Pub Date : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987435
V. Samudrala, N. Revathi, S. Padhi, S. Sasireka, B. Selvalakshmi, Divya Francis
A brain tumor is a common syndrome, where a specific set of cells gather and begin to grow inside a human brain, to interfere with the brain s regular function. Though there are a lot of techniques that act as a preliminary test for tumors, an analysis of the MRI scan image is sometimes enough to predict the presence of the tumor. This study aims in finding the best machine learning algorithm that can detect brain tumors with the highest accuracy value. For this purpose, a dataset of images from MRI scans of human brain s is obtained via Kaggle. After that, this dataset is preprocessed using a few techniques. The techniques involve image scaling and color conversion. Two different machine learning models were produced by two different algorithms. The machine learning algorithms used in this work are the U-net and the FPN. The created models are then trained using the preprocessed datasets. The models are then evaluated using a separate set of photos after training. Two metrics, the IoU and dice coefficient, are used to analyze the training and validation results. Although the parameters for both models remain the same during training and validation, it was ultimately determined that the FPN method is more effective at predicting brain cancers. The algorithm’s ultimate IoU value is 0.865, and its dice coefficient is 0.9034. The model is complete because the results were excellent for an image processing model. Real-time photos are used to test the model one more time before it is finished. This analysis’ findings are also deemed to be exceedingly adequate.
{"title":"Design and Comparison of Tumor Segmentation Using an ML-Based Clustering Method","authors":"V. Samudrala, N. Revathi, S. Padhi, S. Sasireka, B. Selvalakshmi, Divya Francis","doi":"10.1109/I-SMAC55078.2022.9987435","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987435","url":null,"abstract":"A brain tumor is a common syndrome, where a specific set of cells gather and begin to grow inside a human brain, to interfere with the brain s regular function. Though there are a lot of techniques that act as a preliminary test for tumors, an analysis of the MRI scan image is sometimes enough to predict the presence of the tumor. This study aims in finding the best machine learning algorithm that can detect brain tumors with the highest accuracy value. For this purpose, a dataset of images from MRI scans of human brain s is obtained via Kaggle. After that, this dataset is preprocessed using a few techniques. The techniques involve image scaling and color conversion. Two different machine learning models were produced by two different algorithms. The machine learning algorithms used in this work are the U-net and the FPN. The created models are then trained using the preprocessed datasets. The models are then evaluated using a separate set of photos after training. Two metrics, the IoU and dice coefficient, are used to analyze the training and validation results. Although the parameters for both models remain the same during training and validation, it was ultimately determined that the FPN method is more effective at predicting brain cancers. The algorithm’s ultimate IoU value is 0.865, and its dice coefficient is 0.9034. The model is complete because the results were excellent for an image processing model. Real-time photos are used to test the model one more time before it is finished. This analysis’ findings are also deemed to be exceedingly adequate.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121271574","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987314
S. Vijayalakshmi, T. D. Subha, L. Manimegalai, Ektha Sudhakar Reddy, Dama Yaswanth, Sakithya Gopinath
The development of cyber security is very important, and as a result, it has received a significant amount of research interest from academic institutions and industrial groups all over the globe. It is also of the utmost importance to offer computing that is environmentally friendly for the Internet of Things. In order to detect intrusions and identify malicious actors, machine learning algorithms play an essential part in the cyber security of the internet of things (IoT). Because of this, the purpose of this work is to create novel techniques of extracting attributes that take use of the benefits offered by swarm intelligence (SI) method. We devise a technique for the extracting the attributes that is based on the traditional neural networks. In addition, in order to compute the effectiveness of the IDS method that was created, four well recognized public datasets were employed. We also evaluated detailed comparisons to many alternative optimization approaches in order to test the proposed method’s ability to compete successfully in the market. The findings demonstrate that the created strategy performs very well when measured against a variety of assessment metrics.
{"title":"A Novel Approach for IoT Intrusion Detection System using Modified Optimizer and Convolutional Neural Network","authors":"S. Vijayalakshmi, T. D. Subha, L. Manimegalai, Ektha Sudhakar Reddy, Dama Yaswanth, Sakithya Gopinath","doi":"10.1109/I-SMAC55078.2022.9987314","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987314","url":null,"abstract":"The development of cyber security is very important, and as a result, it has received a significant amount of research interest from academic institutions and industrial groups all over the globe. It is also of the utmost importance to offer computing that is environmentally friendly for the Internet of Things. In order to detect intrusions and identify malicious actors, machine learning algorithms play an essential part in the cyber security of the internet of things (IoT). Because of this, the purpose of this work is to create novel techniques of extracting attributes that take use of the benefits offered by swarm intelligence (SI) method. We devise a technique for the extracting the attributes that is based on the traditional neural networks. In addition, in order to compute the effectiveness of the IDS method that was created, four well recognized public datasets were employed. We also evaluated detailed comparisons to many alternative optimization approaches in order to test the proposed method’s ability to compete successfully in the market. The findings demonstrate that the created strategy performs very well when measured against a variety of assessment metrics.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125344496","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987407
Ankur Biswas, A. Karan, Nidhi Nigam, H. Doreswamy, Serikkhan Sadykanova, Mangazina Zhanel Rauliyevna
Cloud computing plays major role in the development of accessing clouduser’s document and sensitive information stored. It has variety of content and representation. Cyber security and attacks in the cloud is a challenging aspect. Information security attains a vital part in Cyber Security management. It involves actions intended to reduce the adverse impacts of such incidents. To access the documents stored in cloud safely and securely, access control will be introduced based on cloud users to access the user’s document in the cloud. To achieve this, it is highly required to combine security components (e.g., Access Control, Usage Control) in the security document to get automatic information. This research work has proposed a Role Key Homomorphic Encryption Algorithm (RKHEA) to monitor the cloud users, who access the services continuously. This method provides access creation of session-based key to store the singularized encryption to reduce the key size from random methods to occupy memory space. It has some terms and conditions to be followed by the cloud users and also has encryption method to secure the document content. Hence the documents are encrypted with the RKHEA algorithm based on Service Key Access (SKA). Then, the encrypted key will be created based on access control conditions. The proposed analytics result shows an enhanced control over the documents in cloud and improved security performance.
{"title":"Implementation of Cyber Security for Enabling Data Protection Analysis and Data Protection using Robot Key Homomorphic Encryption","authors":"Ankur Biswas, A. Karan, Nidhi Nigam, H. Doreswamy, Serikkhan Sadykanova, Mangazina Zhanel Rauliyevna","doi":"10.1109/I-SMAC55078.2022.9987407","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987407","url":null,"abstract":"Cloud computing plays major role in the development of accessing clouduser’s document and sensitive information stored. It has variety of content and representation. Cyber security and attacks in the cloud is a challenging aspect. Information security attains a vital part in Cyber Security management. It involves actions intended to reduce the adverse impacts of such incidents. To access the documents stored in cloud safely and securely, access control will be introduced based on cloud users to access the user’s document in the cloud. To achieve this, it is highly required to combine security components (e.g., Access Control, Usage Control) in the security document to get automatic information. This research work has proposed a Role Key Homomorphic Encryption Algorithm (RKHEA) to monitor the cloud users, who access the services continuously. This method provides access creation of session-based key to store the singularized encryption to reduce the key size from random methods to occupy memory space. It has some terms and conditions to be followed by the cloud users and also has encryption method to secure the document content. Hence the documents are encrypted with the RKHEA algorithm based on Service Key Access (SKA). Then, the encrypted key will be created based on access control conditions. The proposed analytics result shows an enhanced control over the documents in cloud and improved security performance.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115261333","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987359
J. Sreemathy, N. Prasath
In today’s age of automated scenarios and digital lifestyle, online shopping has really made its way to everyone’s household, with one touch anyone can order the required products. The use of digital marketing over conventional marketing is often favored. It is beneficial to both social media marketing professionals and technicians. When conducting research, one may gain preliminary insights into consumers’ perceptions of social media advertisements and online buying habits. Online knowledge exchange allows researchers, academics, and business people to swiftly and easily connect with individuals while conducting searchable mobile brand website research. This research provides a methodical description of a study that only aids consumers in making the optimal smartphone decision for their own parametric needs. A given dataset will be examined utilising machine learning methods, such as brand name predictions with regression and precise results. Groups of people are frequently paid by brands to create internet evaluations, which may be favourable to them or unfavourable to their competitors.
{"title":"Machine Learning based Sales Prediction and Characterization using Consumer Perceptions","authors":"J. Sreemathy, N. Prasath","doi":"10.1109/I-SMAC55078.2022.9987359","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987359","url":null,"abstract":"In today’s age of automated scenarios and digital lifestyle, online shopping has really made its way to everyone’s household, with one touch anyone can order the required products. The use of digital marketing over conventional marketing is often favored. It is beneficial to both social media marketing professionals and technicians. When conducting research, one may gain preliminary insights into consumers’ perceptions of social media advertisements and online buying habits. Online knowledge exchange allows researchers, academics, and business people to swiftly and easily connect with individuals while conducting searchable mobile brand website research. This research provides a methodical description of a study that only aids consumers in making the optimal smartphone decision for their own parametric needs. A given dataset will be examined utilising machine learning methods, such as brand name predictions with regression and precise results. Groups of people are frequently paid by brands to create internet evaluations, which may be favourable to them or unfavourable to their competitors.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122571573","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9986500
S. Nissi, K. G. Saravanan, C. Srivenkateswaran, Nishathini, D.C. JullieJosephine, S. Shibia Malar
This research investigates the social media concern about social judgement. Therefore, immediate utilization to enhance women safety. Unique references are widely distributed in social networking sites and apps like Facebook, Twitter, and Instagram. Instagram typically offers opportunities in a range of fields by using images and videos to educate users. Instagram manages the hash tag messages that are extensively viewed and serves as a forum for women to express their emotions and thoughts. The quotes focusing on the protection of women may be used to read a message from the youth culture and therefore strict measures can be initialized to outlaw the messaging priority using deep learning and actions can be taken against those who abuse women. Instagram and other Instagram handles that post messages with hash tags are useful to establish a global communication. This research study utilized deep learning model to investigate the security and privacy of women social media users.
{"title":"Women Safety and Alertness in Instagram using Deep Learning","authors":"S. Nissi, K. G. Saravanan, C. Srivenkateswaran, Nishathini, D.C. JullieJosephine, S. Shibia Malar","doi":"10.1109/I-SMAC55078.2022.9986500","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9986500","url":null,"abstract":"This research investigates the social media concern about social judgement. Therefore, immediate utilization to enhance women safety. Unique references are widely distributed in social networking sites and apps like Facebook, Twitter, and Instagram. Instagram typically offers opportunities in a range of fields by using images and videos to educate users. Instagram manages the hash tag messages that are extensively viewed and serves as a forum for women to express their emotions and thoughts. The quotes focusing on the protection of women may be used to read a message from the youth culture and therefore strict measures can be initialized to outlaw the messaging priority using deep learning and actions can be taken against those who abuse women. Instagram and other Instagram handles that post messages with hash tags are useful to establish a global communication. This research study utilized deep learning model to investigate the security and privacy of women social media users.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114179568","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987286
Yan Liu
Establishment of the soil preferential flow model based on modern remote sensor observation methods is studied in this study. It is currently the world’s advanced open solution for the process automation systems and a new generation of open system for the industry. Hence, this paper proposes the 2 aspects of novelty. (1) Small satellites can use various forms of the delivery and launch vehicles, and it only takes a few days from preparation to launch and even activation. This technology will be applied in the data collection process. (2) The function of the sink node is responsible for the convergence and forwarding of information in the WSN. This novel sensor model is used to perform information transmission. Besides these, the soil preferential flow model is designed and implemented. The simulation is conducted for the verification of the proposed framework.
{"title":"Establishment of Soil Preferential Flow Model based on Modern Remote Sensor Observation Methods","authors":"Yan Liu","doi":"10.1109/I-SMAC55078.2022.9987286","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987286","url":null,"abstract":"Establishment of the soil preferential flow model based on modern remote sensor observation methods is studied in this study. It is currently the world’s advanced open solution for the process automation systems and a new generation of open system for the industry. Hence, this paper proposes the 2 aspects of novelty. (1) Small satellites can use various forms of the delivery and launch vehicles, and it only takes a few days from preparation to launch and even activation. This technology will be applied in the data collection process. (2) The function of the sink node is responsible for the convergence and forwarding of information in the WSN. This novel sensor model is used to perform information transmission. Besides these, the soil preferential flow model is designed and implemented. The simulation is conducted for the verification of the proposed framework.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116805849","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987336
Changhui Wang
A mathematical model composed of artificial intelligence neural network (BP) and genetic algorithm (GA) is proposed. Taking advantage of the neural network, the genetic algorithm overcomes the defect that the neural network is easy to fall into the local minimum error. Combining the soft measurement technology of DO concentration with the computer automatic control technology, the intelligent monitoring scheme of the sewage treatment process is designed, the overall structure and function of the system are given, the fuzzy system is applied to the particle swarm optimization algorithm, and the dynamic adjustment inertia is established. Fuzzy rules for weights. Simulation research by optimizing the extreme point of the test function.
{"title":"Research on Intelligent Real time Monitoring System based on Neural Network Optimization","authors":"Changhui Wang","doi":"10.1109/I-SMAC55078.2022.9987336","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987336","url":null,"abstract":"A mathematical model composed of artificial intelligence neural network (BP) and genetic algorithm (GA) is proposed. Taking advantage of the neural network, the genetic algorithm overcomes the defect that the neural network is easy to fall into the local minimum error. Combining the soft measurement technology of DO concentration with the computer automatic control technology, the intelligent monitoring scheme of the sewage treatment process is designed, the overall structure and function of the system are given, the fuzzy system is applied to the particle swarm optimization algorithm, and the dynamic adjustment inertia is established. Fuzzy rules for weights. Simulation research by optimizing the extreme point of the test function.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128544803","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987295
Hong Zhang
Chinese classical music has the value of conserving its temperament in the excellent traditional Chinese culture education of college students, making it the value of the times as the inheritor of Chinese cultural emotional experience. The 20dimensional features are obtained by dimensionality reduction optimization, and then the detail coefficients from the first scale to the fourth scale and the approximation coefficients of the fourth scale are extracted as frequency domain features through discrete wavelet transform, which has the power to gather young people to “go up” and “to be kind”. We set, using MDI algorithm and conventional linear fitting and exponential fitting algorithms to obtain the corresponding quantitative map of T2 mental characteristics and calculate and display the noise propagation characteristics of the three algorithms by Monte Carlo method is essential and selected as the core of the proposed model.
{"title":"Analysis of Feature Extraction and Waveform Matching from the Perspective of Multi-Dimensional Information Integration Algorithm","authors":"Hong Zhang","doi":"10.1109/I-SMAC55078.2022.9987295","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987295","url":null,"abstract":"Chinese classical music has the value of conserving its temperament in the excellent traditional Chinese culture education of college students, making it the value of the times as the inheritor of Chinese cultural emotional experience. The 20dimensional features are obtained by dimensionality reduction optimization, and then the detail coefficients from the first scale to the fourth scale and the approximation coefficients of the fourth scale are extracted as frequency domain features through discrete wavelet transform, which has the power to gather young people to “go up” and “to be kind”. We set, using MDI algorithm and conventional linear fitting and exponential fitting algorithms to obtain the corresponding quantitative map of T2 mental characteristics and calculate and display the noise propagation characteristics of the three algorithms by Monte Carlo method is essential and selected as the core of the proposed model.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129458619","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987399
Anandaraj A, P. Alphonse
The process of developing across space and time in the networks of a person with epilepsy occurs through Epileptic seizures. The generalizable technique is developed in this research to predict a particular patient seizure using the evaluation of featurerepresentation to obtain the features from the signals of multichannel EEG. The features are revealed for the signals of EEG using the available parameters. The features are input to the Risk-based Elman learning model (r - ELM) to evaluate feature representation to collectively train the data. The suggested model of r-ELM obtains 0. 096/h as the rate of false prediction, 85% as sensitivity, and 10% as the time in warning to perform the tests from the EEG dataset of CHB-Mn scalp using 10 patients. The suggested method has superiority over the existing results. Various metrics are used in the experiment which shows the epileptic stage as the essential factor affecting seizures’ performance. A subject-oriented method for seizure prediction is presented in the proposed system, which is powerful for the unbalanced data and created for any dataset of scalp EEG with no requirement of subject-oriented engineering.
{"title":"Modelling a Risk-based Network Model for Epileptic Seizure Prediction using Learning Approaches","authors":"Anandaraj A, P. Alphonse","doi":"10.1109/I-SMAC55078.2022.9987399","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987399","url":null,"abstract":"The process of developing across space and time in the networks of a person with epilepsy occurs through Epileptic seizures. The generalizable technique is developed in this research to predict a particular patient seizure using the evaluation of featurerepresentation to obtain the features from the signals of multichannel EEG. The features are revealed for the signals of EEG using the available parameters. The features are input to the Risk-based Elman learning model (r - ELM) to evaluate feature representation to collectively train the data. The suggested model of r-ELM obtains 0. 096/h as the rate of false prediction, 85% as sensitivity, and 10% as the time in warning to perform the tests from the EEG dataset of CHB-Mn scalp using 10 patients. The suggested method has superiority over the existing results. Various metrics are used in the experiment which shows the epileptic stage as the essential factor affecting seizures’ performance. A subject-oriented method for seizure prediction is presented in the proposed system, which is powerful for the unbalanced data and created for any dataset of scalp EEG with no requirement of subject-oriented engineering.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130393993","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 : 2022-11-10DOI: 10.1109/I-SMAC55078.2022.9987347
Han Wu
This paper first introduces the principle, development and application of expert system, and proposes a robust agricultural science and education video text extraction method based on complex background. The algorithm mainly realizes video text extraction through video decoding, MSER text positioning, projection segmentation and Tesseract text recognition. An English-assisted teaching module based on expert system theory, which is aimed at teachers and users. The module classifies and summarizes English knowledge points using a combination of frame-based and production-based knowledge expressions. BP neural network is used to establish students’ autonomous learning and the system module analyzes the test situation of the students, enables the students to self-diagnose, and combines the memory forgetting curve through the students’ repeated practice.
{"title":"Multi-Center Backup Framework based on Audio and Video Complex Information Extraction Algorithm","authors":"Han Wu","doi":"10.1109/I-SMAC55078.2022.9987347","DOIUrl":"https://doi.org/10.1109/I-SMAC55078.2022.9987347","url":null,"abstract":"This paper first introduces the principle, development and application of expert system, and proposes a robust agricultural science and education video text extraction method based on complex background. The algorithm mainly realizes video text extraction through video decoding, MSER text positioning, projection segmentation and Tesseract text recognition. An English-assisted teaching module based on expert system theory, which is aimed at teachers and users. The module classifies and summarizes English knowledge points using a combination of frame-based and production-based knowledge expressions. BP neural network is used to establish students’ autonomous learning and the system module analyzes the test situation of the students, enables the students to self-diagnose, and combines the memory forgetting curve through the students’ repeated practice.","PeriodicalId":306129,"journal":{"name":"2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127004696","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：