Search

Association analysis is critical in data analysis performed to find all co-occurrence relationships ($i.e$ ., frequent itemsets or confident association rules) from the transactional dataset. An association rule can improve the ability of users to discover patterns and develop corresponding strategies. The data analysis process can be summarized as a set of queries, where each query is a real-valued function of the dataset. However, unless restrictions and protections are implemented, accessing the dataset to answer the queries may lead to the disclosure of the private information of individuals. In this paper, we propose an original differentially private association rules mining (DPARM) algorithm, which uses multiple support thresholds to reduce the number of candidate itemsets while reflecting the real nature of the items and uses random truncation and uniform partition to reduce the dimensionality of the dataset. Both of these elaborated approaches can aid in reducing the sensitivity of the queries, and this dramatically reduces the scale of the required noise and improves the utility of the mining results. We significantly stabilize the noise scale by adaptively allocating the privacy levels and bound the overall privacy loss. Through a series of experiments, we prove that our DPARM algorithm outperforms the literature in the accuracy of data mining while satisfying differential privacy. To the best of our knowledge, our work is the first DPARM algorithm to adopt multiple support thresholds while using a set of elaborated approaches to bound the overall privacy loss of the mining process.

Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effect on the global economy and health. COVID-19 cases have been rapidly increasing, with no sign of stopping. As a result, test kits and accurate detection models are in short supply. Early identification of COVID-19 patients will help decrease the infection rate. Thus, developing an automatic algorithm that enables the early detection of COVID-19 is essential. Moreover, patient data are sensitive, and they must be protected to prevent malicious attackers from revealing information through model updates and reconstruction. In this study, we presented a higher privacy-preserving federated learning system for COVID-19 detection without sharing data among data owners. First, we constructed a federated learning system using chest X-ray images and symptom information. The purpose is to develop a decentralized model across multiple hospitals without sharing data. We found that adding the spatial pyramid pooling to a 2D convolutional neural network improves the accuracy of chest X-ray images. Second, we explored that the accuracy of federated learning for COVID-19 identification reduces significantly for non-independent and identically distributed (Non-IID) data. We then proposed a strategy to improve the model’s accuracy on Non-IID data by increasing the total number of clients, parallelism (client-fraction), and computation per client. Finally, for our federated learning model, we applied a differential privacy stochastic gradient descent (DP-SGD) to improve the privacy of patient data. We also proposed a strategy to maintain the robustness of federated learning to ensure the security and accuracy of the model.

Network slicing is a promising technology that network operators can deploy the services by slices with heterogeneous quality of service (QoS) requirements. However, an orchestrator for network operation with efficient slice resource provisioning algorithms is essential. This work stands on Internet service provider (ISP) to design an orchestrator analyzing the critical influencing factors, namely access control, scheduling, and resource migration, to systematically evolve a sustainable network. The scalability and flexibility of resources are jointly considered. The resource management problem is formulated as a mixed-integer programming (MIP) problem. A solution approach based on Lagrangian relaxation (LR) is proposed for the orchestrator to make decisions to satisfy the high QoS applications. It can investigate the resources required for access control within a cost-efficient resource pool and consider allocating or migrating resources efficiently in each network slice. For high system utilization, the proposed mechanisms are modeled in a pay-as-you-go manner. Furthermore, the experiment results show that the proposed strategies perform the near-optimal system revenue to meet the QoS requirement by making decisions.

Determining the price movement of stocks is a challenging problem to solve because of factors such as industry performance, economic variables, investor sentiment, company news, company performance, and social media sentiment. People can predict the price movement of stocks by applying machine learning algorithms on information contained in historical data, stock candlestick-chart data, and social-media data. However, it is hard to predict stock movement based on a single classifier. In this study, we proposed a multichannel collaborative network by incorporating candlestick-chart and social-media data for stock trend predictions. We first extracted the social media sentiment features using the Natural Language Toolkit and sentiment analysis data from Twitter. We then transformed the stock’s historical time series data into a candlestick chart to elucidate patterns in the stock’s movement. Finally, we integrated the stock’s sentiment features and its candlestick chart to predict the stock price movement over 4-, 6-, 8-, and 10-day time periods. Our collaborative network consisted of two branches: the first branch contained a one-dimensional convolutional neural network (CNN) performing sentiment classification. The second branch included a two-dimensional (2D) CNN performing image classifications based on 2D candlestick chart data. We evaluated our model for five high-demand stocks (Apple, Tesla, IBM, Amazon, and Google) and determined that our collaborative network achieved promising results and compared favorably against single-network models using either sentiment data or candlestick charts alone. The proposed method obtained the most favorable performance with 75.38% accuracy for Apple stock. We also found that the stock price prediction achieved more favorable performance over longer periods of time compared with shorter periods of time.

As wireless sensor networks have become more prevalent, data from sensors in daily life are constantly being recorded. Due to cost or energy consumption considerations, optimization-based approaches are proposed to reduce deployed sensors and yield results within the error tolerance. The correlation-aware method is also designed in a mathematical model that combines theoretical and practical perspectives. The sensor deployment strategies, including XGBoost, Pearson correlation, and Lagrangian Relaxation (LR), are determined to minimize deployment costs while maintaining estimation errors below a given threshold. Moreover, the results significantly ensure the accuracy of the gathered information while minimizing the cost of deployment and maximizing the lifetime of the WSN. Furthermore, the proposed solution can be readily applied to sensor distribution problems in various fields.

Low-precision data types for embedded applications reduce the power consumption and enhance the price-performance ratio. Inconsistence between the specified accuracy of a designed filter or controller and an imprecise data type can be overcome using the δ-operator, an alternative to the traditional discrete-time z-operator. Though in many cases it significantly increases accuracy, sometimes it shows no advantage over the shift operator. So the problem of choice between delta and shift operator arises. Therefore, a study on δ-operator applicability bounds is needed to solve this problem and provide δ-operator efficient practical use. In this paper we introduce a concept of the δ-operator applicability criterion. The discrete system implementation technique with discrete-time operator choice is given for the low-precision machine arithmetic.

As the IoT ecosystem becoming more and more mature, hardware and software vendors are trying create new value by connecting all kinds of devices together via IoT. IoT devices are usually equipped with sensors to collect data, and the data collected are transmitted over the air via different kinds of wireless connection. To extract the value of the data collected, the data owner may choose to seek for third-party help on data analysis, or even of the data to the public for more insight. In this scenario it is important to protect the released data from privacy leakage. Here we propose that differential privacy, as a de-identification technique, can be a useful approach to add privacy protection to the data released, as well as to prevent the collected from intercepted and decoded during over-the-air transmission. A way to increase the accuracy of the count queries performed on the edge cases in a synthetic database is also presented in this research.

A combined edge and core cloud computing environment is a novel solution in 5G network slices. The clients’ high availability requirement is a challenge because it limits the possible admission control in front of the edge cloud. This work proposes an orchestrator with a mathematical programming model in a global viewpoint to solve resource management problems and satisfying the clients’ high availability requirements. The proposed Lagrangian relaxation-based approach is adopted to solve the problems at a near-optimal level for increasing the system revenue. A promising and straightforward resource management approach and several experimental cases are used to evaluate the efficiency and effectiveness. Preliminary results are presented as performance evaluations to verify the proposed approach’s suitability for edge and core cloud computing environments. The proposed orchestrator significantly enables the network slicing services and efficiently enhances the clients’ satisfaction of high availability.

The study aims to propose an approach of white LED spectral optimization based on mesopic luminance and color gamut volume for dim lighting conditions. Three optimal white LED spectra with relatively higher mesopic luminance and color gamut volume, the highest mesopic luminance, and the largest gamut volume are recommended for reducing energy consumption and enhancing color perception and recognition of human eyes. The theoretical simulation shows that the spectra with higher correlated color temperatures (CCT) and S/P-ratio increase the mesopic luminance and also extend the range of color gamut with the decreasing of lighting level. An evaluation model is developed to faster predict mesopic luminance, color gamut volume, and S/P ratio for lighting applications.

Providing top-k query services is relevant for storage servers which collect valuable files/data and process queries for data owners and mobile users. However, this kind of service could incur severe security concerns, because hackers or even the managers/administrators of the servers may steal important data sets and deceive users into responding to forged or incomplete query results. Therefore, these data sets need to be preserved in privacy, and moreover, the users should have the capability to verify the authenticity and integrity of the query results. As users will demand distinct information with various preferences and time domains in the pragmatic world, the traditional top-k queries are insufficient to satisfy their demands. To solve the problem, we provide the functional top-k queries in multi-dimensional space, such that the users can launch queries on the conjunction and sum of the dimensions/attributes. Some recent works have studied how to preserve data privacy and/or integrity for top-k queries on data storage applications. However, these prior works are limited to traditional top-k queries in preserving data privacy and/or integrity without permitting to systematically process top-k queries over encrypted domain in multi-dimensional space and without providing an efficiently verifiable mechanism for the corresponding query results. In this paper, we propose an efficient and effective method, called SFTopk, which addresses more challenging security problems in data privacy and verifiable functional top-k queries in multi-dimensional space. From performance evaluation experiments, it is shown that our proposed method is much more efficient than the prior works in terms of communication overhead and computation cost.