Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00121
A. K. Bapatla, S. Mohanty, E. Kougianos, Deepak Puthal
Because of globalization, many different entities distributed across the locations were able to work together and achieve the availability of services even at remote locations. Supply Chains helped in leveraging such businesses globally with reduced costs and increased efficiency. Pharmaceutical Supply Chain (PSC) is one in which the prescription drugs are moved from the manufacturer to the patient. Providing the right medicine at the right time to the right patient in the right doses coming from the right route is called the five rights of medication. Due to the increased number of participating entities, and interactions between entities and adversaries trying to profit by introducing counterfeit drugs into the supply chain, efficient tracking and tracing mechanism is very much needed in PSC. The current paper proposes an architecture that is integrated with Blockchain, Inter Planetary File System (IPFS) along with QR code technologies to provide a secure QR code mechanism for addressing such tracking and tracing issues in PSC. The proposed model is evaluated for security and efficiency using different metrics.
{"title":"PharmaChain 3.0: Blockchain Integrated Efficient QR Code Mechanism for Pharmaceutical Supply Chain","authors":"A. K. Bapatla, S. Mohanty, E. Kougianos, Deepak Puthal","doi":"10.1109/OCIT56763.2022.00121","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00121","url":null,"abstract":"Because of globalization, many different entities distributed across the locations were able to work together and achieve the availability of services even at remote locations. Supply Chains helped in leveraging such businesses globally with reduced costs and increased efficiency. Pharmaceutical Supply Chain (PSC) is one in which the prescription drugs are moved from the manufacturer to the patient. Providing the right medicine at the right time to the right patient in the right doses coming from the right route is called the five rights of medication. Due to the increased number of participating entities, and interactions between entities and adversaries trying to profit by introducing counterfeit drugs into the supply chain, efficient tracking and tracing mechanism is very much needed in PSC. The current paper proposes an architecture that is integrated with Blockchain, Inter Planetary File System (IPFS) along with QR code technologies to provide a secure QR code mechanism for addressing such tracking and tracing issues in PSC. The proposed model is evaluated for security and efficiency using different metrics.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121396937","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00096
Pratyusa Mukherjee, Rabindra Kumar Barik
Geospatial fog computing system offers various benefits as a platform for geospatial computing services closer to the end users, including very low latency, good mobility, precise position awareness, and widespread distribution. In recent years, it has grown quickly. Fog nodes' security is susceptible to a number of assaults, including denial of service and resource abuse, because to their widespread distribution, complex network environments, and restricted resource availability. This paper proposes a Quantum Key Distribution (QKD)-based geospatial quantum fog computing environment that offers a symmetric secret key negotiation protocol that can preserve information-theoretic security. In QKD, after being negotiated between any two fog nodes, the secret keys can be given to several users in various locations to maintain forward secrecy and long-term protection. The new geospatial quantum fog computing environment proposed in this work is able to successfully withstand a variety of fog computing assaults and enhances information security.
{"title":"Fog-QKD:Towards secure geospatial data sharing mechanism in geospatial fog computing system based on Quantum Key Distribution","authors":"Pratyusa Mukherjee, Rabindra Kumar Barik","doi":"10.1109/OCIT56763.2022.00096","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00096","url":null,"abstract":"Geospatial fog computing system offers various benefits as a platform for geospatial computing services closer to the end users, including very low latency, good mobility, precise position awareness, and widespread distribution. In recent years, it has grown quickly. Fog nodes' security is susceptible to a number of assaults, including denial of service and resource abuse, because to their widespread distribution, complex network environments, and restricted resource availability. This paper proposes a Quantum Key Distribution (QKD)-based geospatial quantum fog computing environment that offers a symmetric secret key negotiation protocol that can preserve information-theoretic security. In QKD, after being negotiated between any two fog nodes, the secret keys can be given to several users in various locations to maintain forward secrecy and long-term protection. The new geospatial quantum fog computing environment proposed in this work is able to successfully withstand a variety of fog computing assaults and enhances information security.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125150163","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00018
S. Patra, Sujoy Datta, M. Roy
Speech-Emotion Recognition, (SER) is the process of attempting to recognize the emotional aspects of speech and the affective states irrespective of the semantic contents of the speech. This is to make capital out of the fact that underlying emotions are often reflected in the voice of a person. While studying speech-emotion recognition, it is a pertinent issue to find the combination of the audio features that we can extract from the speech and see which combination falls into place perfectly with a suitable classification system. But having a well-defined database for speech analysis and research is as much important to SER study. Hence, we have used the RAVDESS dataset. In our study we have used acoustic features that can reflect well-defined and sharp changes in emotional expression; for this we have extracted features like Amplitude Envelope, RMS and more from the time-domain, Spectral Centroid, Spectral bandwidth and more from the frequency-domain and Mel-frequency cepstrum coefficients and more from the time-frequency domain. We have used the MLPClassifier for the classification of emotions. Our results show that a combination of MFCC, mel spectrogram and chroma is able to best explain the speech emotions through the MLPClassifier.
{"title":"Analysis on Speech-Emotion Recognition with Effective Feature Combination","authors":"S. Patra, Sujoy Datta, M. Roy","doi":"10.1109/OCIT56763.2022.00018","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00018","url":null,"abstract":"Speech-Emotion Recognition, (SER) is the process of attempting to recognize the emotional aspects of speech and the affective states irrespective of the semantic contents of the speech. This is to make capital out of the fact that underlying emotions are often reflected in the voice of a person. While studying speech-emotion recognition, it is a pertinent issue to find the combination of the audio features that we can extract from the speech and see which combination falls into place perfectly with a suitable classification system. But having a well-defined database for speech analysis and research is as much important to SER study. Hence, we have used the RAVDESS dataset. In our study we have used acoustic features that can reflect well-defined and sharp changes in emotional expression; for this we have extracted features like Amplitude Envelope, RMS and more from the time-domain, Spectral Centroid, Spectral bandwidth and more from the frequency-domain and Mel-frequency cepstrum coefficients and more from the time-frequency domain. We have used the MLPClassifier for the classification of emotions. Our results show that a combination of MFCC, mel spectrogram and chroma is able to best explain the speech emotions through the MLPClassifier.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128059734","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00065
Pranjali Dwivedi, A. Mishra
Fractal Image compression is the type of data compression applied to the digital image to reduce their cost for storage and transmission. In this paper Fractal image compression algorithm using a discrete wavelet transform form has been projected. The concert of the (DWT) projected algorithm is estimated using compression ratio (CR). The experimental result obtained from the projected algorithm gives an improvement in terms of the CR. The Paper concludes with a comparison with the existing algorithm and shows that the projected algorithm performs quite efficiently.
{"title":"Fractal Image Compression based on Discrete Wavelet Transform","authors":"Pranjali Dwivedi, A. Mishra","doi":"10.1109/OCIT56763.2022.00065","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00065","url":null,"abstract":"Fractal Image compression is the type of data compression applied to the digital image to reduce their cost for storage and transmission. In this paper Fractal image compression algorithm using a discrete wavelet transform form has been projected. The concert of the (DWT) projected algorithm is estimated using compression ratio (CR). The experimental result obtained from the projected algorithm gives an improvement in terms of the CR. The Paper concludes with a comparison with the existing algorithm and shows that the projected algorithm performs quite efficiently.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127251783","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00039
Parthasarathi Pattnayak, Sanghamitra Patnaik
The probabilities to have a look at and have interaction with any given spacecraft are intrinsically restricted as compared to ground-based technology because of more than a few of factors. Crew availability, communication lag times, and power budgets are just a few of these. They also take into account the reachability and bandwidth of their ground connection. Every spacecraft must have some amount of autonomy, but research and previous missions have shown that by incorporating more sophisticated autonomous processes, many missions can be much more effective based on consistency, the production of knowledge, and the amount of work required to operate is a method that is becoming more and more popular for obtaining on-board autonomy. However, the variety of artificial intelligence methods and versions that are now written about in the literature is equally as wide-ranging as their prospective fields of application. This paper provides a thorough analysis of the state-of-the-art methods and algorithms for Fault Detection Isolation and Recovery (FDIR) and anomaly detection, and it provides examples of current ground- and space-based applications.
{"title":"Space and Applications of Artificial Intelligence","authors":"Parthasarathi Pattnayak, Sanghamitra Patnaik","doi":"10.1109/OCIT56763.2022.00039","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00039","url":null,"abstract":"The probabilities to have a look at and have interaction with any given spacecraft are intrinsically restricted as compared to ground-based technology because of more than a few of factors. Crew availability, communication lag times, and power budgets are just a few of these. They also take into account the reachability and bandwidth of their ground connection. Every spacecraft must have some amount of autonomy, but research and previous missions have shown that by incorporating more sophisticated autonomous processes, many missions can be much more effective based on consistency, the production of knowledge, and the amount of work required to operate is a method that is becoming more and more popular for obtaining on-board autonomy. However, the variety of artificial intelligence methods and versions that are now written about in the literature is equally as wide-ranging as their prospective fields of application. This paper provides a thorough analysis of the state-of-the-art methods and algorithms for Fault Detection Isolation and Recovery (FDIR) and anomaly detection, and it provides examples of current ground- and space-based applications.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133760157","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00082
Anusha Vaishnav, Amulya Ratna Swain, M. R. Lenka
Fifth-generation mobile network(5G) is the latest cellular technology after 4G networks. The Use of a 5G network enhances the data rate due to more available bandwidth and advanced technologies. Among several other technologies, Device-to-Device (D2D) communication is one of the advanced technologies used in 5G networks for efficient data transmission. D2D technology represents direct communication between two devices without the assistance of a base station. The clustering algorithm is one of the technologies used mostly in D2D communication to handle dynamic devices. The clustering technique helps to group users with similar interests and reconstruct the network to achieve better performance in terms of throughput, spectral efficiency, power, energy consumption, etc. The Affinity Propagation (AP) clustering algorithm has differentiated itself from the other clustering algorithms by dynamically preparing the clusters and cluster heads. However, the other clustering algorithms require the number of clusters and cluster head information beforehand. Hence, this work focuses on improving the AP clustering algorithm to prepare the clusters and cluster heads in a better way to enhance the efficiency of D2D communication.
{"title":"Improved Affinity Propagation Clustering for D2D Communication in 5G","authors":"Anusha Vaishnav, Amulya Ratna Swain, M. R. Lenka","doi":"10.1109/OCIT56763.2022.00082","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00082","url":null,"abstract":"Fifth-generation mobile network(5G) is the latest cellular technology after 4G networks. The Use of a 5G network enhances the data rate due to more available bandwidth and advanced technologies. Among several other technologies, Device-to-Device (D2D) communication is one of the advanced technologies used in 5G networks for efficient data transmission. D2D technology represents direct communication between two devices without the assistance of a base station. The clustering algorithm is one of the technologies used mostly in D2D communication to handle dynamic devices. The clustering technique helps to group users with similar interests and reconstruct the network to achieve better performance in terms of throughput, spectral efficiency, power, energy consumption, etc. The Affinity Propagation (AP) clustering algorithm has differentiated itself from the other clustering algorithms by dynamically preparing the clusters and cluster heads. However, the other clustering algorithms require the number of clusters and cluster head information beforehand. Hence, this work focuses on improving the AP clustering algorithm to prepare the clusters and cluster heads in a better way to enhance the efficiency of D2D communication.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132753237","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00099
Sudeshna Baliarsingh, Prakash Kumar Panda, M. Mohanty
Ahstract-E- Healthcare in this digital world supports patients as well as physicians that satisfy smart healthcare services. However, data exchange and storage aremajor challenges in this scenario. It needs to compress data for effective communication. In this work, the authors have taken an approach to compress the cardiac signal for effective communication. The data is collected from the Physionet database (Records no. 100 and 202) for experimentation. Also, to verify the proposed method the data from Mendeley Database is considered and tested for both the ECG signals(Record no. 202). Initially, the collected data is preprocessed with the SavitzkyGolay filter to eliminate the noise and to smoothen the signal. In one step the signal is decomposed with Empirical Mode Decomposition (EMD) to find out the useful components. Further, the decomposed signals are compressed with DCT which is coded with the said Huffman coding method. The method proved to be efficient and is explained in the result section along with a comparison The proposed technique is suitable for the application and has been verified for e-healthcare systems.
摘要- e -数字世界中的医疗保健为满足智能医疗保健服务的患者和医生提供支持。然而，数据交换和存储是此场景中的主要挑战。它需要压缩数据以实现有效的通信。在这项工作中，作者采取了一种方法来压缩心脏信号，以实现有效的通信。数据从Physionet数据库(记录号:100和202)进行实验。此外，为了验证所提出的方法，考虑了Mendeley数据库的数据，并对心电信号(记录号:202)。首先，用SavitzkyGolay滤波器对采集到的数据进行预处理，以消除噪声并使信号平滑。第一步用经验模态分解(EMD)对信号进行分解，找出有用的分量;进一步，用DCT对分解后的信号进行压缩，DCT用所述霍夫曼编码方法进行编码。该方法被证明是有效的，并在结果部分进行了解释，并进行了比较。所提出的技术适用于该应用程序，并已在电子医疗保健系统中进行了验证。
{"title":"ECG Compression using Decomposed Transform for E-Healthcare","authors":"Sudeshna Baliarsingh, Prakash Kumar Panda, M. Mohanty","doi":"10.1109/OCIT56763.2022.00099","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00099","url":null,"abstract":"Ahstract-E- Healthcare in this digital world supports patients as well as physicians that satisfy smart healthcare services. However, data exchange and storage aremajor challenges in this scenario. It needs to compress data for effective communication. In this work, the authors have taken an approach to compress the cardiac signal for effective communication. The data is collected from the Physionet database (Records no. 100 and 202) for experimentation. Also, to verify the proposed method the data from Mendeley Database is considered and tested for both the ECG signals(Record no. 202). Initially, the collected data is preprocessed with the SavitzkyGolay filter to eliminate the noise and to smoothen the signal. In one step the signal is decomposed with Empirical Mode Decomposition (EMD) to find out the useful components. Further, the decomposed signals are compressed with DCT which is coded with the said Huffman coding method. The method proved to be efficient and is explained in the result section along with a comparison The proposed technique is suitable for the application and has been verified for e-healthcare systems.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132947897","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00093
Rabindra Kumar Barik, S. Tripathy, Aishwarya Nayak, D. S. Roy
The introduction of cloud computing technologies as well as the growth of geospatial big data have both helped to make smart city initiatives more realistically achievable. Using geospatial Big data, cities have the potential to derive useful insights from the vast amounts of geospatial data that have been collected from a variety of sources. In the quest to realise the potential of smart cities in the future, one emerging area of research is the combination of geospatial-focused big data and cloud computing. This combination has posed a number of exciting new challenges. This article proposed and constructed a Geospatial Big Data Infrastructure model based on cloud computing called GeoTCloud for geospatial big data visualisation in the tourism industry. For smart city development, the proposed model aids in the storage, analysis, and presentation of geospatial big data in the tourism sector. Quantum GIS;Open Source GIS is utilised for geospatial database development, while Quantum GIS’ QGIS Plugin is used for geospatial cloud computing infrastructure. GeoTCloud's various geographic overlay analysis is also discussed.
{"title":"Cloud GIS Model for Geospatial Bigdata Visualization towards Smart City: A case study of Bhubaneswar, Odisha","authors":"Rabindra Kumar Barik, S. Tripathy, Aishwarya Nayak, D. S. Roy","doi":"10.1109/OCIT56763.2022.00093","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00093","url":null,"abstract":"The introduction of cloud computing technologies as well as the growth of geospatial big data have both helped to make smart city initiatives more realistically achievable. Using geospatial Big data, cities have the potential to derive useful insights from the vast amounts of geospatial data that have been collected from a variety of sources. In the quest to realise the potential of smart cities in the future, one emerging area of research is the combination of geospatial-focused big data and cloud computing. This combination has posed a number of exciting new challenges. This article proposed and constructed a Geospatial Big Data Infrastructure model based on cloud computing called GeoTCloud for geospatial big data visualisation in the tourism industry. For smart city development, the proposed model aids in the storage, analysis, and presentation of geospatial big data in the tourism sector. Quantum GIS;Open Source GIS is utilised for geospatial database development, while Quantum GIS’ QGIS Plugin is used for geospatial cloud computing infrastructure. GeoTCloud's various geographic overlay analysis is also discussed.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132271893","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00120
Gajjala Savithri, N. Sai
Both industry and academics have recently paid close attention to the Internet of Things (IoT). The overall functionality of the IoT network depends on a dependable and secure IoT connection and communication. Enabling and establishing reliable communication between the items is one method of achieving strong security in an IoT network. In a network of diverse things like the Internet of Things, trust management is crucial. An current answer to this control issue is standardisation via an IoT gateway. Unfortunately, this calls for additional infrastructure. In this paper, initially trust challenges in IoT applications are identified and explained in details. Then impact of trust issues in IoT applications are explained. Blockchain based approach is taken as to address some of the existing trust challenges in IoT application.
{"title":"Blockchain base Solution for Trust Management Challenges Internet of Things application","authors":"Gajjala Savithri, N. Sai","doi":"10.1109/OCIT56763.2022.00120","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00120","url":null,"abstract":"Both industry and academics have recently paid close attention to the Internet of Things (IoT). The overall functionality of the IoT network depends on a dependable and secure IoT connection and communication. Enabling and establishing reliable communication between the items is one method of achieving strong security in an IoT network. In a network of diverse things like the Internet of Things, trust management is crucial. An current answer to this control issue is standardisation via an IoT gateway. Unfortunately, this calls for additional infrastructure. In this paper, initially trust challenges in IoT applications are identified and explained in details. Then impact of trust issues in IoT applications are explained. Blockchain based approach is taken as to address some of the existing trust challenges in IoT application.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"291 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115341935","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 : 2022-12-01DOI: 10.1109/OCIT56763.2022.00012
Aditi Mohapatra, Ananya Dastidar, Saumendra Kumar Mohapatra, M. Mohanty
ECG plays an important role in cardiac disease diagnosis. Classification of this cardiac signal using machine learning techniques will be a supportive tool for the physicians. Authors in this work have classified the ECG by using three different types of classifiers such as Support vector machine (SVM), Gradient boosting, and extreme gradient boosting (XGBoost). The standard statistical features are considered as input to the classifiers. For improving the learning strategy and performance of the proposed models subjected to accuracy, the learning rates are varied for each node of the tree-based ensemble classifiers. Also, the hyperparameters of the XGBoost model are optimized by applying the Bayesian optimization (BO) technique. The best accuracy in SVM classifier is found as 91.69%. 96.58% accuracy is obtained in the modified gradient boosting model. The optimized XGBoost model is providing 100% accuracy which is better than other.
{"title":"Abnormal ECG Detection using Optimized Boosting Tree Classifier","authors":"Aditi Mohapatra, Ananya Dastidar, Saumendra Kumar Mohapatra, M. Mohanty","doi":"10.1109/OCIT56763.2022.00012","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00012","url":null,"abstract":"ECG plays an important role in cardiac disease diagnosis. Classification of this cardiac signal using machine learning techniques will be a supportive tool for the physicians. Authors in this work have classified the ECG by using three different types of classifiers such as Support vector machine (SVM), Gradient boosting, and extreme gradient boosting (XGBoost). The standard statistical features are considered as input to the classifiers. For improving the learning strategy and performance of the proposed models subjected to accuracy, the learning rates are varied for each node of the tree-based ensemble classifiers. Also, the hyperparameters of the XGBoost model are optimized by applying the Bayesian optimization (BO) technique. The best accuracy in SVM classifier is found as 91.69%. 96.58% accuracy is obtained in the modified gradient boosting model. The optimized XGBoost model is providing 100% accuracy which is better than other.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115315416","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：