Pub Date : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528281
Khadija Ashraf, A. Ashok
The ability to perceive safety-critical events by virtually seeing through vehicles and other obstructions on the road can be a very useful driving assistance feature for vehicles. In this paper, we first hypothesize that such a feature can be achieved by vehicles driving ahead proactively communicate information about the visual scenery they perceive using dashboard cameras. Using such a multiple access setting, and considering brake-light light emitting diode (LED) to camera communication as the enabler, in this paper, we position an information processing pipeline for predicting the non-line-of-sight (NLOS) safety event. In particular, we present the algorithmic design of the cognitive information processing system that will continuously warn the host driver about the line-of-sight (LOS) and non-line-sight road situations. We position the use-case of our proposed information processing pipeline through a case-study analysis for a real-world driving scenario.
{"title":"A Cognitive Information Processing Pipeline for Multiple–Access Vehicular Camera Communication","authors":"Khadija Ashraf, A. Ashok","doi":"10.1109/ICSCC51209.2021.9528281","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528281","url":null,"abstract":"The ability to perceive safety-critical events by virtually seeing through vehicles and other obstructions on the road can be a very useful driving assistance feature for vehicles. In this paper, we first hypothesize that such a feature can be achieved by vehicles driving ahead proactively communicate information about the visual scenery they perceive using dashboard cameras. Using such a multiple access setting, and considering brake-light light emitting diode (LED) to camera communication as the enabler, in this paper, we position an information processing pipeline for predicting the non-line-of-sight (NLOS) safety event. In particular, we present the algorithmic design of the cognitive information processing system that will continuously warn the host driver about the line-of-sight (LOS) and non-line-sight road situations. We position the use-case of our proposed information processing pipeline through a case-study analysis for a real-world driving scenario.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124950590","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528170
Sushant Kumar Pandey, A. Tripathi
Software practitioners are continuing to build advanced software defect prediction (SDP) models to help the tester find fault-prone modules. However, the Class Imbalance (CI) problem consists of uncommonly few defective instances, and more non-defective instances cause inconsistency in the performance. We have conducted 880 experiments to analyze the variation in the performance of 10 SDP models by concerning the class imbalance problem. In our experiments, we have used 22 public datasets consists of 41 software metrics, 10 baseline SDP methods, and 4 sampling techniques. We used Mathews Correlation Coefficient (MCC), which is more useful when a dataset is highly imbalanced. We have also compared the predictive performance of various ML models by applying 4 sampling techniques. To examine the performance of different SDP models, we have used the F-measure. We found the performance of the learning models is unsatisfactory, which needs to mitigate. We have also found a few surprising results, some logical patterns between classifier and sampling technique. It provides a connection between sampling technique, software matrices, and a classifier.
{"title":"Class Imbalance Issue in Software Defect Prediction Models by various Machine Learning Techniques: An Empirical Study","authors":"Sushant Kumar Pandey, A. Tripathi","doi":"10.1109/ICSCC51209.2021.9528170","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528170","url":null,"abstract":"Software practitioners are continuing to build advanced software defect prediction (SDP) models to help the tester find fault-prone modules. However, the Class Imbalance (CI) problem consists of uncommonly few defective instances, and more non-defective instances cause inconsistency in the performance. We have conducted 880 experiments to analyze the variation in the performance of 10 SDP models by concerning the class imbalance problem. In our experiments, we have used 22 public datasets consists of 41 software metrics, 10 baseline SDP methods, and 4 sampling techniques. We used Mathews Correlation Coefficient (MCC), which is more useful when a dataset is highly imbalanced. We have also compared the predictive performance of various ML models by applying 4 sampling techniques. To examine the performance of different SDP models, we have used the F-measure. We found the performance of the learning models is unsatisfactory, which needs to mitigate. We have also found a few surprising results, some logical patterns between classifier and sampling technique. It provides a connection between sampling technique, software matrices, and a classifier.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128438967","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528089
Indu Gopan, M. S, S. Joy, Mukundan Kk
Tracking a launch vehicle is of paramount importance, not only for knowing the instantaneous position of the vehicle, but also for taking appropriate and critical real time decisions related to Range safety. Tracking System also provides antenna positioning information for Telemetry, Telecommand and Optical Tracking stations. Active tracking systems consisting of C Band Radar ground station and onboard C Band Transponder provide the necessary input data in real time to the Range Safety Officer for taking necessary decisions. In the ascent phase of Launch Vehicle mission, during the transonic regime, sporadic interrogation is registered on onboard C-Band Transponders and large number of extra echo pulses are observed on Radar displays. Large fluctuations are also observed in signals received onboard and at ground during this time period. Response of the onboard transponders to the additional interrogation pulses lead to the original uplink pulse being missed, thereby causing loss of track by Radars. This paper discusses on the tracking system, the observations during transonic regime, its analysis and the unique solution implemented. Pulse position coding technique has been successfully employed in a novel way in the tracking system to overcome the difficulties caused due to erroneous interrogation and the design has been effectively demonstrated in flight.
{"title":"A Novel Approach to Solve Sporadic Interrogation in Tracking System during Transonic Ascent Flight of Satellite Launch Vehicles","authors":"Indu Gopan, M. S, S. Joy, Mukundan Kk","doi":"10.1109/ICSCC51209.2021.9528089","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528089","url":null,"abstract":"Tracking a launch vehicle is of paramount importance, not only for knowing the instantaneous position of the vehicle, but also for taking appropriate and critical real time decisions related to Range safety. Tracking System also provides antenna positioning information for Telemetry, Telecommand and Optical Tracking stations. Active tracking systems consisting of C Band Radar ground station and onboard C Band Transponder provide the necessary input data in real time to the Range Safety Officer for taking necessary decisions. In the ascent phase of Launch Vehicle mission, during the transonic regime, sporadic interrogation is registered on onboard C-Band Transponders and large number of extra echo pulses are observed on Radar displays. Large fluctuations are also observed in signals received onboard and at ground during this time period. Response of the onboard transponders to the additional interrogation pulses lead to the original uplink pulse being missed, thereby causing loss of track by Radars. This paper discusses on the tracking system, the observations during transonic regime, its analysis and the unique solution implemented. Pulse position coding technique has been successfully employed in a novel way in the tracking system to overcome the difficulties caused due to erroneous interrogation and the design has been effectively demonstrated in flight.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128489646","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528124
G. S, G. C., Shahid Haseem C., Arun Sreenivas, Aleena Maria John, Arathy A. S.
Colorectal cancer(CRC) or colon cancer, is fatal cancer seen in males and females. Colorectal polyps usually develop on the mucosal layer of the colon or rectal part of the large intestine. They may later turn malignant and become cancerous. Diagnosis of colorectal polyps in the initial stages is a key factor in reducing the mortality rate due to CRC. Colonoscopy is considered the golden standard in CRC detection. Automation of polyp detection, localization and segmentation in the screening stage can help the clinicians to a great extent. However, detection, localization and segmentation of polyps of various morphological structures and textures have been proved to be very challenging. Deep neural networks (DNNs) have emerged as a powerful subset of machine learning and recorded a tremendous boost in many visual recognition tasks including medical imaging. Deep learning models often need an immense number of annotated images, which is difficult to collect in the medical domain and these models are computationally expensive and memory intensive. Hence a lot of works are going on to have model compression and acceleration in deep neural networks without significantly decreasing the performance. This work suggests a lightweight deep learning model rooted on auto-encoder decoder architecture for the segmentation of colorectal polyps of various morphological structures and textures. This model can be trained at full length from a considerably less number of images and shows par performance in terms of essential metrics used in semantic segmentation.
{"title":"Lite-Deep : Improved Auto Encoder-Decoder for Polyp Segmentation","authors":"G. S, G. C., Shahid Haseem C., Arun Sreenivas, Aleena Maria John, Arathy A. S.","doi":"10.1109/ICSCC51209.2021.9528124","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528124","url":null,"abstract":"Colorectal cancer(CRC) or colon cancer, is fatal cancer seen in males and females. Colorectal polyps usually develop on the mucosal layer of the colon or rectal part of the large intestine. They may later turn malignant and become cancerous. Diagnosis of colorectal polyps in the initial stages is a key factor in reducing the mortality rate due to CRC. Colonoscopy is considered the golden standard in CRC detection. Automation of polyp detection, localization and segmentation in the screening stage can help the clinicians to a great extent. However, detection, localization and segmentation of polyps of various morphological structures and textures have been proved to be very challenging. Deep neural networks (DNNs) have emerged as a powerful subset of machine learning and recorded a tremendous boost in many visual recognition tasks including medical imaging. Deep learning models often need an immense number of annotated images, which is difficult to collect in the medical domain and these models are computationally expensive and memory intensive. Hence a lot of works are going on to have model compression and acceleration in deep neural networks without significantly decreasing the performance. This work suggests a lightweight deep learning model rooted on auto-encoder decoder architecture for the segmentation of colorectal polyps of various morphological structures and textures. This model can be trained at full length from a considerably less number of images and shows par performance in terms of essential metrics used in semantic segmentation.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128598549","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}
Quality of fruits and vegetables has much relevance in the modern health consortium. Grading of fruits based on the quality is the prime solution. But traditional fruit grading mechanisms are not feasible due to the mass production of fruits and vegetables. Technological advancements in the field of agriculture can help to increase productivity and thereby reduce the selling of damaged or defective products. We propose a real-time fruit and vegetable grading system using Machine Vision to help all users to choose the ideal fruit or vegetable for consumption. Our proposed model will also predict the shelf life of the identified fruit. An Android application is used to scan the fruit or vegetable image in real-time. The features of the objects are extracted, and the data is processed. The chemical ripening in the fruit/vegetable is also detected. Our experimental results show that this mobile application will be useful to the common people for estimating the fruit /vegetable quality along with its shelf life.
{"title":"Detection and Grading of Multiple Fruits and Vegetables Using Machine Vision","authors":"Renju Rachel Varghese, Pramod Mathew Jacob, Sooraj S, Daniel Mathew Ranjan, Jino Cherian Varughese, Hegsymol Raju","doi":"10.1109/ICSCC51209.2021.9528165","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528165","url":null,"abstract":"Quality of fruits and vegetables has much relevance in the modern health consortium. Grading of fruits based on the quality is the prime solution. But traditional fruit grading mechanisms are not feasible due to the mass production of fruits and vegetables. Technological advancements in the field of agriculture can help to increase productivity and thereby reduce the selling of damaged or defective products. We propose a real-time fruit and vegetable grading system using Machine Vision to help all users to choose the ideal fruit or vegetable for consumption. Our proposed model will also predict the shelf life of the identified fruit. An Android application is used to scan the fruit or vegetable image in real-time. The features of the objects are extracted, and the data is processed. The chemical ripening in the fruit/vegetable is also detected. Our experimental results show that this mobile application will be useful to the common people for estimating the fruit /vegetable quality along with its shelf life.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116740853","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：