Data Mining - Concepts and Techniques.

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

Computational Analysis of Microarray Data

韧性（resilience）是指个人面对生活逆境、创伤、悲剧、威胁及其他生活重大压力的良好适应，也是个人应激（stress）和应对（coping）的正面结果。在过去的数十年，护理学等健康相关领域的学者们一直在关注为什么一些人在逆境、压力、疾病等高危（high risk）经历下也能较好地维持健康，而一些人则被逆境打败，身心健康也随之处于不良状态。近年来，应激心理学、健康心理学、精神医学、教育学、护理学等各学科对韧性概念越来越重视，尤其是临床领域的研究，从过去强调人的缺点和脆弱性的病理模式转变为关注个人的优势和强韧性的健康模式。

韧性（Resilience）的概念分析

In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets." Scientific models, such as Newtonian physics or biological gene regulatory networks, are human-driven simplifications of complex phenomena that serve as surrogates for the countless experiments that validated the models. Recently, machine learning has been able to overcome the inaccuracies of approximate modeling by directly learning the entire set of nonlinear interactions from data. However, without any predetermined structure from the scientific basis behind the problem, machine learning approaches are flexible but data-expensive, requiring large databases of homogeneous labeled training data. A central challenge is reconciling data that is at odds with simplified models without requiring "big data". 
In this work we develop a new methodology, universal differential equations (UDEs), which augments scientific models with machine-learnable structures for scientifically-based learning. We show how UDEs can be utilized to discover previously unknown governing equations, accurately extrapolate beyond the original data, and accelerate model simulation, all in a time and data-efficient manner. This advance is coupled with open-source software that allows for training UDEs which incorporate physical constraints, delayed interactions, implicitly-defined events, and intrinsic stochasticity in the model. Our examples show how a diverse set of computationally-difficult modeling issues across scientific disciplines, from automatically discovering biological mechanisms to accelerating the training of physics-informed neural networks and large-eddy simulations, can all be transformed into UDE training problems that are efficiently solved by a single software methodology.

/pdf/universal-differential-equations-for-scientific-machine-7df1mbim0x.pdf

Universal Differential Equations for Scientific Machine Learning

This article highlights some of the basic concepts of bioinformatics and data mining. The major research areas of bioinformatics are highlighted. The application of data mining in the domain of bioinformatics is explained. It also highlights some of the current challenges and opportunities of data mining in bioinformatics.

/pdf/application-of-data-mining-in-bioinformatics-28n5sw4qd2.pdf

Application Of Data Mining In Bioinformatics

Heart diseases are becoming a common public health problem worldwide, mostly due to a lack of health awareness, a poor lifestyle, and unhealthy consumption. Its accurate prediction and diagnosis are major challenges faced by medical centers and hospitals. The advancement in computing technologies has allowed the healthcare industry to collect and store routine medical data that can be used to support medical decisions. In many developed countries, the patients’ data are collected and stored in digital form. The data is then analyzed to make the necessary medical decisions involving prediction, diagnosis, image analysis, and line of treatment. Machine learning algorithms have been playing a vital role in solving complex, highly nonlinear classification and prediction problems. Further, different machine learning algorithms are ensembled in order to increase the classification and prediction accuracy. In this paper, different machine learning techniques have been ensembled using the majority voting technique to predict heart diseases, which achieves an accuracy of 88.88%. The results have been compared with other published works, which show a higher accuracy of the ensemble method over individual classifiers.

Improving the prediction accuracy of heart disease with ensemble learning and majority voting rule

The present study reported a single step synthesis of silver nanoparticles using ampicillin (Amp-AgNps), a second-generation β lactam antibiotic to get nanoformulation having dual properties that of antibiotic and silver. The Amp-AgNps was characterized by UV-VIS spectroscopy, TEM, XRD, FTIR and TGA. FTIR and TGA results suggested that amine group of Ampicllin reduce the metalic silver into nano form. These results were further validated by computational molecular dynamics simulation. The antibacterial potential of Amp-AgNps was investigated against sensitive and drug resistant bacteria. MIC of Amp-AgNps against 6 different bacterial strains were in the range of 3–28 µg/ml which is much lower than the MIC of ampicillin (12–720 µg/ml) and chemically synthesized silver nanoparticles (280–640 µg/ml). The repeated exposure to drugs may lead to development of resistance mechanism in bacteria against that drug, so the efficacy of Amp-AgNps after repeated exposure to bacterial strains were also studied. The results indicate that bacterial strains do not show any resistance to these Amp-AgNps even after exposure up to 15 successive cycles. The biocompatibility of these Amp-AgNps was checked against cell lines by using Keratinocytes cell lines (HaCaT).

/pdf/ampicillin-silver-nanoformulations-against-multidrug-3yrlaugqcj.pdf

Ampicillin Silver Nanoformulations against Multidrug resistant bacteria.

Interpretation of medical images for diagnosis and treatment of complex disease from high-dimensional and heterogeneous data remains a key challenge in transforming healthcare. In the last few years, both supervised and unsupervised deep learning achieved promising results in the area of medical imaging and image analysis. Unlike supervised learning which is biased towards how it is being supervised and manual efforts to create class label for the algorithm, unsupervised learning derive insights directly from the data itself, group the data and help to make data driven decisions without any external bias. This review systematically presents various unsupervised models applied to medical image analysis, including autoencoders and its several variants, Restricted Boltzmann machines, Deep belief networks, Deep Boltzmann machine and Generative adversarial network. Future research opportunities and challenges of unsupervised techniques for medical image analysis have also been discussed.

Khalid Raza

Papers

Application Of Data Mining In Bioinformatics

Improving the prediction accuracy of heart disease with ensemble learning and majority voting rule

Ampicillin Silver Nanoformulations against Multidrug resistant bacteria.

A Tour of Unsupervised Deep Learning for Medical Image Analysis

Integrative approaches to reconstruct regulatory networks from multi-omics data: A review of state-of-the-art methods.