this simulation . It contains the number of threads per task , communication patterns between threads, data generation and also defects in random inupt data. Many parallel aplication programs has its specific communication patterns, and there are computation and communication phases. Therefore, this phase informatin cannot be obtained random input data. If we get trace data from some real applications. we can simulate the problem more realistic . On the other hand, simualtion results will be waseteful unless sufficient trace data with varisous communication patterns is gathered. In this project , random input data are used for simulation . Only controllable data are the number of threads of each task and mapping strategy. First, each task runs independently. After that , each task shres one and more processors with other tasks. As more processors are shared , there will be performance degradation . Form this degradation rate , we can know the overhead of processor sharing . Process scheduling policy can affects the results of simulation . For process scheduling, priority queue and FIFO queue are implemented to support round-robin scheduling and priority scheduling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3638-3657
• /
• 2022

In urban vehicular edge computing (VEC) environments, one edge server always serves many task requests in its coverage which results in the resource-constrained problem. To resolve the problem and improve system utilization, we first design a general hierarchical resource management framework based on typical VEC network structures. Following the framework, a specific interacting protocol is also designed for our decision algorithm. Secondly, a greedy bidding-based multi-hop task scheduling decision algorithm is proposed to realize effective task scheduling in resource-constrained VEC environments. In this algorithm, the goal of maximizing system utility is modeled as an optimization problem with the constraints of task deadlines and available computing resources. Then, an auction mechanism named greedy bidding is used to match task requests to edge servers in the case of multiple hops to maximize the system utility. Simulation results show that our proposal can maximize the number of tasks served in resource constrained VEC networks and improve the system utility.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.

• 대한전자공학회논문지TC
• /
• 제41권4호
• /
• pp.1-10
• /
• 2004

차세대 망(Next Generation Network)에서는 안정된 속도와 높은 수준의 보안 보장, 다양한 분야의 서비스 요구 등 고급화 되어가는 소비자의 요구를 만족시키기 위해, 자원과 정보에 대한 통합적인 관리가 필수적이다. 이와 관련하여 한정된 자원을 효율적으로 사용하기 위한 기술에 대한 관심이 커지고 있으며, 따라서 네트워크 서비스 정책이 중요하게 다루어지고 있다. 특히 최근에 차세대 망에서 사용자 맞춤 서비스인 DEN(directory-Enabled Network) 기반 개인화 서비스를 위해, 그리고 한정된 자원의 통합적이고 효율적인 사용과 관리를 위해 통신 서비스 환경과 사용자 요구(user on demand)에 따른 정책을 정의하고 적용하는 PBNM 기술이 매우 중요하게 되었으며, 이와 관련하여 PBNM 최적화를 어떻게 할 것인가에 대한 연구가 필수적이다. 본 논문에서는 DMTF(Distributed Management Task Forte)에서 표준화 한 DEN(Directory-Enabled Network)기반에서의 PBNM(Policy-Based Network Management)을 제안하였으며, 최적화된 시스템을 설계하였다.

• 한국치위생학회지
• /
• 제16권2호
• /
• pp.241-248
• /
• 2016

Objectives: The purpose of the study is to evaluate the dental website usability in Korea. The dental website included dental university hospital, network dental hospital and dental office. Methods: The study was carried out by three age groups including twenties, thirties, and forties. Each group consisted of ten customers and evaluated twelve websites of dental hospitals. Each was assigned to four hospitals and three tasks including easiness of online reservation, preventive information, and treatment information. They filled out the self-administered questionnaire. The questionnaire included the easiness of on-line reservation, satisfaction on the quality and quantity of preventive informations, satisfaction on the quality and quantity of treatment informations, predictiveness on the sub-menu, usefulness of site map, information on the main page of web site, usefulness of decision on visit to dentistry, and revisit intention. Results: The easiness of on-line reservation was the highest in the private dental office, and university dental hospital and network dental hospitals followed in conducting task(1). The anticipated value and measurement on the usefulness of web site were the lowest in network dental hospitals and the time interval between two values was 57 seconds. This discrepancy showed the largest difference. The satisfaction on treatment information in task(3) was higher than that of the satisfaction on preventive information in task (2). The revisit intention was the highest in dental university hospitals. Conclusions: This study showed the comparison in usefulness of web site of university dental hospitals, network dental hospitals and private dental office. The web site focused on the treatment information rather than preventive information. This study suggested that the most important function of dental web site would be the preventive information that was mainly operated by the role of dental hygienists rather than treatment information in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Investigative Magnetic Resonance Imaging
• /
• 제25권1호
• /
• pp.10-22
• /
• 2021

Purpose: To overcome the difficulty in building a large data set with a high-quality in medical imaging, a concept of 'blended-transfer learning' (BTL) using a combination of both source data and target data is proposed for the target task. Materials and Methods: Source and target tasks were defined as training of the source and target networks to reconstruct cardiac CINE images from undersampled data, respectively. In transfer learning (TL), the entire neural network (NN) or some parts of the NN after conducting a source task using an open data set was adopted in the target network as the initial network to improve the learning speed and the performance of the target task. Using BTL, an NN effectively learned the target data while preserving knowledge from the source data to the maximum extent possible. The ratio of the source data to the target data was reduced stepwise from 1 in the initial stage to 0 in the final stage. Results: NN that performed BTL showed an improved performance compared to those that performed TL or standalone learning (SL). Generalization of NN was also better achieved. The learning curve was evaluated using normalized mean square error (NMSE) of reconstructed images for both target data and source data. BTL reduced the learning time by 1.25 to 100 times and provided better image quality. Its NMSE was 3% to 8% lower than with SL. Conclusion: The NN that performed the proposed BTL showed the best performance in terms of learning speed and learning curve. It also showed the highest reconstructed-image quality with the lowest NMSE for the test data set. Thus, BTL is an effective way of learning for NNs in the medical-imaging domain where both quality and quantity of data are always limited.

• 한국컴퓨터정보학회논문지
• /
• 제19권11호
• /
• pp.9-15
• /
• 2014

본 논문에서는 하둡 클러스터의 네트워크 사용량 감소를 위한 블록 재배치 알고리즘을 제안한다. 하둡 클러스터의 스케줄러는 사용자들에게 작업을 받아 다중 태스크로 작업을 나누어서 각 노드들에게 할당한다. 이 때 스케줄러는 데이터 지역성(Data locality)을 만족시키는 노드에 우선적으로 태스크를 할당한다. 만약 처리할 데이터(블록)가 없는 노드에 태스크가 할당되면 다른 노드로부터 전송받아 처리한다. 클러스터의 블록들은 사용 빈도가 각각 다르기 때문에 노드 간 작업 부하의 차이가 발생하며 이로 인해 노드 간 데이터 전송이 빈번해진다. 그래서 제안하는 블록 재배치 알고리즘은 하둡 스케줄러의 작업 할당 패턴에 따라 블록들을 균등하게 재배치한다. 결국 노드들의 작업부하는 평준화 되고 처리할 블록이 없는 노드에서 태스크를 처리하는 경우가 감소하기 때문에 클러스터의 네트워크 트래픽이 감소한다. 시뮬레이션으로 제안하는 블록 재배치 정책의 성능평가를 진행했으며 기본 지연 스케줄링으로 작업을 처리한 경우와 비교하여 최대 23.3%의 네트워크 사용량 감소를 보였다.

• 아동학회지
• /
• 제17권2호
• /
• pp.61-78
• /
• 1996

The purpose of this study was to describe maternal social networks and to examine their relationships to maternal perceptions of parenting task difficulty. One hundred and thirty-three mothers of preschool children responded to a questionnaire indicating individuals in their networks, support functions, and perceptions of task difficulty. Mothers reported an average of 6.5 persons in their networks, including primarily with her own mother, the husband, mother-in-law, and sisters. While support was provided mainly by her husband and her own family members, the kinds of support varied depending on the person in networks. It was also found that support functions were different in terms of maternal job status, sex of the child, and the child's previous experience in day care or early childhood education settings. Emotional support from networks was significantly related to parenting task difficulty, especially in daily routine care. Mothers who perceived more emotional support from networks reported parenting to be less difficult.