Pub Date : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910274
Sakdipat Ontoum, Jonathan H. Chan
Automated text summarizing helps the scientific and medical sectors by identifying and extracting relevant information from articles. Automatic text summarization is a way of compressing text documents so that users may find important and useful information in the original text in reduced time. We will first review some new works in the field of summarization that uses deep learning approaches, and then we will explain the application to COVID-19 related research papers. The ease with which a reader can grasp written text is referred to as the readability test. The substance of text determines its readability in natural language processing. We constructed word clouds using the abstracts’ most commonly used text. By looking at those three measurements, we can determine the performance measures of ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-L-SUM. Our findings indicated that Distilbart-mnli-12-6 and GPT2-large outperform than others considered.
{"title":"Automatic Text Summarization of COVID-19 Scientific Research Topics Using Pre-trained Models from Hugging Face","authors":"Sakdipat Ontoum, Jonathan H. Chan","doi":"10.1109/RI2C56397.2022.9910274","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910274","url":null,"abstract":"Automated text summarizing helps the scientific and medical sectors by identifying and extracting relevant information from articles. Automatic text summarization is a way of compressing text documents so that users may find important and useful information in the original text in reduced time. We will first review some new works in the field of summarization that uses deep learning approaches, and then we will explain the application to COVID-19 related research papers. The ease with which a reader can grasp written text is referred to as the readability test. The substance of text determines its readability in natural language processing. We constructed word clouds using the abstracts’ most commonly used text. By looking at those three measurements, we can determine the performance measures of ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-L-SUM. Our findings indicated that Distilbart-mnli-12-6 and GPT2-large outperform than others considered.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115834194","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910315
Kamol Boonlom, R. Viratikul, P. Janpugdee, J. Konpang, N. Chudpooti, I. Robertson, Timothy J. Amsdon, N. Somjit
Presented within this paper are the findings and illustrated a new methodology for the design and development of a pre-equalizer utilizing method optimized filter synthesis, which can expand the bandwidth of optical wireless communication as required. The design circuit consists of an active-passive hybrid equalization circuit using the passive RC high pass filter cascaded with the non-inverting active Sallen-Key amplifier and the RF broadband amplifier circuit. The design shows that at -3 dB bandwidth of the optical wireless communication can expand the frequency bandwidth of 1 MHz to 700 MHz. Additionally, it can amplify the input signal to compensate for the attenuation in the frequency operation range of 18 dB. However, the proposed pre-equalizer system offers various preferable features as it can expand the bandwidth to be higher and the input signal can be amplified. Also, it shows the real experimental results demonstrating an improvement of bandwidth.
{"title":"Active Pre-Equalizer for Broadband Optical Wireless Communication Integrated with RF Amplifier","authors":"Kamol Boonlom, R. Viratikul, P. Janpugdee, J. Konpang, N. Chudpooti, I. Robertson, Timothy J. Amsdon, N. Somjit","doi":"10.1109/RI2C56397.2022.9910315","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910315","url":null,"abstract":"Presented within this paper are the findings and illustrated a new methodology for the design and development of a pre-equalizer utilizing method optimized filter synthesis, which can expand the bandwidth of optical wireless communication as required. The design circuit consists of an active-passive hybrid equalization circuit using the passive RC high pass filter cascaded with the non-inverting active Sallen-Key amplifier and the RF broadband amplifier circuit. The design shows that at -3 dB bandwidth of the optical wireless communication can expand the frequency bandwidth of 1 MHz to 700 MHz. Additionally, it can amplify the input signal to compensate for the attenuation in the frequency operation range of 18 dB. However, the proposed pre-equalizer system offers various preferable features as it can expand the bandwidth to be higher and the input signal can be amplified. Also, it shows the real experimental results demonstrating an improvement of bandwidth.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125373363","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910303
Mohammad Afkar, R. Gavagsaz-Ghoachani, M. Phattanasak
One of the basic and important topics is students’ familiarity with practical work. One of the interesting subfields of experimental tests is understanding the waveforms and stability of the system. Different methods for student activities in the classroom are introduced to get acquainted with some examples of these signals and their behavior. Four waveforms are examined. Two waveforms for the state variables are considered in a DC-DC converter: the inductor current and capacitor voltage. The behavior of these waveforms is investigated for changes in a parameter of the modulated-hysteresis current controller. The command signal for the switch of this converter is also studied. Different tests to study a DC-DC boost converter in different operating areas, such as T-periodic and multi-periodic are shown by changing a control parameter at several operating points.
{"title":"Study and teach different operational areas of a converter using an experimental short video","authors":"Mohammad Afkar, R. Gavagsaz-Ghoachani, M. Phattanasak","doi":"10.1109/RI2C56397.2022.9910303","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910303","url":null,"abstract":"One of the basic and important topics is students’ familiarity with practical work. One of the interesting subfields of experimental tests is understanding the waveforms and stability of the system. Different methods for student activities in the classroom are introduced to get acquainted with some examples of these signals and their behavior. Four waveforms are examined. Two waveforms for the state variables are considered in a DC-DC converter: the inductor current and capacitor voltage. The behavior of these waveforms is investigated for changes in a parameter of the modulated-hysteresis current controller. The command signal for the switch of this converter is also studied. Different tests to study a DC-DC boost converter in different operating areas, such as T-periodic and multi-periodic are shown by changing a control parameter at several operating points.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126037895","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910288
Zohreh Shahrouei, R. Gavagsaz-Ghoachani, M. Phattanasak, S. Pierfederici
According to a high power density of supercapacitors, they have become interesting for electric vehicles. However, a boost converter is needed to step up the low voltage of the supercapacitor in its application. In this paper, a three-level DC-DC boost converter with supercapacitors is investigated. The two-loop sliding mode control is used to control the system. Simulation and experimental results are presented for start-up and steady-state. The converter can deliver power to load as expected from the experimental results.
{"title":"A three-level converter for supercapacitor in electric vehicles","authors":"Zohreh Shahrouei, R. Gavagsaz-Ghoachani, M. Phattanasak, S. Pierfederici","doi":"10.1109/RI2C56397.2022.9910288","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910288","url":null,"abstract":"According to a high power density of supercapacitors, they have become interesting for electric vehicles. However, a boost converter is needed to step up the low voltage of the supercapacitor in its application. In this paper, a three-level DC-DC boost converter with supercapacitors is investigated. The two-loop sliding mode control is used to control the system. Simulation and experimental results are presented for start-up and steady-state. The converter can deliver power to load as expected from the experimental results.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116109886","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910262
S. Mekruksavanich, Ponnipa Jantawong, Narit Hnoohom, A. Jitpattanakul
People have been encouraged to wear masks and avoid touching their faces in public as part of the new measures to prevent the spread of coronavirus 2019 (COVID-19). During the COVID-19 epidemic, few research have examined the effect of everyday living on the frequency of facial touch activity. To develop a face touching avoidance system, deep learning algorithms have been proposed and have demonstrated their amazing performance. However, an important drawback of deep learning is its extensive dependence on hyperparameters. The results of deep learning algorithms may vary depending on hyperparameters, such as the size of the filters, the number of filters, the batch size, the number of epochs, and the training optimization technique used. In this paper, we present an effective approach for hyperparameter tuning of convolutional neural networks (CNNs) for efficiently recognized face touching activities based on accelerometer data. Two hyperparameter tuning methods (Grid search and Bayesian optimization) were evaluated in order to construct the CNN with high performance. The experiment results show that Bayesian optimization can provide suitable hyperparameters for CNNs for face touching recognition with the highest accuracy of 96.61%.
{"title":"Hyperparameter Tuning in Convolutional Neural Network for Face Touching Activity Recognition using Accelerometer Data","authors":"S. Mekruksavanich, Ponnipa Jantawong, Narit Hnoohom, A. Jitpattanakul","doi":"10.1109/RI2C56397.2022.9910262","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910262","url":null,"abstract":"People have been encouraged to wear masks and avoid touching their faces in public as part of the new measures to prevent the spread of coronavirus 2019 (COVID-19). During the COVID-19 epidemic, few research have examined the effect of everyday living on the frequency of facial touch activity. To develop a face touching avoidance system, deep learning algorithms have been proposed and have demonstrated their amazing performance. However, an important drawback of deep learning is its extensive dependence on hyperparameters. The results of deep learning algorithms may vary depending on hyperparameters, such as the size of the filters, the number of filters, the batch size, the number of epochs, and the training optimization technique used. In this paper, we present an effective approach for hyperparameter tuning of convolutional neural networks (CNNs) for efficiently recognized face touching activities based on accelerometer data. Two hyperparameter tuning methods (Grid search and Bayesian optimization) were evaluated in order to construct the CNN with high performance. The experiment results show that Bayesian optimization can provide suitable hyperparameters for CNNs for face touching recognition with the highest accuracy of 96.61%.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":" 44","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113947851","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910291
Kitipoth Wasayangkool, Wilaiporn Lee, K. Srisomboon
To achieve the spectrum utilization objective of cognitive radio, the unauthorized user (SU) should avoid interference to the authorized user (PU) when the SU accesses the licensed channel and should access the licensed channel when it is actually available. In a normal scenario, traditional spectrum sensing determines the channel status when all samples of the sensing slot contain the PU signal. However, PU can utilize the licensed channel indulgently where the PU has the right to access or leave the channel anytime during the sensing interval. However, the indulgent access behavior of PU affects the detection performance of traditional spectrum sensing techniques since they do not take the behavior into the account. Later, modern techniques address the indulgent access behavior issue by exploiting micro-slots detection concepts. However, they did not evaluate the detection performance under noise uncertainty environment where the noise uncertainty is the major concern of the spectrum sensing. Therefore, in this paper, we determine the generalization character of the three modern spectrum sensing, micro-slotted dual-stage spectrum sensing (MDMS), split-half spectrum sensing (SPHS) and elastic fusion dual-stage spectrum sensing (EFDS), where the generalization can be met when the spectrum sensing presents reliable detection under various condition of spectrum usage of PU with noise uncertainty environment. As a result, EFDS can achieve the generalization character since it is capable of adjusting the required number of PU detected adjacent micro-slots.
{"title":"Evaluation of Micro-slots Spectrum Sensing under Noise uncertainty and PU Random Access","authors":"Kitipoth Wasayangkool, Wilaiporn Lee, K. Srisomboon","doi":"10.1109/RI2C56397.2022.9910291","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910291","url":null,"abstract":"To achieve the spectrum utilization objective of cognitive radio, the unauthorized user (SU) should avoid interference to the authorized user (PU) when the SU accesses the licensed channel and should access the licensed channel when it is actually available. In a normal scenario, traditional spectrum sensing determines the channel status when all samples of the sensing slot contain the PU signal. However, PU can utilize the licensed channel indulgently where the PU has the right to access or leave the channel anytime during the sensing interval. However, the indulgent access behavior of PU affects the detection performance of traditional spectrum sensing techniques since they do not take the behavior into the account. Later, modern techniques address the indulgent access behavior issue by exploiting micro-slots detection concepts. However, they did not evaluate the detection performance under noise uncertainty environment where the noise uncertainty is the major concern of the spectrum sensing. Therefore, in this paper, we determine the generalization character of the three modern spectrum sensing, micro-slotted dual-stage spectrum sensing (MDMS), split-half spectrum sensing (SPHS) and elastic fusion dual-stage spectrum sensing (EFDS), where the generalization can be met when the spectrum sensing presents reliable detection under various condition of spectrum usage of PU with noise uncertainty environment. As a result, EFDS can achieve the generalization character since it is capable of adjusting the required number of PU detected adjacent micro-slots.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128150985","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910324
M. Siripruchyanun, Burin Theppota, W. Saksiri
This article describes a novel voltage-mode instrumentation amplifier with fully electronic controllability and temperature insensitivity. Its circuit description is very simple comprising only single active building block namely voltage differencing gain amplifier (VDGA) without any passive elements to achieve high differential-mode gain and common-mode rejection ratio (CMRR). Its gain can be widely adjustable by electronic method via input bias currents, it then can be easily modified to automatic or microcontroller-based control systems. Several performances of workability of the proposed instrumentation amplifier are disclosed using PSpice simulation with the model parameter of 0.25μm CMOS process. The output deviation due to temperature variation is about 0.00135%/°C. The total harmonic distortion (THD) of output voltage is 0.89%. Total power consumption of the proposed circuit is 0.18mW at ±1.2V power supply.
{"title":"A Resistorless Temperature-insensitive Electronically-adjustable Single VDGA-based Voltage-mode Instrumentation Amplifier","authors":"M. Siripruchyanun, Burin Theppota, W. Saksiri","doi":"10.1109/RI2C56397.2022.9910324","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910324","url":null,"abstract":"This article describes a novel voltage-mode instrumentation amplifier with fully electronic controllability and temperature insensitivity. Its circuit description is very simple comprising only single active building block namely voltage differencing gain amplifier (VDGA) without any passive elements to achieve high differential-mode gain and common-mode rejection ratio (CMRR). Its gain can be widely adjustable by electronic method via input bias currents, it then can be easily modified to automatic or microcontroller-based control systems. Several performances of workability of the proposed instrumentation amplifier are disclosed using PSpice simulation with the model parameter of 0.25μm CMOS process. The output deviation due to temperature variation is about 0.00135%/°C. The total harmonic distortion (THD) of output voltage is 0.89%. Total power consumption of the proposed circuit is 0.18mW at ±1.2V power supply.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123229099","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910306
N. Maliwan, Chonlada Maliwan, R. Suwalak
This paper provides information about the design of the mobile application for transportation management. Initially, the user must be logged in to access the mobile application. It is divided into 3 access roles, i.e., 1) administrator can use job summary, time verification function, and driver function, 2) staff can use the driver’s time and time verification function, and 3) driver can use the job function. The application’s movement data since login. Confirmation of the time of the car leaving the plant. Job verification on behalf of the driver, including the driver confirming the customer submission, is stored in the entire database, which is notified every time it is logged in and when the work is sent to the customer via the Line Notification, as well as the daily revenue amount and monthly income is displayed. Displays within the proposed mobile application to keep drivers informed. The mobile application is convenient to use and work very well for the transportation management of the SUBTAWEE Concrete Company Langsuan Co., Ltd. This mobile application can be applied to the transportation management and the others similarly process.
{"title":"SUBTAWEE Transportation Management on Mobile Application","authors":"N. Maliwan, Chonlada Maliwan, R. Suwalak","doi":"10.1109/RI2C56397.2022.9910306","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910306","url":null,"abstract":"This paper provides information about the design of the mobile application for transportation management. Initially, the user must be logged in to access the mobile application. It is divided into 3 access roles, i.e., 1) administrator can use job summary, time verification function, and driver function, 2) staff can use the driver’s time and time verification function, and 3) driver can use the job function. The application’s movement data since login. Confirmation of the time of the car leaving the plant. Job verification on behalf of the driver, including the driver confirming the customer submission, is stored in the entire database, which is notified every time it is logged in and when the work is sent to the customer via the Line Notification, as well as the daily revenue amount and monthly income is displayed. Displays within the proposed mobile application to keep drivers informed. The mobile application is convenient to use and work very well for the transportation management of the SUBTAWEE Concrete Company Langsuan Co., Ltd. This mobile application can be applied to the transportation management and the others similarly process.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"33 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128227242","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910323
Yeganeh Ghandriz, Sara Mahmoodian-Yonesi, Y. Alvari, M. Zandi, R. Gavagsaz-Ghoachani, M. Phattanasak
In today's complex world, energy challenges are interconnected with water, environmental, and food challenges. Because of the better understanding and complex connection that exists between these resources, a concept called nexus is defined. The most comprehensive nexus that most of the parameters are considered is water, environment, food and energy nexus (WEFEN). A volumetric view of WEFEN is an attitude that can be very effective in achieving sustainable development goals. Energetic dark greenhouse (EDG) is an innovative idea with the WEFEN volume view that solves the challenges of sustainable security, water, environment, food, and energy. Three examples of EDG capabilities are described in order to provide sustainable security in this research. These three capabilities include supplying electrical energy through renewable energy resources, decreasing the peak with changes in the pattern of electricity consumption, and reducing consumer electricity costs in the EDG. In this research, in order to decrease the peak by changing the pattern of electricity consumption, the appropriate lighting period of the plant has been selected. Also, from a techno-economic point of view, the best time to start the lighting period of this system is selected in terms of optimal cost for the user.
{"title":"A new techno-economic solution to supply energy, decrease the peak and reduce the cost of electricity consumed in the new agricultural structure","authors":"Yeganeh Ghandriz, Sara Mahmoodian-Yonesi, Y. Alvari, M. Zandi, R. Gavagsaz-Ghoachani, M. Phattanasak","doi":"10.1109/RI2C56397.2022.9910323","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910323","url":null,"abstract":"In today's complex world, energy challenges are interconnected with water, environmental, and food challenges. Because of the better understanding and complex connection that exists between these resources, a concept called nexus is defined. The most comprehensive nexus that most of the parameters are considered is water, environment, food and energy nexus (WEFEN). A volumetric view of WEFEN is an attitude that can be very effective in achieving sustainable development goals. Energetic dark greenhouse (EDG) is an innovative idea with the WEFEN volume view that solves the challenges of sustainable security, water, environment, food, and energy. Three examples of EDG capabilities are described in order to provide sustainable security in this research. These three capabilities include supplying electrical energy through renewable energy resources, decreasing the peak with changes in the pattern of electricity consumption, and reducing consumer electricity costs in the EDG. In this research, in order to decrease the peak by changing the pattern of electricity consumption, the appropriate lighting period of the plant has been selected. Also, from a techno-economic point of view, the best time to start the lighting period of this system is selected in terms of optimal cost for the user.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131325800","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 : 2022-08-04DOI: 10.1109/RI2C56397.2022.9910301
Narit Hnoohom, Pitchaya Chotivatunyu, Sumeth Yuenyong, K. Wongpatikaseree, S. Mekruksavanich, A. Jitpattanakul
Weapon detection is a difficult task that requires accurate identification of weapon objects in images. The object localization approach is mostly used because it combines a gradient with a convolutional layer to create a map of key locations on the image. This paper presents an Eigen-CAM method to localize and detect objects in an image for a Faster Region-based Convolutional Neural Network (Faster R-CNN) residual neural network (ResNet 50) model, giving a visual explanation. The Internet Movie Firearms Database (IMFDB) was used to train a deep learning model with the Faster R-CNN ResNet 50 model of the pre-trained PyTorch framework. Experimental results indicated that the Faster R-CNN ResNet 50 model achieved the highest mAP of 0.497 with 0.5 IoU. The Eigen-CAM method performed effectively for visual image representation.
{"title":"Object Identification and Localization of Visual Explanation for Weapon Detection","authors":"Narit Hnoohom, Pitchaya Chotivatunyu, Sumeth Yuenyong, K. Wongpatikaseree, S. Mekruksavanich, A. Jitpattanakul","doi":"10.1109/RI2C56397.2022.9910301","DOIUrl":"https://doi.org/10.1109/RI2C56397.2022.9910301","url":null,"abstract":"Weapon detection is a difficult task that requires accurate identification of weapon objects in images. The object localization approach is mostly used because it combines a gradient with a convolutional layer to create a map of key locations on the image. This paper presents an Eigen-CAM method to localize and detect objects in an image for a Faster Region-based Convolutional Neural Network (Faster R-CNN) residual neural network (ResNet 50) model, giving a visual explanation. The Internet Movie Firearms Database (IMFDB) was used to train a deep learning model with the Faster R-CNN ResNet 50 model of the pre-trained PyTorch framework. Experimental results indicated that the Faster R-CNN ResNet 50 model achieved the highest mAP of 0.497 with 0.5 IoU. The Eigen-CAM method performed effectively for visual image representation.","PeriodicalId":403083,"journal":{"name":"2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121590427","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：