Pub Date : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9988676
A. Rana, A. Reddy, Anurag Shrivastava, Devvret Verma, Md. Sakil Ansari, D. Singh
Patients of Smart Healthcare Systems have access to their medical records through an online portal. Due to the fact that patients do not want their names made public, maintaining data privacy and security is essential to the success of the organisation. Users are required to submit personal information to an authentication server before they can proceed with the login process. The information includes a login ID as well as a password. It is possible that the patient's adversaries will be able to violate their right to privacy if they are able to keep an eye on the patient or get in touch with them. Therefore, in this body of work, we suggest a strategy to protect the privacy of patients and the confidentiality of their medical information from dangers posed by the Authorization Service and other parties. In the course of this research, we utilised a method known as camel-based rotating panel signature. This was done not merely to protect the patients' privacy but also to protect the network itself from potential threats. The theoretical analysis of the performance of the software revealed numerous layers of security that are able to withstand a broad variety of different kinds of attacks.
{"title":"Secure and Smart Healthcare System using IoT and Deep Learning Models","authors":"A. Rana, A. Reddy, Anurag Shrivastava, Devvret Verma, Md. Sakil Ansari, D. Singh","doi":"10.1109/ICTACS56270.2022.9988676","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9988676","url":null,"abstract":"Patients of Smart Healthcare Systems have access to their medical records through an online portal. Due to the fact that patients do not want their names made public, maintaining data privacy and security is essential to the success of the organisation. Users are required to submit personal information to an authentication server before they can proceed with the login process. The information includes a login ID as well as a password. It is possible that the patient's adversaries will be able to violate their right to privacy if they are able to keep an eye on the patient or get in touch with them. Therefore, in this body of work, we suggest a strategy to protect the privacy of patients and the confidentiality of their medical information from dangers posed by the Authorization Service and other parties. In the course of this research, we utilised a method known as camel-based rotating panel signature. This was done not merely to protect the patients' privacy but also to protect the network itself from potential threats. The theoretical analysis of the performance of the software revealed numerous layers of security that are able to withstand a broad variety of different kinds of attacks.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129300766","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9987850
Samrat Ray, A. M, Anand Srinivasa Rao, Surendra Kumar Shukla, Shubhi Gupta, Poonam Rawat
Today, cosmetics have a big impact on how individuals look. It can be challenging to select the best skincare item. People can select the ideal product for their skin type using the predictive way it offers. Traditional methods cannot compare to the compositional notion. In IT departments for cosmetics and beauty care, complex procedures are streamlined using deep learning algorithms. The client base and product selection of the beauty sector have both grown over time. The importance of selecting the best cosmetics grows as the number of goods and consumers rises. A person's look (skin quality) is greatly influenced by cosmetics, thus consumers must select the ideal cosmetics for them depending on their unique qualities. Finding cosmetics that work for their skin type can be challenging because everyone has a distinct type. The composition will vary depending on whether the skin is dry, oily, or neutral. Because they can examine vast amounts of unstructured data and offer illuminating solutions, Deep learning algorithms are particularly well-suited to tackle this issue.
{"title":"Cosmetics Suggestion System using Deep Learning","authors":"Samrat Ray, A. M, Anand Srinivasa Rao, Surendra Kumar Shukla, Shubhi Gupta, Poonam Rawat","doi":"10.1109/ICTACS56270.2022.9987850","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9987850","url":null,"abstract":"Today, cosmetics have a big impact on how individuals look. It can be challenging to select the best skincare item. People can select the ideal product for their skin type using the predictive way it offers. Traditional methods cannot compare to the compositional notion. In IT departments for cosmetics and beauty care, complex procedures are streamlined using deep learning algorithms. The client base and product selection of the beauty sector have both grown over time. The importance of selecting the best cosmetics grows as the number of goods and consumers rises. A person's look (skin quality) is greatly influenced by cosmetics, thus consumers must select the ideal cosmetics for them depending on their unique qualities. Finding cosmetics that work for their skin type can be challenging because everyone has a distinct type. The composition will vary depending on whether the skin is dry, oily, or neutral. Because they can examine vast amounts of unstructured data and offer illuminating solutions, Deep learning algorithms are particularly well-suited to tackle this issue.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130101786","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9988064
Sarthak Parakh, M. Ashraf, Nandita Tripathi, Kumud Pant, Md. Sakil Ansari, P. Negi
The bell has a lot of pepper. Farming in India is about much more than just providing for one's family. The fact that India is a substantial exporter of food, grains, and other horticulture commodities gives the country's agribusiness sector a lot of importance. At least seventy percent of India's rural population is dependent on agriculture for their means of subsistence. Indian ranchers suffer significant financial losses on a yearly basis as a direct result of the loss of 42 percent of their harvests. Damage caused by pests accounts for 15.7% of total crop loss. Therefore, the early diagnosis of plant diseases is absolutely necessary in order to prevent damage to the plant as a whole. Historically, the health of plants has been determined by examining the changes in the leaf appearance; however, this method is inefficient because the plant is already sick at that stage. It is advised that current approaches, such as picture handling and PC vision calculations, be utilised in order to detect diseases in their earliest stages. This is the case provided that all other aspects stay same. It is vital to conduct disease analysis that is both accurate and thorough in order to ensure that the insecticides and bug sprays used do not impair the quality of the soil and to prevent endangering crop health by applying an excessive amount of these chemicals. It is essential to correctly diagnose plant illness in a timely way in order to avoid unfavorable effects connected to a reduction in crop quality or quantity. In order to classify and divide images for the purpose of locating early signs of illness, the Laplacian channel and the U nsharp covering method were used for image processing. Canny edge finding was also employed in this endeavour. In order to accomplish this goal, a clustering model called “convolution brain organization,” which is based on “deep learning arrangements,” is being utilised.
{"title":"Detection of Bell Pepper Crop Diseases Using Convolution Neural Network","authors":"Sarthak Parakh, M. Ashraf, Nandita Tripathi, Kumud Pant, Md. Sakil Ansari, P. Negi","doi":"10.1109/ICTACS56270.2022.9988064","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9988064","url":null,"abstract":"The bell has a lot of pepper. Farming in India is about much more than just providing for one's family. The fact that India is a substantial exporter of food, grains, and other horticulture commodities gives the country's agribusiness sector a lot of importance. At least seventy percent of India's rural population is dependent on agriculture for their means of subsistence. Indian ranchers suffer significant financial losses on a yearly basis as a direct result of the loss of 42 percent of their harvests. Damage caused by pests accounts for 15.7% of total crop loss. Therefore, the early diagnosis of plant diseases is absolutely necessary in order to prevent damage to the plant as a whole. Historically, the health of plants has been determined by examining the changes in the leaf appearance; however, this method is inefficient because the plant is already sick at that stage. It is advised that current approaches, such as picture handling and PC vision calculations, be utilised in order to detect diseases in their earliest stages. This is the case provided that all other aspects stay same. It is vital to conduct disease analysis that is both accurate and thorough in order to ensure that the insecticides and bug sprays used do not impair the quality of the soil and to prevent endangering crop health by applying an excessive amount of these chemicals. It is essential to correctly diagnose plant illness in a timely way in order to avoid unfavorable effects connected to a reduction in crop quality or quantity. In order to classify and divide images for the purpose of locating early signs of illness, the Laplacian channel and the U nsharp covering method were used for image processing. Canny edge finding was also employed in this endeavour. In order to accomplish this goal, a clustering model called “convolution brain organization,” which is based on “deep learning arrangements,” is being utilised.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126546667","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9987810
Gayas Ahmad, Md. Shahid, Akhilesh Kumar
One of the critical issues in financial management is portfolio selection and optimization. It seeks to determine the optimal resource allocation for a group of assets. Since Harry Markowitz established the traditional Mean- Variance model in 1952 and William Sharpe subsequently refined it, this subject has been researched, and several models have been put forward. The effectiveness of nature-inspired algorithms in solving challenging computational optimization problems has prompted academics to create and use these algorithms for a range of optimization issues. This study proposes an unconstrained portfolio optimization strategy using a cultural algorithm (CA) to maximize the Sharpe ratio. The cultural algorithm is an evolutionary algorithm. It includes both the population and knowledge components (belief space). The experimental evaluation of the suggested strategy is shown by comparative analysis with the genetic algorithm (GA) performance. The proposed technique has produced very competitive results on the standard benchmark dataset, namely, DAX 100, Hang Seng 31, FTSE 100, and S&P 100 employed in our study.
{"title":"Towards Portfolio Selection Strategy Using Cultural Algorithm Based Solution Approach","authors":"Gayas Ahmad, Md. Shahid, Akhilesh Kumar","doi":"10.1109/ICTACS56270.2022.9987810","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9987810","url":null,"abstract":"One of the critical issues in financial management is portfolio selection and optimization. It seeks to determine the optimal resource allocation for a group of assets. Since Harry Markowitz established the traditional Mean- Variance model in 1952 and William Sharpe subsequently refined it, this subject has been researched, and several models have been put forward. The effectiveness of nature-inspired algorithms in solving challenging computational optimization problems has prompted academics to create and use these algorithms for a range of optimization issues. This study proposes an unconstrained portfolio optimization strategy using a cultural algorithm (CA) to maximize the Sharpe ratio. The cultural algorithm is an evolutionary algorithm. It includes both the population and knowledge components (belief space). The experimental evaluation of the suggested strategy is shown by comparative analysis with the genetic algorithm (GA) performance. The proposed technique has produced very competitive results on the standard benchmark dataset, namely, DAX 100, Hang Seng 31, FTSE 100, and S&P 100 employed in our study.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125414416","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9987895
S. G, S. K
Image Segmentation is one of the very important optimistic and emerging fields in all image processing applications. It has a wide range of applications like machine vision, fingerprint recognition, digital forensics, medical imaging, and face recognition and so on. Based on specific application, various image segmentation techniques like thresholding, region growing, watershed, clustering algorithms, fuzzy algorithms etc., are used to segment or partition the input images, labels each pixel in the images, locate the points, edges, boundaries and objects to identify various problems in the medical images. Also the identification of important parameters, detection of fractures and diseases, to decrease the death rate of patients suffering from various health problems is challenging research work in medical images. In this paper, author carryout the analysis for the automatic detection of bone fracture in early stage by taking two input x-ray medical images that are captured at different timings. This process is carried out and registered in 4 stages: In first stage-acquire input images and perform pre-processing by using geometrical transformation and register the input images, in second stage- the registered image is segmented using adaptive k-means clustering method, in third stage- automatic detection of the important features in x-ray image is extracted using image registration feature-based method. Automatic feature extraction is carried out for the observation of bone fracture in initial phase to increase the complexity of geometrical alignments of input images. Finally in the fourth stage, the performance of the results is analyzed with respect to accuracy and error rate.
{"title":"Analysis of Medical Images using Image Registration Feature-based Segmentation Techniques","authors":"S. G, S. K","doi":"10.1109/ICTACS56270.2022.9987895","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9987895","url":null,"abstract":"Image Segmentation is one of the very important optimistic and emerging fields in all image processing applications. It has a wide range of applications like machine vision, fingerprint recognition, digital forensics, medical imaging, and face recognition and so on. Based on specific application, various image segmentation techniques like thresholding, region growing, watershed, clustering algorithms, fuzzy algorithms etc., are used to segment or partition the input images, labels each pixel in the images, locate the points, edges, boundaries and objects to identify various problems in the medical images. Also the identification of important parameters, detection of fractures and diseases, to decrease the death rate of patients suffering from various health problems is challenging research work in medical images. In this paper, author carryout the analysis for the automatic detection of bone fracture in early stage by taking two input x-ray medical images that are captured at different timings. This process is carried out and registered in 4 stages: In first stage-acquire input images and perform pre-processing by using geometrical transformation and register the input images, in second stage- the registered image is segmented using adaptive k-means clustering method, in third stage- automatic detection of the important features in x-ray image is extracted using image registration feature-based method. Automatic feature extraction is carried out for the observation of bone fracture in initial phase to increase the complexity of geometrical alignments of input images. Finally in the fourth stage, the performance of the results is analyzed with respect to accuracy and error rate.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"171 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131991949","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9988050
Mrinal Paliwal, Pankaj Saraswat
Diabetes mellitus is an inherited metabolism disorder described employing higher - blood sugar. This major medical type types one diabetes as well as type two diabetes. Presently, this generation for the younger generation suffering from type-one -diabetes has improved importantly. The type-one diabetes is prolonged whenever it occurs in adolescence also infancy, as well as has a long- incubation- period. These initial symptoms, in the beginning, are not clear, which might lead to failure or delaying treatment as well as the detection in time. Long-term higher- blood sugar may cause the especially eyes, kidneys, heart, blood vessels, and nerves, dysfunction of various tissues, as well as chronic damage. Thus, this initial prediction of diabetes is especially crucial. In the present study, we use managed machine-learning algorithms such as Naive Bayes classifier, Light-GBM also Support- Vector Machine (SVM) to instruct onto the actual data of potential diabetic patients aged sixteen to ninety as well as five-hundred twenty diabetic patients. In the comparative survey of the classification and recognition accuracy, the performance of the support vector machine is the best.
{"title":"Research on Diabetes Prediction Method Based on Machine Learning","authors":"Mrinal Paliwal, Pankaj Saraswat","doi":"10.1109/ICTACS56270.2022.9988050","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9988050","url":null,"abstract":"Diabetes mellitus is an inherited metabolism disorder described employing higher - blood sugar. This major medical type types one diabetes as well as type two diabetes. Presently, this generation for the younger generation suffering from type-one -diabetes has improved importantly. The type-one diabetes is prolonged whenever it occurs in adolescence also infancy, as well as has a long- incubation- period. These initial symptoms, in the beginning, are not clear, which might lead to failure or delaying treatment as well as the detection in time. Long-term higher- blood sugar may cause the especially eyes, kidneys, heart, blood vessels, and nerves, dysfunction of various tissues, as well as chronic damage. Thus, this initial prediction of diabetes is especially crucial. In the present study, we use managed machine-learning algorithms such as Naive Bayes classifier, Light-GBM also Support- Vector Machine (SVM) to instruct onto the actual data of potential diabetic patients aged sixteen to ninety as well as five-hundred twenty diabetic patients. In the comparative survey of the classification and recognition accuracy, the performance of the support vector machine is the best.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132047217","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9988170
Preetkamal Singh, J. Kaur
The battery-powered sensors are equipped with a finite amount of energy in Wireless Sensor Network (WSN). The majority of WSN applications generally concentrate on extending network life by utilizing various strategies. One of the most effective methods for enhancing the functionality of WSN has shown to be cluster-based routing algorithms. The WSN's clustering-based techniques control network operation to make the greatest use of the available energy and extend network lifetime. Due to the constrained energy, processing, and communication range of sensor nodes, cluster-based protocols allow the network to function under these restrictions. Network clustering has been demonstrated as an effective method for data gathering and routing in WSNs over the last two decades. When compared to other technologies, it offers a number of benefits in terms of energy efficiency, scalability, even energy distribution, etc. In this paper, we have performed simulation investigation of recently proposed cluster-based routing algorithms and also proposed Improved Zone-based Stable Election Protocol. The simulation is performed in MATLAB software and performance metrics of network lifetime, first node dead, throughput, etc. are taken into consideration to examine the performance.
{"title":"Simulation Investigation of State-of-Art Cluster-Based Routing Protocols in WSN","authors":"Preetkamal Singh, J. Kaur","doi":"10.1109/ICTACS56270.2022.9988170","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9988170","url":null,"abstract":"The battery-powered sensors are equipped with a finite amount of energy in Wireless Sensor Network (WSN). The majority of WSN applications generally concentrate on extending network life by utilizing various strategies. One of the most effective methods for enhancing the functionality of WSN has shown to be cluster-based routing algorithms. The WSN's clustering-based techniques control network operation to make the greatest use of the available energy and extend network lifetime. Due to the constrained energy, processing, and communication range of sensor nodes, cluster-based protocols allow the network to function under these restrictions. Network clustering has been demonstrated as an effective method for data gathering and routing in WSNs over the last two decades. When compared to other technologies, it offers a number of benefits in terms of energy efficiency, scalability, even energy distribution, etc. In this paper, we have performed simulation investigation of recently proposed cluster-based routing algorithms and also proposed Improved Zone-based Stable Election Protocol. The simulation is performed in MATLAB software and performance metrics of network lifetime, first node dead, throughput, etc. are taken into consideration to examine the performance.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131513143","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9988468
Anurag Shrivastava, Midhun Chakkaravarthy, M. Shah
Machine learning can assist in the difficult work of extracting meaningful information from the seemingly useless data produced by IoT devices (ML). The careful deployment of hybrid technologies has reaped benefits for a wide range of institutions, including businesses, governments, schools, and hospitals. The Internet of Things (IoT) may use machine learning (ML) to identify previously hidden patterns in large volumes of data in order to create accurate forecasts and recommendations. The Internet of Things (IoT) and machine learning (ML) are being applied in the field of medicine in order to automate the process of creating medical records, predicting illness diagnoses, and, most importantly, continuously monitoring patients. On different datasets, different machine learning algorithms achieve differing degrees of success. The numerous predictions may or may not end up having an effect on the eventual result. The degree to which the results differ from one another plays a crucial part in the therapeutic decision-making process. The healthcare industry relies significantly on a variety of ML algorithms in order to successfully manage the data generated by IoT devices. In this post, we are going to talk about how popular machine learning techniques can be used in the field of medicine for categorization and prediction purposes. The objective of this study is to provide evidence that utilizing a more sophisticated ML model for the analysis of IoT health data is beneficial. After a substantial amount of time spent on the matter, we came to the realization that a number of well-known ML prediction algorithms have significant weaknesses. The type of Internet of Things dataset that is being utilized will determine the technique that will be most effective when attempting to anticipate vital health data. The paper demonstrates a number of the ways in which the Internet of Things and machine learning have affected the delivery of healthcare in a variety of settings.
{"title":"Improved IoT for Health Behaviour System Based on Machine Learning Model","authors":"Anurag Shrivastava, Midhun Chakkaravarthy, M. Shah","doi":"10.1109/ICTACS56270.2022.9988468","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9988468","url":null,"abstract":"Machine learning can assist in the difficult work of extracting meaningful information from the seemingly useless data produced by IoT devices (ML). The careful deployment of hybrid technologies has reaped benefits for a wide range of institutions, including businesses, governments, schools, and hospitals. The Internet of Things (IoT) may use machine learning (ML) to identify previously hidden patterns in large volumes of data in order to create accurate forecasts and recommendations. The Internet of Things (IoT) and machine learning (ML) are being applied in the field of medicine in order to automate the process of creating medical records, predicting illness diagnoses, and, most importantly, continuously monitoring patients. On different datasets, different machine learning algorithms achieve differing degrees of success. The numerous predictions may or may not end up having an effect on the eventual result. The degree to which the results differ from one another plays a crucial part in the therapeutic decision-making process. The healthcare industry relies significantly on a variety of ML algorithms in order to successfully manage the data generated by IoT devices. In this post, we are going to talk about how popular machine learning techniques can be used in the field of medicine for categorization and prediction purposes. The objective of this study is to provide evidence that utilizing a more sophisticated ML model for the analysis of IoT health data is beneficial. After a substantial amount of time spent on the matter, we came to the realization that a number of well-known ML prediction algorithms have significant weaknesses. The type of Internet of Things dataset that is being utilized will determine the technique that will be most effective when attempting to anticipate vital health data. The paper demonstrates a number of the ways in which the Internet of Things and machine learning have affected the delivery of healthcare in a variety of settings.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134288280","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 : 2022-10-10DOI: 10.1109/ICTACS56270.2022.9987984
P. Dinesh, G. Uganya
This work aims to compress the color images using Novel DC transform (Discrete Cosine Transform) and compare the efficiency and sensitivity with Discrete Wavelet Transform (DWT). Novel DCT and DWT algorithms were implemented to compress the image without losing quality. Group 1 with 20 samples using DWT and group 2 with 20 pieces using Novel DCT. These two groups can be performed with the help of collecting 40 samples. These algorithms were implemented to evaluate the efficiency and sensitivity of the compressed images. From the simulation result, the proposed algorithm achieves the image compression ratio of 23:1 with 96% efficiency and 98% sensitivity. The DWT algorithm achieves an image compression ratio of 21:1 with 94% of efficiency and 93% of sensitivity. The significance value obtained was 0.02, which is less than 0.05. The novel DCT algorithm has significantly better efficiency and sensitivity than the DWT algorithm.
{"title":"Enhancing the Efficiency and Sensitivity in Discrete Cosine Transform based Image Compression and Comparing with Discrete Wavelet Transform","authors":"P. Dinesh, G. Uganya","doi":"10.1109/ICTACS56270.2022.9987984","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9987984","url":null,"abstract":"This work aims to compress the color images using Novel DC transform (Discrete Cosine Transform) and compare the efficiency and sensitivity with Discrete Wavelet Transform (DWT). Novel DCT and DWT algorithms were implemented to compress the image without losing quality. Group 1 with 20 samples using DWT and group 2 with 20 pieces using Novel DCT. These two groups can be performed with the help of collecting 40 samples. These algorithms were implemented to evaluate the efficiency and sensitivity of the compressed images. From the simulation result, the proposed algorithm achieves the image compression ratio of 23:1 with 96% efficiency and 98% sensitivity. The DWT algorithm achieves an image compression ratio of 21:1 with 94% of efficiency and 93% of sensitivity. The significance value obtained was 0.02, which is less than 0.05. The novel DCT algorithm has significantly better efficiency and sensitivity than the DWT algorithm.","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133351108","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}
Machine learning is a crucial technology that may assist individuals in various fields (agriculture, healthcare, household, transportation, etc.) and stages of life. Machine learning improves performance precision (prediction). It utilises numerous data formats (picture, video, audio, and text) for varied applications and purposes. Our effort has centred on the early detection of cactus diseases to prevent the quantitative and qualitative decline of crop yield. To do this, we have utilised photos of diseased and healthy cacti. Using the imadjust, guided filter, and K-means clustering approaches, the images were improved, noises were removed, and the images were segmented to generate a better model. After executing each technique and evaluating their performance, these picture preparation techniques were picked from a large pool of options. As part of the model creation process, feature extraction approaches (Color histogram, Bag of features, and GLCM) were used to extract colour, bag of features, and texture features, respectively. After testing the model with these features, a bag of features was determined to be the best for generating a better model, hence they were chosen as the model's features. Our proposed machine learning model will be developed utilising a bag of features and linear SVM. We will use VGG16 to clear and enhanced the image quality. Other machine learning techniques will tried to train and evaluate the model for disease detection, however linear SVM will demonstrate the highest performance (97.2%) as we analyze and predict it from the previous work (average).
{"title":"Disease Detection in Cactus (Beles) via the Use of Machine Learning: A Proposed Technique","authors":"Sandeep Kaur, Manik Rakhra, Dalwinder Singh, Ashutosh Kumar Singh, S. Aggarwal","doi":"10.1109/ICTACS56270.2022.9988580","DOIUrl":"https://doi.org/10.1109/ICTACS56270.2022.9988580","url":null,"abstract":"Machine learning is a crucial technology that may assist individuals in various fields (agriculture, healthcare, household, transportation, etc.) and stages of life. Machine learning improves performance precision (prediction). It utilises numerous data formats (picture, video, audio, and text) for varied applications and purposes. Our effort has centred on the early detection of cactus diseases to prevent the quantitative and qualitative decline of crop yield. To do this, we have utilised photos of diseased and healthy cacti. Using the imadjust, guided filter, and K-means clustering approaches, the images were improved, noises were removed, and the images were segmented to generate a better model. After executing each technique and evaluating their performance, these picture preparation techniques were picked from a large pool of options. As part of the model creation process, feature extraction approaches (Color histogram, Bag of features, and GLCM) were used to extract colour, bag of features, and texture features, respectively. After testing the model with these features, a bag of features was determined to be the best for generating a better model, hence they were chosen as the model's features. Our proposed machine learning model will be developed utilising a bag of features and linear SVM. We will use VGG16 to clear and enhanced the image quality. Other machine learning techniques will tried to train and evaluate the model for disease detection, however linear SVM will demonstrate the highest performance (97.2%) as we analyze and predict it from the previous work (average).","PeriodicalId":385163,"journal":{"name":"2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115323815","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：