2022 12th International Conference on System Engineering and Technology (ICSET)最新文献

筛选
英文 中文
Template-Based Supervised Deep Homography Estimation Based on SqueezeNet 基于SqueezeNet的模板监督深度单应性估计
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10010997
Poppy Luscovius Purba, C. Machbub
{"title":"Template-Based Supervised Deep Homography Estimation Based on SqueezeNet","authors":"Poppy Luscovius Purba, C. Machbub","doi":"10.1109/ICSET57543.2022.10010997","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010997","url":null,"abstract":"Homography estimation is a common method used to solve many computer vision problems. Homography can be used to implement measurement on instruments based on image processing, replacing the common sensor required for a direct approach with the measured objects. Using the deep neural network in estimating homography is already quite popular among researchers and computer vision-related developers. Many networks are being implemented to solve homography based on classification network to find the transformation matrix. However, implementation of homography from previous studies with complex network requires high computing and is difficult to apply to embedded systems with limited capacity. Our research demonstrates the deep homography estimation for image transformation calibration based on template image with simpler network and requires less computational capability. We use the renowned SqueezeNet network model for the main network backbone with modification on the network head to solve the corner displacement of the homograph. We create the dataset from template image of symbols and train the network from the beginning. We change the output of the SqueezeNet classifier to regression output to acquire the displacement of the corner of perturbed image. To validate the network results, we compare the perturbed input image with the result of homography matrix prediction against the main template image to get the confidence level of the predicted homographic image. The results of our study are close to those of similar studies using more complex networks, but our network requires significantly less computing and power consumption and shorter training time.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121345258","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
Hybrid Feature Selection with K-Nearest Neighbors for Optimal Heart Failure Detection 基于k近邻的混合特征选择优化心力衰竭检测
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10010922
R. D. Prayogo, S. Karimah
{"title":"Hybrid Feature Selection with K-Nearest Neighbors for Optimal Heart Failure Detection","authors":"R. D. Prayogo, S. Karimah","doi":"10.1109/ICSET57543.2022.10010922","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010922","url":null,"abstract":"The selection of an optimal feature subset plays an important role in medical data handling. The accuracy of diagnosis is affected by the data dimensionality and is often degraded caused of irrelevant information in the features. Filter-based feature selection can be applied to select the most significant features based on ranking. However, the use of an independent filter-based technique is still incapable to identify the optimal features as it does not consider the top dominant feature subsets among feature selectors. Therefore, a hybrid filter-based feature selection is proposed in this study by considering the emergence rate of the selected features identified in Information Gain (IG), Correlation (CR), Chi-Squared (CS), and Relief-F (RL). An advantage of the hybrid filter-based technique is that the emergence of the selected features in each filter can be considered to determine the optimal feature subsets. The proposed technique is examined using K-Nearest Neighbors (KNN) classifier with 10-fold Cross-validation on the heart failure clinical record dataset retrieved from the UCI Machine Learning repository. We apply the proposed technique to predict the patients' survival and to rank the most significant features. The results indicate that the proposed technique successfully improves the classification performances for heart failure detection with an accuracy of 84.61%, a precision of 0.84, recall of 0.84, and an F1-score of 0.84. It has been observed that the fewer selected features in the feature subset, the more optimal the classification performance.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114869101","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
01_ICSET_Cover
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/icset57543.2022.10010892
{"title":"01_ICSET_Cover","authors":"","doi":"10.1109/icset57543.2022.10010892","DOIUrl":"https://doi.org/10.1109/icset57543.2022.10010892","url":null,"abstract":"","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131924325","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
Rainfall Nowcasting based on Satellite Images using Convolutional Long-Short Term Memory 基于卷积长短期记忆的卫星图像降水临近预报
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10010806
Beatrice Connie Majang, N. Zaini, Lucyantie Mazalan
{"title":"Rainfall Nowcasting based on Satellite Images using Convolutional Long-Short Term Memory","authors":"Beatrice Connie Majang, N. Zaini, Lucyantie Mazalan","doi":"10.1109/ICSET57543.2022.10010806","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010806","url":null,"abstract":"Rain that falls at a small and moderate rate is a blessing but incessant rainfall can bring many adverse effects such as loss of life, and destruction of property, crops and fields. One of the ways that can reduce the negative effects of natural disasters like this is to study trends and make predictions about what will happen. The predictive system, e.g. a nowcasting model can play an important role in dealing with rain issues, especially being able to provide early warning before bad weather occurs and this to some extent can help save lives and property. However, the determination of predictive models is a technically challenging task because rainfall is a non-linear phenomenon. In this research, a combination of a deep learning model called Convolutional Long-Short Term Memory (ConvLSTM) assisted by digital image processing is applied to real-time radar time series and satellite images. The goal is to predict the next event in a sequence of images with different timestamps i.e., 10-minutes, 30-minutes, and 60-minutes. Experimental results were evaluated with performance metrics using the Structural Similarity Index Measure (SSIM).","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128060516","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
Design and Implementation of IMU, BLE Proximity and GPS-Based Theft Detection System 基于IMU、BLE接近和gps的盗窃检测系统的设计与实现
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10010979
Muhammad Ogin Hasanuddin, Reihan Augeetiansyah, Gotawa Aryo Prakoso, B. R. Hermanto
{"title":"Design and Implementation of IMU, BLE Proximity and GPS-Based Theft Detection System","authors":"Muhammad Ogin Hasanuddin, Reihan Augeetiansyah, Gotawa Aryo Prakoso, B. R. Hermanto","doi":"10.1109/ICSET57543.2022.10010979","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010979","url":null,"abstract":"Efforts to resolve vehicle theft cases carried out by the police face several obstacles. Delay in reporting from the owner to the police and minimal information on the missing vehicle are the main factor in solving this vehicle theft case. This paper will describe the development of vehicle-tracking and theft-detection methods for vehicle theft experiments. Vehicle tracking uses GPS to get the location in latitude and longitude coordinates. The theft-attempt detection method uses a combination of acceleration from IMU and authentication from BLE proximity. This developed product can provide location accuracy of 10 meters with 98.1% certainty and an average theft-detection response time of 2.71 seconds.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125357118","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
Evaluation of Fuzzy PID controller design for coffee roasting temperature regulation 模糊PID控制器设计对咖啡烘焙温度调节的评价
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10011075
M. T. Miskon, M. Rahiman, M. Taib
{"title":"Evaluation of Fuzzy PID controller design for coffee roasting temperature regulation","authors":"M. T. Miskon, M. Rahiman, M. Taib","doi":"10.1109/ICSET57543.2022.10011075","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10011075","url":null,"abstract":"The time-temperature progression is one of the most influential factors in determining the beverage's overall quality. This is because the roasted bean takes on noticeably different qualities in the cup depending on the roasting profile used, even though both varieties will have the same colour at the end of the process. This is specifically due to the fact that roasted beans take on the characteristics of the roasting profile used. Thus, the temperature profile of the coffee bean pile while it is being roasted can be replicated in a significant manner by employing a readily available PID controller. Due to the difficulty of adjusting the PID parameters, however, the controller's performance is seldom optimized. This article compares the performance of PID controllers tuned with M-constrained Integral Gain Optimization (AMIGO) to that of two Fuzzy-PID controllers with three and five membership functions. The step responses, setpoint tracking, and disturbance rejection simulation test results for the Fuzzy-PID controller indicated a significant performance improvement. This includes an average improvement of greater than 90 % in overshoot and greater than 10 % in settling time.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130404666","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
Scholarship Recipients Prediction Model using k-Nearest Neighbor Algorithm and Synthetic Minority Over-sampling Technique 基于k-最近邻算法和合成少数派过采样技术的奖学金获得者预测模型
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10010947
D. Kurniadi, Fitri Nuraeni, Nia Abania, L. Fitriani, A. Mulyani, Yoga Handoko Agustin
{"title":"Scholarship Recipients Prediction Model using k-Nearest Neighbor Algorithm and Synthetic Minority Over-sampling Technique","authors":"D. Kurniadi, Fitri Nuraeni, Nia Abania, L. Fitriani, A. Mulyani, Yoga Handoko Agustin","doi":"10.1109/ICSET57543.2022.10010947","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010947","url":null,"abstract":"This research aims to develop a prediction model for scholarship recipients using the k-Nearest Neighbor (KNN) and Synthetic Minority Over Sampling Technique (SMOTE) algorithms. The method in model development uses the Cross-Industry Standard Process for Data Mining (CRISP-DM) which consists of phases of business understanding, data understanding, data processing, modeling, evaluation, and deployment. The dataset used is the Indonesian Smart College Card (KIP-K) Scholarship data in the real world obtained at one of the universities in Indonesia. The evaluation of the model uses a confusion matrix to calculate the values of accuracy, recall, precision, F1-Score, and AUC. The research results show seven attributes that influence the selection process for prospective scholarship recipients, namely non-academic achievement scores, selection test scores, survey scores, interview scores, economic condition scores, academic achievement, and choice of study programs. While the results of model testing produce the best model performance at a value of k=3 with 90.12% accuracy, 85.57% precision, 96.51% recall, 90.71% F1-score, and 0.957 AUC, which are included in the Excellent Classification category. Based on the test results, the model can be applied to a prediction system for prospective scholarship recipients at higher education institutions to make it more targeted.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117109120","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
Gamification of Animal Recognition Learning for Children with Deaf in Elementary School Using Dance Pad Media 利用舞垫媒介对小学聋哑儿童动物识别学习的游戏化
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10011098
E. Sudarmilah, Azie Melasari, Devi Afriyantari Puspa Putri, Wiwien Dinar Pratisti, F. Y. Irsyadi
{"title":"Gamification of Animal Recognition Learning for Children with Deaf in Elementary School Using Dance Pad Media","authors":"E. Sudarmilah, Azie Melasari, Devi Afriyantari Puspa Putri, Wiwien Dinar Pratisti, F. Y. Irsyadi","doi":"10.1109/ICSET57543.2022.10011098","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10011098","url":null,"abstract":"Madrasah Ibtiyah Muhammadiyah Special Program (MIM PK) Kartasura is an elementary school for children with special needs, one of which is the deaf, located in Kartasura. As technology develops, the MIM PK school continues to strive to improve innovation and quality in learning, one of which is using educational games. Based on the age of elementary school children, education is needed in recognizing the things around them, one of which is the introduction of animals so that they will know about the various kinds of animals that are around them. The solution that the researcher provides is using animal recognition gamification for children with special needs (ABK) with hearing impairment in 4th grade using the Media Dance Pad. The method used is divided into several stages including requirements analysis, system design, implementation and code writing, testing, evaluation, and maintenance. The making of this educational game uses Construct 2 as the software used in making the game and uses a dance pad as a connecting device for the controller and Figma as a component in the game. Based on the BlackBox and questionnaire tests that have been carried out, it is hope that the educational game is useful and easily as a learning media that makes it easier for students to receive the material, especially in animal recognition.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127256318","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
Design and Analysis of IoT-based Aquarium Monitoring System for Guppy Fish Habitats 基于物联网的孔雀鱼生境水族监测系统设计与分析
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10010912
Y. M. Yusof, Murizah Kassim, N. Azlan
{"title":"Design and Analysis of IoT-based Aquarium Monitoring System for Guppy Fish Habitats","authors":"Y. M. Yusof, Murizah Kassim, N. Azlan","doi":"10.1109/ICSET57543.2022.10010912","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10010912","url":null,"abstract":"Total lifespan of guppies in the wild varies and it is typically identified as around 2 years. Variations characteristics of life guppies are observed in different populations, indicating that different evolutionary pressures exist. Guppy eats a variety of foods including brine shrimp, bloodworms, or pellet. Too many foods in the water tank or aquarium will cause pollution and affect guppies' life habitats and most probably they get poisoned and died. This research aims to design and analyze an IoT-based monitoring system for Guppy fish in suitable habitats. An Arduino Uno acted as the microcontroller and temperature sensor, turbidity sensor, and pH sensor were installed as inputs. PuTTY software was used to record the data from all the sensors and synchronized daily to google drive. Four experiments have been conducted to identify suitable foods for the guppies. The result presents the analysis of Baby Brine Shrimp (BBS) type of fish food is safe due to the changes in pH value for the experiments are less than pellet type pH value. The turbidity level shown in experiment 3 is also very promising as it is the lowest turbidity level with 3.1 NTU. It is identified that a good range for guppy habitat is from 22°C to 32°C. This research is significant for guppies' fish breeders in monitoring and maintaining the quality of good guppies' habitats in agriculture.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132578017","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: 2
Performance Study of LoRa IoT Technology LoRa物联网技术性能研究
2022 12th International Conference on System Engineering and Technology (ICSET) Pub Date : 2022-10-03 DOI: 10.1109/ICSET57543.2022.10011110
Liya Yuni Astutik, Rahadian Yusuf
{"title":"Performance Study of LoRa IoT Technology","authors":"Liya Yuni Astutik, Rahadian Yusuf","doi":"10.1109/ICSET57543.2022.10011110","DOIUrl":"https://doi.org/10.1109/ICSET57543.2022.10011110","url":null,"abstract":"LoRa (Long Range) is a wireless connectivity technology module intended for IoT systems. The LoRa module is patented and manufactured by the Semtech Corporation. The advantages of LoRa technology are wide area coverage with low power consumption, thousands of nodes can be connected in a network making it suitable for the Internet of Things (IoT). Based on claims of the superiority of LoRa technology from various references, the purpose from this study is to test the performance of LoRa under various conditions. The test will be carried out in 2 conditions, Los and Non-Los. Los is a test condition when there is no obstacle/ open space. Non-Los is a test condition when there is an obstacle/ enclosed space. Loss and Non-Los testing will get a system performance analysis consisting of delay analysis, data delivery and data loss. Referring to the test results, LoRa on the monitoring system is very effective based on data transmission and distance. Data transmission 92% was successful in a closed space with a distance of 6 meters within the building, 100% was successful in an open space with a distance of 6 meters with many residential areas, trees, vehicles, and people passing by.","PeriodicalId":110899,"journal":{"name":"2022 12th International Conference on System Engineering and Technology (ICSET)","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128803965","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书