Pub Date : 2023-07-06DOI: 10.1109/ICESC57686.2023.10192937
Neetu Mittal, Akash Bhanja
Soil is the foremost and elementary resource to improve efficiency in agricultural. Many advanced Computing Techniques are arisen and are get executed in different domains of agriculture. The main intent of the work is to develop an application that associates crop names and to expose the basic capabilities of the system. The Aim is to build a machine learning model that recommends the most suitable crop for a given region based on a variety of factors such as soil type, climate, precipitation, and available resources. The model will be trained using NLP techniques to analyze and extract useful information from text data on various crops, including their characteristics, growth conditions, and yield potential. A machine learning model trained using the extracted features and may be capable of predicting the most suitable crop for a given region based on the input data. The proposed model is used as a web service to facilitate faster development.
{"title":"Implementation and Identification of Crop based on Soil Texture using AI","authors":"Neetu Mittal, Akash Bhanja","doi":"10.1109/ICESC57686.2023.10192937","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10192937","url":null,"abstract":"Soil is the foremost and elementary resource to improve efficiency in agricultural. Many advanced Computing Techniques are arisen and are get executed in different domains of agriculture. The main intent of the work is to develop an application that associates crop names and to expose the basic capabilities of the system. The Aim is to build a machine learning model that recommends the most suitable crop for a given region based on a variety of factors such as soil type, climate, precipitation, and available resources. The model will be trained using NLP techniques to analyze and extract useful information from text data on various crops, including their characteristics, growth conditions, and yield potential. A machine learning model trained using the extracted features and may be capable of predicting the most suitable crop for a given region based on the input data. The proposed model is used as a web service to facilitate faster development.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115281084","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193515
P. L. Priya, V. Prakash
Anxiety and depression are on the rise, particularly since the COVID-19 epidemic, yet detection rates have not kept pace. There has been a lot of talk about people showing signs of mental health problems on social media sites like Facebook, Twitter etc. The social media anxiety and sadness detected using machine learning algorithms is considered and reviewed in this research. Soon after depression was recognized as a major public health problem around the world, efforts were made to improve its detection. The speed with which technology is developing is changing the way people talk to one another. Standardized scales that rely on patients’ subjective reactions or clinical diagnoses from attending clinicians are typically used to detect depression, despite their limitations. First, the replies patients give on conventional standardized measures may be influenced by factors such as the patient’s current mental state, the nature of the clinician-patient relationship, the patient’s current mood, and the patient’s previous experiences and memory bias. Social media platforms like Twitter, Facebook, Telegram, and Instagram have exploded in popularity as places for people to open up about their innermost thoughts, psyche, and feelings with the proliferation of the Internet. Text is analyzed using psychological analysis to pull out relevant aspects, characteristics, and information from the perspectives of users. Psychological analysts rely on social media for the early identification of depressive symptoms and patterns of behavior. A person’s social network may tell us a lot about the thoughts and actions that precede the start of depression, such as the person’s isolation, the importance they place on themselves, and the hours they spend awake. This research presents a brief review that attempts to synthesize the literature on the use of Machine Learning (ML) techniques on social media text data for the purpose of detecting depressive symptoms and to point the way toward future research in this field.
{"title":"A Broad Survey on Detection of Depression in Societal Platforms using Machine Learning Model for the Public Health Care System","authors":"P. L. Priya, V. Prakash","doi":"10.1109/ICESC57686.2023.10193515","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193515","url":null,"abstract":"Anxiety and depression are on the rise, particularly since the COVID-19 epidemic, yet detection rates have not kept pace. There has been a lot of talk about people showing signs of mental health problems on social media sites like Facebook, Twitter etc. The social media anxiety and sadness detected using machine learning algorithms is considered and reviewed in this research. Soon after depression was recognized as a major public health problem around the world, efforts were made to improve its detection. The speed with which technology is developing is changing the way people talk to one another. Standardized scales that rely on patients’ subjective reactions or clinical diagnoses from attending clinicians are typically used to detect depression, despite their limitations. First, the replies patients give on conventional standardized measures may be influenced by factors such as the patient’s current mental state, the nature of the clinician-patient relationship, the patient’s current mood, and the patient’s previous experiences and memory bias. Social media platforms like Twitter, Facebook, Telegram, and Instagram have exploded in popularity as places for people to open up about their innermost thoughts, psyche, and feelings with the proliferation of the Internet. Text is analyzed using psychological analysis to pull out relevant aspects, characteristics, and information from the perspectives of users. Psychological analysts rely on social media for the early identification of depressive symptoms and patterns of behavior. A person’s social network may tell us a lot about the thoughts and actions that precede the start of depression, such as the person’s isolation, the importance they place on themselves, and the hours they spend awake. This research presents a brief review that attempts to synthesize the literature on the use of Machine Learning (ML) techniques on social media text data for the purpose of detecting depressive symptoms and to point the way toward future research in this field.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120971667","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193056
R. Mahima, M. Maheswari, P. Ramkumar, N. Kaushik, N. M. Karthik, S. Nishanth
Most of all computations carried out by these DSP cores are contributed by the arithmetic units, particularly multipliers. For the creation of energy-effectual digital signal processing cores, a high economical and low power design is also a crucial necessity. The DSP processors in portable devices run multimedia programs and produces image and video outputs for human consumption. Because human vision is limited, an approximate architecture can be employed to achieve excellent energy consumption with minimal performance loss. The theme is to design a reconfigurable ROBA multiplier by using floating numbers as an input. The architectural (circuit and logic levels) and algorithmic of ROBA multiplier can used to approximate values within arithmetic units. As a result, researchers in the subject of approximation computing have focused particularly on developing approximate arithmetic units, ROBA multiplier offers a superior trade-off between power, performance, and computational error. The design is stimulated by Xilinix Vivado software.
{"title":"Reconfigurable Rounding based Approximate Multiplier for Floating Point Numbers","authors":"R. Mahima, M. Maheswari, P. Ramkumar, N. Kaushik, N. M. Karthik, S. Nishanth","doi":"10.1109/ICESC57686.2023.10193056","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193056","url":null,"abstract":"Most of all computations carried out by these DSP cores are contributed by the arithmetic units, particularly multipliers. For the creation of energy-effectual digital signal processing cores, a high economical and low power design is also a crucial necessity. The DSP processors in portable devices run multimedia programs and produces image and video outputs for human consumption. Because human vision is limited, an approximate architecture can be employed to achieve excellent energy consumption with minimal performance loss. The theme is to design a reconfigurable ROBA multiplier by using floating numbers as an input. The architectural (circuit and logic levels) and algorithmic of ROBA multiplier can used to approximate values within arithmetic units. As a result, researchers in the subject of approximation computing have focused particularly on developing approximate arithmetic units, ROBA multiplier offers a superior trade-off between power, performance, and computational error. The design is stimulated by Xilinix Vivado software.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121047230","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193080
Karri Narendra Reddy, Kolapalli Naga, Venkatesh, Dr. T. Prem
In recent years, web applications have become increasingly vulnerable to hacking, with an estimated occurrence of 32,590 attacks every day. However, many web developers and website owners are unprepared to identify and prevent these attacks. Hackers utilize various techniques, including phishing websites to gain unauthorized access or compromise authentic web programmers. This research study examines the web application security and the frequency of attacks on such systems. This study focuses on the most common types of attacks and suggests effective detection methods for preventing them. Recently, the secure coding methodologies and machine learning algorithms are used to detect and block unauthorized access and phishing attacks.In almost all the existing research works, a web application is developed to test several website URLs. The findings suggest that the model is capable of detecting malicious web application attacks. Furthermore, the model compares the performance of several machine learning algorithms for identifying phishing website links and detecting with the best model.
{"title":"Detection of Malicious URL Websites using Machine Learning Models","authors":"Karri Narendra Reddy, Kolapalli Naga, Venkatesh, Dr. T. Prem","doi":"10.1109/ICESC57686.2023.10193080","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193080","url":null,"abstract":"In recent years, web applications have become increasingly vulnerable to hacking, with an estimated occurrence of 32,590 attacks every day. However, many web developers and website owners are unprepared to identify and prevent these attacks. Hackers utilize various techniques, including phishing websites to gain unauthorized access or compromise authentic web programmers. This research study examines the web application security and the frequency of attacks on such systems. This study focuses on the most common types of attacks and suggests effective detection methods for preventing them. Recently, the secure coding methodologies and machine learning algorithms are used to detect and block unauthorized access and phishing attacks.In almost all the existing research works, a web application is developed to test several website URLs. The findings suggest that the model is capable of detecting malicious web application attacks. Furthermore, the model compares the performance of several machine learning algorithms for identifying phishing website links and detecting with the best model.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116638521","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193539
Sujay D. Mainkar
As the entire world is proceeding towards experiencing 5G/6G wireless technologies, the performance requirements imposed on antenna size, effectiveness, frequency of operation, and reconfigurability are increasing day-by-day. This has inspired scientists working on antennas to create several models that adhere to these stringent specifications. Despite of this multiconstrained scenario, the use of fractal geometry in the construction of antennas is one of the unique approaches towards enhancing antenna performance. The proposed work targets at systematic investigation of promising performance demonstrated by miniaturized fractal antennas facilitating multiband operation.
{"title":"Performance Comparison of Triangular KOCH Curve and SIERPINSKI Gasket Fractal Antenna Designs for Wireless Applications","authors":"Sujay D. Mainkar","doi":"10.1109/ICESC57686.2023.10193539","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193539","url":null,"abstract":"As the entire world is proceeding towards experiencing 5G/6G wireless technologies, the performance requirements imposed on antenna size, effectiveness, frequency of operation, and reconfigurability are increasing day-by-day. This has inspired scientists working on antennas to create several models that adhere to these stringent specifications. Despite of this multiconstrained scenario, the use of fractal geometry in the construction of antennas is one of the unique approaches towards enhancing antenna performance. The proposed work targets at systematic investigation of promising performance demonstrated by miniaturized fractal antennas facilitating multiband operation.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123808531","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10192990
M. Jaishree, M. Mohamed Asharaf, T. Naveenkumar, V. Nikil
People are currently involved in numerous accidents while travelling by car. Drunk driving and reckless driving during peak hours are the leading causes of accidents. This project contributes to the prevention of such accidents by developing a system that, using a sensor, prevents an intoxicated driver from driving the vehicle and, as a result, controls the ignition of the vehicle’s engine. Accidents occur frequently near school zones. As a result, controlling the vehicle speed is the most important aspect to deal with. This mechanism regulates the vehicle’s speed in school, college, and hospital zones when the camera detects school and hospital zone signs. The method for gathering and detecting signs is mainly reliant on digital image processing. The image processing algorithm takes the necessary action for the acquired indicators. The traffic signs were captured using image enhancement techniques through the Raspberry Pi camera port. The features of speed signs are investigated using the embedded system small computing platform. At that period of daytime vision, the Haar Cascade approach had been used for form analysis to distinguish traffic symbols. The proposed work uses Raspberry Pi 3 board to implement the existing traffic signaling technique.
{"title":"Smart System for Accident Prevention Using Drunk and Drive Controller","authors":"M. Jaishree, M. Mohamed Asharaf, T. Naveenkumar, V. Nikil","doi":"10.1109/ICESC57686.2023.10192990","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10192990","url":null,"abstract":"People are currently involved in numerous accidents while travelling by car. Drunk driving and reckless driving during peak hours are the leading causes of accidents. This project contributes to the prevention of such accidents by developing a system that, using a sensor, prevents an intoxicated driver from driving the vehicle and, as a result, controls the ignition of the vehicle’s engine. Accidents occur frequently near school zones. As a result, controlling the vehicle speed is the most important aspect to deal with. This mechanism regulates the vehicle’s speed in school, college, and hospital zones when the camera detects school and hospital zone signs. The method for gathering and detecting signs is mainly reliant on digital image processing. The image processing algorithm takes the necessary action for the acquired indicators. The traffic signs were captured using image enhancement techniques through the Raspberry Pi camera port. The features of speed signs are investigated using the embedded system small computing platform. At that period of daytime vision, the Haar Cascade approach had been used for form analysis to distinguish traffic symbols. The proposed work uses Raspberry Pi 3 board to implement the existing traffic signaling technique.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124936981","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193266
Afsha Jabeen, Ch Rajendra prasad
The growing popularity of cloud computing has necessitated the development of more efficient and secure methods of searching and retrieving data from cloud storage. In this paper, we propose an advanced keyword-searching model that ensures data security in cloud computing environments. To ensure data confidentiality and safety, our model employs advanced encryption techniques such as symmetric-key, homomorphic, and attribute-based encryption. Also, this study introduces an optimized indexing technique using a binary search algorithm to reduce search time and improve search efficiency. Furthermore, our model employs a secure multi-party computation approach to enable fast computation between multiple parties while keeping private information private. Using a benchmark dataset, this study demonstrates that the proposed model achieves high accuracy and efficiency while maintaining data security. The proposed model can be used in various applications, such as healthcare, finance, and ecommerce, where sensitive data must be securely stored and retrieved. The proposed model provides an efficient and secure solution for keyword searching in cloud computing environments.
{"title":"An Advanced Keyword Searching Model with Data Security in Cloud Computing","authors":"Afsha Jabeen, Ch Rajendra prasad","doi":"10.1109/ICESC57686.2023.10193266","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193266","url":null,"abstract":"The growing popularity of cloud computing has necessitated the development of more efficient and secure methods of searching and retrieving data from cloud storage. In this paper, we propose an advanced keyword-searching model that ensures data security in cloud computing environments. To ensure data confidentiality and safety, our model employs advanced encryption techniques such as symmetric-key, homomorphic, and attribute-based encryption. Also, this study introduces an optimized indexing technique using a binary search algorithm to reduce search time and improve search efficiency. Furthermore, our model employs a secure multi-party computation approach to enable fast computation between multiple parties while keeping private information private. Using a benchmark dataset, this study demonstrates that the proposed model achieves high accuracy and efficiency while maintaining data security. The proposed model can be used in various applications, such as healthcare, finance, and ecommerce, where sensitive data must be securely stored and retrieved. The proposed model provides an efficient and secure solution for keyword searching in cloud computing environments.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116575565","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193604
Y.Alekya Rani, T. Bhaskar, M. Arshad, B. Allam
Crop harm as a result of animal assaults is one of the foremost threats in decreasing the crop yield. Crop in farms is often broken via local animals like buffalos, cows, goats, wild animals like bears, monkeys, wild pigs, elephants, etc and many other birds like sparrows, crows, pigeons. These may cause serious damage to crops which in turn ends in large losses for the farmers. It is difficult for the field owners to build physical barriers to entire field and monitor it. The existing systems mainly based on observation. Farmers take actions according to the animal that entered. The other ways farmers use to prevent the crop destruction by virtue of animals include constructing barricades, electrical fences and manual surveillance. Farmers also use human puppets in middle of fields to ward off animals or birds. So here this study proposes an AI based Scarecrow that protects the crops from wild animals with the help of scanning using camera, it detects the stray animals or birds and when it detects the stray animals or birds then it produces a sound of animal extermination. This study makes a program with the help of live video detecting object using yolov3, coco names, cv2 modules. It ensures complete safety of crops from animals causing damage to it.
{"title":"AI based Scarecrow Preventing from Crop Vandalization","authors":"Y.Alekya Rani, T. Bhaskar, M. Arshad, B. Allam","doi":"10.1109/ICESC57686.2023.10193604","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193604","url":null,"abstract":"Crop harm as a result of animal assaults is one of the foremost threats in decreasing the crop yield. Crop in farms is often broken via local animals like buffalos, cows, goats, wild animals like bears, monkeys, wild pigs, elephants, etc and many other birds like sparrows, crows, pigeons. These may cause serious damage to crops which in turn ends in large losses for the farmers. It is difficult for the field owners to build physical barriers to entire field and monitor it. The existing systems mainly based on observation. Farmers take actions according to the animal that entered. The other ways farmers use to prevent the crop destruction by virtue of animals include constructing barricades, electrical fences and manual surveillance. Farmers also use human puppets in middle of fields to ward off animals or birds. So here this study proposes an AI based Scarecrow that protects the crops from wild animals with the help of scanning using camera, it detects the stray animals or birds and when it detects the stray animals or birds then it produces a sound of animal extermination. This study makes a program with the help of live video detecting object using yolov3, coco names, cv2 modules. It ensures complete safety of crops from animals causing damage to it.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116601104","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193255
L. Prathyusha, Vadlamudi Jhansi, A. Madhuri, E. Jyothi, Sampreeth Chowdary, S. Sindhura
The system of Cyber Supply Chain (CSC) is characterized by its complexity, consisting of several subsystems, each responsible for a distinct set of responsibilities. Securing the supply chain presents a challenge due to the presence of vulnerabilities and threats throughout the system that has the potential to be taken advantage of at any time, considering that any component of the system is susceptible to such attacks. As a result, supply chain security is difficult to achieve. This has the potential to create a significant interruption to the overall continuity of the company. Therefore, it is of the utmost importance to identify the hazards and make educated guesses about their likely outcomes so that organizations can take the appropriate precautions to ensure the safety of their supply chains. By leveraging a range of factors, such as the expertise and incentives of threat actors, Tactics, Techniques, and Procedures (TT and P), as well as Indicators of Compromise (IoC), the analysis of Cyber Threat Intelligence (CTI) offers valuable information on both identified ansignd unidentified cybersecurity threats. In order to increase the safety of the cyber supply chain, the purpose of this article is to investigate and speculate on potential dangers. The CTI and Machine Learning (ML) approaches have been employed by us in order to study and forecast the risks based on the CTI attributes. This makes it possible to detect the inherent CSC vulnerabilities, which enables suitable control. To enhance the overall security of computer systems, it is imperative to implement specific actions, including the collection of CTI data and the adoption of various machine learning techniques. These techniques encompass Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Cat Boost, and Gradient Boost, which are employed in analyzing the Microsoft Malware Prediction dataset to create predictive analytics. This is done in order to illustrate that the technique can be applied to a variety of situations.As input parameters, the experiment takes into account the assault and the TTP, while as output parameters, it takes into account vulnerabilities and indicators of compromise (IoC). According to the findings of the investigation, the most foreseen dangers in CSC are spyware and ransomware, as well as spear phishing. When it came to forecasting vulnerabilities, the predictive models that were produced using the Random Forest algorithm obtained the best accuracy rate of 91%, while the predictive models that were developed using the LR method earned the highest accuracy rate of 86%. In light of the results, the paper strongly advise putting appropriate controls into place in order to combat these dangers. The paper strongly recommend that the ML predicate model make use of CTI data in order to improve the CSC’s cyber security on the whole.
{"title":"Securing the Cyber Supply Chain: A Risk-based Approach to Threat Assessment and Mitigation","authors":"L. Prathyusha, Vadlamudi Jhansi, A. Madhuri, E. Jyothi, Sampreeth Chowdary, S. Sindhura","doi":"10.1109/ICESC57686.2023.10193255","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193255","url":null,"abstract":"The system of Cyber Supply Chain (CSC) is characterized by its complexity, consisting of several subsystems, each responsible for a distinct set of responsibilities. Securing the supply chain presents a challenge due to the presence of vulnerabilities and threats throughout the system that has the potential to be taken advantage of at any time, considering that any component of the system is susceptible to such attacks. As a result, supply chain security is difficult to achieve. This has the potential to create a significant interruption to the overall continuity of the company. Therefore, it is of the utmost importance to identify the hazards and make educated guesses about their likely outcomes so that organizations can take the appropriate precautions to ensure the safety of their supply chains. By leveraging a range of factors, such as the expertise and incentives of threat actors, Tactics, Techniques, and Procedures (TT and P), as well as Indicators of Compromise (IoC), the analysis of Cyber Threat Intelligence (CTI) offers valuable information on both identified ansignd unidentified cybersecurity threats. In order to increase the safety of the cyber supply chain, the purpose of this article is to investigate and speculate on potential dangers. The CTI and Machine Learning (ML) approaches have been employed by us in order to study and forecast the risks based on the CTI attributes. This makes it possible to detect the inherent CSC vulnerabilities, which enables suitable control. To enhance the overall security of computer systems, it is imperative to implement specific actions, including the collection of CTI data and the adoption of various machine learning techniques. These techniques encompass Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Cat Boost, and Gradient Boost, which are employed in analyzing the Microsoft Malware Prediction dataset to create predictive analytics. This is done in order to illustrate that the technique can be applied to a variety of situations.As input parameters, the experiment takes into account the assault and the TTP, while as output parameters, it takes into account vulnerabilities and indicators of compromise (IoC). According to the findings of the investigation, the most foreseen dangers in CSC are spyware and ransomware, as well as spear phishing. When it came to forecasting vulnerabilities, the predictive models that were produced using the Random Forest algorithm obtained the best accuracy rate of 91%, while the predictive models that were developed using the LR method earned the highest accuracy rate of 86%. In light of the results, the paper strongly advise putting appropriate controls into place in order to combat these dangers. The paper strongly recommend that the ML predicate model make use of CTI data in order to improve the CSC’s cyber security on the whole.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125293284","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 : 2023-07-06DOI: 10.1109/ICESC57686.2023.10193040
Rajeshree Parsingbhai Vasava, Hetal A. Joshiara
The sounds produced by the lungs when breathing might provide important information to physicians. Based on the findings, a deep learning-based approach is recommended for the prediction of breathing-related lung sounds. The Proposed model was trained in lung sounds collected from people suffering from a broad variety of respiratory conditions. The research improves classifying lung sounds, by audio to image spectrogram features is taken and used to train a deep convolutional neural network. The proposed technique accurately predicts many different types of respiratory lung sounds, demonstrating the promise of deep learning in this domain. This research results have important implications for the development of automated diagnostic tools that might help doctors make correct diagnoses of respiratory disorders more quickly and accurately.
{"title":"Different Respiratory Lung Sounds Prediction using Deep Learning","authors":"Rajeshree Parsingbhai Vasava, Hetal A. Joshiara","doi":"10.1109/ICESC57686.2023.10193040","DOIUrl":"https://doi.org/10.1109/ICESC57686.2023.10193040","url":null,"abstract":"The sounds produced by the lungs when breathing might provide important information to physicians. Based on the findings, a deep learning-based approach is recommended for the prediction of breathing-related lung sounds. The Proposed model was trained in lung sounds collected from people suffering from a broad variety of respiratory conditions. The research improves classifying lung sounds, by audio to image spectrogram features is taken and used to train a deep convolutional neural network. The proposed technique accurately predicts many different types of respiratory lung sounds, demonstrating the promise of deep learning in this domain. This research results have important implications for the development of automated diagnostic tools that might help doctors make correct diagnoses of respiratory disorders more quickly and accurately.","PeriodicalId":235381,"journal":{"name":"2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130118758","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：