Heart disease is a major global health problem, and successful treatment and prevention depend greatly on early and correct diagnosis. Machine learning methods have showed promise in the medical data analysis and in h...
Heart disease is a major global health problem, and successful treatment and prevention depend greatly on early and correct diagnosis. Machine learning methods have showed promise in the medical data analysis and in helping to categorise diseases. In this article, we investigate the application of ensemble machine learning methods for the categorization of cardiac patient data. Three machine learning algorithms—XGBoost, SVM, and KNN are combined in our ensemble method. The robust gradient boosting method XGBoost is renowned for its capacity to manage intricate data connections. SVM is a flexible classifier that can detect boundaries in non-linear decisions. KNN is a straightforward yet powerful algorithm that uses the closeness of examples to classify data. We want to use the strengths of these algorithms by combining their predictions to make them stronger and improve categorization. The experimental findings show how well the suggested ensemble strategy for classifying cardiac patient data works. The ensemble classifier outperforms the individual classifiers with an accuracy of 88.52%. This proves that integrating the predictions of many algorithms results in a more reliable model and better classification performance. The results of this study provide a contribution to the categorization of medical data and give medical practitioners important information about identifying cardiac disease. The ensemble classifier can help in the prompt and accurate identification of patients who are at risk, allowing for early intervention and the development of effective treatment plans. The promise of ensemble machine learning algorithms in the categorization of cardiac patent data is shown by our research, in conclusion. The ensemble method using XGBoost, SVM, and KNN outperforms individual classifiers, producing a classification model that is more accurate and dependable. In order to improve the model's classification performance and interpretability, next research might conc
At present, some network security defense systems expand their knowledge base by extracting network threat Intelligence (CTI) to understand the common attack techniques and processes of malicious attack groups. Howeve...
At present, some network security defense systems expand their knowledge base by extracting network threat Intelligence (CTI) to understand the common attack techniques and processes of malicious attack groups. However, there are potential risks to this approach. Hackers can spread fake CTI through the Open-Source Intelligence (OSINT) platform to fool defense systems into learning false information. In this article, we focus on how to generate fake CTI text using the GPT-Neo model and show that the generated text is highly confident. By fine-tuning a common language model like GPT-Neo, we can generate text similar to real CTI. At the end of the paper, we propose two disinformation detection methods that can help us to eliminate unreliable content.
Wireless sensor networks (WSNs) play a crucial role in environmental monitoring and data collection. However, ensuring data security in WSNs poses challenges due to the vulnerabilities of wireless communication channe...
Wireless sensor networks (WSNs) play a crucial role in environmental monitoring and data collection. However, ensuring data security in WSNs poses challenges due to the vulnerabilities of wireless communication channels. In this paper, we address this concern by exploring the application of cryptographic techniques to enhance data security in WSNs. Considering the limited sensor power, computing power, and storage resources, we propose a novel approach that evaluates the suitability of symmetric and asymmetric cryptographic algorithms in WSNs. Through performance comparisons based on computation power and storage capacity requirements, we identify key insights for selecting appropriate encryption algorithms in WSNs. Our findings emphasize the importance of considering the specific requirements and constraints of WSN applications, highlighting the efficiency of symmetric key-based encryption algorithms in resource-constrained environments and the stronger security and key distribution mechanisms provided by ECC-based asymmetric encryption algorithms for secure communication among multiple nodes. This research contributes to the existing knowledge by offering an effective solution to enhance data security in WSNs while considering computational and storage limitations
Machine learning has attracted a lot of interest in the last few years as a solution to a variety of difficult challenges in many disciplines. An emerging area is that of embedded devices, where machine learning is de...
详细信息
Machine learning has attracted a lot of interest in the last few years as a solution to a variety of difficult challenges in many disciplines. An emerging area is that of embedded devices, where machine learning is deployed to efficiently carry out tasks like data analysis, prediction, and decision-making in real-time applications. Challenges such as the necessity for fast and effective algorithms and the restricted resources available in embedded systems to cover the computational and storage demands need to be confronted to successfully integrate machine learning models into embedded systems. This work aims to provide an overview of the use of machine learning in embedded systems, including past and current solutions, and to present the challenges that need to be addressed. Future directions for the use of machine learning in embedded systems are also discussed.
Cloud computing imparts huge storage at low cost, because the internet is so widely used around the world, massive amounts of data are stored on local devices and integrated and stored on a common platform for easy ac...
Cloud computing imparts huge storage at low cost, because the internet is so widely used around the world, massive amounts of data are stored on local devices and integrated and stored on a common platform for easy access, sharing, and, high availability. The cloud environment provides a convenient way for normal users and enterprises to migrate their apps, data, and storage to the cloud-based server for storage due to the high availability of its services and the flexibility of computing processes. Securing information is the primary challenge in cloud computing. Securing the data from unauthorized modification and access is one of the key challenges of the cloud environment. In order to secure user data, different security algorithms were adapted. This paper provides a client-level monitoring approach to secure data in a cloud environment. The monitoring approach consists of the user or client system, monitor, and cloud storage. The user uploads the encrypted form of documents onto the cloud storage and the cloud storage stores the encrypted form of user documents, and the monitor periodically monitors or the user directs the monitor to check the integrity of user data.
Spatial data analysis is a technique used to analyze large amounts of spatial data generated by on-demand cab services such as Uber, Lyft, and Grab. This type of data includes information on the pickup and drop-off lo...
Spatial data analysis is a technique used to analyze large amounts of spatial data generated by on-demand cab services such as Uber, Lyft, and Grab. This type of data includes information on the pickup and drop-off locations of riders, the trajectories of drivers, and the time when demand for cabs is highest. By analyzing this data, the on-demand cab services can gain insights on the customer demand, optimize driver allocation, improve pricing strategies, and enhance overall system efficiency. Spark is an open-source framework used for processing large-scale spatial data. It provides a set of APIs for processing and analyzing spatial data in distributed computing environments by using Apache Spark as its computing engine. This research explores the utilization of Spark, an open-source framework tailored for large-scale spatial dataprocessing. Spark offers a comprehensive set of APIs designed for distributed computing environments, leveraging the power of Apache Spark as its underlying computational engine. By using Spark, on on-demand cab services can efficiently analyze large amounts of spatial data generated by their systems, enabling them to make data-driven decisions and improve the efficiency of their services. There by, we did analyze and visualize, handle the spatial data through spark with the help of graphs.
The concept of edge computing is a fresh approach that has garnered notable attention in recent times, primarily driven by the use of the Internet of Thingsand the requirement for instantaneous dataprocessing and exa...
The concept of edge computing is a fresh approach that has garnered notable attention in recent times, primarily driven by the use of the Internet of Thingsand the requirement for instantaneous dataprocessing and examination. Edge computing technology offers various benefits, including diminished latency, enhanced efficiency, and heightened dependability. Nonetheless, it also introduces a range of obstacles, such as the safeguarding of security and the management of dispersed computational assets. Edge computing minimizes latency and cuts down on bandwidth expenditures in the realm of Health Information Technology by relocating a portion of the dataprocessing and analytical tasks from the central server or cloud to the periphery of the network, precisely where data originates or is utilized. This approach ensures that only indispensable or pertinent data is dispatched to the cloud or server, while the remaining data is either managed locally or disregarded. As a result, the volume of data requiring transmission is reduced, leading to bandwidth preservation and heightened swiftness. Furthermore, edge computing facilitates real-time or nearly real-time dataprocessing and analysis, contributing to latency reduction and overall improved responsiveness. Edge gateways function as intermediaries connecting edge devices and cloud servers, aiding in data routing and supplying supplementary processing capabilities whenever required. Cloud servers furnish extra computational potency and storage aptitude, affording enterprises the ability to handle and scrutinize substantial data quantities instantaneously. Edge computing architecture latency reduction accuracy. The main contribution of the study is to analyze the effects of edge computing on latency reduction and real-time dataprocessing.
Quality of placements is an important parameter considered by accreditation bodies while ranking Universities or Institutes of Higher Education. Thanks to the increasing automation of placement grooming related activi...
详细信息
Quality of placements is an important parameter considered by accreditation bodies while ranking Universities or Institutes of Higher Education. Thanks to the increasing automation of placement grooming related activities, universities have started exploring using intelligent computing techniques to anticipate placement status of upcoming batches and identifying factors that play an important role in improving placement quality. In this work, machine learning techniques have been used to predict placement students of engineering students of computer science discipline. Logistic Regression and Decision Tree algorithms gave best prediction performance. Marks in ‘Xth’, ‘XIIth’, ‘Current CGPA’ and ‘Present Attendance’ were among the important factors affecting placement status of students.
Introducing Artificial Intelligence (AI) in the Automotive Industry and developing related technologies will significantly impact the automotive industry. A technological innovation like Autonomous driving entails usi...
详细信息
Introducing Artificial Intelligence (AI) in the Automotive Industry and developing related technologies will significantly impact the automotive industry. A technological innovation like Autonomous driving entails using artificial intelligence (AI), which represents the future of transportation and applications that will influence the concept of driving. New businesses related to mobility will emerge, and the already existing ones will have to adapt to the necessary shifts. Some security and AI algorithms are used in the vehicle security domain. This research aims to give some idea and understanding about how Artificial Intelligence (AI) is important and impacts the automotive industry. While discussing autonomous vehicles, there is a question to ask or focus on – what about the feasibility of autonomous production? Some light has been thrown on the benefits and requirements for automation of production plants, and its future has been discussed.
In the healthcare sector, data mining stands as a crucial tool for analyzing vast patient datasets to unearth significant revelations. This manuscript provides a comprehensive exploration of data mining's contribu...
详细信息
ISBN:
(数字)9798350317008
ISBN:
(纸本)9798350317015
In the healthcare sector, data mining stands as a crucial tool for analyzing vast patient datasets to unearth significant revelations. This manuscript provides a comprehensive exploration of data mining's contributions to healthcare, spanning from pandemic research, treatment efficacy assessment, predictive modeling, insurance fraud detection, medical device optimization, to streamlined hospital management. It delves into various data mining techniques such as clustering, classification, statistical analysis, unsupervised pattern recognition, and web-based data scrutiny, emphasizing their relevance in healthcare contexts. algorithms like the Naïve Bayes Classifier and K-means clustering are underscored for their prevalent use in health-related scenarios. The treatise wraps up by shedding light on the emerging trajectories for healthcare data mining and pinpointing exciting avenues for impending inquiries.
暂无评论