Big Data for Health Care Analytics using Extreme Machine Learning Based on Map Reduce

A large volume of datasets is available in various fields that are stored to be somewhere which is called big data. Big Data healthcare has clinical data set of every patient records in huge amount and they are maintained by Electronic Health Records (EHR). More than 80 % of clinical data is the unstructured format and reposit in hundreds of forms. The challenges and demand for data storage, analysis is to handling large datasets in terms of efficiency and scalability. Hadoop Map reduces framework uses big data to store and operate any kinds of data speedily. It is not solely meant for storage system however conjointly a platform for information storage moreover as processing. It is scalable and fault-tolerant to the systems. Also, the prediction of the data sets is handled by machine learning algorithm. This work focuses on the Extreme Machine Learning algorithm (ELM) that can utilize the optimized way of finding a solution to find disease risk prediction by combining ELM with Cuckoo Search optimization-based Support Vector Machine (CS-SVM). The proposed work also considers the scalability and accuracy of big data models, thus the proposed algorithm greatly achieves the computing work and got good results in performance of both veracity and efficiency.

Download Full-text

Big data, machine learning and artificial intelligence: a neurologist’s guide

Practical Neurology ◽

10.1136/practneurol-2020-002688 ◽

2020 ◽

pp. practneurol-2020-002688

Author(s):

Stephen D Auger ◽

Benjamin M Jacobs ◽

Ruth Dobson ◽

Charles R Marshall ◽

Alastair J Noyce

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Neural Networks ◽

Big Data ◽

Clinical Practice ◽

Clinical Data ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Basic Principles ◽

Biological Neural Networks

Modern clinical practice requires the integration and interpretation of ever-expanding volumes of clinical data. There is, therefore, an imperative to develop efficient ways to process and understand these large amounts of data. Neurologists work to understand the function of biological neural networks, but artificial neural networks and other forms of machine learning algorithm are likely to be increasingly encountered in clinical practice. As their use increases, clinicians will need to understand the basic principles and common types of algorithm. We aim to provide a coherent introduction to this jargon-heavy subject and equip neurologists with the tools to understand, critically appraise and apply insights from this burgeoning field.

Download Full-text

Intelligent and Effective Intrusion Detection System using Machine Learning Algorithm

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.f1231.089620 ◽

2020 ◽

Vol 9 (6) ◽

pp. 237-240

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Intrusion Detection ◽

Intrusion Detection System ◽

Learning Algorithm ◽

Detection System ◽

Support Vector ◽

Machine Learning Algorithm ◽

Data Set ◽

Training Time

Intrusion Detection System observes the network traffic and identifies the attack and also inform the admin to corrective action. Powerful Intrusion Detection system is required for detection to various modern attack. There is need of efficient Intrusion Detection system .The focus of IDS research is the application of machine Learning and Deep Learning techniques. Projected work is combination of Deep Learning Technique in which Non Symmetric Deep Auto Encoder and Machine Learning Algorithm, Support Vector Machine Classifier is used to develop the Model. Stack power of the Non symmetric Deep Auto Encoder and Quickness with exactness of the SVM makes the Model very efficient. This Model not only improves the accuracy value but also improve recall and precision. It also cause the reduction of training time .To evaluate the performance of the Model and do the analysis the special Data set which are used are KDD CUP and NSL KDD Dataset.

Download Full-text

Breast Cancer Prediction Using Machine Learning Algorithm with Big Data Concept

International Journal of Scientific Research in Science Engineering and Technology ◽

10.32628/ijsrset1207232 ◽

2020 ◽

pp. 123-127

Author(s):

R. Nirmalan ◽

M. Javith Hussain Khan ◽

V. Sounder ◽

A. Manikkaraja

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Support Vector Machine ◽

Big Data ◽

Learning Algorithm ◽

Support Vector ◽

Data Set ◽

Cancer Prediction ◽

Modern Computer ◽

Huge Data

The evolution in modern computer technology produce an huge amount of data by the way of using updated technology world with the lot and lot of inventions. The algorithms which we used in machine-learning traditionally might not support the concept of big data. Here we have discussed and implemented the solution for the problem, while predicting breast cancer using big data. DNA methylation (DM) as well gene expression (GE) are the two types of data used for the prediction of breast cancer. The main objective is to classify individual data set in the separate manner. To achieve this main objective, we have used a platform Apache Spark. Here,we have applied three types of algorithms used for classification, they are decision tree, random forest algorithm, support vector machine algorithm which will be mentioned as SVM .These three types of algorithm used for producing models used for breast cancer prediction. Analyze have done for finding which algorithm will produce the better result with good accuracy and less error rate. Additionally, the platforms like Weka and Spark are compared, to find which will have the better performance while dealing with the huge data. The obtained outcome have proved that the Support Vector Machine classifier which is scalable might given the better performance than all other classifiers and it have achieved the lowest error range with the highest accuracy using GE data set

Download Full-text

Can 1H-Nuclear magnetic resonance (NMR) be used for early detection of hepatocellular cancer (HCC)?

Journal of Clinical Oncology ◽

10.1200/jco.2007.25.18_suppl.15107 ◽

2007 ◽

Vol 25 (18_suppl) ◽

pp. 15107-15107

Author(s):

R. V. Iyer ◽

B. Tennant ◽

M. Ruiz ◽

T. Szyperski ◽

D. Trump ◽

...

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

Hepatocellular Cancer ◽

Screening Tools ◽

Supervised Machine Learning ◽

Support Vector ◽

Machine Learning Algorithm ◽

Data Set ◽

H Nmr ◽

Kappa Value

15107 Background: HCC is a common and rapidly fatal cancer. Current screening tools are inadequate for identification of potentially curable cases. Our aim was to determine whether H-NMR can identify HCC compared to controls in the woodchuck (WC) model of hepatitis related HCC. Methods: Eastern WCs were bred and inoculated at birth with dilute sera from WCs that are chronic carriers of Woodchuck Hepatitis B Virus (WHV). This resulted in chronic hepatitis in ∼60% animals and all carriers developed HCC by 24–36 months. Serum from 10 chronic WHV carriers with HCC (group 1), 5 WHV carriers with no HCC (group 2) and 15 matched non-infected controls (group 3) was obtained. 45uL serum was diluted with 5uL of D2O containing 27mM formic acid + 0.9% saline. Spectra were collected on a 600 MHz INOVA spectrometer using a CapNMR flow probe with 10uL flow cell at 298K without knowledge of group assignments. The resulting 1D spectra were processed using Nuts from AcornNMR. Results: Principle component analysis and supervised PLS-DA was performed using Simca P+ from Umetrics. Despite general separation of groups, the Q2 value of this model was relatively low (0.20). We trained a Support Vector Machine (SVM) algorithm, a supervised machine-learning algorithm, to learn to identify the groups. Evaluation of the performance of the algorithm using 10-fold validation on the data set achieved a Kappa value of 0.43. This algorithm learnt to identify HCC [0.765 ROC, 0.8 sensitivity, and 0.727 positive predictive value (PPV)] and controls (0.75 ROC, 0.69 sensitivity and 0.73 PPV) but not the WHV carrier group, likely due to the small numbers. In a second analysis of 10 HCC and 15 controls, PLS-DA showed clear separation using three components (Q2= 0.5). The corresponding SVM model showed a kappa value of 0.52 and ROC values of 0.767 for both classes. Conclusions: Our preliminary results indicate that H-NMR spectra alone can be used to distinguish HCC from healthy controls using the machine-learning algorithm for classification. Further validation in a larger cohort of woodchucks is ongoing and confirmation of these preliminary findings would support investigation of this technique as a screening tool in patients at risk for developing HCC. No significant financial relationships to disclose.

Download Full-text

Misalignment Detection of a Rotating Machine Shaft Using a Support Vector Machine Learning Algorithm

International Journal of Precision Engineering and Manufacturing ◽

10.1007/s12541-020-00462-1 ◽

2021 ◽

Vol 22 (3) ◽

pp. 409-416

Author(s):

Yong Eun Lee ◽

Bok-Kyung Kim ◽

Jun-Hee Bae ◽

Kyung Chun Kim

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Learning Algorithm ◽

Support Vector ◽

Machine Learning Algorithm ◽

Rotating Machine

Download Full-text

Detection of FAKE NEWS on SOCIAL MEDIA using CLASSIFICATION Data Mining Techniques

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.a1637.109119 ◽

2019 ◽

Vol 9 (1) ◽

pp. 3132-3138

Keyword(s):

Machine Learning ◽

Data Mining ◽

Social Media ◽

Information Exchange ◽

Learning Algorithm ◽

Daily Life ◽

Support Vector ◽

Machine Learning Algorithm ◽

Fake News ◽

Other Information

In today’s world social media is one of the most important tool for communication that helps people to interact with each other and share their thoughts, knowledge or any other information. Some of the most popular social media websites are Facebook, Twitter, Whatsapp and Wechat etc. Since, it has a large impact on people’s daily life it can be used a source for any fake or misinformation. So it is important that any information presented on social media should be evaluated for its genuineness and originality in terms of the probability of correctness and reliability to trust the information exchange. In this work we have identified the features that can be helpful in predicting whether a given Tweet is Rumor or Information. Two machine learning algorithm are executed using WEKA tool for the classification that is Decision Tree and Support Vector Machine.

Download Full-text

Machine Learning for Internet of Things

International Journal Of Engineering And Computer Science ◽

10.18535/ijecs/v8i07.4346 ◽

2019 ◽

Vol 8 (07) ◽

pp. 24680-24782

Author(s):

Manisha Bagri ◽

Neha Aggarwal

Keyword(s):

Machine Learning ◽

Internet Of Things ◽

Learning Algorithm ◽

Weather Prediction ◽

Support Vector ◽

The Internet ◽

Machine Learning Algorithm ◽

Learning Patterns ◽

New Development ◽

Share Data

By 2020 around 25-50 billion devices are likely to be connected to the internet. Due to this new development, it gives rise to something called Internet of Things (IoT). The interconnected devices can generate and share data over a network. Machine Learning plays a key role in IoT to handle the vast amount of data. It gives IoT and devices a brain to think, which is often called as intelligence. The data can be feed to machines for learning patterns, based on training the machines can identify to predict for the future. This paper gives a brief explanation of IoT. This paper gives a crisp explanation of machine learning algorithm and its types. However, Support Vector Machine (SVM) is explained in details along with its merits and demerits. An algorithm is also proposed for weather prediction using SVM for IoT.

Download Full-text

CAN A MACHINE LEARNING ALGORITHM IDENTIFY SARS-COV-2 VARIANTS BASED ON CONVENTIONAL rRT-PCR? PROOF OF CONCEPT

10.1101/2021.11.12.21266286 ◽

2021 ◽

Author(s):

jorge cabrera Alvargonzalez ◽

Ana Larranaga Janeiro ◽

Sonia Perez ◽

Javier Martinez Torres ◽

Lucia martinez lamas ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Supervised Classification ◽

Learning Algorithm ◽

Support Vector ◽

Classification Algorithms ◽

Machine Learning Algorithm ◽

Proof Of Concept ◽

The Past ◽

Number Of Cycles

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been and remains one of the major challenges humanity has faced thus far. Over the past few months, large amounts of information have been collected that are only now beginning to be assimilated. In the present work, the existence of residual information in the massive numbers of rRT-PCRs that tested positive out of the almost half a million tests that were performed during the pandemic is investigated. This residual information is believed to be highly related to a pattern in the number of cycles that are necessary to detect positive samples as such. Thus, a database of more than 20,000 positive samples was collected, and two supervised classification algorithms (a support vector machine and a neural network) were trained to temporally locate each sample based solely and exclusively on the number of cycles determined in the rRT-PCR of each individual. Finally, the results obtained from the classification show how the appearance of each wave is coincident with the surge of each of the variants present in the region of Galicia (Spain) during the development of the SARS-CoV-2 pandemic and clearly identified with the classification algorithm.

Download Full-text