Pub Date : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514124
Muhammad Salman Kabir, Ikechi Ndukwe, Engr. Zainab Shahid Awan
Drone detection technology is a new frontier in defence systems. With increasing incidences of crimes and terroristic attacks using commercial drones, detection of unauthorized drones is critical for timely responses from law enforcement agencies. In this paper, the issues of unavailability of benchmark dataset and performance metrics for drone detection are addressed and three single shot detectors, based on YOLOv4, YOLOv5 and DETR architectures are presented. A maximum of 99% average precision (AP) with an average Intersection over Union (IOU) of 84% was achieved. The precision-recall curves corroborate the generalization and fitness of the trained detection models.
{"title":"Deep Learning Inspired Vision based Frameworks for Drone Detection","authors":"Muhammad Salman Kabir, Ikechi Ndukwe, Engr. Zainab Shahid Awan","doi":"10.1109/ICECCE52056.2021.9514124","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514124","url":null,"abstract":"Drone detection technology is a new frontier in defence systems. With increasing incidences of crimes and terroristic attacks using commercial drones, detection of unauthorized drones is critical for timely responses from law enforcement agencies. In this paper, the issues of unavailability of benchmark dataset and performance metrics for drone detection are addressed and three single shot detectors, based on YOLOv4, YOLOv5 and DETR architectures are presented. A maximum of 99% average precision (AP) with an average Intersection over Union (IOU) of 84% was achieved. The precision-recall curves corroborate the generalization and fitness of the trained detection models.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"27 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125614918","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514168
Jun O. Seo, S. Manoharan, U. Speidel
Network packets can be used to hide information in space or in time, a steganographic technique known as a covert channel. Steganalysis is the science of finding the presence of covert channels. Re-embedding steganalysis has been shown to be effective in detecting both the presence and the amount of hidden information. The technique, however, is impractical because it required manual analysis of every network flow. This paper proposes methods to automate the analysis process effectively. The experimental results suggest that automatic detection is possible and that re-embedding steganalysis is practical.
{"title":"Automatic Detection of Storage-Based Covert Channels","authors":"Jun O. Seo, S. Manoharan, U. Speidel","doi":"10.1109/ICECCE52056.2021.9514168","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514168","url":null,"abstract":"Network packets can be used to hide information in space or in time, a steganographic technique known as a covert channel. Steganalysis is the science of finding the presence of covert channels. Re-embedding steganalysis has been shown to be effective in detecting both the presence and the amount of hidden information. The technique, however, is impractical because it required manual analysis of every network flow. This paper proposes methods to automate the analysis process effectively. The experimental results suggest that automatic detection is possible and that re-embedding steganalysis is practical.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116534394","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514109
Taha Darwassh Hanawy Hussein, M. Frikha, Sulayman Ahmed, Javad Rahebi
In this paper, ambulance vehicles are routed using BAT algorithm. The city map is created by node method. The control station receives the information about accident place and then this information is communicated to the ambulance and hospital. The drive feed the data i.e., node position of the accident and ambulance vehicle in the bat algorithm based vehicle routing method and it provides shortest path for reaching accident place to driver. After reaching accident place, drive feed the position of the accident place and hospital position in the bat algorithm vehicle routing method and it provide shortest path for reaching hospital to driver. Shortest bath and quick reach time is generated using this algorithm.
{"title":"Ambulance Vehicle Routing using BAT Algorithm","authors":"Taha Darwassh Hanawy Hussein, M. Frikha, Sulayman Ahmed, Javad Rahebi","doi":"10.1109/ICECCE52056.2021.9514109","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514109","url":null,"abstract":"In this paper, ambulance vehicles are routed using BAT algorithm. The city map is created by node method. The control station receives the information about accident place and then this information is communicated to the ambulance and hospital. The drive feed the data i.e., node position of the accident and ambulance vehicle in the bat algorithm based vehicle routing method and it provides shortest path for reaching accident place to driver. After reaching accident place, drive feed the position of the accident place and hospital position in the bat algorithm vehicle routing method and it provide shortest path for reaching hospital to driver. Shortest bath and quick reach time is generated using this algorithm.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127732027","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514118
Nyandika, Kimwele, Okeyo
The paper introduces handover system by use of two radio connections fitted in the train operating on different channels as well as use of the train's location and directional information to aid in reducing ping pong during handover. The paper formulates the Global Systems for Mobiles Railway (GSM-R) algorithm to help make decisions on when to handover with the objective of minimizing the handoff latency. These measures allow seamless connection to the network while moving along the railway boundaries which improves communication. This reduces outage duration. Simulation of the system is done using MATLAB. The algorithm used is disruption free and quite effective in high speed train travel, and the handoff decision is very efficient and more exact. This will therefore significantly improve service availability and reduce latency in data communication.
{"title":"Handover Enhancement in Wireless Communication-Based Train Control Systems","authors":"Nyandika, Kimwele, Okeyo","doi":"10.1109/ICECCE52056.2021.9514118","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514118","url":null,"abstract":"The paper introduces handover system by use of two radio connections fitted in the train operating on different channels as well as use of the train's location and directional information to aid in reducing ping pong during handover. The paper formulates the Global Systems for Mobiles Railway (GSM-R) algorithm to help make decisions on when to handover with the objective of minimizing the handoff latency. These measures allow seamless connection to the network while moving along the railway boundaries which improves communication. This reduces outage duration. Simulation of the system is done using MATLAB. The algorithm used is disruption free and quite effective in high speed train travel, and the handoff decision is very efficient and more exact. This will therefore significantly improve service availability and reduce latency in data communication.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131912916","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514068
E. A. Ogbodo, Augustine O. Nwajana
Coupled resonators are commonly used in the design of filters with bandpass response. Majority of these filters are designed using edge coupled or direct coupled technique. This paper proposes the implementation of the edge coupled and the direct coupled technique in the designing of a bandpass filter using microstrip technology. This is to ease the bandwidth and the frequency control of the circuit. The bandpass filter is designed to operate at a centre frequency of 1.95 GHz, using the open-loop resonators for the ease of edge coupling and a λ/4 resonator for the direct coupling. The measured response of the prototyped design and the simulated response show good agreements between the two.
{"title":"A Bandpass Filter Using Edge Coupled and Direct Coupled Techniques","authors":"E. A. Ogbodo, Augustine O. Nwajana","doi":"10.1109/ICECCE52056.2021.9514068","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514068","url":null,"abstract":"Coupled resonators are commonly used in the design of filters with bandpass response. Majority of these filters are designed using edge coupled or direct coupled technique. This paper proposes the implementation of the edge coupled and the direct coupled technique in the designing of a bandpass filter using microstrip technology. This is to ease the bandwidth and the frequency control of the circuit. The bandpass filter is designed to operate at a centre frequency of 1.95 GHz, using the open-loop resonators for the ease of edge coupling and a λ/4 resonator for the direct coupling. The measured response of the prototyped design and the simulated response show good agreements between the two.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"2010 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133542634","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514218
Ömer Yiğit Astepe, Ali Seymen Alkara
In Tiipras oil refineries, an average of 100 thousand maintenance requests are created annually for more than 140 thousand pieces of equipment. These requests are prioritized manually by chief experts with over 25 years of experience and classified as urgent or planned. If maintenance requests that need to be solved urgently in the refining industry are mislabeled and delayed, they may cause process upsets leading to health & safety hazards, environment problems or big asset damage. To minimize this risk, we think that supporting the decision mechanism with algorithms and cross checking/replacing human decisions by using today's AI technologies is the right approach that reduces the possibility of human error. In this study, our main goal is to automate maintenance prioritization process with supervised and unsupervised ML algorithms, deploy an AI system and achieve high accuracy. Our study was carried out basically in 4 main steps: • Exploratory Data Analysis • Clustering - Feature Addition - Feature Selection • Model Selection and Results • Additional Studies With this study, we aim to explain our AI study, share our experience with other partners that have similar needs and provide them an effective tool and systematic approach about management of transition from human to machine with a real industry case. We believe that the transfer of priority selection process from human to algorithms ensure consistent decisions, reduce costs and tolerate experience losses.
{"title":"Predicting “Maintenance Priority” with AI","authors":"Ömer Yiğit Astepe, Ali Seymen Alkara","doi":"10.1109/ICECCE52056.2021.9514218","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514218","url":null,"abstract":"In Tiipras oil refineries, an average of 100 thousand maintenance requests are created annually for more than 140 thousand pieces of equipment. These requests are prioritized manually by chief experts with over 25 years of experience and classified as urgent or planned. If maintenance requests that need to be solved urgently in the refining industry are mislabeled and delayed, they may cause process upsets leading to health & safety hazards, environment problems or big asset damage. To minimize this risk, we think that supporting the decision mechanism with algorithms and cross checking/replacing human decisions by using today's AI technologies is the right approach that reduces the possibility of human error. In this study, our main goal is to automate maintenance prioritization process with supervised and unsupervised ML algorithms, deploy an AI system and achieve high accuracy. Our study was carried out basically in 4 main steps: • Exploratory Data Analysis • Clustering - Feature Addition - Feature Selection • Model Selection and Results • Additional Studies With this study, we aim to explain our AI study, share our experience with other partners that have similar needs and provide them an effective tool and systematic approach about management of transition from human to machine with a real industry case. We believe that the transfer of priority selection process from human to algorithms ensure consistent decisions, reduce costs and tolerate experience losses.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125546847","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514240
K. Hamid, M. A. Bakar, A. Jalar, A. H. Badarisman
The semiconductor packaging industry driven by packaging complexity and product miniaturization. Hence, the problem identification methodology in semiconductor industries is a critical interest, and a basis of continuous improvement where the lesson learned is an integral part of it. Nevertheless, the problem identification approach is stagnant at the traditional method, such as the statistical-based methodology. There are several studies on the problem identification process in semiconductor through the six-sigma methodology and statistical approach, however, the scope is limited to the inferential statistic. Therefore, the focus of this paper is proposing using big data approach which grounded on the information theory. The big data analysis approach is utilizing the algorithm and data visualization. Big data methods, such as MINE and clustering was applied to data from hundreds of variables that contain essential and undiscovered relationship. The big data analysis enables the potential factors that contributed to the root causes and provided significant input to the design of experiment and reliability analysis.
{"title":"Incorporation of Big Data in Methodology of Identifying Corrosion Factors in the Semiconductor Package","authors":"K. Hamid, M. A. Bakar, A. Jalar, A. H. Badarisman","doi":"10.1109/ICECCE52056.2021.9514240","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514240","url":null,"abstract":"The semiconductor packaging industry driven by packaging complexity and product miniaturization. Hence, the problem identification methodology in semiconductor industries is a critical interest, and a basis of continuous improvement where the lesson learned is an integral part of it. Nevertheless, the problem identification approach is stagnant at the traditional method, such as the statistical-based methodology. There are several studies on the problem identification process in semiconductor through the six-sigma methodology and statistical approach, however, the scope is limited to the inferential statistic. Therefore, the focus of this paper is proposing using big data approach which grounded on the information theory. The big data analysis approach is utilizing the algorithm and data visualization. Big data methods, such as MINE and clustering was applied to data from hundreds of variables that contain essential and undiscovered relationship. The big data analysis enables the potential factors that contributed to the root causes and provided significant input to the design of experiment and reliability analysis.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"26 Suppl 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131453617","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514217
Oliver Niebuhr, Anna Gutnyk
Anchored in the field of communication engineering or, more specifically, pronunciation engineering and with the aim of evaluating and training public speaking performances, we apply a new device called the MARRYS cap. Using two transducer belts along the speaker's cheeks, the cap can measure articulatory details of jaw lowering and relate them to a time-aligned recording of acoustic charisma features. By linking the speech-production results of 14 speakers to speech-perception results of 34 listeners, the present paper provides, for the first time, empirical evidence for correlations between articulatory dimensions (of jaw lowering) and speaker charisma. Besides the practical implications of our findings, we discuss whether these correlations are direct or just reflect acoustic features that are indirectly (and not inevitably) related to the speaker's jaw movement patterns.
{"title":"Pronunciation engineering: Investigating the link between jaw-movement patterns and perceived speaker charisma using the MARRYS cap","authors":"Oliver Niebuhr, Anna Gutnyk","doi":"10.1109/ICECCE52056.2021.9514217","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514217","url":null,"abstract":"Anchored in the field of communication engineering or, more specifically, pronunciation engineering and with the aim of evaluating and training public speaking performances, we apply a new device called the MARRYS cap. Using two transducer belts along the speaker's cheeks, the cap can measure articulatory details of jaw lowering and relate them to a time-aligned recording of acoustic charisma features. By linking the speech-production results of 14 speakers to speech-perception results of 34 listeners, the present paper provides, for the first time, empirical evidence for correlations between articulatory dimensions (of jaw lowering) and speaker charisma. Besides the practical implications of our findings, we discuss whether these correlations are direct or just reflect acoustic features that are indirectly (and not inevitably) related to the speaker's jaw movement patterns.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131566258","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514269
Fatima Zahra EL Bouni, Tareq El Hariri, Chaime Zouitni, Ilham Ben Bahva, Hafida El Aboui, Aziza El ouaazizi
The birdwatchers and pepole admiring the beauty of birds search in the books and the encyclopedias to identify species and provide information that characterizes eash bird but this solusion is not pratical, we proposed to develope an android platform named Birds Predictor to assist users in recognizing about 30 species of endemic birds in the world. Bird images are injected in a convolutional neural network (CNN) to localize prominent features. First, we create an image generator for the training data. Then, we load training images. After that, we create a neural network and the convolutional layer. Finally, we load the unknown bird image and applied the argmax function to get a probability of bird features. To identify the images downloaded or captured by mobile users the results of the parameters learned from the characteristics of the birds are used. For the Mobile Application we use IBM Cloud that offers the possibility to store a lot of data and trains it using the visual recognition service, then we send the image that we want to predict its type from our android application. We just connect the IBM project that contains the training images with our Android Studio project using an API Key, and IBM process classifies the image captured or uploaded from the application and returned the type of bird.
{"title":"Bird image recognition and classification using Watson visual recognition services from IBMCloud and Conventional Neural Network (CNN)","authors":"Fatima Zahra EL Bouni, Tareq El Hariri, Chaime Zouitni, Ilham Ben Bahva, Hafida El Aboui, Aziza El ouaazizi","doi":"10.1109/ICECCE52056.2021.9514269","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514269","url":null,"abstract":"The birdwatchers and pepole admiring the beauty of birds search in the books and the encyclopedias to identify species and provide information that characterizes eash bird but this solusion is not pratical, we proposed to develope an android platform named Birds Predictor to assist users in recognizing about 30 species of endemic birds in the world. Bird images are injected in a convolutional neural network (CNN) to localize prominent features. First, we create an image generator for the training data. Then, we load training images. After that, we create a neural network and the convolutional layer. Finally, we load the unknown bird image and applied the argmax function to get a probability of bird features. To identify the images downloaded or captured by mobile users the results of the parameters learned from the characteristics of the birds are used. For the Mobile Application we use IBM Cloud that offers the possibility to store a lot of data and trains it using the visual recognition service, then we send the image that we want to predict its type from our android application. We just connect the IBM project that contains the training images with our Android Studio project using an API Key, and IBM process classifies the image captured or uploaded from the application and returned the type of bird.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131909468","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514209
N. A. N. Muhammad, U. Khairuddin, Rubiyah Yusof, Nik Mohamad Aizuddin Nik Azmi, Ridzuan Yunus
The halal food industry has a high demand in halal meat and poultry especially in Muslim countries. In order to slaughter a chicken according to the Islamic Law, it is required to sever the trachea, esophagus and both the carotid arteries and jugular veins to accelerate the chicken's bleeding and death. Syariah Compliance Automated Chicken Processing System (SYCUT) uses the Vision Inspection Technology which is built for the purpose of detecting and classifying whether a chicken is halal or not. The previous work on the system faced a few challenges regarding the image conditions which negatively affected the detection results. This paper discusses the possibility of deep learning approach to combat the challenges and its potential for esophagus detection. The deep learning model used is RetinaN et-MaskRCNN with ResNet50 as the backbone. The evaluation of the trained model yields 92.8% mean average precision (mAP) which performs better than the previous work. The model has a high recall value but a low precision value due to multi-detections.
{"title":"Esophagus Detection Using Deep Learning Method","authors":"N. A. N. Muhammad, U. Khairuddin, Rubiyah Yusof, Nik Mohamad Aizuddin Nik Azmi, Ridzuan Yunus","doi":"10.1109/ICECCE52056.2021.9514209","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514209","url":null,"abstract":"The halal food industry has a high demand in halal meat and poultry especially in Muslim countries. In order to slaughter a chicken according to the Islamic Law, it is required to sever the trachea, esophagus and both the carotid arteries and jugular veins to accelerate the chicken's bleeding and death. Syariah Compliance Automated Chicken Processing System (SYCUT) uses the Vision Inspection Technology which is built for the purpose of detecting and classifying whether a chicken is halal or not. The previous work on the system faced a few challenges regarding the image conditions which negatively affected the detection results. This paper discusses the possibility of deep learning approach to combat the challenges and its potential for esophagus detection. The deep learning model used is RetinaN et-MaskRCNN with ResNet50 as the backbone. The evaluation of the trained model yields 92.8% mean average precision (mAP) which performs better than the previous work. The model has a high recall value but a low precision value due to multi-detections.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"34 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132609131","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：