Search

Privacy-preserving in mobile business supplying location-based services (LBS) has the potential to become a primary concern for clients and service providers. In m-business providing LBS services, a client sends its exact locations to service providers. This data may involve sensitive and private personal information. Therefore, the misuse of location information by service providers creates privacy issues for clients. Moreover, the query must not be linked to the mobile client, even if the location information is exposed willingly by her/him to obtain specific services. Thus, there are location cloaking algorithms that allow the protection of the location privacy of mobile users. Hence, many temporal and spatial approaches to cloaking a specific user's location have been proposed. Different from the existing methods, the current works define location and query privacy separately. Therefore, in this paper, we investigate the issues related to the mobile client privacy. Mainly, we aim to preserve the client location privacy as well as the continuous queries privacy, where mobile clients continuously emit different queries during their travels. It's on this premise that we propose a new clique-based cloaking algorithm named Mobile Clique Cloak (MCC) to preserve the mobile client's privacy in the M-business providing LBS services. Also, to build the cloaking region in our approach, we take into account the similarity of client velocity and direction to obtain a right balance between quality of service QoS and privacy. Furthermore, we generate different realistic dummies instead of dropping the query; thus, all queries will be processed even in the case of k−1 other mobile clients' queries cannot be found. Moreover, our work deals with a series of attacks in the same cloaking process (location attack, tracking attack, query sampling attacks and homogenous attack). We evaluate our approach from three aspects: privacy guaranty, quality of service and performance. Experimental evaluation of our algorithms on a real world map shows that our approach ensures total privacy for clients and protects the privacy of clients during the entire query period whiles allowing clients' choice of privacy requirements. Besides, we compare our algorithm with existing privacy protection algorithms such as V-DCA, D-TC and GCA. According to the evaluation results and a comparison of the algorithms, our algorithm MCC can make a good balance between quality of service, performance and privacy. [ABSTRACT FROM AUTHOR]

Misdiagnosis is a critical issue in healthcare, which can lead to severe consequences for patients, including delayed or inappropriate treatment, unnecessary procedures, psychological distress, financial burden, and legal implications. To mitigate this issue, we propose using deep learning algorithms to improve diagnostic accuracy. However, building accurate deep learning models for medical diagnosis requires substantial amounts of high-quality data, which can be challenging for individual healthcare sectors or organizations to acquire. Therefore, combining data from multiple sources to create a diverse dataset for efficient training is needed. However, sharing medical data between different healthcare sectors can be problematic from a security standpoint due to sensitive information and privacy laws. To address these challenges, we propose using blockchain technology to provide a secure, decentralized, and privacy-respecting way to share locally trained deep learning models instead of the data itself. Our proposed method of model ensembling, which combines the weights of several local deep learning models to build a single global model, that enables accurate diagnosis of complex medical conditions across multiple locations while preserving patient privacy and data security. Our research demonstrates the effectiveness of this approach in accurately diagnosing three diseases (breast cancer, lung cancer, and diabetes) with high accuracy rates, surpassing the accuracy of local models and building a multi-diagnosis application. [ABSTRACT FROM AUTHOR]

User-generated content on social media platforms has reached big data levels. Sentiment analysis of this data provides opportunities to gain valuable insights into any domain. However, analyzing real-world data may confront the challenge of class imbalance, which can adversely affect the generalization ability of models due to majority class overfitting. Therefore, having an efficient model that manages any scenario of imbalanced data is practically needed. In this light, this work proposes different models based on studying the impact of data quality and transfer learning through pre-trained embeddings on boosting minority class detection. The proposed models are tested on imbalanced datasets related to social media and education. The experimental results highlight the effectiveness of Wor2vec, Glove, and Fasttext embeddings with preprocessed data. In contrast, BERT embeddings present better results with no-preprocessed data. Furthermore, in comparison with other methods, the best-performing model resulting from this study shows outperformance with notable improvements. [ABSTRACT FROM AUTHOR]