Data Mining Practical Machine Learning Tools and Techniques

https://bura.brunel.ac.uk/bitstream/2438/13152/4/Fulltext.pdf

Critical analysis of Big Data challenges and analytical methods

Giant and isotropic magnetoresistance as huge as −53% was observed in magnetic manganese oxide La0.72Ca0.25MnOz films with an intrinsic antiferromagnetic spin structure. We ascribe this magnetoresistance to spin‐dependent electron scattering due to spin canting of the manganese oxide.

31p-S-4 Giant Magnetoresistance in Magnetic Manganese Oxide with Intrinsic Antiferromagnetic Spin Structure

In the era of the Internet of Things (IoT), an enormous amount of sensing devices collect and/or generate various sensory data over time for a wide range of fields and applications. Based on the nature of the application, these devices will result in big or fast/real-time data streams. Applying analytics over such data streams to discover new information, predict future insights, and make control decisions is a crucial process that makes IoT a worthy paradigm for businesses and a quality-of-life improving technology. In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely deep learning (DL), to facilitate the analytics and learning in the IoT domain. We start by articulating IoT data characteristics and identifying two major treatments for IoT data from a machine learning perspective, namely IoT big data analytics and IoT streaming data analytics. We also discuss why DL is a promising approach to achieve the desired analytics in these types of data and applications. The potential of using emerging DL techniques for IoT data analytics are then discussed, and its promises and challenges are introduced. We present a comprehensive background on different DL architectures and algorithms. We also analyze and summarize major reported research attempts that leveraged DL in the IoT domain. The smart IoT devices that have incorporated DL in their intelligence background are also discussed. DL implementation approaches on the fog and cloud centers in support of IoT applications are also surveyed. Finally, we shed light on some challenges and potential directions for future research. At the end of each section, we highlight the lessons learned based on our experiments and review of the recent literature.

Deep Learning for IoT Big Data and Streaming Analytics: A Survey

Healthcare data are a valuable source of healthcare intelligence. Sharing of healthcare data is one essential step to make healthcare system smarter and improve the quality of healthcare service. Healthcare data, one personal asset of patient, should be owned and controlled by patient, instead of being scattered in different healthcare systems, which prevents data sharing and puts patient privacy at risks. Blockchain is demonstrated in the financial field that trusted, auditable computing is possible using a decentralized network of peers accompanied by a public ledger. In this paper, we proposed an App (called Healthcare Data Gateway (HGD)) architecture based on blockchain to enable patient to own, control and share their own data easily and securely without violating privacy, which provides a new potential way to improve the intelligence of healthcare systems while keeping patient data private. Our proposed purpose-centric access model ensures patient own and control their healthcare data; simple unified Indicator-Centric Schema (ICS) makes it possible to organize all kinds of personal healthcare data practically and easily. We also point out that MPC (Secure Multi-Party Computing) is one promising solution to enable untrusted third-party to conduct computation over patient data without violating privacy.

Healthcare Data Gateways: Found Healthcare Intelligence on Blockchain with Novel Privacy Risk Control

To solve the problem that it is difficult to calculate system coupling in the field of systems science and software engineering, this article discussed quantitative analysis of system coupling It is difficult to calculate system coupling in the field of system science and software engineering Consequently, this paper discussed quantitative analysis of system coupling to solve this problem According to the dependencies between the entities in a system, this paper proposed two mathematical models to measure system coupling based on entropy and judgment matrix With these two models, it is possible to measure the coupling of each entity in the system and provide a basis for reducing the system coupling Finally, this paper verified the validity and utility of the proposed models via a case of data warehouse structure

Quantitative analysis of system coupling

Ship detection in sea clutter environment using scanning radar is of vital importance, but with challenges due to low angular resolution. To solve the problem, an angular superresolution algorithm for radar imaging based on Bayesian deconvolution theory is proposed. Firstly, the statistic characteristics of the sea clutter are modeled using compound K-distribution. Then the signal model of radar echo in sea environment is formulated as the convolution of the antenna pattern and the reflectivity of the original scene plus the reflectivity of sea clutter. The ship detection task in sea clutter environment using the deconvolution method is converted into an equivalent maximum a posteriori estimation problem, which is solved using the optimization method in this paper. Simulation results demonstrate the validity of the proposed method in terms of ship detection in sea clutter environment.

A deconvolution method for ship detection in sea clutter environment

High resolution is always the most concerned issue of radar imaging. Traditional radar systems, which obtain echo data using single platform, can achieve limited imaging resolution in a specific view angle. Distributed radar system, which expands multi-platform in space to obtain high imaging resolution by forming a large aperture, is a novel and hot research point. Matched filter, such as inverse fast Fourier transform (IFFT), is a conventional method to deal with distributed radar imaging. However, the method relies strictly on geometric configuration. In this paper, an iterative adaptive approach (IAA) based method is proposed to solve the problem of configuration adaptability. It can maintain the performance of matrix during the iteration. Then, the distributed radar system can keep high resolution in different geometric configurations. Simulation results verified the excellent performance of the proposed IAA-based imaging method.

Improved Configuration Adaptability Based on IAA for Distributed Radar Imaging

Group division is a typical task involved in online social network analysis. Group division can be based on static and dynamic relationships. Compared to static group division, dynamic interactions between users can better reflect the intimacy of relationships between users in the online social network. This paper proposes a group division method based on the analysis of interactive behaviors among users and constructs a single-dimensional network structure between users based on behaviors of connecting, commenting, forwarding, and liking among users. Then, several single-dimensional networks are integrated into one complex network, this complex network is divided into groups and different groups of the online social network are identified. The experimental results show that the group division method based on users and behaviors is effective. The method proposed in this paper is used to identify Tibetan user groups and provides a theoretical basis for analyzing the health statuses of Tibetan user groups from online social networks.

Tibetan Weibo User Group Division Based on User Behaviors for Analyzing Health Problems

The low angular resolution of scanning radar limits the application in the forward-looking imaging field. This paper proposes the mixed method of truncated singular value decomposition (TSVD) with regularization l 1 norm to achieve the angular super-resolution. First, the TSVD technique is applied to suppress the noise amplification and keep the main information of targets. Then the angular super-resolution is obtained by analyzing the main information in the form of regularization l 1 norm. The mixed method has the better performance, comparing with the TSVD method and regularization method. The performance has the lower sensitivity to the regularization parameter. Simulations and experimental results verify the efficacy of this method.

Yin Zhang

Papers

Quantitative analysis of system coupling

A deconvolution method for ship detection in sea clutter environment

Improved Configuration Adaptability Based on IAA for Distributed Radar Imaging

Tibetan Weibo User Group Division Based on User Behaviors for Analyzing Health Problems

The regularization method based on tsvd for forward-looking radar angular superresolution