Pub Date : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466006
Rezki Wulandari Arief, I. Nurtanio, Faizal Arya Samman
Traffic signs are one of the important road equipment facilities to inform road users about regulations and visual directions. Currently, an automatic Traffic Sign Recognition (TSR) system is being developed which is implemented in an advanced driver system (ADAS) so that road users can be safe and secure while on the road. Therefore, this paper aims to be able to detect and recognize traffic signs on the highway to provide information on the meaning of these traffic signs automatically. In this study, 35 classes of signs were used which consisted of warning signs, prohibitions signs, mandatory signs, and instructions signs. This system is implemented using the Darknet framework with the You Only Look Once version 4 (YOLOv4) model. The investigation carried out in this study is a system that detects and recognizes traffic signs evaluated on offline-based video in one-way traffic during the day. The result of mAP (mean Average Precision) in this system is 95.15%.
交通标志是一种重要的道路设备设施，用于向道路使用者告知交通法规和视觉方向。目前，一种自动交通标志识别(TSR)系统正在开发中，该系统在高级驾驶系统(ADAS)中实施，以便道路使用者在路上可以安全可靠。因此，本文的目标是能够对高速公路上的交通标志进行检测和识别，并自动提供这些交通标志的含义信息。在这项研究中，使用了35类标志，包括警告标志、禁止标志、强制性标志和指示标志。该系统是使用暗网框架与你只看一次版本4 (YOLOv4)模型实现的。本研究中进行的调查是一个检测和识别交通标志的系统，该系统在白天的单向交通中通过离线视频进行评估。该系统的mAP (mean Average Precision)精度为95.15%。
{"title":"Traffic Signs Detection and Recognition System Using the YOLOv4 Algorithm","authors":"Rezki Wulandari Arief, I. Nurtanio, Faizal Arya Samman","doi":"10.1109/AIMS52415.2021.9466006","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466006","url":null,"abstract":"Traffic signs are one of the important road equipment facilities to inform road users about regulations and visual directions. Currently, an automatic Traffic Sign Recognition (TSR) system is being developed which is implemented in an advanced driver system (ADAS) so that road users can be safe and secure while on the road. Therefore, this paper aims to be able to detect and recognize traffic signs on the highway to provide information on the meaning of these traffic signs automatically. In this study, 35 classes of signs were used which consisted of warning signs, prohibitions signs, mandatory signs, and instructions signs. This system is implemented using the Darknet framework with the You Only Look Once version 4 (YOLOv4) model. The investigation carried out in this study is a system that detects and recognizes traffic signs evaluated on offline-based video in one-way traffic during the day. The result of mAP (mean Average Precision) in this system is 95.15%.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130940768","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466007
Saad Arif, Mahad Arif, Saba Munawar, Y. Ayaz, Muhammad Jawad Khan, Noman Naseer
A passive brain-computer interface (BCI) based upon electroencephalography (EEG) brain signals was developed to classify alert and drowsy states during the driving task. This BCI modality acquired electrical neuronal activity of five healthy male subjects from prefrontal and occipital cortices of the human brain for earlier drowsiness detection. Brain activity is recorded using a 16-channel EEG headset from these brain locations. Sleep-deprived subjects drove the vehicle in a simulated driving environment while neuronal activity was continuously monitored in prefrontal and occipital regions. Spectral band power and power spectral density estimate for $alpha$ and $beta$ frequency bands were used as features along with k-nearest neighbor (kNN) and support vector machine (SVM) classifiers. Average classification accuracies are 95.8% for kNN and 93.8% for SVM with a 10-fold cross-validation model. Spectral analysis shows that $alpha$-rhythms are more prominent in the occipital region as compared to the prefrontal region during drowsy driving and hence vision-based brain data is more effective for earlier detection as compared to the focus-based brain data. The proposed EEG-based passive BCI scheme is promising for earlier differentiation between drowsy and alert states from the occipital region of the human brain.
提出了一种基于脑电图(EEG)信号的被动脑机接口(BCI)，用于对驾驶过程中的清醒和困倦状态进行分类。该脑机接口模式从人类大脑前额叶和枕叶皮层获取5名健康男性受试者的电神经元活动，用于早期嗜睡检测。大脑活动是用16通道脑电图耳机从这些大脑位置记录下来的。睡眠不足的受试者在模拟驾驶环境中驾驶车辆，同时持续监测前额叶和枕叶区域的神经元活动。使用$alpha$和$beta$频段的频谱带功率和功率谱密度估计作为特征，以及k-最近邻(kNN)和支持向量机(SVM)分类器。平均分类准确率为95.8% for kNN and 93.8% for SVM with a 10-fold cross-validation model. Spectral analysis shows that $alpha$-rhythms are more prominent in the occipital region as compared to the prefrontal region during drowsy driving and hence vision-based brain data is more effective for earlier detection as compared to the focus-based brain data. The proposed EEG-based passive BCI scheme is promising for earlier differentiation between drowsy and alert states from the occipital region of the human brain.
{"title":"EEG Spectral Comparison Between Occipital and Prefrontal Cortices for Early Detection of Driver Drowsiness","authors":"Saad Arif, Mahad Arif, Saba Munawar, Y. Ayaz, Muhammad Jawad Khan, Noman Naseer","doi":"10.1109/AIMS52415.2021.9466007","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466007","url":null,"abstract":"A passive brain-computer interface (BCI) based upon electroencephalography (EEG) brain signals was developed to classify alert and drowsy states during the driving task. This BCI modality acquired electrical neuronal activity of five healthy male subjects from prefrontal and occipital cortices of the human brain for earlier drowsiness detection. Brain activity is recorded using a 16-channel EEG headset from these brain locations. Sleep-deprived subjects drove the vehicle in a simulated driving environment while neuronal activity was continuously monitored in prefrontal and occipital regions. Spectral band power and power spectral density estimate for $alpha$ and $beta$ frequency bands were used as features along with k-nearest neighbor (kNN) and support vector machine (SVM) classifiers. Average classification accuracies are 95.8% for kNN and 93.8% for SVM with a 10-fold cross-validation model. Spectral analysis shows that $alpha$-rhythms are more prominent in the occipital region as compared to the prefrontal region during drowsy driving and hence vision-based brain data is more effective for earlier detection as compared to the focus-based brain data. The proposed EEG-based passive BCI scheme is promising for earlier differentiation between drowsy and alert states from the occipital region of the human brain.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130894741","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466020
Abdul Azis Lihawa, E. Palantei, Y. Akil
Fishing industries in tropical countries needed to spend big portion of their resources to freeze their fish product to postpone its rotten condition. This study aimed to offer lower cost solution to postpone fish rotting process. The solution used electromagnetic heating process in a big metal chamber powered by a magnetron which was connected to a waveguide and a pyramidal horn antenna. Non-uniform heating problem was addressed using electromagnetic wave stirring mechanism. Computer simulation showed that various angle of wave stirring mechanism (0°, 15°, 30°, 45°, 60° and 75°) provide different pattern of hot and cold spot in the chamber, thus swinging the stirring mechanism created more uniform heating process. Experimental validation showed that fish samples can be heated to 70 °C in various spots, high enough to kill the microbes that made the fish rotten.
{"title":"The Effect of Wave Stirring Mechanism in Improving Heating Uniformity in Microwave Chamber For Fishing Industry","authors":"Abdul Azis Lihawa, E. Palantei, Y. Akil","doi":"10.1109/AIMS52415.2021.9466020","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466020","url":null,"abstract":"Fishing industries in tropical countries needed to spend big portion of their resources to freeze their fish product to postpone its rotten condition. This study aimed to offer lower cost solution to postpone fish rotting process. The solution used electromagnetic heating process in a big metal chamber powered by a magnetron which was connected to a waveguide and a pyramidal horn antenna. Non-uniform heating problem was addressed using electromagnetic wave stirring mechanism. Computer simulation showed that various angle of wave stirring mechanism (0°, 15°, 30°, 45°, 60° and 75°) provide different pattern of hot and cold spot in the chamber, thus swinging the stirring mechanism created more uniform heating process. Experimental validation showed that fish samples can be heated to 70 °C in various spots, high enough to kill the microbes that made the fish rotten.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114755290","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466092
Hamidan Z. Wijasena, R. Ferdiana, S. Wibirama
Emotion recognition may establish a clinical framework for measuring emotional wellbeing and screening for quality of life, cognitive dysfunction, and mental disorder. Emotions are conveyed not just through interpersonal actions but also by several physiological differences. Emotions can be monitored using physiological signals in wearable devices such as smartwatches or wrist bands. However, there are various challenges for detecting emotion in unrestricted daily life using wearable or smartwatch devices. These challenges result in lower performances of such systems compared to semi-restricted and laboratory environment studies. The addition of uniqueness in each individual physiological signal, physical activity level, and activity type to the physiological signals can affect classification accuracy of these systems. To tackle these challenges, we present a brief literature review on the study of physiological signals using wearable devices primarily from the last three years. The phase of emotion recognition using physiological signals is briefly defined. This paper also presents listed forms of physiological signals and various sensors for detecting them. In addition, we discussed the emotional models and emotional stimulation approaches. This study is expected to bring new insight into research challenges, limitations, and possible future emotion detection and recognition using wearable or smartwatch devices.
{"title":"A Survey of Emotion Recognition using Physiological Signal in Wearable Devices","authors":"Hamidan Z. Wijasena, R. Ferdiana, S. Wibirama","doi":"10.1109/AIMS52415.2021.9466092","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466092","url":null,"abstract":"Emotion recognition may establish a clinical framework for measuring emotional wellbeing and screening for quality of life, cognitive dysfunction, and mental disorder. Emotions are conveyed not just through interpersonal actions but also by several physiological differences. Emotions can be monitored using physiological signals in wearable devices such as smartwatches or wrist bands. However, there are various challenges for detecting emotion in unrestricted daily life using wearable or smartwatch devices. These challenges result in lower performances of such systems compared to semi-restricted and laboratory environment studies. The addition of uniqueness in each individual physiological signal, physical activity level, and activity type to the physiological signals can affect classification accuracy of these systems. To tackle these challenges, we present a brief literature review on the study of physiological signals using wearable devices primarily from the last three years. The phase of emotion recognition using physiological signals is briefly defined. This paper also presents listed forms of physiological signals and various sensors for detecting them. In addition, we discussed the emotional models and emotional stimulation approaches. This study is expected to bring new insight into research challenges, limitations, and possible future emotion detection and recognition using wearable or smartwatch devices.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114824136","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466060
Adam R A Saad, R. S. Wibowo, D. Riawan
Renewable energy resources were getting the attention in the electricity research fields, many countries invested in the renewable energy to replace the existing generation systems which depends on the fossil fuels resources. This could provide cheap, affordable and clean energy by decreasing the level of CO2 emissions. This research presented a real case study in AL-Bayda city, Libya, focused in decreasing the burden from the main medium voltage electricity network came from Benghazi city as this source could not satisfy the total load in Al-Bayda city, that's why the electricity occasionally died during the week especially in the residential loads. Injecting a photovoltaic (PV) system with batteries beside a diesel generator (DG) is the solution for this research by choosing the optimum operation, the optimum size of the DG and defined the best bus location which could provide the minimum losses and costs using the Firefly Algorithm (FA). Considering the MPPT to get the maximum output power which we could get from the PV system. Forward-backward method used to do the power flow calculation for this radial network which consisted of 71 busses. Collares-Pereira and Rabel statistical method used before by researchers to calculate the hourly solar radiation, and will be implemented it in this research as the provided data is the daily solar radiation. The optimum values of the injected PV, DG and Batteries were 2.0, 2.5 and 0.6 Megawatt respectively.
{"title":"Minimizing the Losses and Cost of a Radial Network Connected to DG, PV and Batteries using Firefly Algorithm in Al-Bayda city, Libya","authors":"Adam R A Saad, R. S. Wibowo, D. Riawan","doi":"10.1109/AIMS52415.2021.9466060","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466060","url":null,"abstract":"Renewable energy resources were getting the attention in the electricity research fields, many countries invested in the renewable energy to replace the existing generation systems which depends on the fossil fuels resources. This could provide cheap, affordable and clean energy by decreasing the level of CO2 emissions. This research presented a real case study in AL-Bayda city, Libya, focused in decreasing the burden from the main medium voltage electricity network came from Benghazi city as this source could not satisfy the total load in Al-Bayda city, that's why the electricity occasionally died during the week especially in the residential loads. Injecting a photovoltaic (PV) system with batteries beside a diesel generator (DG) is the solution for this research by choosing the optimum operation, the optimum size of the DG and defined the best bus location which could provide the minimum losses and costs using the Firefly Algorithm (FA). Considering the MPPT to get the maximum output power which we could get from the PV system. Forward-backward method used to do the power flow calculation for this radial network which consisted of 71 busses. Collares-Pereira and Rabel statistical method used before by researchers to calculate the hourly solar radiation, and will be implemented it in this research as the provided data is the daily solar radiation. The optimum values of the injected PV, DG and Batteries were 2.0, 2.5 and 0.6 Megawatt respectively.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116010045","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466028
Zaki Akhmad Faridzan, Ratna Mayasari, N. Karna
The increasing population in Indonesia has resulted in an increase in the community's need for land ownership. Although the government has made regulations regarding the installation of land boundary markers using boundary markers, there are still several conflicts over land grabbing which are carried out by removing or removing land boundary markers that have been installed. For this reason, a prototype monitoring system for boundary markers based on the internet of things and a website was designed using the Long-Range (LoRa) module. LoRa or LoRaWAN is a Low Power Wide Area Network (LPWAN) technology. In this monitoring system, there is a GPS module on the LoRa end-device to detect the coordinates of the boundary markers. To make monitoring easier, the website designed will display data from the Firebase database. The system designed has QoS performance with a delay value from the LoRa end-device to the LoRa gateway at the lowest spreading factor of SF7, namely 0.751 seconds, while the highest is SF12, which is 2.514 seconds at a transmission distance of 500 m, and SF7 has the highest percentage of packet loss. The GPS used has an accuracy of 1.329096 m. SF7 has the lowest transmit current consumption compared to other SF when transmitting, namely 11.31 mA.
{"title":"IoT Long Range (LoRa) for Land Boundary Monitoring System","authors":"Zaki Akhmad Faridzan, Ratna Mayasari, N. Karna","doi":"10.1109/AIMS52415.2021.9466028","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466028","url":null,"abstract":"The increasing population in Indonesia has resulted in an increase in the community's need for land ownership. Although the government has made regulations regarding the installation of land boundary markers using boundary markers, there are still several conflicts over land grabbing which are carried out by removing or removing land boundary markers that have been installed. For this reason, a prototype monitoring system for boundary markers based on the internet of things and a website was designed using the Long-Range (LoRa) module. LoRa or LoRaWAN is a Low Power Wide Area Network (LPWAN) technology. In this monitoring system, there is a GPS module on the LoRa end-device to detect the coordinates of the boundary markers. To make monitoring easier, the website designed will display data from the Firebase database. The system designed has QoS performance with a delay value from the LoRa end-device to the LoRa gateway at the lowest spreading factor of SF7, namely 0.751 seconds, while the highest is SF12, which is 2.514 seconds at a transmission distance of 500 m, and SF7 has the highest percentage of packet loss. The GPS used has an accuracy of 1.329096 m. SF7 has the lowest transmit current consumption compared to other SF when transmitting, namely 11.31 mA.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128933366","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466047
E. Joelianto
Conventional control systems have been known to experience difficulties in achieving the multi-objective faced by controlled systems. Advanced control methods beyond the one-degree-of-freedom (1-DOF) controller have been considered to solve the multi-criteria requirements in the control system design. Two-degree-of-freedom (2-DOF) controllers are renowned for offering flexibility in handling the stability, tracking response, and disturbance or noise rejection requirements of closed-loop systems. Such powerful capabilities are achieved with feedback and/or feed-forward configurations. In addition, the configuration can be carried out with cascade and/or parallel structures. The cascade control structure in the 2-DOF controllers has received a lot of attention over the decades. On the other hand, parallel control structures are less discussed in the literature. In this paper, the parallel control structures are reviewed and discussed along with the development of their potential to deal with today's increasingly complex control problems. The discussion covers conventional to intelligent approaches related to the development of intelligent systems that have been applied everywhere recently.
{"title":"Parallel Control Structure: From Conventional To Intelligent","authors":"E. Joelianto","doi":"10.1109/AIMS52415.2021.9466047","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466047","url":null,"abstract":"Conventional control systems have been known to experience difficulties in achieving the multi-objective faced by controlled systems. Advanced control methods beyond the one-degree-of-freedom (1-DOF) controller have been considered to solve the multi-criteria requirements in the control system design. Two-degree-of-freedom (2-DOF) controllers are renowned for offering flexibility in handling the stability, tracking response, and disturbance or noise rejection requirements of closed-loop systems. Such powerful capabilities are achieved with feedback and/or feed-forward configurations. In addition, the configuration can be carried out with cascade and/or parallel structures. The cascade control structure in the 2-DOF controllers has received a lot of attention over the decades. On the other hand, parallel control structures are less discussed in the literature. In this paper, the parallel control structures are reviewed and discussed along with the development of their potential to deal with today's increasingly complex control problems. The discussion covers conventional to intelligent approaches related to the development of intelligent systems that have been applied everywhere recently.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132323714","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466046
I. A. Dahlan, Dananjaya Ariateja, F. Hamami, Heryanto
Internet of Things (IoT) makes many devices getting smarter and more connected in the 4.0 industrial revolution. One of the implementations of the Internet of Things is smart energy. It allows communication between humans or between things that make a building smarter. This paper proposes the implementation of the MQTT-based smart meter. The smart meter is used to make it easier for users to monitor and manage the energy consumption of buildings in real-time. It is considered as the main component of a smart network to make efficient and manage energy consumption remotely. Taking into account the increasing demand for electricity in Indonesia, smart meters can reduce overall energy use and reduce global warming by optimizing energy utilization through the internet of things and artificial intelligence. This paper proposes the implementation of the MQTT-based smart meter. This smart meter can measure energy consumption, transmit information related to the energy used, and provide an early warning system to stakeholders through the website in real-time analytics with predictive data on the following month and what days are most used to support energy consumption efficiency planning. This study conducted LTSM and ARIMA to determine forecasting energy consumption with 59 epochs, 8 batch sizes, 64 hidden layers with the results of MSE Error, RMSE Error, Mean Accuracy 0.14,0.373, and 95.16%, respectively. This result is better than ARIMA with MSE error results of 0.812 and 0.66 and RMSE error.
{"title":"The Implementation of Building Intelligent Smart Energy using LSTM Neural Network","authors":"I. A. Dahlan, Dananjaya Ariateja, F. Hamami, Heryanto","doi":"10.1109/AIMS52415.2021.9466046","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466046","url":null,"abstract":"Internet of Things (IoT) makes many devices getting smarter and more connected in the 4.0 industrial revolution. One of the implementations of the Internet of Things is smart energy. It allows communication between humans or between things that make a building smarter. This paper proposes the implementation of the MQTT-based smart meter. The smart meter is used to make it easier for users to monitor and manage the energy consumption of buildings in real-time. It is considered as the main component of a smart network to make efficient and manage energy consumption remotely. Taking into account the increasing demand for electricity in Indonesia, smart meters can reduce overall energy use and reduce global warming by optimizing energy utilization through the internet of things and artificial intelligence. This paper proposes the implementation of the MQTT-based smart meter. This smart meter can measure energy consumption, transmit information related to the energy used, and provide an early warning system to stakeholders through the website in real-time analytics with predictive data on the following month and what days are most used to support energy consumption efficiency planning. This study conducted LTSM and ARIMA to determine forecasting energy consumption with 59 epochs, 8 batch sizes, 64 hidden layers with the results of MSE Error, RMSE Error, Mean Accuracy 0.14,0.373, and 95.16%, respectively. This result is better than ARIMA with MSE error results of 0.812 and 0.66 and RMSE error.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130595814","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466043
Tahreer Mahmood, Wurod Qasim Mohamed, O. Imran
The telecommunication systems are typically restricted by the wireless channel environment. As a dissimilar to the expected features of a wired channel, the wireless channel is unexpected. Actually, to reach a more realistic state of the path loss pattern a combination created between the path loss exponent (m) and free space path loss that change with the environments. The main target of this investigate is to make staff in this area become closer with these factors influencing in addition to impart an understanding of the parameters that impact general path loss models. During this study, we classify the factors that effect on these models into frequencies, different antenna gains, and path loss exponent. The effectiveness of these factors has been simulated and analyzed by using MATLAB software program. The results show that reducing the antenna gains from 1 to 0.25 unit will increases the path loss by 1 dB, and when the number of path loss exponent (m) set as 5, the path loss exceeds 120 dB accounts for only 800 meters of transmitted signals when obstructed in building have been used, approximately. But when the in-building LOS set up (m =1.6), the path loss exceeds 85 dB accounts for almost 800 meters of transmitted signals. It is detected that the frequencies, and path loss exponent have a considerable effect on the path losses performance. Nevertheless, different antenna gains can have a small effect on a performance. This study seeks to clarify the impact of each of these elements on the transmitter and receiver through path loss propagation models to helps the researcher and reader of improvement or put some new ideas.
{"title":"Factors Influencing the Shadow Path Loss Model with Different Antenna Gains Over Large-Scale Fading Channel","authors":"Tahreer Mahmood, Wurod Qasim Mohamed, O. Imran","doi":"10.1109/AIMS52415.2021.9466043","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466043","url":null,"abstract":"The telecommunication systems are typically restricted by the wireless channel environment. As a dissimilar to the expected features of a wired channel, the wireless channel is unexpected. Actually, to reach a more realistic state of the path loss pattern a combination created between the path loss exponent (m) and free space path loss that change with the environments. The main target of this investigate is to make staff in this area become closer with these factors influencing in addition to impart an understanding of the parameters that impact general path loss models. During this study, we classify the factors that effect on these models into frequencies, different antenna gains, and path loss exponent. The effectiveness of these factors has been simulated and analyzed by using MATLAB software program. The results show that reducing the antenna gains from 1 to 0.25 unit will increases the path loss by 1 dB, and when the number of path loss exponent (m) set as 5, the path loss exceeds 120 dB accounts for only 800 meters of transmitted signals when obstructed in building have been used, approximately. But when the in-building LOS set up (m =1.6), the path loss exceeds 85 dB accounts for almost 800 meters of transmitted signals. It is detected that the frequencies, and path loss exponent have a considerable effect on the path losses performance. Nevertheless, different antenna gains can have a small effect on a performance. This study seeks to clarify the impact of each of these elements on the transmitter and receiver through path loss propagation models to helps the researcher and reader of improvement or put some new ideas.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133101599","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 : 2021-04-28DOI: 10.1109/AIMS52415.2021.9466038
Aryandi Marta, A. Muis
The dual thrust system hybrid UAV combines the hover capabilities of the quadcopter and the endurance capabilities of the fixed-wing types in one aircraft. Its main goal was to eliminate the needs for runway access in the takeoff and landing process. This concept was implemented in the LSU-02 NGLD VTOL design to enhance flight missions. In general, this type of UAV have three flight modes: hover flight mode, transition mode, and fixed-wing mode. The design of transition control from hover to cruise flight was a challenge in itself. This study described the stages of designed mathematical model of Hybrid UAVs flight dynamic and gives an overview of transition control strategy to handle unstable and nonlinearities of flight movement. From motor specification, the drag and torque coefficient were set to $2. 2times 10^{-4} N/s^{2}$ and $5.58times 10^{-6} Nm/ s^{2}$ respectively to completed the model.
{"title":"Flight Dynamics Modeling of Dual Thrust System Hybrid UAV","authors":"Aryandi Marta, A. Muis","doi":"10.1109/AIMS52415.2021.9466038","DOIUrl":"https://doi.org/10.1109/AIMS52415.2021.9466038","url":null,"abstract":"The dual thrust system hybrid UAV combines the hover capabilities of the quadcopter and the endurance capabilities of the fixed-wing types in one aircraft. Its main goal was to eliminate the needs for runway access in the takeoff and landing process. This concept was implemented in the LSU-02 NGLD VTOL design to enhance flight missions. In general, this type of UAV have three flight modes: hover flight mode, transition mode, and fixed-wing mode. The design of transition control from hover to cruise flight was a challenge in itself. This study described the stages of designed mathematical model of Hybrid UAVs flight dynamic and gives an overview of transition control strategy to handle unstable and nonlinearities of flight movement. From motor specification, the drag and torque coefficient were set to $2. 2times 10^{-4} N/s^{2}$ and $5.58times 10^{-6} Nm/ s^{2}$ respectively to completed the model.","PeriodicalId":299121,"journal":{"name":"2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133110764","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：