Pub Date : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088332
P. Yakaiah, P. Bhavani, B. Kumar, Srija Masireddy, Peter Elari
The objective of this paper is to implement a system which is to provide security to desired person. It is also useful to the people when they need medical emergency and also to provide security to women. In this work, we use the GPS, GSM modules, Raspberry pi, Raspberry pi camera, Flex sensor and a display that are interfaced with Arduino Nano. When a person is in danger and in need of any emergency then He/she can press the button or the Flex sensor. When the person presses the button then it is considered as the Medical need. When the person presses the Flex Sensor then it can be considered as the Danger. The entire system will be triggered by pressing the button or flex sensor, and an SMS will be sent to concerned folks with their location and the recorded photo will be sent to the concerned emails.
{"title":"Design of an IoT-Enabled Smart Safety Device","authors":"P. Yakaiah, P. Bhavani, B. Kumar, Srija Masireddy, Peter Elari","doi":"10.1109/ASSIC55218.2022.10088332","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088332","url":null,"abstract":"The objective of this paper is to implement a system which is to provide security to desired person. It is also useful to the people when they need medical emergency and also to provide security to women. In this work, we use the GPS, GSM modules, Raspberry pi, Raspberry pi camera, Flex sensor and a display that are interfaced with Arduino Nano. When a person is in danger and in need of any emergency then He/she can press the button or the Flex sensor. When the person presses the button then it is considered as the Medical need. When the person presses the Flex Sensor then it can be considered as the Danger. The entire system will be triggered by pressing the button or flex sensor, and an SMS will be sent to concerned folks with their location and the recorded photo will be sent to the concerned emails.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121470769","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}
Academic advising is a crucial and challenging task at the beginning of each term. It remains a manual process in Saudi universities, that needs to be automated. Our solution consists of a chatbot as a digital academic advisor helping students make logical decisions based on analyzing data like what course must be essential or have more required courses, and answer the common questions. This chatbot is knowledge-based and is always available, students can use it to plan the semester courses, as well. It collects the data and develops them to build better decisions.
{"title":"A chatbot for Academic advising","authors":"Reoof Al-Jedaie, Reem Al-Hindy, Hanan Al-Onazi, Elham Kariri, Fatma Masmoudi","doi":"10.1109/ASSIC55218.2022.10088317","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088317","url":null,"abstract":"Academic advising is a crucial and challenging task at the beginning of each term. It remains a manual process in Saudi universities, that needs to be automated. Our solution consists of a chatbot as a digital academic advisor helping students make logical decisions based on analyzing data like what course must be essential or have more required courses, and answer the common questions. This chatbot is knowledge-based and is always available, students can use it to plan the semester courses, as well. It collects the data and develops them to build better decisions.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"308 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131589222","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088325
H. K. Bhuyan, Biswajit Brahma, P. Rao
This paper addresses to assess the relevant visual strength between two videos based on a great deal with image content analysis. After custom pre-trained image and video content using multi-level feature learning model, video features are widely applied to image and video representation. Although, certain features are task-specific, two videos cannot be the best for all types of work. Additionally, for various reasons like ownership, including anonymity, people only have access to predetermined video functions. Refined video features can be reused without returning to the original video information. For example, an affine transformation is accomplished by reimagining a known function into a new space. We proposed to use maximizing the re-learning method for video recommendation. Instead of creating more training data, we suggested a modern data enhancement approach for a frame-by-frame and video-by-video basis task. Extensive testing of our proposed model is considered using real time data set and found the efficacy of the process and lends strong proof to the performance of video recommendation.
{"title":"Multi-level feature learning approaches for video recommendation","authors":"H. K. Bhuyan, Biswajit Brahma, P. Rao","doi":"10.1109/ASSIC55218.2022.10088325","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088325","url":null,"abstract":"This paper addresses to assess the relevant visual strength between two videos based on a great deal with image content analysis. After custom pre-trained image and video content using multi-level feature learning model, video features are widely applied to image and video representation. Although, certain features are task-specific, two videos cannot be the best for all types of work. Additionally, for various reasons like ownership, including anonymity, people only have access to predetermined video functions. Refined video features can be reused without returning to the original video information. For example, an affine transformation is accomplished by reimagining a known function into a new space. We proposed to use maximizing the re-learning method for video recommendation. Instead of creating more training data, we suggested a modern data enhancement approach for a frame-by-frame and video-by-video basis task. Extensive testing of our proposed model is considered using real time data set and found the efficacy of the process and lends strong proof to the performance of video recommendation.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133952930","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088386
Somireddy Sumanth, Kadiyam Jyosthana, Jonnala Karthik Reddy, G. Geetha
The pitch and content of the speech in this proposed work can be picked up by lip movements. We investigate the function of lip and speech combinations that is, Learn the word uttered only by the motion of lips. Emphasis is to decode the full content of speech produced by different categories of speakers. Identification of speakers is caught not only from facial features such as age, gender, and nationality, but also from shape and lip movements, making the identification of speaker as a perceptible expression. Here, we present a new approach to gain proper lip movement in unrestrained situations. Different comprehensive examinations are carried out based on quantity, quality indicators and individual tests.
{"title":"Computer Vision Lip Reading(CV)","authors":"Somireddy Sumanth, Kadiyam Jyosthana, Jonnala Karthik Reddy, G. Geetha","doi":"10.1109/ASSIC55218.2022.10088386","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088386","url":null,"abstract":"The pitch and content of the speech in this proposed work can be picked up by lip movements. We investigate the function of lip and speech combinations that is, Learn the word uttered only by the motion of lips. Emphasis is to decode the full content of speech produced by different categories of speakers. Identification of speakers is caught not only from facial features such as age, gender, and nationality, but also from shape and lip movements, making the identification of speaker as a perceptible expression. Here, we present a new approach to gain proper lip movement in unrestrained situations. Different comprehensive examinations are carried out based on quantity, quality indicators and individual tests.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125612541","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}
A vital component of clinical medical diagnosis is blood cell count. CNN has devised an effective way of automatically counting blood cells using deep learning-based detection method. Inadequate bounding box alignment and overlapping item recognition are challenges for the CNN detection approach. We suggest a brand-new deep-learning technique called CNN to get over these restrictions. Channel, spatial attention mechanism is incorporated into the feature extraction network resulting in CNN. For residual fusion, CNN can assist the network in increasing detection accuracy by replacing the original feature vector and employing the filtered and weighted feature vector. The experimental results show that the typical CNN network may improve blood cell count detection performance without adding too many extra parameters, where the accuracy of identifying cells (RBCs, WBCs, and platelets) has been done.
{"title":"Blood Cell Detection and Counting via Deep Learning","authors":"Achal Narsale, Sakshi Nalwade, Medha Badgire, Sandhyarani Survase, Chetan. N. Aher","doi":"10.1109/ASSIC55218.2022.10088344","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088344","url":null,"abstract":"A vital component of clinical medical diagnosis is blood cell count. CNN has devised an effective way of automatically counting blood cells using deep learning-based detection method. Inadequate bounding box alignment and overlapping item recognition are challenges for the CNN detection approach. We suggest a brand-new deep-learning technique called CNN to get over these restrictions. Channel, spatial attention mechanism is incorporated into the feature extraction network resulting in CNN. For residual fusion, CNN can assist the network in increasing detection accuracy by replacing the original feature vector and employing the filtered and weighted feature vector. The experimental results show that the typical CNN network may improve blood cell count detection performance without adding too many extra parameters, where the accuracy of identifying cells (RBCs, WBCs, and platelets) has been done.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122056305","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088348
Syed Naushad Ali Hashmi, Anurag Saxena, Niraj Kumar Sharma, Raghav C Dwivedi, K. Kushwaha
In the method of power transmission electrical energy can we transmitted without any wire that is also known as wireless transmission process, which is used for transmitted the power from one place to another without using any wired material which is a good conductor of electricity. This power or energy can be received by flexible antenna. The design and simulation of flexible antenna is done on CST Software at 12.57 GHz resonant frequency. For designing the antenna, It can be used different materials like glass epoxy, leather, etc but in this research textile material is used which is having 1.7 dielectric constant. Since, the wireless transmission of electrical energy is difficult so the textile antenna is good candidate for this. The RF Energy that comes from the flexible antenna can be converted into DC signal by the use of rectifier circuit. All the relative information like the parameters of the rectenna are mentioned and explain in this paper by the use of graphical representation. The implementation of bridge rectifier circuit can be done on PCB (Printed Circuit Board).
{"title":"Wireless Energy by Flexible Antenna and Conversion of Energy from RF to DC","authors":"Syed Naushad Ali Hashmi, Anurag Saxena, Niraj Kumar Sharma, Raghav C Dwivedi, K. Kushwaha","doi":"10.1109/ASSIC55218.2022.10088348","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088348","url":null,"abstract":"In the method of power transmission electrical energy can we transmitted without any wire that is also known as wireless transmission process, which is used for transmitted the power from one place to another without using any wired material which is a good conductor of electricity. This power or energy can be received by flexible antenna. The design and simulation of flexible antenna is done on CST Software at 12.57 GHz resonant frequency. For designing the antenna, It can be used different materials like glass epoxy, leather, etc but in this research textile material is used which is having 1.7 dielectric constant. Since, the wireless transmission of electrical energy is difficult so the textile antenna is good candidate for this. The RF Energy that comes from the flexible antenna can be converted into DC signal by the use of rectifier circuit. All the relative information like the parameters of the rectenna are mentioned and explain in this paper by the use of graphical representation. The implementation of bridge rectifier circuit can be done on PCB (Printed Circuit Board).","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125413506","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088318
B. A. Kumar, T. Vinod, M. Rao
The material and presenting it on the screen using the application is a part of the interaction that is possible through the computer vision air canvas. Having the various colours present is also a part of this interaction. The varied colour schemes make it easier for the user to identify things and provide greater clarity. Accessing the built-in web camera on the laptop or the independent web camera that was installed is required to accomplish this. This contributes to a better overall knowledge and provides the user with a more concise description of the air. In addition to that, this is utilised for text visualisation and drawing for the audience. This has the potential to serve as a stepping stone for more innovative streams and material that is engaging in the future. Simply moving your finger through the air will allow you to draw your creative ideas, which does make use of computer vision technology. In the respective paper, we construct a screen through which the information or text that we draw by waving is displayed appropriately on the screen for which is done by employing shooting the motion of finger using internet digital camera. This is accomplished in a manner similar to how a touch screen works. The detection of the colours, tracking of the marker, and establishment of the coordinates are the objectives of this particular piece of writing.
{"title":"Interaction through Computer Vision Air Canvas","authors":"B. A. Kumar, T. Vinod, M. Rao","doi":"10.1109/ASSIC55218.2022.10088318","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088318","url":null,"abstract":"The material and presenting it on the screen using the application is a part of the interaction that is possible through the computer vision air canvas. Having the various colours present is also a part of this interaction. The varied colour schemes make it easier for the user to identify things and provide greater clarity. Accessing the built-in web camera on the laptop or the independent web camera that was installed is required to accomplish this. This contributes to a better overall knowledge and provides the user with a more concise description of the air. In addition to that, this is utilised for text visualisation and drawing for the audience. This has the potential to serve as a stepping stone for more innovative streams and material that is engaging in the future. Simply moving your finger through the air will allow you to draw your creative ideas, which does make use of computer vision technology. In the respective paper, we construct a screen through which the information or text that we draw by waving is displayed appropriately on the screen for which is done by employing shooting the motion of finger using internet digital camera. This is accomplished in a manner similar to how a touch screen works. The detection of the colours, tracking of the marker, and establishment of the coordinates are the objectives of this particular piece of writing.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123393743","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088364
K. Anand, A. Jena, Tanisha Choudhary
Software Testing is an essential activity in the development process of a software product. A defect-free software is the need of the hour. Identifying the defects as early as possible is critical to avoid any disastrous consequences in the later stages of development. Software Defect Prediction (SDP) is a process of early identification of defect-prone modules. Lately, software defect prediction coupled with machine learning techniques has gained momentum as it significantly brings down maintenance costs. Feature selection (FS) plays a very significant role in a defect prediction model's efficiency; hence, choosing a suitable FS method is challenging when building a defect prediction model. This paper evaluates six filter-based FS techniques, four wrapper-based FS techniques, and two embedded FS techniques using four supervised learning classifiers over six NASA datasets from the PROMISE repository. The experimental results strengthened that FS techniques significantly improve the model's predictive performance. From our experimental data, we concluded that SVM based defect prediction model showed the best performance among all other studied models. We also observed that Fisher's score, a filter-based FS technique, outperformed all other FS techniques studied in this work.
{"title":"Performance Analysis of Feature Selection Techniques in Software Defect Prediction using Machine Learning","authors":"K. Anand, A. Jena, Tanisha Choudhary","doi":"10.1109/ASSIC55218.2022.10088364","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088364","url":null,"abstract":"Software Testing is an essential activity in the development process of a software product. A defect-free software is the need of the hour. Identifying the defects as early as possible is critical to avoid any disastrous consequences in the later stages of development. Software Defect Prediction (SDP) is a process of early identification of defect-prone modules. Lately, software defect prediction coupled with machine learning techniques has gained momentum as it significantly brings down maintenance costs. Feature selection (FS) plays a very significant role in a defect prediction model's efficiency; hence, choosing a suitable FS method is challenging when building a defect prediction model. This paper evaluates six filter-based FS techniques, four wrapper-based FS techniques, and two embedded FS techniques using four supervised learning classifiers over six NASA datasets from the PROMISE repository. The experimental results strengthened that FS techniques significantly improve the model's predictive performance. From our experimental data, we concluded that SVM based defect prediction model showed the best performance among all other studied models. We also observed that Fisher's score, a filter-based FS technique, outperformed all other FS techniques studied in this work.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131087453","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088359
S. Navya, P. Nishitha, V. Hema
The classification of medical imaging is that specialists and radiologists stick to the end of the disorder. Basic studies based on convolutional cerebrum relationships (CNNs) are used to aid flexibility at the end of the clinic. Three systems are considered to distinguish affected tissues. CNN contextually identifies every single pixel of the image as an a location that is both intriguing and uninteresting. RoI is then used to separate the impacted area. The second method removes pixel position information from image data using scalable and improved techniques (autoencoders). The non-convolutional layer separates geographic information associated with opposing features and also forgets to retrieve important ward information for prominent components of the level. In the third structure, the U-Net thought module receives the relevant ward information. Channel size, read rate, and k-crease section verification were adjusted to break the membrane similarity coefficient (DSC).
{"title":"Medical Image Segmentation Using Deep Learning","authors":"S. Navya, P. Nishitha, V. Hema","doi":"10.1109/ASSIC55218.2022.10088359","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088359","url":null,"abstract":"The classification of medical imaging is that specialists and radiologists stick to the end of the disorder. Basic studies based on convolutional cerebrum relationships (CNNs) are used to aid flexibility at the end of the clinic. Three systems are considered to distinguish affected tissues. CNN contextually identifies every single pixel of the image as an a location that is both intriguing and uninteresting. RoI is then used to separate the impacted area. The second method removes pixel position information from image data using scalable and improved techniques (autoencoders). The non-convolutional layer separates geographic information associated with opposing features and also forgets to retrieve important ward information for prominent components of the level. In the third structure, the U-Net thought module receives the relevant ward information. Channel size, read rate, and k-crease section verification were adjusted to break the membrane similarity coefficient (DSC).","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129518542","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088330
Devang Jagdale, Sukrut Bidwai, Tejashvini R. Hiremath, Neil Bhutada, S. Bhingarkar
River networks are widely observed and scrutinized for various purposes, which incorporate determining the terrestrial positions of water bodies, examining the gauge levels of the river, predicting river flows, and conserving sustainable energy resources as a consequence of Global warming. Extraction of these River networks on digital imagery systems are executed by various segmentation and machine learning model integration. In this paper, distinct datasets are used from Kaggle and Google Earth Engine, Segmentation methods such as Image segmentation, gray scaling, enhancement, global thresholding, and Deep Learning UNet Architecture are integrated with contemplation of extracting river networks from satellite images which result in achieving 80.98 % dice score for the developed UNet Model. Hence, these developed techniques can further be used for river extraction from satellite images. And can be applied to various semantic segmentation detection datasets.
{"title":"Extraction of River Networks from Satellite Images using Image Processing & Deep Learning Techniques","authors":"Devang Jagdale, Sukrut Bidwai, Tejashvini R. Hiremath, Neil Bhutada, S. Bhingarkar","doi":"10.1109/ASSIC55218.2022.10088330","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088330","url":null,"abstract":"River networks are widely observed and scrutinized for various purposes, which incorporate determining the terrestrial positions of water bodies, examining the gauge levels of the river, predicting river flows, and conserving sustainable energy resources as a consequence of Global warming. Extraction of these River networks on digital imagery systems are executed by various segmentation and machine learning model integration. In this paper, distinct datasets are used from Kaggle and Google Earth Engine, Segmentation methods such as Image segmentation, gray scaling, enhancement, global thresholding, and Deep Learning UNet Architecture are integrated with contemplation of extracting river networks from satellite images which result in achieving 80.98 % dice score for the developed UNet Model. Hence, these developed techniques can further be used for river extraction from satellite images. And can be applied to various semantic segmentation detection datasets.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130969391","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：