Pub Date : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126310
A. Raj, Rio G. L. D'Souza
A supplementary method for ensuring that private data is inaccessible to outside parties is data anonymization. Anonymization might affect the outcomes of data mining procedures since it may make it more difficult for commonly used algorithms to analyze the data. This practical experience report compares the performance impact of current data anonymization algorithms to the suggested k-anonymization methods utilizing both original and anonymized data in order to assess the correctness and execution time. Through the use of kanonymization, l-diversity, t-closeness, and differential privacy techniques, a sample of genuine data produced by a healthcare facility was made anonymous. Contrary to predictions, the Hadoop framework was able to handle anonymization approaches, improving accuracy and performance while speeding up execution. These findings show that data anonymization techniques, when properly implemented through Hadoop ecosystems, can help to increase the effectiveness of data anonymization. Furthermore, the suggested method can produce the data anonymization with the necessary utility and protection trade-offs and with a performance scalable to large datasets.
{"title":"Performance Metrics Evaluation Towards The Effectiveness of Data Anonymization","authors":"A. Raj, Rio G. L. D'Souza","doi":"10.1109/I2CT57861.2023.10126310","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126310","url":null,"abstract":"A supplementary method for ensuring that private data is inaccessible to outside parties is data anonymization. Anonymization might affect the outcomes of data mining procedures since it may make it more difficult for commonly used algorithms to analyze the data. This practical experience report compares the performance impact of current data anonymization algorithms to the suggested k-anonymization methods utilizing both original and anonymized data in order to assess the correctness and execution time. Through the use of kanonymization, l-diversity, t-closeness, and differential privacy techniques, a sample of genuine data produced by a healthcare facility was made anonymous. Contrary to predictions, the Hadoop framework was able to handle anonymization approaches, improving accuracy and performance while speeding up execution. These findings show that data anonymization techniques, when properly implemented through Hadoop ecosystems, can help to increase the effectiveness of data anonymization. Furthermore, the suggested method can produce the data anonymization with the necessary utility and protection trade-offs and with a performance scalable to large datasets.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114419136","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126478
M. V. Gopala Rao, V. Chandra Prakash, M. V. M. G. Guru Charan, G. Venkata Bhargav, M. N. Rao
Diabetic Retinopathy (DR) is one of the main causes of visual disorder in patients affected with diabetes. Prior diagnosis is needed to reduce the visual impairment, so that damage to eye can be minimized. In the DR, Microaneurysm (MA) is the earliest medical sign which appears as tiny individual retinal patterns. So, powerful computer aided diagnose techniques for MA detection are needed. In this paper, a new approach for the automatic detection of MAs in eye fundus images is proposed. Eleven features based on shape and intensity characteristics are extracted from MA candidates and true MAs are classified from false candidates using KNN, SVM and NB classifiers. This proposed approach is evaluated on a publicly available dataset (E-ophtha). The performance of this method is measured by using sensitivity, specificity, and accuracy metrics. The experimental outcome demonstrated that the proposed method is efficient to diagnose clinically.
{"title":"Automatic Detection and Classification of Microaneurysms for Early Detection of Diabetic Retinopathy in Color Fundus Images","authors":"M. V. Gopala Rao, V. Chandra Prakash, M. V. M. G. Guru Charan, G. Venkata Bhargav, M. N. Rao","doi":"10.1109/I2CT57861.2023.10126478","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126478","url":null,"abstract":"Diabetic Retinopathy (DR) is one of the main causes of visual disorder in patients affected with diabetes. Prior diagnosis is needed to reduce the visual impairment, so that damage to eye can be minimized. In the DR, Microaneurysm (MA) is the earliest medical sign which appears as tiny individual retinal patterns. So, powerful computer aided diagnose techniques for MA detection are needed. In this paper, a new approach for the automatic detection of MAs in eye fundus images is proposed. Eleven features based on shape and intensity characteristics are extracted from MA candidates and true MAs are classified from false candidates using KNN, SVM and NB classifiers. This proposed approach is evaluated on a publicly available dataset (E-ophtha). The performance of this method is measured by using sensitivity, specificity, and accuracy metrics. The experimental outcome demonstrated that the proposed method is efficient to diagnose clinically.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114763997","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126219
Shreya Chakravarty, R. Khandelwal
The "thinking machines" today, breathe hand-in-hand with the blessing of expunging human effort, as well as the disadvantage of being misused easily. There are enormous applications of automation, one of the most popular being speech recognition. Automated systems can now be controlled by voice commands, and also can provide human-like responses, whether it is appearance or communication media like speech. There won’t always be times when the source of audio would be in ideal surroundings. This aggravates the possibility of human-system interaction involving audio aberrations and hence, raises a great apprehension regarding forensic issues like authenticity and the source of the given audio, which calls for a challenge to resolve. This paper seeks to illustrate thorough augmentation of audio data for a robust solution that eradicates the anomalies in audio using a pipeline approach. We propose analysing the spectrogram representation of an audio signal to determine a mask that segregates noise from pure signal, and results in a signal that can be processed for speech recognition, further extending to fabrication of a deep neural network having an accuracy of 95.87%.
{"title":"A Robust Pipeline based Deep Learning Approach to Detect Speech Attribution","authors":"Shreya Chakravarty, R. Khandelwal","doi":"10.1109/I2CT57861.2023.10126219","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126219","url":null,"abstract":"The \"thinking machines\" today, breathe hand-in-hand with the blessing of expunging human effort, as well as the disadvantage of being misused easily. There are enormous applications of automation, one of the most popular being speech recognition. Automated systems can now be controlled by voice commands, and also can provide human-like responses, whether it is appearance or communication media like speech. There won’t always be times when the source of audio would be in ideal surroundings. This aggravates the possibility of human-system interaction involving audio aberrations and hence, raises a great apprehension regarding forensic issues like authenticity and the source of the given audio, which calls for a challenge to resolve. This paper seeks to illustrate thorough augmentation of audio data for a robust solution that eradicates the anomalies in audio using a pipeline approach. We propose analysing the spectrogram representation of an audio signal to determine a mask that segregates noise from pure signal, and results in a signal that can be processed for speech recognition, further extending to fabrication of a deep neural network having an accuracy of 95.87%.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115990084","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126375
Basil Jose, S. Mini
The Internet of Things is a rapidly growing field, and the management of IoT nodes is becoming increasingly important. Perpetual energy supply remains a major area of concern for IoT devices. IoT nodes with low energy levels may go into a sleep state, making them unavailable for use and they must be recharged to be reused. The challenge is to select the nodes that should be charged to minimize downtime and maximize uptime. This paper proposes the use of the Gur game algorithm to optimize the management of IoT nodes for maximum uptime and minimum downtime. The Gur game algorithm is used to proactively select the nodes to be charged, considering the current energy levels of the nodes and the utilization of IoT nodes in the network. A preliminary result is proposed in this paper. The proposed method is a unique approach in managing IoT nodes, providing an effective way to ensure optimal utilization of resources and efficient operation of IoT systems.
{"title":"Efficient Device Management for Enhanced Energy Utilization and Operational Performance in Internet of Things","authors":"Basil Jose, S. Mini","doi":"10.1109/I2CT57861.2023.10126375","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126375","url":null,"abstract":"The Internet of Things is a rapidly growing field, and the management of IoT nodes is becoming increasingly important. Perpetual energy supply remains a major area of concern for IoT devices. IoT nodes with low energy levels may go into a sleep state, making them unavailable for use and they must be recharged to be reused. The challenge is to select the nodes that should be charged to minimize downtime and maximize uptime. This paper proposes the use of the Gur game algorithm to optimize the management of IoT nodes for maximum uptime and minimum downtime. The Gur game algorithm is used to proactively select the nodes to be charged, considering the current energy levels of the nodes and the utilization of IoT nodes in the network. A preliminary result is proposed in this paper. The proposed method is a unique approach in managing IoT nodes, providing an effective way to ensure optimal utilization of resources and efficient operation of IoT systems.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116336084","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126390
Vijay U. Rathod, S. Gumaste
The term "Mobile Ad Hoc Networks" (MANETs) refers to a technology that is currently gaining worldwide popularity. A MANET is a network without any centralized management and without any infrastructure. It is made up of mobile nodes (MNs), which create the network on the fly. Although mobile nodes can quickly change their topology, effective routing protocols are required to build the network connecting nodes for this purpose. A key component of the routing protocol is the ability for mobile nodes to move independently. The network's overall performance may be directly impacted by them. Therefore, the effectiveness of the MANET routing protocol is significantly influenced by node mobility. The movement pattern displays how positions, locations, and node velocities of mobile users change over time in real-world applications. To get the best performance metrics, it is difficult to create an efficient and effective mobility model for MANET. In this study, we discuss the effects of the random walk (RW) and random waypoint (RWP) mobility models on the routing parameters. In the past, different routing systems' effects on network performance have been assessed using mobility models. As a result, the mobility pattern's characteristics will substantially influence how well the network performs. The accurate route adjustments must be rearranged in the correct sequence by the routing protocols. As a result, traffic routing update overheads are very high. These mobility patterns affect various network protocols or applications differently.
{"title":"Role of Routing Protocol in Mobile Ad-Hoc Network for Performance of Mobility Models","authors":"Vijay U. Rathod, S. Gumaste","doi":"10.1109/I2CT57861.2023.10126390","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126390","url":null,"abstract":"The term \"Mobile Ad Hoc Networks\" (MANETs) refers to a technology that is currently gaining worldwide popularity. A MANET is a network without any centralized management and without any infrastructure. It is made up of mobile nodes (MNs), which create the network on the fly. Although mobile nodes can quickly change their topology, effective routing protocols are required to build the network connecting nodes for this purpose. A key component of the routing protocol is the ability for mobile nodes to move independently. The network's overall performance may be directly impacted by them. Therefore, the effectiveness of the MANET routing protocol is significantly influenced by node mobility. The movement pattern displays how positions, locations, and node velocities of mobile users change over time in real-world applications. To get the best performance metrics, it is difficult to create an efficient and effective mobility model for MANET. In this study, we discuss the effects of the random walk (RW) and random waypoint (RWP) mobility models on the routing parameters. In the past, different routing systems' effects on network performance have been assessed using mobility models. As a result, the mobility pattern's characteristics will substantially influence how well the network performs. The accurate route adjustments must be rearranged in the correct sequence by the routing protocols. As a result, traffic routing update overheads are very high. These mobility patterns affect various network protocols or applications differently.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116811315","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126200
Prajakta Kubal, Namita D. Pulgam, V. Mane
The volume of images and the videos are being shared on various social media platform are huge and there are cybercrimes happening in these areas. Hence, identification of the main source of social network, based on the images uploaded or downloaded from social network has become an important activity in the multimedia forensic analysis. When media shared on social network there are possibilities of exploiting different pattern embedding in image content by social network. To make it easier system is proposed with discrete cosine transform (DCT) method and JPEG Quantization to identify the changes in shared images on social networks applications. The quantization used in JPEG compression is used to help in separating the images that have been processed by software. DCT finds the pixel value of the blur images and it is easier in implementation. The combination of DCT and JPEG quantization can give the better accuracy rate which helps in finding the images shared or the source of the images.
{"title":"Identifying Image Modifications using DCT and JPEG Quantization Technique","authors":"Prajakta Kubal, Namita D. Pulgam, V. Mane","doi":"10.1109/I2CT57861.2023.10126200","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126200","url":null,"abstract":"The volume of images and the videos are being shared on various social media platform are huge and there are cybercrimes happening in these areas. Hence, identification of the main source of social network, based on the images uploaded or downloaded from social network has become an important activity in the multimedia forensic analysis. When media shared on social network there are possibilities of exploiting different pattern embedding in image content by social network. To make it easier system is proposed with discrete cosine transform (DCT) method and JPEG Quantization to identify the changes in shared images on social networks applications. The quantization used in JPEG compression is used to help in separating the images that have been processed by software. DCT finds the pixel value of the blur images and it is easier in implementation. The combination of DCT and JPEG quantization can give the better accuracy rate which helps in finding the images shared or the source of the images.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123976594","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126403
Lakshay Girdher, D. Kumar, V. Kukreja
The proposed study uses a hybrid model of convolutional neural networks (CNN) and long Short-Term Memory (LSTM) for the classification of healthy and leaf-spot diseased images of the Golden Pothos plant. A dataset of 8000 images was collected and pre-processed before being used for training and testing the model. The images were first classified into binary categories of healthy and leaf spot diseased and then into four different severity levels of the disease. The performance of the model was evaluated using various performance parameters, including accuracy, precision, recall, and F1-score. The model achieved an overall accuracy of 95.4% and 97.5% for binary and multi-class classification, respectively. The proposed model outperformed other state-of-the-art models for disease classification in plants, making it a promising solution for detecting plant diseases. Our study provides insights into the potential of using hybrid models in plant disease diagnosis and paves the way for further research in this area.
{"title":"Detecting and Estimating Severity of Leaf Spot Disease in Golden Pothos using Hybrid Deep Learning Approach","authors":"Lakshay Girdher, D. Kumar, V. Kukreja","doi":"10.1109/I2CT57861.2023.10126403","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126403","url":null,"abstract":"The proposed study uses a hybrid model of convolutional neural networks (CNN) and long Short-Term Memory (LSTM) for the classification of healthy and leaf-spot diseased images of the Golden Pothos plant. A dataset of 8000 images was collected and pre-processed before being used for training and testing the model. The images were first classified into binary categories of healthy and leaf spot diseased and then into four different severity levels of the disease. The performance of the model was evaluated using various performance parameters, including accuracy, precision, recall, and F1-score. The model achieved an overall accuracy of 95.4% and 97.5% for binary and multi-class classification, respectively. The proposed model outperformed other state-of-the-art models for disease classification in plants, making it a promising solution for detecting plant diseases. Our study provides insights into the potential of using hybrid models in plant disease diagnosis and paves the way for further research in this area.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125785947","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126418
Priyanka Mane, S. Suryawanshi, Vilas S. Bugade
A research work is being carried out on Micro grid system operation and control. Also, analysis, design and implementation of laboratory scale Micro Grid (MG) are much optimized work for the researchers. It is well documented in many publications, literatures and group discussions about the design analysis, battery design issues, design of Inverter, and Buck converter problem. The actual implementation of MG laboratory test bed leads to different issues mentioned earlier and has to overcome by doing actual software simulation before implementation. The scheme MG comprises of Solar PV panel, Wind Turbine, Energy Storage, Converter, Inverter, Charge Controller and several electrical loads which are fed through a Voltage Source Inverter (VSI).The Inverter which is proposed here is with PWM control with Proportional Resonant (PR) Controller. Whenever some disturbances occur in the system, Static Transfer Switch (STS) has to open & should isolate the Utility and MG within a very short duration. By this time the Distributed Energy Sources (DERs) is able to supply to the connected load maintains the good voltage regulation. Now, the DERs must deliver the power to connected loads and when fault clears and system is healthy, the MG should be able to re-synchronize with utility grid smoothly from Islanding mode of operation. The designed MG lab test bed will be undergone the different analysis about Total Harmonic Distortion (THD), transient behavior and other analysis regarding power system such as improvement of Power Factor on load side. By the use of DERs in the MG topology it is very beneficial to the environment as there is massive use of Renewable Energy Resources (RES).
{"title":"Performance Analysis of Voltage Source Sine PWM Inverter for Micro Grid Topology","authors":"Priyanka Mane, S. Suryawanshi, Vilas S. Bugade","doi":"10.1109/I2CT57861.2023.10126418","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126418","url":null,"abstract":"A research work is being carried out on Micro grid system operation and control. Also, analysis, design and implementation of laboratory scale Micro Grid (MG) are much optimized work for the researchers. It is well documented in many publications, literatures and group discussions about the design analysis, battery design issues, design of Inverter, and Buck converter problem. The actual implementation of MG laboratory test bed leads to different issues mentioned earlier and has to overcome by doing actual software simulation before implementation. The scheme MG comprises of Solar PV panel, Wind Turbine, Energy Storage, Converter, Inverter, Charge Controller and several electrical loads which are fed through a Voltage Source Inverter (VSI).The Inverter which is proposed here is with PWM control with Proportional Resonant (PR) Controller. Whenever some disturbances occur in the system, Static Transfer Switch (STS) has to open & should isolate the Utility and MG within a very short duration. By this time the Distributed Energy Sources (DERs) is able to supply to the connected load maintains the good voltage regulation. Now, the DERs must deliver the power to connected loads and when fault clears and system is healthy, the MG should be able to re-synchronize with utility grid smoothly from Islanding mode of operation. The designed MG lab test bed will be undergone the different analysis about Total Harmonic Distortion (THD), transient behavior and other analysis regarding power system such as improvement of Power Factor on load side. By the use of DERs in the MG topology it is very beneficial to the environment as there is massive use of Renewable Energy Resources (RES).","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124855039","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}
Strokes damage the central nervous system and are one of the leading causes of death today. Compared with several kinds of stroke, hemorrhagic and ischemic causes have a negative impact on the human central nervous system. One of the cerebrovascular health conditions, stroke has a significant impact on a person’s life and health. In order to diagnose and treat stroke, brain CT scan images must undergo electronic quantitative analysis. An essential tool for damage revelation is provided by deep neural networks, which have a tremendous capacity for data learning. In this paper, we aim to detect brain strokes with the help of CT-Scan images by using a convolutional neural network. After training and testing the model on a CT-scan dataset comprising 2551 images, we obtained the best accuracy of 90%.
{"title":"Brain Stroke Detection Using CNN Algorithm","authors":"Prasad Gahiwad, Nilesh Deshmane, Sachet Karnakar, Sujit Mali, Rohini. G. Pise","doi":"10.1109/I2CT57861.2023.10126125","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126125","url":null,"abstract":"Strokes damage the central nervous system and are one of the leading causes of death today. Compared with several kinds of stroke, hemorrhagic and ischemic causes have a negative impact on the human central nervous system. One of the cerebrovascular health conditions, stroke has a significant impact on a person’s life and health. In order to diagnose and treat stroke, brain CT scan images must undergo electronic quantitative analysis. An essential tool for damage revelation is provided by deep neural networks, which have a tremendous capacity for data learning. In this paper, we aim to detect brain strokes with the help of CT-Scan images by using a convolutional neural network. After training and testing the model on a CT-scan dataset comprising 2551 images, we obtained the best accuracy of 90%.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125043904","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126208
G. S. Krishna Kireeti, J. Prithvi, Mangala Divya, C. Kumari
Analysing students’ performance concerning their future plans (after under-graduation) is essential in universities, colleges, schools or coaching centres etc. Prospective graduate students always face a dilemma when choosing master’s programs and universities based on their scores (such as GRE, TOEFL, etc.). At the same time, students who opt for jobs as their objective career face a dilemma regarding their employability chances based on their academics, placements and training test scores (such as coding, English, communication etc.). Predicting the candidates’ employability or admission chances based on their scores will guide them to improve their performance. This prediction also helps the faculty improve their teaching skills, provide more resources to the students, and train them most effectively. This paper addresses various machine-learning regression models, such as Gradient Boosting regression, Support Vector Regression, Random Forest regression, Decision Tree Regression, and Ridge Regression. We select the best-performing model, which we will use to indicate whether the university that the MS aspirants are considering is ambitious or safe, and predict the student’s employability chances for their academic placements. This paper also addresses using of streamlit (an open-source app framework) for developing a user-friendly web application interface for users using the best-performing model.
{"title":"Predicting Employability and Admission for MS Students using ML Regression Models","authors":"G. S. Krishna Kireeti, J. Prithvi, Mangala Divya, C. Kumari","doi":"10.1109/I2CT57861.2023.10126208","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126208","url":null,"abstract":"Analysing students’ performance concerning their future plans (after under-graduation) is essential in universities, colleges, schools or coaching centres etc. Prospective graduate students always face a dilemma when choosing master’s programs and universities based on their scores (such as GRE, TOEFL, etc.). At the same time, students who opt for jobs as their objective career face a dilemma regarding their employability chances based on their academics, placements and training test scores (such as coding, English, communication etc.). Predicting the candidates’ employability or admission chances based on their scores will guide them to improve their performance. This prediction also helps the faculty improve their teaching skills, provide more resources to the students, and train them most effectively. This paper addresses various machine-learning regression models, such as Gradient Boosting regression, Support Vector Regression, Random Forest regression, Decision Tree Regression, and Ridge Regression. We select the best-performing model, which we will use to indicate whether the university that the MS aspirants are considering is ambitious or safe, and predict the student’s employability chances for their academic placements. This paper also addresses using of streamlit (an open-source app framework) for developing a user-friendly web application interface for users using the best-performing model.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125050387","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：