TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)最新文献_第7页

Ventricular Arrhythmia Classification and Interpretation Using Residual Neural Network with Guided Backpropagation 基于引导反向传播残差神经网络的室性心律失常分类与解释

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707469

Deepankar Nankani, R. Baruah

{"title":"Ventricular Arrhythmia Classification and Interpretation Using Residual Neural Network with Guided Backpropagation","authors":"Deepankar Nankani, R. Baruah","doi":"10.1109/TENCON54134.2021.9707469","DOIUrl":"https://doi.org/10.1109/TENCON54134.2021.9707469","url":null,"abstract":"Sudden cardiac death is the leading cause of natural death ocurring due to life-threatening lethal ventricular arrhythmias such as Ventricular Tachycardia (VT) and Ventricular Fibrillation (VF). This paper employs a supervised deep-learning interpretable framework for detecting VT and VF from Electrocardiogram (ECG) signals. The framework consists of two stages: (i) single-lead ECG classification using convolution-based Residual Neural Network (ResNet); and (ii) interpretation of classified segments using gradient-based Guided Backpropagation. The single-lead ECG is decluttered from noise, augmented, and classified using the ResNet classifier. The convolution layers in ResNet encode temporal variations present in ECG to provide better feature abstraction. The fully connected layer aggregates the encoding based on clinical relevance and performs classification. Lastly, the saliency maps of the penultimate convolution layer are visualized using guided backpropagation to highlight important signal timestamps responsible for classification. The proposed method is robust and outperforms state-of-the-art methods when verified on datasets acquired from five different geographic locations.","PeriodicalId":405859,"journal":{"name":"TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114183151","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}

引用次数: 1

Thermoelectric Generation System with Maximum Power Point Tracking Algorithm 最大功率点跟踪算法的热电发电系统

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707228

Bryan E. Escoto, Ge Ang

引用次数: 4

Verification of spatiotemporal continuous complex event processing rules by a synthesized data set 基于合成数据集的时空连续复杂事件处理规则验证

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707251

Sanghyun Lee, B. Hong, Woochan Kim

引用次数: 0

Hyperspectral Image Classification Based on Multi-stage Vision Transformer with Stacked Samples 基于多级视觉变换叠加样本的高光谱图像分类

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707289

Xiaoyue Chen, Sei-ichiro Kamata, Weilian Zhou

{"title":"Hyperspectral Image Classification Based on Multi-stage Vision Transformer with Stacked Samples","authors":"Xiaoyue Chen, Sei-ichiro Kamata, Weilian Zhou","doi":"10.1109/TENCON54134.2021.9707289","DOIUrl":"https://doi.org/10.1109/TENCON54134.2021.9707289","url":null,"abstract":"Hyperspectral image classification (HSIC) is a task assigning the correct label to each pixel. It is a hot topic in the remote sensing field, which has been processed in several deep learning methods. Recently, there are some works that apply Vision Transformer (ViT) methods to the HSIC task, but the performance is not as good as some CNN-structured methods, considering that Vision Transformer uses attention to capture global information but ignores local characteristics. In this paper, a multi-stage Vision Transformer model referring to the feature extraction structure of CNN is proposed, and the result shows the realizability and reliability. Besides, experiments show that the modified ViT structure needs more samples for training. An innovative data augmentation method is used to generate extended samples with virtual yet reliable labels. The generated samples are combined with the original ones as the stacked samples, which are used for the following feature extraction process. Experiments explain the optimization of the multi-stage Vision Transformer structure with stacked samples in the accuracy term compared with other methods.","PeriodicalId":405859,"journal":{"name":"TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126661568","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}

引用次数: 4

A Comparative Finite Element Analysis of a Two-Story Residential Building Using Concrete Hollow Blocks and Po-lite Hollow Blocks 混凝土空心砌体与聚乙烯空心砌体两层住宅结构的有限元对比分析

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707385

Ria Liza C. Canlas, Ares Baron Talusan, M. Principe, Llevie Gonzales, Vicente E. DyReyes, Christ Anne Jovy Regonios

{"title":"A Comparative Finite Element Analysis of a Two-Story Residential Building Using Concrete Hollow Blocks and Po-lite Hollow Blocks","authors":"Ria Liza C. Canlas, Ares Baron Talusan, M. Principe, Llevie Gonzales, Vicente E. DyReyes, Christ Anne Jovy Regonios","doi":"10.1109/TENCON54134.2021.9707385","DOIUrl":"https://doi.org/10.1109/TENCON54134.2021.9707385","url":null,"abstract":"This paper presents a comparative linear static, and dynamic analysis of two types of models of a two-story residential building considering three essential parameters: stress, and displacement. The first model utilizes a Concrete hollow block (CHB), while the second model utilizes Po-Lite hollow block (PHB), both with concrete structural components. The models were subjected to Finite Element Analysis (FEA) using MSC Patran and Nastran, considering dead load, live load, and wind load with pre-determined dimensions and material properties for each structural element. Based on the FEA, it has been determined that the PHB model is significantly superior when it comes to stresses imposed on the structure. However, it is also revealed that the CHB model is significantly superior in resisting deflections and deformation. Furthermore, the utilization of Po-lite leads to cost-efficiency as it eliminates other construction scope of work such as finishing works. Because of this, it only requires fewer construction processes than conventional construction, which reduces labor time and construction costs.","PeriodicalId":405859,"journal":{"name":"TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123688219","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}

引用次数: 0

Finite Element Analysis on a Single-story Geodesic Dome Structure Using Combination of Po-Lite Hollow Blocks and Cold-Formed Steel 冷弯型钢与钴酸盐空心块组合单层测地圆顶结构的有限元分析

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707403

Ria Liza C. Canlas, M. Principe, Gwenzel S. Riego, Vicente E. DyReyes

{"title":"Finite Element Analysis on a Single-story Geodesic Dome Structure Using Combination of Po-Lite Hollow Blocks and Cold-Formed Steel","authors":"Ria Liza C. Canlas, M. Principe, Gwenzel S. Riego, Vicente E. DyReyes","doi":"10.1109/TENCON54134.2021.9707403","DOIUrl":"https://doi.org/10.1109/TENCON54134.2021.9707403","url":null,"abstract":"Geodesic domes are complex in structural design due to their unique shape. However, Dome-shaped structures are efficient in weakening elements such as wind. This paper presents the Finite Element Analysis (FEA) of geodesic dome design utilizing a combination of Po-Lite Triangular Tiles and Cold-Formed Steel (CFS) Framing in terms of static and dynamic analysis using MSC Patran and Nastran. This paper aims to determine the capabilities of combining the two Design-to-build materials against varying load conditions. The results show that the geodesic dome design for static analysis considering the data for stress tensor, displacement, and deformation did not exceed the allowable values, thus supporting the loads' linear relationship to the structure. Lastly, the dynamic analysis obtained acceptable values from maximum yielding stress, maximum displacement, and maximum deformation against four different wind loading cases. Thus, it supports that the dome utilizing both construction materials can withstand wind loads. Moreover, the results obtained from the dome analysis have validated the quality-efficiency of Po-Lite and Cold-Formed Steel in terms of structural strength, which adds to other benefits such as manufacturing, assembly, and delivery.","PeriodicalId":405859,"journal":{"name":"TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123720525","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}

引用次数: 1

Phase-based accelerated motion magnification using image pyramid 使用图像金字塔的相位加速运动放大

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707375

Tomohito Mizokami, Kenjiro Sugimoto, S. Kamata

引用次数: 0

Portable Executable Malware Classifier Using Long Short Term Memory and Sophos-ReversingLabs 20 Million Dataset 使用长短期记忆和Sophos-ReversingLabs 2000万数据集的便携式可执行恶意软件分类器

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707353

Julianne Alyson I. Diaz, A. Bandala

引用次数: 3

IoT-based On-demand Feeding System for Nile Tilapia (Oreochromis niloticus) 基于物联网的尼罗罗非鱼按需投料系统

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707241

Maria Gemel B. Palconit, Ronnie S. Concepcion, Jonnel D. Alejandrino, V. Fonseca, E. Sybingco, A. Bandala, R. R. Vicerra, E. Dadios

{"title":"IoT-based On-demand Feeding System for Nile Tilapia (Oreochromis niloticus)","authors":"Maria Gemel B. Palconit, Ronnie S. Concepcion, Jonnel D. Alejandrino, V. Fonseca, E. Sybingco, A. Bandala, R. R. Vicerra, E. Dadios","doi":"10.1109/TENCON54134.2021.9707241","DOIUrl":"https://doi.org/10.1109/TENCON54134.2021.9707241","url":null,"abstract":"Fish feeding management is one of the most crucial considerations in aquaculture production. The traditional feeding method such as table-based and scheduled automated feeding schemes are inaccurate. In contrast, the automated on-demand feeding system has reduced the inaccuracies of the older feeding schemes. However, existing on-demand systems have limited accessibility because their monitoring systems are only stored by their local devices. This paper proposes an on-demand fish feeding system with online and real-time monitoring using the Internet of Things (IoT) and an accelerometer to sense the fish' demand by hitting it. An overhead surveillance camera was installed on the fish tank to automatically record and monitor the fish feeding activity on the first day of the implementation. Two groups of fish were used for the observation—the adults and pre-growth Nile tilapia (Oreochromis niloticus). Results have shown that the on-demand feeding system is highly effective on 21 pre-growth fish with an average weight of 88 grams and a standard deviation (SD) of ± 39 grams. Additionally, the feed intake ratio (FIR) of the pre-growth fish was $1.35pm 0.69$ grams, i.e., 73% to 86% lower than the recommended table-based feeding scheme. Thus, more efficient.","PeriodicalId":405859,"journal":{"name":"TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132139513","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}

引用次数: 1

Real-time traffic monitoring and traffic offense detection using YOLOv4 and OpenCV DNN 使用YOLOv4和OpenCV DNN进行实时交通监控和交通违规检测

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON) Pub Date : 2021-12-07 DOI: 10.1109/TENCON54134.2021.9707406

Fahimul Hoque Shubho, Fahim Iftekhar, Ekhfa Hossain, Shahnewaz Siddique

{"title":"Real-time traffic monitoring and traffic offense detection using YOLOv4 and OpenCV DNN","authors":"Fahimul Hoque Shubho, Fahim Iftekhar, Ekhfa Hossain, Shahnewaz Siddique","doi":"10.1109/TENCON54134.2021.9707406","DOIUrl":"https://doi.org/10.1109/TENCON54134.2021.9707406","url":null,"abstract":"This paper presents a computer vision-based system for traffic offense detection. The system detects traffic offenses such as speed limit violations, unauthorized vehicles, traffic signal violations, unauthorized parking, wrong-way driving, and motorbike riders without helmets. The traffic offense detection system consists of a pipeline of four different modules. These are a vehicle detection module, a vehicle classification module, a vehicle tracking module, and a traffic offense detection module. Vehicles on the roads are detected in the vehicle detection module using visual data such as live camera feed. Next, after the vehicles are detected, they are classified into different classes using a vehicle classification module. A vehicle tracking module is developed to track the vehicle as it moves through the traffic. Lastly, we have implemented a traffic offense detection module that analyzes traffic patterns and detects different types of traffic violations in real-time. The entire system is implemented using OpenCV Deep Neural Network (DNN) module. We have used YOLOv4 to detect vehicles on the roads with high accuracy. For motorbike riders without helmets, we have used a fast YOLOv4-tiny model. The DeepSORT algorithm is used to track vehicles in real-time. Obtained accuracies are 86% in YOLOv4 for vehicle detection and 92% in YOLOv4-tiny for helmet detection.","PeriodicalId":405859,"journal":{"name":"TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133751906","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}

引用次数: 4