Pub Date : 2022-06-25DOI: 10.1109/I2CACIS54679.2022.9815268
Muhammad Fareez Mohd Ainul Hakeem, N. Sulaiman, M. Kassim, N. M. Isa
Bus transportation is important for public users and bus waiting is important in time and schedule management. Today, bus transportation schedules are crucial, especially in identifying the available passengers on the bus and the intended passengers cannot view the available seats on the bus. Another problem is tracking bus location sometimes takes time causing passengers to wait for a long time. This paper presents a simple Internet of Things (IoT) prototype for users to view or for authorities to monitor the bus activity via a mobile application on the available bus seats, bus schedule, and bus activities. The design prototype is using the NodeMCU ESP32 controller which communicates using Wi-Fi. IR sensor and GPS module are used for the input sensors. Blynk and cloud applications are used to present the data analysis on mobile apps. The mobile application was designed where users can view the number of passengers on the bus and the location of the bus. The online database is designed to capture all records of the bus passengers entering and leaving the bus. the result presents the GPS module able to get the exact location of the bus and detect its latitude and longitude. Passengers’ activities on entering and leaving the bus are recorded every 5 seconds. The number of passengers has increased to 20 passengers in 3 minutes at one bus stop. The number of passengers leaving the bus also are recorded and analyzed. These activities can be monitored by the authorities which helps for good services, time, and management for the bus transport services.
{"title":"IoT Bus Monitoring System via Mobile Application","authors":"Muhammad Fareez Mohd Ainul Hakeem, N. Sulaiman, M. Kassim, N. M. Isa","doi":"10.1109/I2CACIS54679.2022.9815268","DOIUrl":"https://doi.org/10.1109/I2CACIS54679.2022.9815268","url":null,"abstract":"Bus transportation is important for public users and bus waiting is important in time and schedule management. Today, bus transportation schedules are crucial, especially in identifying the available passengers on the bus and the intended passengers cannot view the available seats on the bus. Another problem is tracking bus location sometimes takes time causing passengers to wait for a long time. This paper presents a simple Internet of Things (IoT) prototype for users to view or for authorities to monitor the bus activity via a mobile application on the available bus seats, bus schedule, and bus activities. The design prototype is using the NodeMCU ESP32 controller which communicates using Wi-Fi. IR sensor and GPS module are used for the input sensors. Blynk and cloud applications are used to present the data analysis on mobile apps. The mobile application was designed where users can view the number of passengers on the bus and the location of the bus. The online database is designed to capture all records of the bus passengers entering and leaving the bus. the result presents the GPS module able to get the exact location of the bus and detect its latitude and longitude. Passengers’ activities on entering and leaving the bus are recorded every 5 seconds. The number of passengers has increased to 20 passengers in 3 minutes at one bus stop. The number of passengers leaving the bus also are recorded and analyzed. These activities can be monitored by the authorities which helps for good services, time, and management for the bus transport services.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114452317","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815466
Noormadinah Allias, M. M. Noor, Mohd. Taha Ismail, M. Ismail
The Long-Term Evolution network (LTE) has been introduced to cater to the rich content applications of multimedia services. With its ability to support lower latency and higher Throughput, the LTE network can provide faster data download speeds. However, once the mobile user moves from one location to another, the performance tends to degrade. Thus, it required the handover from the serving base station to the target base station. Therefore, the telecommunication service providers must provide a further service enhancement to increase the network quality. As a result, the Key Performance Index (KPI) modeling and predictions can be utilized to achieve this objective. In this article, the Extreme Gradient Boosting regressor algorithm has been selected. However, the hyper-parameter associated with this algorithm needs to be optimized first to produce good prediction results. Three optimization algorithms have been chosen: the Annealing Search, Random Search, and the Tree Parzen Estimator. The experiment results show that the Extreme Gradient Boosting with Annealing Search outperformed the Random Search and the Tree Parzen Estimator by producing the lowest MAE and RMSE and higher R2.
{"title":"Optimization Algorithms: Who own the Crown in Predicting Multi-Output Key Performance Index of LTE Handover","authors":"Noormadinah Allias, M. M. Noor, Mohd. Taha Ismail, M. Ismail","doi":"10.1109/i2cacis54679.2022.9815466","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815466","url":null,"abstract":"The Long-Term Evolution network (LTE) has been introduced to cater to the rich content applications of multimedia services. With its ability to support lower latency and higher Throughput, the LTE network can provide faster data download speeds. However, once the mobile user moves from one location to another, the performance tends to degrade. Thus, it required the handover from the serving base station to the target base station. Therefore, the telecommunication service providers must provide a further service enhancement to increase the network quality. As a result, the Key Performance Index (KPI) modeling and predictions can be utilized to achieve this objective. In this article, the Extreme Gradient Boosting regressor algorithm has been selected. However, the hyper-parameter associated with this algorithm needs to be optimized first to produce good prediction results. Three optimization algorithms have been chosen: the Annealing Search, Random Search, and the Tree Parzen Estimator. The experiment results show that the Extreme Gradient Boosting with Annealing Search outperformed the Random Search and the Tree Parzen Estimator by producing the lowest MAE and RMSE and higher R2.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122071325","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815456
Kuan-Yu Chen, Jungpil Shin, Md. Al Mehedi Hasan, Jiun-Jian Liaw
Sports are full of people’s lives, and regular exercise has become an indicator of people’s health. Due to the high price, most people who exercise at home will not hire fitness trainers, but learn about fitness through media communities. This is likely to lead to the wrong posture of fitness, which can lead to injury. A cheap, simple, and accurate fitness recognition system could increase fitness awareness. This paper proposes a deep transfer learning method that uses Yolov4 to classify fitness movements, which can instantly recognize fitness movements with only one network camera. We built a database, which contains 20 users and online fitness photos, a total of 16302 images, including 12 kinds of fitness movements. 10 user and online photos are used to train Yolov4, and another 10 user photos are used for testing. In the experiment based on Yolov4 to detect fitness, mAP is 99.71%, Precision is 97.9%, Recall is 98.56%, and F1-score is 98.23%. The results show that fitness movements can be detected accurately and quickly using this method.
{"title":"Deep Transfer Learning Based Real Time Fitness Movement Identification","authors":"Kuan-Yu Chen, Jungpil Shin, Md. Al Mehedi Hasan, Jiun-Jian Liaw","doi":"10.1109/i2cacis54679.2022.9815456","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815456","url":null,"abstract":"Sports are full of people’s lives, and regular exercise has become an indicator of people’s health. Due to the high price, most people who exercise at home will not hire fitness trainers, but learn about fitness through media communities. This is likely to lead to the wrong posture of fitness, which can lead to injury. A cheap, simple, and accurate fitness recognition system could increase fitness awareness. This paper proposes a deep transfer learning method that uses Yolov4 to classify fitness movements, which can instantly recognize fitness movements with only one network camera. We built a database, which contains 20 users and online fitness photos, a total of 16302 images, including 12 kinds of fitness movements. 10 user and online photos are used to train Yolov4, and another 10 user photos are used for testing. In the experiment based on Yolov4 to detect fitness, mAP is 99.71%, Precision is 97.9%, Recall is 98.56%, and F1-score is 98.23%. The results show that fitness movements can be detected accurately and quickly using this method.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124540573","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815460
H. Nisar, Kee Wee Boon, Yeap Kim Ho, Teoh Shen Khang
Decoding motor imagery (MI) signals accurately is important for Brain-Computer Interface (BCI) systems for healthcare applications. Electroencephalography (EEG) decoding is a challenging task because of its complexity, and dynamic nature. By improving EEG signal classification, the performance of MI-based BCI can be enhanced. In this paper, five features (Band Power (BP), Approximate Entropy (ApEn), statistical features, wavelet-based features, and Common Spatial Pattern (CSP)) are extracted from EEG signals. For classification, Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Artificial Neural Network (ANN) are used. These methods are tested on a publicly available Physionet motor imagery database. The EEG signals are recorded from 64 channels for 50 subjects, while the subject is performing four different MI tasks. The proposed method achieved an accuracy of 98.53% for left and right hands MI tasks with ApEn feature (overlapping ratio~ 0.8) and SVM classifier. Hence the proposed method shows better results than several EEG MI classification methods proposed in the literature.
{"title":"Brain-Computer Interface: Feature Extraction and Classification of Motor Imagery-Based Cognitive Tasks","authors":"H. Nisar, Kee Wee Boon, Yeap Kim Ho, Teoh Shen Khang","doi":"10.1109/i2cacis54679.2022.9815460","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815460","url":null,"abstract":"Decoding motor imagery (MI) signals accurately is important for Brain-Computer Interface (BCI) systems for healthcare applications. Electroencephalography (EEG) decoding is a challenging task because of its complexity, and dynamic nature. By improving EEG signal classification, the performance of MI-based BCI can be enhanced. In this paper, five features (Band Power (BP), Approximate Entropy (ApEn), statistical features, wavelet-based features, and Common Spatial Pattern (CSP)) are extracted from EEG signals. For classification, Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Artificial Neural Network (ANN) are used. These methods are tested on a publicly available Physionet motor imagery database. The EEG signals are recorded from 64 channels for 50 subjects, while the subject is performing four different MI tasks. The proposed method achieved an accuracy of 98.53% for left and right hands MI tasks with ApEn feature (overlapping ratio~ 0.8) and SVM classifier. Hence the proposed method shows better results than several EEG MI classification methods proposed in the literature.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121430007","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815486
Mohd Fikri Hadrawi, S. Shariff, Nur Ashikin Muhamad, Nurin Alya Abdullah, Nurshafiqah Ahmad Damanhuri
The Covid-19 pandemic is worrying the workforce, especially in the transportation sector since transportation has been one of Malaysia's crucial sectors. The problem of losing jobs during the Covid-19 pandemic largely contributes to low economic Malaysians, especially in the urgent need for change. Thus, adopting a strategic approach is needed to plan and manage workforce trends to prevent a drop in the economy. This study examines the workforce pattern in the transportation sector in Malaysia, comparing them using time series models and forecasting them using the best fit time series model. It studies explicitly the export and import volume in Malaysia from the year 2010 until 2020 and the number of workforces in the transportation sector in Malaysia from 2012 until 2020. The data were used to model and forecast the export and import volume and the number of workers in the transportation sector in Malaysia. It is found that ARIMA (0, 1, 1) model was able to produce the forecasted values for the year 2020 for export volume in Malaysia based on the values of RMSE and Holt’s (α = 0.34, β = 0.01, γ = 0.3) were able to forecast for export volume in Malaysia when the MAE and MAPE values were considered. Also, it is found that ARIMA (2, 1, 3) model was able to produce the forecast value for import volume in Malaysia for 2020 when the MAE and RMSE were used while Holt’s model (α = 0.41, β = 0.04, γ = 0.5) when MAPE value was considered. Lastly, ARIMA (1,1,1) was used as the selection criteria for forecasting the number of workers in the transportation sector in Malaysia for 2020 when RMSE and MAPE were used Holt’s (α =0.62, β = 0.00000000000000034694) model meanwhile when MAE value was considered.
{"title":"Modelling Workforce For Transportation Sector In Malaysia (Considering Covid-19 Pandemic)","authors":"Mohd Fikri Hadrawi, S. Shariff, Nur Ashikin Muhamad, Nurin Alya Abdullah, Nurshafiqah Ahmad Damanhuri","doi":"10.1109/i2cacis54679.2022.9815486","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815486","url":null,"abstract":"The Covid-19 pandemic is worrying the workforce, especially in the transportation sector since transportation has been one of Malaysia's crucial sectors. The problem of losing jobs during the Covid-19 pandemic largely contributes to low economic Malaysians, especially in the urgent need for change. Thus, adopting a strategic approach is needed to plan and manage workforce trends to prevent a drop in the economy. This study examines the workforce pattern in the transportation sector in Malaysia, comparing them using time series models and forecasting them using the best fit time series model. It studies explicitly the export and import volume in Malaysia from the year 2010 until 2020 and the number of workforces in the transportation sector in Malaysia from 2012 until 2020. The data were used to model and forecast the export and import volume and the number of workers in the transportation sector in Malaysia. It is found that ARIMA (0, 1, 1) model was able to produce the forecasted values for the year 2020 for export volume in Malaysia based on the values of RMSE and Holt’s (α = 0.34, β = 0.01, γ = 0.3) were able to forecast for export volume in Malaysia when the MAE and MAPE values were considered. Also, it is found that ARIMA (2, 1, 3) model was able to produce the forecast value for import volume in Malaysia for 2020 when the MAE and RMSE were used while Holt’s model (α = 0.41, β = 0.04, γ = 0.5) when MAPE value was considered. Lastly, ARIMA (1,1,1) was used as the selection criteria for forecasting the number of workers in the transportation sector in Malaysia for 2020 when RMSE and MAPE were used Holt’s (α =0.62, β = 0.00000000000000034694) model meanwhile when MAE value was considered.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121669570","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815482
Syahrul Nizam Samsudin, B. Abdullah, Noriah Yusoff
Service Advisor in Automotive Service Centre plays an important role as the frontline in providing exceptional services. The automotive service centre has to adopt big data applications in understanding customers’ needs by collecting data promptly and analysing scientifically. The objective of this paper is to evaluate Customer Satisfaction (CS) and Service Advisor Experience (SAE) scores via an online survey based on big data analytics. Thus, applying a Quadrifid graph in identifying focus regions for improvement activities. The application of big data online survey platforms is an efficient way of gathering customer feedback for continuous improvement activities. The study focused on Service Advisor (SA) services throughout Malaysia with selected one automotive brand. It explains the definition of customer process and customer satisfaction by comparing high-density customer regions namely Central, Northern and Southern regions with low-density customer regions namely East Coast and East Malaysia regions. There are five steps in deriving the output, which are the consolidation of customer data, customer selection, survey execution, score calculation and analytical report. Thus, the big data applications analyse the expectation SA gap and propose recommendation actions. The online survey results achieved a minimum of 879.90 points for Customer Satisfaction while Service Advisor Experience was minimum at 73%. SA achieved a high score for portraying courtesy and professionalism, while a lack of performing the visual inspection is the main gap for all regions. Detailed analysis using Quadrifid graph interpreted Southern region recorded the lowest correlation with R-square value less than 0.1 and level of CS & SAE below the average value of 800 relates to response towards needs by SA. In this paper, the outcome of the execution is centralization of customer information, Service Level Agreement standard, customer handling norms and work efficiency improvement. Such indicators lead to the SA’s professionalism in managing customer expectations.
{"title":"Customer Satisfaction and Service Experience in Big Data Analytics for Automotive Service Advisor","authors":"Syahrul Nizam Samsudin, B. Abdullah, Noriah Yusoff","doi":"10.1109/i2cacis54679.2022.9815482","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815482","url":null,"abstract":"Service Advisor in Automotive Service Centre plays an important role as the frontline in providing exceptional services. The automotive service centre has to adopt big data applications in understanding customers’ needs by collecting data promptly and analysing scientifically. The objective of this paper is to evaluate Customer Satisfaction (CS) and Service Advisor Experience (SAE) scores via an online survey based on big data analytics. Thus, applying a Quadrifid graph in identifying focus regions for improvement activities. The application of big data online survey platforms is an efficient way of gathering customer feedback for continuous improvement activities. The study focused on Service Advisor (SA) services throughout Malaysia with selected one automotive brand. It explains the definition of customer process and customer satisfaction by comparing high-density customer regions namely Central, Northern and Southern regions with low-density customer regions namely East Coast and East Malaysia regions. There are five steps in deriving the output, which are the consolidation of customer data, customer selection, survey execution, score calculation and analytical report. Thus, the big data applications analyse the expectation SA gap and propose recommendation actions. The online survey results achieved a minimum of 879.90 points for Customer Satisfaction while Service Advisor Experience was minimum at 73%. SA achieved a high score for portraying courtesy and professionalism, while a lack of performing the visual inspection is the main gap for all regions. Detailed analysis using Quadrifid graph interpreted Southern region recorded the lowest correlation with R-square value less than 0.1 and level of CS & SAE below the average value of 800 relates to response towards needs by SA. In this paper, the outcome of the execution is centralization of customer information, Service Level Agreement standard, customer handling norms and work efficiency improvement. Such indicators lead to the SA’s professionalism in managing customer expectations.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132652351","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815490
Jewel Kate D. Lagman, Alden B. Evangelista, C. Paglinawan
When a disaster or accident occurs, the first thing that must be done is search operations; this must be done carefully and discretely using a well-defined procedure. Its purpose is to help people who are in immediate danger. However, conducting search operations by a person, especially in a risky location, is not safe due to limited equipment and dangerous scenarios. This study developed an Unmanned Aerial Vehicles (UAV) prototype that captures even with an overview head image for the search operation and detects humans in the image. After detecting the presence of a human in an image, the prototype counts the actual people in the frame and displays the total number of people discovered in real time. Suppose the same person was detected twice but in a different frame, it will be still counted on the overall person counts. In object detection, You Only Look Once Version 5 (YOLOv5) is used as an algorithm. Thermal camera will be added for more accurate results from the detected person.
当灾难或事故发生时，必须做的第一件事是搜索行动;这必须小心谨慎地使用一个定义良好的程序来完成。它的目的是帮助那些处于直接危险中的人。然而，由于有限的设备和危险的情况，一个人进行搜索行动是不安全的，特别是在危险的地方。该研究开发了一种无人机(UAV)原型机，该原型机可以捕获用于搜索操作的全景头部图像，并在图像中检测人类。在检测到图像中存在人类后，该原型会对帧中的实际人物进行计数，并实时显示发现的总人数。假设同一个人被检测了两次，但在不同的帧中，它仍然会被计算在总人数上。在目标检测中，使用You Only Look Once Version 5 (YOLOv5)作为算法。为了从被检测的人那里获得更准确的结果，将增加热像仪。
{"title":"Unmanned Aerial Vehicle with Human Detection and People Counter Using YOLO v5 and Thermal Camera for Search Operations","authors":"Jewel Kate D. Lagman, Alden B. Evangelista, C. Paglinawan","doi":"10.1109/i2cacis54679.2022.9815490","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815490","url":null,"abstract":"When a disaster or accident occurs, the first thing that must be done is search operations; this must be done carefully and discretely using a well-defined procedure. Its purpose is to help people who are in immediate danger. However, conducting search operations by a person, especially in a risky location, is not safe due to limited equipment and dangerous scenarios. This study developed an Unmanned Aerial Vehicles (UAV) prototype that captures even with an overview head image for the search operation and detects humans in the image. After detecting the presence of a human in an image, the prototype counts the actual people in the frame and displays the total number of people discovered in real time. Suppose the same person was detected twice but in a different frame, it will be still counted on the overall person counts. In object detection, You Only Look Once Version 5 (YOLOv5) is used as an algorithm. Thermal camera will be added for more accurate results from the detected person.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131713845","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815483
R. S. Alejandrino, Maria Carmela G. Diomampo, Jessie R. Balbin
This study delves upon the design and development of a smart water meter system that provides an IoT-based platform which provides consumption and billing reports in real time. The system is capable of automated data collection and upload phases in times of meter inactivity. Google Apps Scripting (GAS) was used to provide interfacing between the physical prototype, Google Sheets, and a mobile application. A calibrated equation for the determination of water consumption and flow rate is generated using MATLAB Curve Fitting Tool. Having undergone statistical analysis, the volume measurement methods deployed were of no significant difference with each other. Overall, the system was verified to be functional in all aspects of its operation.
{"title":"Smart Water Meter with Cloud Database and Water Bill Consumption Monitoring via SMS and Mobile Application","authors":"R. S. Alejandrino, Maria Carmela G. Diomampo, Jessie R. Balbin","doi":"10.1109/i2cacis54679.2022.9815483","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815483","url":null,"abstract":"This study delves upon the design and development of a smart water meter system that provides an IoT-based platform which provides consumption and billing reports in real time. The system is capable of automated data collection and upload phases in times of meter inactivity. Google Apps Scripting (GAS) was used to provide interfacing between the physical prototype, Google Sheets, and a mobile application. A calibrated equation for the determination of water consumption and flow rate is generated using MATLAB Curve Fitting Tool. Having undergone statistical analysis, the volume measurement methods deployed were of no significant difference with each other. Overall, the system was verified to be functional in all aspects of its operation.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120947485","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 : 2022-06-25DOI: 10.1109/I2CACIS54679.2022.9815495
Yong Ching Lee, Y. Alshebly, Marwan Nafea
Four-dimensional (4D) printed structures have great potential to be deployed in various sectors, such as industrial and biomedical applications. The high complexity allowed by additive manufacturing, coupled with the shape change allowed by shape memory materials (SMMs) opened a wide range of applications for this field. However, most methods used to activate SMMs rely on the use of hot air or hot water. Such methods limit the application ranges of 4D printed structures. Thus, in this paper, polylactic acid combined with carbon black is used as the filament material for the printing process, which relies on the fused deposition modeling approach. The carbon black makes the filament conductive, allowing it to be heated by an electrical current. Joule heating is used to activate four actuators printed at different printing speeds, causing larger bending as the printing speed increases. The activation of the actuators is made by allowing electrical current to pass through the actuators and gradually heating them from 30 °C to 80 °C. The heating process requires 69 to 85 seconds to reach full deformation while the voltage and current are stable. The actuators achieved bending angles of 13°, 19°, 26°, and 32° when the printing speed of the active layers was 20, 40, 60, and 80 mm/s, the respectively. The developed actuators show promising performance, making them suitable for various applications in robotics.
{"title":"Joule Heating Activation of 4D Printed Conductive PLA Actuators","authors":"Yong Ching Lee, Y. Alshebly, Marwan Nafea","doi":"10.1109/I2CACIS54679.2022.9815495","DOIUrl":"https://doi.org/10.1109/I2CACIS54679.2022.9815495","url":null,"abstract":"Four-dimensional (4D) printed structures have great potential to be deployed in various sectors, such as industrial and biomedical applications. The high complexity allowed by additive manufacturing, coupled with the shape change allowed by shape memory materials (SMMs) opened a wide range of applications for this field. However, most methods used to activate SMMs rely on the use of hot air or hot water. Such methods limit the application ranges of 4D printed structures. Thus, in this paper, polylactic acid combined with carbon black is used as the filament material for the printing process, which relies on the fused deposition modeling approach. The carbon black makes the filament conductive, allowing it to be heated by an electrical current. Joule heating is used to activate four actuators printed at different printing speeds, causing larger bending as the printing speed increases. The activation of the actuators is made by allowing electrical current to pass through the actuators and gradually heating them from 30 °C to 80 °C. The heating process requires 69 to 85 seconds to reach full deformation while the voltage and current are stable. The actuators achieved bending angles of 13°, 19°, 26°, and 32° when the printing speed of the active layers was 20, 40, 60, and 80 mm/s, the respectively. The developed actuators show promising performance, making them suitable for various applications in robotics.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116638952","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 : 2022-06-25DOI: 10.1109/i2cacis54679.2022.9815275
David Nathan Arulnathan, Brenda Chia Wen Koay, W. Lai, T. K. Ong, Li Li Lim
Image background subtraction is an important and essential process in many computer vision applications as allows for a more effective processing of the foreground objects. Various methods have been proposed for performing background subtraction in the literature. In this study, we investigated various background subtraction to automatically identify the correct class of the foreground objects. There are only a few major producers of palm oil and Malaysia is the world’s second-largest producer and exporter of palm oil in terms of volume. In 2019, the gross domestic product (GDP) contribution from palm oil in Malaysia was estimated to be around 37.6 billion ringgit to Malaysia’s economy or at 2.7 percent of the country’s GDP. Among the many major industries, it is one of Malaysia’s primary industries, and a main agricultural export. There are various studies to automatically identify fruit ripeness, ranging from mangos to strawberries, etc. In addition, there have been some work in recent years to identify the maturity of the palm oil fruit bunches, and the use of Raman spectroscopy on individual fruitlets, etc. This study investigates the effect of background subtraction on the performance of a deep neural network to accurately identify the ripeness of palm oil fruitlets i.e. ripe, unripe and over ripe. This was compared with a feature based probabilistic approach.
{"title":"Background Subtraction for Accurate Palm Oil Fruitlet Ripeness Detection","authors":"David Nathan Arulnathan, Brenda Chia Wen Koay, W. Lai, T. K. Ong, Li Li Lim","doi":"10.1109/i2cacis54679.2022.9815275","DOIUrl":"https://doi.org/10.1109/i2cacis54679.2022.9815275","url":null,"abstract":"Image background subtraction is an important and essential process in many computer vision applications as allows for a more effective processing of the foreground objects. Various methods have been proposed for performing background subtraction in the literature. In this study, we investigated various background subtraction to automatically identify the correct class of the foreground objects. There are only a few major producers of palm oil and Malaysia is the world’s second-largest producer and exporter of palm oil in terms of volume. In 2019, the gross domestic product (GDP) contribution from palm oil in Malaysia was estimated to be around 37.6 billion ringgit to Malaysia’s economy or at 2.7 percent of the country’s GDP. Among the many major industries, it is one of Malaysia’s primary industries, and a main agricultural export. There are various studies to automatically identify fruit ripeness, ranging from mangos to strawberries, etc. In addition, there have been some work in recent years to identify the maturity of the palm oil fruit bunches, and the use of Raman spectroscopy on individual fruitlets, etc. This study investigates the effect of background subtraction on the performance of a deep neural network to accurately identify the ripeness of palm oil fruitlets i.e. ripe, unripe and over ripe. This was compared with a feature based probabilistic approach.","PeriodicalId":332297,"journal":{"name":"2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114955309","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：