Pub Date : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073852
Chamandeep Kaur, Tuhina Panda, Subhasis Panda, Abdul Rahman Mohammed Al Ansari, M. Nivetha, B. Kiran Bala
Machine learning is widely used in many aspects of healthcare. The development of medical technology has made it possible to gather better data for early disease symptom diagnosis. This study makes an effort to categorize Alzheimer’s disorder. Alzheimer’s disease is a fatal disorder that may result in memory loss and mental impairment. To prepare for medical attention, this needs early disease diagnosis. Magnetic resonance imaging (MRI) can be used to accurately and non-invasively diagnose Alzheimer’s disease. Effective feature extraction and segmentation techniques are necessary for the accurate diagnosis of MRI images. Utilizing MRI data of the brain’s white matter, grey matter, and cerebrospinal fluid, feature selection is carried out. Random forest trees are used in standard machine learning methods like regression and classification. The results of the utilized method were next contrasted with those of other machine learning techniques. As a result, RF model-based interpolation analysis surpasses the RF non-imputation method with greater accuracy, specificity, sensitivity, f-measure, and ROC.
{"title":"Utilizing the Random Forest Algorithm to Enhance Alzheimer’s disease Diagnosis","authors":"Chamandeep Kaur, Tuhina Panda, Subhasis Panda, Abdul Rahman Mohammed Al Ansari, M. Nivetha, B. Kiran Bala","doi":"10.1109/ICAIS56108.2023.10073852","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073852","url":null,"abstract":"Machine learning is widely used in many aspects of healthcare. The development of medical technology has made it possible to gather better data for early disease symptom diagnosis. This study makes an effort to categorize Alzheimer’s disorder. Alzheimer’s disease is a fatal disorder that may result in memory loss and mental impairment. To prepare for medical attention, this needs early disease diagnosis. Magnetic resonance imaging (MRI) can be used to accurately and non-invasively diagnose Alzheimer’s disease. Effective feature extraction and segmentation techniques are necessary for the accurate diagnosis of MRI images. Utilizing MRI data of the brain’s white matter, grey matter, and cerebrospinal fluid, feature selection is carried out. Random forest trees are used in standard machine learning methods like regression and classification. The results of the utilized method were next contrasted with those of other machine learning techniques. As a result, RF model-based interpolation analysis surpasses the RF non-imputation method with greater accuracy, specificity, sensitivity, f-measure, and ROC.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"368 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131527287","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073891
Bondalkunta Vishnu Vikas, Nimmagadda Skb Karthikeya, Gokavarapu Sai Chandu, G. Raja, N. Sai
The main motive of our research is to interpret the enhancement of the way to show the data accurately. To get acquainted with the effort that is put in during the initial stages of implementing data science applications such as data -visualization tools in analyzing the cyber data logs as cyber threats and hacking are being improved by leaps and bounds. In this, to pinpoint the usages of data about data breaches around the globe is also one of our motives. To find the usage of forensic tools after utilizing data visualization tools to the fullest extent. This paper also focuses on the aspects where the enhancement is required in the usage of data visualization. Also, to think of the next steps that are required accordingly. In recent times, as a part of awareness to the present society, developers need to let the threats that a cyber-criminal or an attacker possess be known to every network user for a better understanding of the unreadable language of the cyber logs data. Visualization tools are used to process the analyzing tasks and interpret them.
{"title":"Study of Enhancing Usage of Data Visualization in Cyber Security- Quick, Efficient, and Complete","authors":"Bondalkunta Vishnu Vikas, Nimmagadda Skb Karthikeya, Gokavarapu Sai Chandu, G. Raja, N. Sai","doi":"10.1109/ICAIS56108.2023.10073891","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073891","url":null,"abstract":"The main motive of our research is to interpret the enhancement of the way to show the data accurately. To get acquainted with the effort that is put in during the initial stages of implementing data science applications such as data -visualization tools in analyzing the cyber data logs as cyber threats and hacking are being improved by leaps and bounds. In this, to pinpoint the usages of data about data breaches around the globe is also one of our motives. To find the usage of forensic tools after utilizing data visualization tools to the fullest extent. This paper also focuses on the aspects where the enhancement is required in the usage of data visualization. Also, to think of the next steps that are required accordingly. In recent times, as a part of awareness to the present society, developers need to let the threats that a cyber-criminal or an attacker possess be known to every network user for a better understanding of the unreadable language of the cyber logs data. Visualization tools are used to process the analyzing tasks and interpret them.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131607522","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073917
Arulmurugan Azhaganantham, Kanimozhi M, G. S, Jayasuriya S
The integrity of Integrated Circuits (ICs) has become a critical issue as a result of information security needs. Increased physical security is one of the most critical strategies for increasing the dependability of these circuits. Both computational and physical securities are required for these types of devices. The Physical Unclonable Function (PUF) contributes to the physical security of ICs in order to resist piracy and illegal access. The PUF generates random numbers that are unique to a particular IC. Pseudo Random Number Generators (PRNGs), on the other hand, are deterministic periodic finite state machines whose goal is to simulate the unpredictable behavior of a truly random number source over a finite period of time. In this paper, Chaos based Ring Oscillator-PUF (RO-PUF) using Tent map and Bernoulli Shift map are proposed to increase the randomness and uniqueness of the RNGs. Chaotic signs which are generated from the Tent map and Bernoulli Shift map have given as challenge to the PUF. Responses from the PUF have passed around 9 NIST tests with having p-value greater than 0.01 which satisfies the expected random behaviour.
{"title":"FPGA Implementation of RO-PUF using Chaotic Maps","authors":"Arulmurugan Azhaganantham, Kanimozhi M, G. S, Jayasuriya S","doi":"10.1109/ICAIS56108.2023.10073917","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073917","url":null,"abstract":"The integrity of Integrated Circuits (ICs) has become a critical issue as a result of information security needs. Increased physical security is one of the most critical strategies for increasing the dependability of these circuits. Both computational and physical securities are required for these types of devices. The Physical Unclonable Function (PUF) contributes to the physical security of ICs in order to resist piracy and illegal access. The PUF generates random numbers that are unique to a particular IC. Pseudo Random Number Generators (PRNGs), on the other hand, are deterministic periodic finite state machines whose goal is to simulate the unpredictable behavior of a truly random number source over a finite period of time. In this paper, Chaos based Ring Oscillator-PUF (RO-PUF) using Tent map and Bernoulli Shift map are proposed to increase the randomness and uniqueness of the RNGs. Chaotic signs which are generated from the Tent map and Bernoulli Shift map have given as challenge to the PUF. Responses from the PUF have passed around 9 NIST tests with having p-value greater than 0.01 which satisfies the expected random behaviour.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133738145","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}
Parkinson’s disease is one type of neurological disorders that affects the systema nervosum and causes unintended or uncontrollable movement in the body parts. More than 6 million people all over the world were affected by PD disease. It is difficult to identify the disease at its early stages. Signs of the disease may be can vary from person to person. Symptoms usually begin with a tremor in one hand and gradually start affecting the whole body. At present, there is no clinical equipment or process to recognize this disease at the beginning stage of Parkinson’s disease. Doctors usually diagnose the person by taking a previous medical history and MRI images of the person’s brain and also by observing the symptoms of the person manually which takes more time and cannot detect the disease at its early stages. This disease can be detected at early stages using a machine learning approach with high accuracy. Voice and spiral drawing dataset are collected from normal and PD-affected people and is given as input. 60% of the total dataset is used to train and build the model and the resting 40% dataset is used to test the model. By applying Linear regression and support vector machine and KNN algorithms on voice data sets, this system measures the deflections in the voice of a person. Accuracy with different algorithms is measured. Random forest and CNN algorithms are applied to the spiral data set. Random forest converts spiral drawings into pixels which are very helpful for classification. At the time of testing, the pixels of the current drawing are compared with the previously trained models to detect the disease. By combining the results of the voice dataset and spiral drawings dataset, the machine will detect the disease with high accuracy. The data of a person can be entered into the dataset to detect the disease.
{"title":"An Effective Machine Learning Techniques to Detect Parkinson's Disease","authors":"Narisetty Srinivasarao, Daram Anusha, Uravakonda Mayuri, Surisetti Eswar","doi":"10.1109/ICAIS56108.2023.10073685","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073685","url":null,"abstract":"Parkinson’s disease is one type of neurological disorders that affects the systema nervosum and causes unintended or uncontrollable movement in the body parts. More than 6 million people all over the world were affected by PD disease. It is difficult to identify the disease at its early stages. Signs of the disease may be can vary from person to person. Symptoms usually begin with a tremor in one hand and gradually start affecting the whole body. At present, there is no clinical equipment or process to recognize this disease at the beginning stage of Parkinson’s disease. Doctors usually diagnose the person by taking a previous medical history and MRI images of the person’s brain and also by observing the symptoms of the person manually which takes more time and cannot detect the disease at its early stages. This disease can be detected at early stages using a machine learning approach with high accuracy. Voice and spiral drawing dataset are collected from normal and PD-affected people and is given as input. 60% of the total dataset is used to train and build the model and the resting 40% dataset is used to test the model. By applying Linear regression and support vector machine and KNN algorithms on voice data sets, this system measures the deflections in the voice of a person. Accuracy with different algorithms is measured. Random forest and CNN algorithms are applied to the spiral data set. Random forest converts spiral drawings into pixels which are very helpful for classification. At the time of testing, the pixels of the current drawing are compared with the previously trained models to detect the disease. By combining the results of the voice dataset and spiral drawings dataset, the machine will detect the disease with high accuracy. The data of a person can be entered into the dataset to detect the disease.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115324677","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073924
P. S, Humaira Nishat, D. B, R. P, Pon Bharathi A
To cater the needs of network scalability and improved performance, 5G networks are set to achieve accurate localization in Indoor/Outdoor environment. This capability can be imparted in the network by training it to behave like a Real Dynamic Network (RDN). The proposed Accurate localization algorithm enable network nodes with self learning capability based on local observations. The decision making of the network is clearly autonomous and due to its self-learning capability, it behaves like a Heterogeneous network. With Ultra-Wide Band communication, the following measurements include Time of Arrival (TOA), Channel State Information (CSI) and Time Difference of Arrival (TDOA) are calculated for the network to justify the accuracy of the proposed algorithm. The Q learning model enhances the decision-making capability of nodes and base stations, which in turn enhance the localization of the proposed network. Simulation results prove that the Q learning model outperforms conventional approaches in terms of matching the performance requirements of 5G networks.
{"title":"A Machine Learning based Accurate Localization Technique for 5G Networks","authors":"P. S, Humaira Nishat, D. B, R. P, Pon Bharathi A","doi":"10.1109/ICAIS56108.2023.10073924","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073924","url":null,"abstract":"To cater the needs of network scalability and improved performance, 5G networks are set to achieve accurate localization in Indoor/Outdoor environment. This capability can be imparted in the network by training it to behave like a Real Dynamic Network (RDN). The proposed Accurate localization algorithm enable network nodes with self learning capability based on local observations. The decision making of the network is clearly autonomous and due to its self-learning capability, it behaves like a Heterogeneous network. With Ultra-Wide Band communication, the following measurements include Time of Arrival (TOA), Channel State Information (CSI) and Time Difference of Arrival (TDOA) are calculated for the network to justify the accuracy of the proposed algorithm. The Q learning model enhances the decision-making capability of nodes and base stations, which in turn enhance the localization of the proposed network. Simulation results prove that the Q learning model outperforms conventional approaches in terms of matching the performance requirements of 5G networks.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115538671","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073775
Kiran M K, Kusum Meda Ravi, U. V
The aim of this research is to analyze and detect the most commonly found facial skin conditions like acne vulgaris and dark circles. In the skin analysis algorithm, the occurrences of facial acne and dark circles are detected by using existing Computer Vision algorithms such as Otsu’s thresholding algorithm and Deep Learning (DL) techniques. These techniques are further modified to suit the prepared dataset and achieve greater value of evaluation metrics. This article proposes two techniques for the detection of dark circles, which are the difference in Skin Tone Pixel Values and the Thresholding Technique and compare their performance. In the Thresholding Technique, the IoU obtained was 0.737, which provided better visualization of the affected region. Further, acne detection was carried out using two deep learning backbones viz, Inception ResNet 50 and MobileNet. The accuracy obtained for both the methods was 99%.
{"title":"Facial Skin Analysis for Detection of Dark Circles and Acne","authors":"Kiran M K, Kusum Meda Ravi, U. V","doi":"10.1109/ICAIS56108.2023.10073775","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073775","url":null,"abstract":"The aim of this research is to analyze and detect the most commonly found facial skin conditions like acne vulgaris and dark circles. In the skin analysis algorithm, the occurrences of facial acne and dark circles are detected by using existing Computer Vision algorithms such as Otsu’s thresholding algorithm and Deep Learning (DL) techniques. These techniques are further modified to suit the prepared dataset and achieve greater value of evaluation metrics. This article proposes two techniques for the detection of dark circles, which are the difference in Skin Tone Pixel Values and the Thresholding Technique and compare their performance. In the Thresholding Technique, the IoU obtained was 0.737, which provided better visualization of the affected region. Further, acne detection was carried out using two deep learning backbones viz, Inception ResNet 50 and MobileNet. The accuracy obtained for both the methods was 99%.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114380469","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073877
S. K, Jayaprakash S, H. M, R. R.
This article presents the hybrid Renewable Energy Sources (RES) like wind and Fuel Cell (FC) stack used for more efficiency and utilized the current fed inverter. The proposed system has two sources: a current-fed inverter (CFI) and a Proportional Integral (PI) controller controlling the switch. The main objective of the suggested inverter is to provide high voltage gain by two renewable energy sources and produce high voltage for AC loads. Two essential characteristics can achieve this CFI: switching boost inverter and impedance source. Further, the harmonics of the proposed system can be controlled by an LC filter employed nearer to the AC loads. The proposed method is validated by using MATLAB/Simulink software and analyzed through the Simulink waveforms. This THD indicates that the system is executing correctly, and IEEE standards limit THD to 5%. The method with enhanced performance analysis within the range is designed.
{"title":"Hybrid Energy Sources using Current Fed Inverter for High Gain in Single Phase to AC Loads","authors":"S. K, Jayaprakash S, H. M, R. R.","doi":"10.1109/ICAIS56108.2023.10073877","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073877","url":null,"abstract":"This article presents the hybrid Renewable Energy Sources (RES) like wind and Fuel Cell (FC) stack used for more efficiency and utilized the current fed inverter. The proposed system has two sources: a current-fed inverter (CFI) and a Proportional Integral (PI) controller controlling the switch. The main objective of the suggested inverter is to provide high voltage gain by two renewable energy sources and produce high voltage for AC loads. Two essential characteristics can achieve this CFI: switching boost inverter and impedance source. Further, the harmonics of the proposed system can be controlled by an LC filter employed nearer to the AC loads. The proposed method is validated by using MATLAB/Simulink software and analyzed through the Simulink waveforms. This THD indicates that the system is executing correctly, and IEEE standards limit THD to 5%. The method with enhanced performance analysis within the range is designed.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115076032","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073674
P. Sivakumar, R. Rajalakshmi, A. T., R. Nandakishore Reddy, G. Mounika, K. S. Kumar
The detection of overflow of septic tank is being carried out manually only after finding the leakage from the outlet because of its enclosed underground structure. However, direct human handling is dangerous due to the formation of poisonous gases from the decomposed storage of human wastes which causes unpleasantness to human, and communicable diseases such as cholera that are challenging for public health. Here, in septic tanks, the contaminated water that has low density is discharged from the outlet whereas the colloidal or semi-solid waste is stored. Hence the detection of exact leakage other than the contaminated water from the septic tank is difficult. To resolve this problem, a density sensing system that can sense the density of the colloidal fluid and a sensor that can detect the gases especially methane is placed at the appropriate place on the septic tank with a battery-operated sensing system that needs low maintenance. This system can be applied to every household that has a septic tank for earlier detection of overflow of sewage.
{"title":"A Novel Sensing System to Detect the Overflow of Septic Tanks","authors":"P. Sivakumar, R. Rajalakshmi, A. T., R. Nandakishore Reddy, G. Mounika, K. S. Kumar","doi":"10.1109/ICAIS56108.2023.10073674","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073674","url":null,"abstract":"The detection of overflow of septic tank is being carried out manually only after finding the leakage from the outlet because of its enclosed underground structure. However, direct human handling is dangerous due to the formation of poisonous gases from the decomposed storage of human wastes which causes unpleasantness to human, and communicable diseases such as cholera that are challenging for public health. Here, in septic tanks, the contaminated water that has low density is discharged from the outlet whereas the colloidal or semi-solid waste is stored. Hence the detection of exact leakage other than the contaminated water from the septic tank is difficult. To resolve this problem, a density sensing system that can sense the density of the colloidal fluid and a sensor that can detect the gases especially methane is placed at the appropriate place on the septic tank with a battery-operated sensing system that needs low maintenance. This system can be applied to every household that has a septic tank for earlier detection of overflow of sewage.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122041671","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073719
S. Kanumalli, L. K, Rajeswari A, Samyuktha P, Tejaswi M
As cloud technologies are used more frequently, network intrusion detection systems are becoming increasingly well-liked. Due to ever-increasing network traffic and the regular emergence of new types of assaults, Network Intrusion Detection (NIDS) came into existence as a key aspect of network security and must be extremely effective. These kind of IDS systems employ either an anomaly detection system based on machine learning or a system for matching patterns. The False Positive Rate for pattern matching approaches is high, but AI/ML-based systems determine the possibility of an attack by identifying a metric or characteristic or a connection between a number of metrics or characteristics. The most popular models include KNN, SVM, and others, they only work on a small range of traits, are not very accurate, and have a high False Positive Rate. This study created a deep learning system to learn the temporal and spatial data properties using the advantages of CNN and Bidirectional LSTM. The system present in this paper is trained and analyzed using the openly available dataset NSL-KDD. The proposed model has a high rate of detection and a low incidence of false positives. A lot of cutting-edge Network Intrusion Detection systems that use Machine Learning/Deep Learning models perform better than the suggested model.
{"title":"A Scalable Network Intrusion Detection System using Bi-LSTM and CNN","authors":"S. Kanumalli, L. K, Rajeswari A, Samyuktha P, Tejaswi M","doi":"10.1109/ICAIS56108.2023.10073719","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073719","url":null,"abstract":"As cloud technologies are used more frequently, network intrusion detection systems are becoming increasingly well-liked. Due to ever-increasing network traffic and the regular emergence of new types of assaults, Network Intrusion Detection (NIDS) came into existence as a key aspect of network security and must be extremely effective. These kind of IDS systems employ either an anomaly detection system based on machine learning or a system for matching patterns. The False Positive Rate for pattern matching approaches is high, but AI/ML-based systems determine the possibility of an attack by identifying a metric or characteristic or a connection between a number of metrics or characteristics. The most popular models include KNN, SVM, and others, they only work on a small range of traits, are not very accurate, and have a high False Positive Rate. This study created a deep learning system to learn the temporal and spatial data properties using the advantages of CNN and Bidirectional LSTM. The system present in this paper is trained and analyzed using the openly available dataset NSL-KDD. The proposed model has a high rate of detection and a low incidence of false positives. A lot of cutting-edge Network Intrusion Detection systems that use Machine Learning/Deep Learning models perform better than the suggested model.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116854175","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 : 2023-02-02DOI: 10.1109/ICAIS56108.2023.10073678
Zhaoheng Ai, Hao Wu
The multi-level spatial structure of chromosomes allows remote regulatory elements in the linear coordinate space to closely regulate the expression level of the target genes in the three-dimensional structural space, so, the efficient analysis will be essential. Especially, this paper focuses on the Hi-C data resolution improvement method based on ensemble learning. Hi-C data standardization is used to remove the systematic bias between samples introduced by the various unavoidable nonrandom factors, hence, the accuracy is essential. Therefore, this study utilizes the stacking integration model to achieve the ensemble task, the designed model can avoid the problems of low prediction accuracy and the poor model robustness. Similarly, the multi-objective regression evolved based on the idea of multi-label classification. After testing the designed model on the public data sets, the accuracy can reach more than 99%. Compared with the traditional tools, our designed algorithm reaches better results.
{"title":"Hi-C Data Resolution Improvement Method based on Ensemble Learning","authors":"Zhaoheng Ai, Hao Wu","doi":"10.1109/ICAIS56108.2023.10073678","DOIUrl":"https://doi.org/10.1109/ICAIS56108.2023.10073678","url":null,"abstract":"The multi-level spatial structure of chromosomes allows remote regulatory elements in the linear coordinate space to closely regulate the expression level of the target genes in the three-dimensional structural space, so, the efficient analysis will be essential. Especially, this paper focuses on the Hi-C data resolution improvement method based on ensemble learning. Hi-C data standardization is used to remove the systematic bias between samples introduced by the various unavoidable nonrandom factors, hence, the accuracy is essential. Therefore, this study utilizes the stacking integration model to achieve the ensemble task, the designed model can avoid the problems of low prediction accuracy and the poor model robustness. Similarly, the multi-objective regression evolved based on the idea of multi-label classification. After testing the designed model on the public data sets, the accuracy can reach more than 99%. Compared with the traditional tools, our designed algorithm reaches better results.","PeriodicalId":164345,"journal":{"name":"2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117121624","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：