2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)最新文献

{"title":"Analysis of Thread Block Scheduling Algorithms for General Purpose GPU Systems","authors":"Soyeon Park, Kyungwoon Cho, H. Bahn","doi":"10.1109/CSDE53843.2021.9718419","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718419","url":null,"abstract":"Modern GPGPUs (General-Purpose Graphics Processing Units) have the ability of executing thousands of threads simultaneously. However, the resource utilization of GPGPU in real systems is limited as the load balancing between SMs (Stream Multiprocessors) is difficult during the scheduling of thread blocks, which are the basic units for resource allocation in GPGPU. In order to schedule thread blocks in GPGPU, the current hardware scheduler allocates thread blocks to SMs by the Round-Robin order. Although this is simple and easy to implement, we show that Round-Robin is not efficient when thread blocks of heterogeneous workloads are mixed. In such environments, efficient resource sharing in GPGPU is challenging as workloads have different resource usage patterns, but scheduling should be performed instantly. In this paper, we present a new thread block scheduling algorithm that has the ability of analyzing the load of SMs and the characteristics of pending thread blocks. Specifically, we formulate thread block scheduling as a bin-packing problem, and aim to minimize the internal fragmentation of SMs by arranging size-aware filling of thread blocks to overall SMs in advance. To do so, we make use of multiple queues for incoming thread blocks according to their sizes and perform scheduling by considering the load balancing of SMs. Our experimental results under a wide range of workload conditions show that the proposed algorithm improves the performance of GPGPU by 24.8% on average compared to the Round-Robin scheduler.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132038911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Based Decision Support Framework for Cardiovascular Disease Prediction","authors":"Nitten Singh Rajjliwal, G. Chetty","doi":"10.1109/CSDE53843.2021.9718459","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718459","url":null,"abstract":"In this paper we propose a novel decision support framework based on deep learning for cardiovascular disease prediction. The proposed framework based on an innovative stacked dense neural layer and convolution neural network cascade architecture, addresses the significant imbalance in class distribution in CVD event detection task. The experimental evaluation of the proposed model was done on the NHANES super-dataset, obtained by fusion of different subsets of publicly NHANES (National Health and Nutrition Examination Survey) data for prediction of cardiovascular disease. Many machines and deep learning models have been proposed in the literature for CVD event detection. However, they assume balanced class distribution between positive and negative disease classes. For clinical settings, there is significant class imbalance, with few positive class samples as compared to abundant samples from normal or control class. Hence most of the traditional machine and deep learning models are vulnerable to class imbalance, even after using class-specific adjustment of weights (well established method for handling class imbalance) and can lead to poor performance for the minority class detection. The proposed model based on stacked-Dense-CNN cascade architecture is robust and resilient to the class imbalance and has better overall detection accuracy. The first stage of the stacked-Dense-CNN cascade consists of an optimal feature learning stage, comprising a LASSO (least absolute shrinkage and selection) and majority voting step, for extraction of significant and homogenized features. The second stage use of a novel stacked-Dense-CNN cascade model and a novel model development protocol involving an unique train-test dataset partitioning strategy. Also, by using a specific training routine per epoch, similar to the simulated annealing approach, it was possible to achieve enhanced detection performance, particularly for detection of minority class, and robustness to class imbalance. The experimental evaluation of the novel stacked-Dense-CNN cascade model on a super dataset obtained by fusing multiple data subsets of publicly available NHANES data, resulted in an accuracy of 81.8% accuracy for negative CVD cases (majority class), and 85% for the positive CVD cases (minority class), an improved performance as compared to previously proposed research approaches for imbalanced clinical data settings.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114796582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Object Clarity In Single Channel Night Vision Images Using Deep Reinforcement Learning","authors":"Mohammad Elham Robbani, Adil Hossain, Md. Riaz Ul Haque Sazid, Sk. Shahiduzzaman Siam, Wasiu Abtahee, Amitabha Chakrabarty","doi":"10.1109/CSDE53843.2021.9718444","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718444","url":null,"abstract":"This paper implements a system of enhancing single channel night vision images using reinforcement learning approach and optimizing pixel prediction using q-table. We implemented some models to learn and process a small static images dataset using a reward bias q-table in a reinforcement learning architecture thus optimizing computational complexities and requirements of large dataset with the help of q-table. It also outperformed with respect to existing CNN models like SRCNN. Where SRCNN is observed to generate a PSNR of 24. S13 on average at 256 batch size. Our system generated a PSNR of 24.1 on average with results in a 10.29% increase of relative efficiency at 3000 epoch. It has shown a 10.39% and 10.36% increase of efficiency with respect to VDSR (at 12S batch size) model and DRCN (at filter number 16) model respectively.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128642222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preventing Timing Side-Channel Attacks in Software-Defined Networks","authors":"Faizan Shoaib, Yang-Wai Chow, Elena Vlahu-Gjorgievska","doi":"10.1109/CSDE53843.2021.9718377","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718377","url":null,"abstract":"Software-defined networking (SDN) is a technology for programming and efficiently managing networks. SDNs are prone to numerous threats, such as Distributed Denial of Service (DDoS), Man-in-the-middle, ARP Spoofing, Side-channels, and several other attacks. Separation of the data plane from the control plane makes SDN vulnerable to timing side-channel attacks. By comparing the response time of probe queries, an adversary can infer a pattern of request, which can invoke the controller and eventually discover information about the network. An adversary can apply these attacks to extract flow tables, routes, controller type, ports, etc. In this paper, we propose a novel security solution ‘Netkasi’ (kaŝi means ‘hide’ in Esperanto), to counter timing side-channel attacks in SDN. This solution hides the original response time information from the attacker and provides random response timing. As this security solution is designed to integrate with SDN, its architecture ensures minimal impact on the network traffic and consumption of network resources. The current solutions are a massive overhead on the network, whereas ‘Netkasi’ is implemented as a peripheral solution having its resources without causing significant overhead on the traffic. Analysis of the overall design shows that our solution is effective for the prevention of timing side-channel attacks in SDN.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132834456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Conditional Generative Adversarial Network for Non-rigid Point Set Registration","authors":"H. Tang, Yanxiao Zhao","doi":"10.1109/CSDE53843.2021.9718461","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718461","url":null,"abstract":"This paper proposes a novel approach to perform non-rigid point set registration without an iterative process. The main idea is to design a conditional generative adversarial network, termed Point Registration Generative Adversarial Network (PR-GAN). The proposed PR-GAN establishes an adversarial game between a generator and a discriminator. The generator aims to generate the geometric transformation parameters, and the discriminator aims to force the generated parameters to register two point sets accurately. After effective training, PRGAN can generate the desired transformation parameters to register a never-seen-before point set pair without an iterative optimization process. Furthermore, we design a pre-trained autoencoder to represent the point sets before feeding to PRGAN. Experiments with deformation, noise, and outlier are conducted. Results exhibit that PR-GAN achieves remarkably better performance compared to traditional iterative solutions.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124856071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Critical success factors and challenges for cloud ERP system implementations in SMEs: A vendors’ perspective","authors":"Sunchai Tongsuksai, Sanjay Mathrani, K. Weerasinghe","doi":"10.1109/CSDE53843.2021.9718428","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718428","url":null,"abstract":"To reduce costs and enhance the efficiency and effectiveness of enterprises, implementation of enterprise resource planning (ERP) systems is required in a highly competitive market. ERP systems have evolved from on-premise to cloud-based, which employ cloud computing features through an application-oriented software for storing data on remote servers. However, there have been few studies that have investigated the critical success factors (CSFs) and challenges for cloud ERP systems, particularly from a vendors’ perspective in the New Zealand (NZ) environment. This paper evaluates the CSFs and challenges which influence implementation of cloud ERP systems in NZ SMEs, based on vendors’ perspectives. Indepth interviews are conducted from six cloud ERP vendors in NZ to provide a comprehensive understanding of cloud ERP implementations. Findings reveal technology-enhanced skillsets, good governance, and innovative culture as the key CSFs and lack of information compatibility between departments, failure in governance, and cost overruns as the major challenges for cloud ERP implementations in NZ SMEs. Findings from this study provide practical insights to vendors and company managers that can assist in implementing cloud ERP systems.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126157116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AgileML: A Machine Learning Project Development Pipeline Incorporating Active Consumer Engagement","authors":"R. Shukla, J. Cartlidge","doi":"10.1109/CSDE53843.2021.9718470","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718470","url":null,"abstract":"Machine learning (ML) project deployments often have long lead times and may face delays or failures due to lack of data, poor data quality, and data drift. To address these problems, we introduce AgileML, a novel machine learning product development lifecycle where the end consumer and development team work collaboratively through an iterative process of development. We use AgileML to develop a commercial spend classification service and demonstrate that the earliest alpha deployment can offer users significant commercial value. User-testing with a professional spend analyst demonstrates that the system can lead to a five-fold increase in classification speed.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130217110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-modal Emotion Recognition for Determining Employee Satisfaction","authors":"Farhan Uz Zaman, Maisha Tasnia Zaman, Md. Ashraful Alam, Md. Golam Rabiul Alam","doi":"10.1109/CSDE53843.2021.9718373","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718373","url":null,"abstract":"Emotion recognition has been popular in the field of research for quite a while now. In this paper bi-modal emotion detection has been used to find employee satisfaction in workplaces. Interviews were taken of employees from different workplaces and were recorded. The recorded interviews were then used to detect the emotions of the employees from which their satisfaction level was derived. From the interviews, six different entities of emotion were detected, which are: Happiness, Sadness, Neutral, Disgust, Anger and Surprise. Two separate independent neural networks have been utilised. In one the facial expressions were detected and in the other sentiment analysis was done on the speech of the interviews after converting it into text. The extracted emotions were then fed into a Support Vector Machine (SVM) for determining the satisfaction of the employees. The satisfactions were categorized into five different levels which are: Highly dissatisfied, Dissatisfied, Neutral, Satisfied and Highly satisfied.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127154753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual-Stage Attention-Based Recurrent Neural Networks for Market Microstructure","authors":"Chae-Shick Chung, Sukjin Park","doi":"10.1109/CSDE53843.2021.9718424","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718424","url":null,"abstract":"This paper applies the Dual-Stage Attention-Based Recurrent Neural Network(DA-RNN) model to predict future price movements using microstructure variables. We analyze whether microstructure variables have predictive power for future price movements, and what factors influence this predictive power. We find that microstructure variables possess predictive power against the direction of future price movements. This predictive power depends on how many uninformed traders exist in the market. Moreover, the importance of microstructure variables is negatively related to market liquidity. Thus, while microstructure variables are more important in severe market conditions with high transaction costs, the effect of trading on price dynamics depends on market structure.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"291 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129914868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A state-space model for induction machine stator inter-turn fault and its evaluation at low severities by PCA","authors":"K. Raj, Sukhde H Joshi, Rahul R. Kumar","doi":"10.1109/CSDE53843.2021.9718479","DOIUrl":"https://doi.org/10.1109/CSDE53843.2021.9718479","url":null,"abstract":"Early fault detection in rotating machines saves time, money and labor that must be spent repairing or replacing the machine caused by a abrupt breakdown while stopping the production process. Due to this reason, industries invest in routine maintenance, intending to diagnose faults and take preventive measures before the problem becomes severe. This paper presents a state-space model of the healthy and faulty induction motor. The fault considered in this study is the stator inter-turn fault, with the severity ranging from 0.3%-2.11% in a phase. This article gives an overview of the simulated model and shows how the healthy three-phase current signature is different from the faulty ones. The Principal Component Analysis (PCA) and Space Vector Loci (SVL), in particular, have been utilized to visualize and present the differences between the healthy and faulty current signatures. Furthermore, both PCA and SVL have also been instrumental in denoting minor fault severities.","PeriodicalId":166950,"journal":{"name":"2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130109550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}