No abstract

Disease detection is a critical issue in the field of medical diagnostics. Failure to identify heart disease (HD) at an early stage can lead to mortality. The lack of access to expert physicians in remote areas further exacerbates the problem. Big data analytics (BDA) is an emerging area that can help extract valuable information from vast amounts of data and improve medical diagnosis while reducing costs. Machine learning (ML) algorithms have been effectively employed in many fields, including medical diagnostics. ML methods can help doctors detect and forecast illnesses at an early stage by creating classifier systems. In this article, we propose a unique ML- and BDA-based squirrel search-optimized Gradient Boosted Decision Tree (SS-GBDT) for the detection of heart disease. The effectiveness of the proposed method is demonstrated through various performance indicators. The results show that the proposed method is highly efficient in medical diagnosis, with 95% accuracy rate, 95.8% precision, 96.8% recall and 96.3% F1-measure achieved by the SS-GBDT. The use of BDA and ML can greatly enhance medical diagnosis and this proposed method is a significant step in this direction.

Cloud computing is now a fundamental type of computing due to technological innovation and it is believed to be a benefit for mid-scale enterprises. The use of cloud computing is increasing daily, which improves service quality but also gives rise to security concerns. Finding trustworthy service can be very challenging, take a great deal of time, or produce subpar services. Due to these difficulties, the client needs a service that is dependable, suitable, time-saving, and trustworthy. As a result, from the end user’s perspective, adopting a cloud service’s trustworthiness becomes crucial. Trust is a measure of how well users’ expectations about a service’s capabilities are realized. In this research, a recommendation system for cloud service customers based on random iterative fuzzy computation (RIFTC) is proposed. RIFTC focuses on the assessment of trust using Quality of Service (QoS) characteristics. RIFTC calculates trust using the machine learning approach Support Vector Regression (SVR). RIFTC can helpfully recommend a cloud service to the end user and anticipate the trust values of cloud services.. Precision (97%), latency (51%), throughput (25.99 mbps), mean absolute error (54%), and re-call (97%) rates are used to assess how well this recommendation system performs. RIFTC’s average F-measure rate is calculated by adjusting the number of users from 200 to 300, and it is 93.46% more accurate on average with less time spent than the current methodologies.

Broadcast Communication is crucial in VANET communication, to send and receive safety messages within network. Securing these beacon message is a challenge, since they are very prone to clone and Sybil attacks. Many works have been proposed to address this problem but they failed to address how to detect and protect these messages from clone attacks and also limited to static networks with limited data sizes.  To achieve this a secure authentication and attack detection mechanism can be designed. In this paper we propose a secure broadcast message authentication and attack detection mechanism with Identity – Based Signatures. Experimental results proved that it can be used in both V2V and V2RSU c communications.   Our scheme shown best performance compared to existing schemes in terms of packet delivery ration, detection rate and detection time.

<p class="Abstract">Integrity and data privacy are the main security parameters between the vehicle and roadside unit (RSU) over large VANETs.  The integrity of the vehicle is used to check its identity against the neighboring nodes, whereas data privacy ensures that the data of a vehicle has not been altered during the communication process. VANETs provide vehicles to give information about the security parameters and identity to vehicle to infrastructure communication and vehicle to vehicle communication. Most of the traditional VANETs are vulnerable to data security, integrity and authentication due to change in dynamic topology. Also, Traditional security models require limited data size for data security between the V2V or V2I. In this paper, an integrity verification model and non-linear double encryption model were proposed and implemented on large geographical VANET map. The main objective of the proposed model is to improve the security of the V2V communication in large VANETs. Experimental results proved that the proposed security model has less computation cost for encryption model and higher bit change during integrity verification compared to the existing approaches.</p>