Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608597
S. Sabilla, Malikhah, R. Sarno
Human axillary odor produces gas from sweat which concentration will change depends on the activities and metabolism in the body. Sweat concentration can be used as information to determine body health. Nowadays, e-nose is widely used in medicine, food industry, agriculture, and biotechnology. An electronic nose (e-nose) is a device that mimics how the human nose works. This paper will build an e-nose with seven sensors from Figaro Taguchi series (TGS) sensors and one sensor from humidity and temperature sensors (SHT-15 series). The e-nose was used to obtain the human axillary odor in the morning, afternoon, and evening. Several classifiers are used in the classification process and the result showed that Random Forest with tuned hyperparameter produced the best result with an accuracy of 87.43%. By using the ANOVA f-test, it is showed that methane and ethanol from sensor TGS 2612 are the most significant gas in the classification process. The experimental result showed that human axillary odor produced different ethanol and methane gas concentration in the morning, afternoon, and evening.
{"title":"Classification and Gas Concentration Measurements of Human Axillary Odor using Electronic Nose","authors":"S. Sabilla, Malikhah, R. Sarno","doi":"10.1109/ICTS52701.2021.9608597","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608597","url":null,"abstract":"Human axillary odor produces gas from sweat which concentration will change depends on the activities and metabolism in the body. Sweat concentration can be used as information to determine body health. Nowadays, e-nose is widely used in medicine, food industry, agriculture, and biotechnology. An electronic nose (e-nose) is a device that mimics how the human nose works. This paper will build an e-nose with seven sensors from Figaro Taguchi series (TGS) sensors and one sensor from humidity and temperature sensors (SHT-15 series). The e-nose was used to obtain the human axillary odor in the morning, afternoon, and evening. Several classifiers are used in the classification process and the result showed that Random Forest with tuned hyperparameter produced the best result with an accuracy of 87.43%. By using the ANOVA f-test, it is showed that methane and ethanol from sensor TGS 2612 are the most significant gas in the classification process. The experimental result showed that human axillary odor produced different ethanol and methane gas concentration in the morning, afternoon, and evening.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"1 1","pages":"161-166"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91538209","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608390
M. E. Mital
The adverse effects of neurodegenerative diseases are aimed to be reduced if not totally diminished. Parkinson's Disease (PD), a type of neurodegenerative disease, has been a trend in research and medicine with regards to its classification and early detection. There is a count on the symptoms experienced by PD patients such as tremors, rigidity, and slowness, but the majority of these patients have an impairment in speech; thus, considering voice attributes as an outstanding feature. Using extensive voice parameters including but not limited to Mel Frequency Cepstral Coefficients (MFCC) and Tunable Q-Factor Wavelet Transform (TQWT) based features, this study does not only focus on one learning machine - which is the usual subject of related literature, but on evaluating the generalization performance of 7 classification systems including their variants. This will provide a summative report on their accuracies so that researchers can proceed to higher levels of studies. As a result, the best learning classifier utilizing the data set acquired is optimized k-NN with 95.6% accuracy. This is achieved in a 10-fold cross-validation configuration.
{"title":"Implementation and Evaluation of Learning Classifiers in Detecting Parkinson's Disease Using Extensive Speech Parameters","authors":"M. E. Mital","doi":"10.1109/ICTS52701.2021.9608390","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608390","url":null,"abstract":"The adverse effects of neurodegenerative diseases are aimed to be reduced if not totally diminished. Parkinson's Disease (PD), a type of neurodegenerative disease, has been a trend in research and medicine with regards to its classification and early detection. There is a count on the symptoms experienced by PD patients such as tremors, rigidity, and slowness, but the majority of these patients have an impairment in speech; thus, considering voice attributes as an outstanding feature. Using extensive voice parameters including but not limited to Mel Frequency Cepstral Coefficients (MFCC) and Tunable Q-Factor Wavelet Transform (TQWT) based features, this study does not only focus on one learning machine - which is the usual subject of related literature, but on evaluating the generalization performance of 7 classification systems including their variants. This will provide a summative report on their accuracies so that researchers can proceed to higher levels of studies. As a result, the best learning classifier utilizing the data set acquired is optimized k-NN with 95.6% accuracy. This is achieved in a 10-fold cross-validation configuration.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"36 1","pages":"241-246"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87001922","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9607870
M. E. Mital
Parkinson's Disease detection can be considered a relevant yet overlooked issue in the field of research and medicine. Its effects are progressive in nature and worsens if not detected and treated accordingly. In this study, standardized tests such as static and dynamic spiral tests (SST and DST) are employed. On top of these, machine learning, specifically transfer learning is implemented. 14 pre-trained models are considered; 3 solvers are evaluated for each machine - these processes are repeated in 4 different scenarios. Based from the results, the pre-trained model with the highest accuracy is MobileNetV2 (93.94%), while the model with the sub-optimal performance is Vgg-19 (27.27%). In addition, it is realized that Stochastic Gradient Descent with Momentum (sgdm) and Adaptive Momentum (adam) are preferred over Root Mean Square Propagation (rmsprop) as the main solver for this kind of PD classification. Nonetheless, it is claimed that DST images are more correlated and significant than SST or a combination of both.
{"title":"Detection of Parkinson's Disease Through Static and Dynamic Spiral Test Drawings: A Transfer Learning Approach","authors":"M. E. Mital","doi":"10.1109/ICTS52701.2021.9607870","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9607870","url":null,"abstract":"Parkinson's Disease detection can be considered a relevant yet overlooked issue in the field of research and medicine. Its effects are progressive in nature and worsens if not detected and treated accordingly. In this study, standardized tests such as static and dynamic spiral tests (SST and DST) are employed. On top of these, machine learning, specifically transfer learning is implemented. 14 pre-trained models are considered; 3 solvers are evaluated for each machine - these processes are repeated in 4 different scenarios. Based from the results, the pre-trained model with the highest accuracy is MobileNetV2 (93.94%), while the model with the sub-optimal performance is Vgg-19 (27.27%). In addition, it is realized that Stochastic Gradient Descent with Momentum (sgdm) and Adaptive Momentum (adam) are preferred over Root Mean Square Propagation (rmsprop) as the main solver for this kind of PD classification. Nonetheless, it is claimed that DST images are more correlated and significant than SST or a combination of both.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"26 1","pages":"247-251"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90920648","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608000
Samrudhi Mohdiwale, Mridu Sahu, G. Sinha
Cognitive State Assessment has a significant role in analyzing the mental status of personals involved in high-risk tasks where decision-making is important. In this paper, authors have proposed a model to classify the cognitive states accurately. In the model, subband statistical wavelet-based features are extracted. Every feature may not be important for the classification of cognitive workload and introduces the problem of higher dimensionality. To solve the problem of high dimensionality, Chaotic Jaya Optimization based binary feature selection model is proposed. The model has been designed such that it not only improves the classification accuracy but also selects the relevant features. The extensive experiment has been performed using different techniques, and results show that without feature selection, 73.3% maximum accuracy is obtained using decision tree classifier. Further optimization techniques are employed for feature selection, and results are improved up to 96.11%. The results are also compared with the existing techniques and it has been observed that the proposed approach gives maximum classification accuracy and converges at least number of iterations. In the proposed approach, features are also reduced up to its 60%.
{"title":"Binary Chaotic Jaya Optimization for Cognitive State Assessment","authors":"Samrudhi Mohdiwale, Mridu Sahu, G. Sinha","doi":"10.1109/ICTS52701.2021.9608000","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608000","url":null,"abstract":"Cognitive State Assessment has a significant role in analyzing the mental status of personals involved in high-risk tasks where decision-making is important. In this paper, authors have proposed a model to classify the cognitive states accurately. In the model, subband statistical wavelet-based features are extracted. Every feature may not be important for the classification of cognitive workload and introduces the problem of higher dimensionality. To solve the problem of high dimensionality, Chaotic Jaya Optimization based binary feature selection model is proposed. The model has been designed such that it not only improves the classification accuracy but also selects the relevant features. The extensive experiment has been performed using different techniques, and results show that without feature selection, 73.3% maximum accuracy is obtained using decision tree classifier. Further optimization techniques are employed for feature selection, and results are improved up to 96.11%. The results are also compared with the existing techniques and it has been observed that the proposed approach gives maximum classification accuracy and converges at least number of iterations. In the proposed approach, features are also reduced up to its 60%.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"75 1","pages":"301-305"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86020608","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9607962
Mikhael Ming Khosasih, D. Herumurti, Hadziq Fabroyir
This research aims to know and compare the purchase intention on the web, AR, and VR applications using Technology Acceptance Model (TAM). The background of this research is mainly due to the Covid-19 pandemic that makes the e-commerce industry grows rapidly. Nowadays, most e-commerce in Indonesia uses 2D websites, although AR and VR can be applied in e-commerce. This research involved 50 participants trying three different applications (Web, AR, and VR) and filling out online questionnaires. This research used the S-O-R framework as a research model because of interactivity as a stimulus, ease of use, usefulness, enjoyment, subjective norm as an organism, and purchase intention as a response. Partial Least Squares Structural Equation Modelling (PLS-SEM) was used to look for and to compare the effects resulting from the apps. The results of the online questionnaires also tested the validity and reliability of the research using Cronbach Alpha, Composite Reliability (CR), and Average Variance Extracted (AVE). The finding indicates that web applications had a powerful impact on purchasing intention. AR application had a positive effect but was not higher than a web application. VR application didn't have an effect to purchase intention.
{"title":"Evaluation on Purchase Intention of Electronic Devices in Web, AR, and VR Application with Technology Acceptance Model","authors":"Mikhael Ming Khosasih, D. Herumurti, Hadziq Fabroyir","doi":"10.1109/ICTS52701.2021.9607962","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9607962","url":null,"abstract":"This research aims to know and compare the purchase intention on the web, AR, and VR applications using Technology Acceptance Model (TAM). The background of this research is mainly due to the Covid-19 pandemic that makes the e-commerce industry grows rapidly. Nowadays, most e-commerce in Indonesia uses 2D websites, although AR and VR can be applied in e-commerce. This research involved 50 participants trying three different applications (Web, AR, and VR) and filling out online questionnaires. This research used the S-O-R framework as a research model because of interactivity as a stimulus, ease of use, usefulness, enjoyment, subjective norm as an organism, and purchase intention as a response. Partial Least Squares Structural Equation Modelling (PLS-SEM) was used to look for and to compare the effects resulting from the apps. The results of the online questionnaires also tested the validity and reliability of the research using Cronbach Alpha, Composite Reliability (CR), and Average Variance Extracted (AVE). The finding indicates that web applications had a powerful impact on purchasing intention. AR application had a positive effect but was not higher than a web application. VR application didn't have an effect to purchase intention.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"28 1","pages":"18-23"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86897646","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608788
Rafif Rahman Darmawan, F. Rozin, Cynthia Evani, I. Idris, D. Sumardi
Tomato consumption in Indonesia continues to increase every year. Early blight and late blight diseases often attack tomato plants and cause large losses. In this article, an accurate plant disease detection system is designed for the research process of developing high yielding varieties of tomato that are resistant to diseases. The system consists of five subsystems, namely Control, Data Acquisition, Data Storage, Machine Learning, and Data Visualization. Control and Data Visualization are implemented using an Android application. Data Acquisition is implemented with a robotic framework consisting of a sliding cart, an arm, and a camera. The actuators used are stepper motors and servo motors. The data collection is carried out with an Arducam OV5647 with a capturing speed of 8.23 seconds. Data Storage is implemented on three servers: Firebase, CloudMQTT, and Dataplicity, with MQTT and HTTP as the IoT communication protocol. Machine Learning is implemented with an SSD MobileNet V2 FPNLite 640x640 which has an mAP value of 77.25% with an average inference time of 3.71 seconds.
{"title":"IoT and Machine Learning System for Early/Late Blight Disease Severity Level Identification on Tomato Plants","authors":"Rafif Rahman Darmawan, F. Rozin, Cynthia Evani, I. Idris, D. Sumardi","doi":"10.1109/ICTS52701.2021.9608788","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608788","url":null,"abstract":"Tomato consumption in Indonesia continues to increase every year. Early blight and late blight diseases often attack tomato plants and cause large losses. In this article, an accurate plant disease detection system is designed for the research process of developing high yielding varieties of tomato that are resistant to diseases. The system consists of five subsystems, namely Control, Data Acquisition, Data Storage, Machine Learning, and Data Visualization. Control and Data Visualization are implemented using an Android application. Data Acquisition is implemented with a robotic framework consisting of a sliding cart, an arm, and a camera. The actuators used are stepper motors and servo motors. The data collection is carried out with an Arducam OV5647 with a capturing speed of 8.23 seconds. Data Storage is implemented on three servers: Firebase, CloudMQTT, and Dataplicity, with MQTT and HTTP as the IoT communication protocol. Machine Learning is implemented with an SSD MobileNet V2 FPNLite 640x640 which has an mAP value of 77.25% with an average inference time of 3.71 seconds.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"39 1","pages":"288-293"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83575169","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608492
Michael Siek, Kevin Guswanto
People are all currently living in the world where data has changed how company think, act and plan. Data, if used correctly, might be able to become a company's sharpest weapon in fighting the competition with other companies. Inventory cost is one of the most burdening costs in the food and beverage industry with the items like degradable raw materials or fresh ingredients. If not managed correctly might become a waste causing loss to the company. Degraded ingredients also might lower the overall food quality which might result in unsatisfied customers. Managing inventory, however, is not as easy as it seems, especially with the traditional method. This paper focuses on development of accurate predictive model using computational intelligence for optimal inventory management with a case study of restaurant ingredient management. Several machine learning algorithms like linear regression, multi-layer perceptron, random tree, random forest, and model trees were utilized to build accurate predictive models from time series data of the restaurant inventory. With good prediction system using computational intelligence, the inventory cost and wasted ingredients can be significantly reduced, which this eventually maximizes the profit.
{"title":"Developing Accurate Predictive Model Using Computational Intelligence for Optimal Inventory Management","authors":"Michael Siek, Kevin Guswanto","doi":"10.1109/ICTS52701.2021.9608492","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608492","url":null,"abstract":"People are all currently living in the world where data has changed how company think, act and plan. Data, if used correctly, might be able to become a company's sharpest weapon in fighting the competition with other companies. Inventory cost is one of the most burdening costs in the food and beverage industry with the items like degradable raw materials or fresh ingredients. If not managed correctly might become a waste causing loss to the company. Degraded ingredients also might lower the overall food quality which might result in unsatisfied customers. Managing inventory, however, is not as easy as it seems, especially with the traditional method. This paper focuses on development of accurate predictive model using computational intelligence for optimal inventory management with a case study of restaurant ingredient management. Several machine learning algorithms like linear regression, multi-layer perceptron, random tree, random forest, and model trees were utilized to build accurate predictive models from time series data of the restaurant inventory. With good prediction system using computational intelligence, the inventory cost and wasted ingredients can be significantly reduced, which this eventually maximizes the profit.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"38 1","pages":"218-223"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76180912","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608407
Tasnim Sakib Apon, A. Islam, Md. Golam Rabiul Alam
Presently online video games have become a progressively favorite source of recreation and Counter Strike: Global Offensive (CS: GO) is one of the top-listed online first-person shooting games. Numerous competitive games are arranged every year by Esports. Nonetheless, (i) No study has been conducted on video analysis and action recognition of CS: GO game-play which can play a substantial role in the gaming industry for prediction model (ii) No work has been done on the real-time application on the actions and results of a CS: GO match (iii) Game data of a match is usually available in the HLTV as a CSV formatted file however it does not have open access and HLTV tends to prevent users from taking data. This manuscript aims to develop a model for accurate prediction of 4 different actions and compare the performance among the five different transfer learning models with our self-developed deep neural network and identify the best-fitted model and also including major voting later on, which is qualified to provide real time prediction and the result of this model aids to the construction of the automated system of gathering and processing more data alongside solving the issue of collecting data from HLTV.
{"title":"Action Recognition using Transfer Learning and Majority Voting for CSGO","authors":"Tasnim Sakib Apon, A. Islam, Md. Golam Rabiul Alam","doi":"10.1109/ICTS52701.2021.9608407","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608407","url":null,"abstract":"Presently online video games have become a progressively favorite source of recreation and Counter Strike: Global Offensive (CS: GO) is one of the top-listed online first-person shooting games. Numerous competitive games are arranged every year by Esports. Nonetheless, (i) No study has been conducted on video analysis and action recognition of CS: GO game-play which can play a substantial role in the gaming industry for prediction model (ii) No work has been done on the real-time application on the actions and results of a CS: GO match (iii) Game data of a match is usually available in the HLTV as a CSV formatted file however it does not have open access and HLTV tends to prevent users from taking data. This manuscript aims to develop a model for accurate prediction of 4 different actions and compare the performance among the five different transfer learning models with our self-developed deep neural network and identify the best-fitted model and also including major voting later on, which is qualified to provide real time prediction and the result of this model aids to the construction of the automated system of gathering and processing more data alongside solving the issue of collecting data from HLTV.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"226 1","pages":"235-240"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77123541","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608573
A. M. Shiddiqi, Deddy Aditya Pramana, E. Nurhayati, A. B. Raharjo
Small leaks research has attracted researchers for many years due to the impact on economy and environment. The challenge of small leaks detection due to its characteristics that tend to be undetected requires sophisticated method by involving the collaborations of sensor readings. This challenge is even harder in pipeline network with fluctuating minimum n ight fl ow (M NF) in a District Metered Area (DMA). We propose a method that uses the lean graph to place sensors and use the readings to detect and localize small leaks in such situation. Experimental results indicate the lean graph is reliable in finding strategic sensor locations to detect a nd localize leaks.
{"title":"Sensor Placement Strategy to Localize Leaks in Water Distribution Networks with Fluctuating Minimum Night Flow","authors":"A. M. Shiddiqi, Deddy Aditya Pramana, E. Nurhayati, A. B. Raharjo","doi":"10.1109/ICTS52701.2021.9608573","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608573","url":null,"abstract":"Small leaks research has attracted researchers for many years due to the impact on economy and environment. The challenge of small leaks detection due to its characteristics that tend to be undetected requires sophisticated method by involving the collaborations of sensor readings. This challenge is even harder in pipeline network with fluctuating minimum n ight fl ow (M NF) in a District Metered Area (DMA). We propose a method that uses the lean graph to place sensors and use the readings to detect and localize small leaks in such situation. Experimental results indicate the lean graph is reliable in finding strategic sensor locations to detect a nd localize leaks.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"87 1","pages":"264-270"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76985677","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}
Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9607973
Ankit Soni
Mobile robots are effective in search and rescue missions, as well as exploration and surveillance. Autonomous exploration is based on the detection and traversal of frontiers defined by environmental scanning. Many researchers proposed many approaches to successfully explore the entire environment with the use of a frontier. We analyze few approaches in this paper based on three critical factors: The environment's geometry, the laser scanner's field of view, and the robot's energy consumption. Additionally, we analyze the effect of altering the environment's geometry on the robot's energy consumption. Simultaneously, we analyze the impact of changing the laser sensor's field of view on the robot's energy consumption. We can also see the impact of the environment's geometry and the FOV of the laser scanner on the robot's completion time and cost to cover the entire environment. We compared six different Task allocation approaches on two other maps using three different laser scanners (Hokuyo URG1-04LX-UG01, Sick LMS200, and Sick Tim561) and a single pioneer 2-Dx robot.
{"title":"Performance Analysis of Task Allocation for Mobile Robot Exploration Under Energy Constraints","authors":"Ankit Soni","doi":"10.1109/ICTS52701.2021.9607973","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9607973","url":null,"abstract":"Mobile robots are effective in search and rescue missions, as well as exploration and surveillance. Autonomous exploration is based on the detection and traversal of frontiers defined by environmental scanning. Many researchers proposed many approaches to successfully explore the entire environment with the use of a frontier. We analyze few approaches in this paper based on three critical factors: The environment's geometry, the laser scanner's field of view, and the robot's energy consumption. Additionally, we analyze the effect of altering the environment's geometry on the robot's energy consumption. Simultaneously, we analyze the impact of changing the laser sensor's field of view on the robot's energy consumption. We can also see the impact of the environment's geometry and the FOV of the laser scanner on the robot's completion time and cost to cover the entire environment. We compared six different Task allocation approaches on two other maps using three different laser scanners (Hokuyo URG1-04LX-UG01, Sick LMS200, and Sick Tim561) and a single pioneer 2-Dx robot.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"30 1","pages":"282-287"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74978125","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：