Knee Osteoarthritis Detection Using a Machine Learning Method from Magnetic Resonance Imaging: A 3-D Independent Component Analysis-Based Approach | Chapter 9 | Theory and Applications of Engineering Research Vol. 2

In this chapter, a machine learning-based knee Osteoarthritis (OA) detection system from magnetic resonance (MR) images is proposed. This system is capable of detecting the presence of OA considering two classification categories: ‘non-OA’ and ‘OA’. OA is one of the most prevalent condition resulting to disability particularly in elderly population. OA is the most common articular disease of the developed world and a leading cause of chronic disability, mainly as a consequence of the knee OA and/or hip OA. Nowadays, medical images such as MR images are widely used for the OA diagnosis. For this, a medical specialist analyzes medical images by measuring the changes and in particular for knee OA, the changes in the compartment of the tibio-femoral cartilage. The proposed method consists mainly of both a data processing module and binary classification module, which process the 3-D data from MR images. In this study, we present a novel knee OA diagnostic approach that can identify the condition using magnetic resonance MR images using the Support Vector Machine (SVM) algorithm. Our suggested method is predicated on using 3-D data from MR scans of an actual cohort and the Independent Component Analysis (ICA) technique. The experimental results showed that our ICA-SVM machine learning model achieved 86% of testing accuracy with both 72% of specificity and 100% of sensitivity, once trained with a small MR image dataset. Furthermore, a benchmark evaluation was performed. The results suggest that using a larger and more diverse dataset could ensure the robustness of the proposed method. In future works, we will study the complementary use of ICA components from MR images and a convolutional neural network (CNN) to try to achieve better predictive rates in supervised learning using a larger dataset.

Author(s) Details:

Marco Oyarzo Huichaqueo,
School of Engineering, Rovira i Virgili University, 43007, Tarragona, Spain.

Please see the link here: https://stm.bookpi.org/TAER-V2/article/view/13114

Developments and Evaluation of Twin Learning Algorithms: A Systematic Review | Chapter 9 | Research and Applications Towards Mathematics and Computer Science Vol. 3

 This stage contributes a itemized study on the developments of twin learning algorithms that are took place on top of the Twin Support Vector Machine (TWSVM), Twin Extreme Learning Machine (TELM) and Twin Random Vector Functional Link (TRVFL). Various types of machine intelligence algorithms such as directed, unsupervised, semi-directed, and reinforcement education exist in the extent. Besides, the deep learning, that is part of a fuller family of machine intelligence methods, can intelligently resolve the data considerably. According to the demands of the digital age, machine intelligence algorithms have made significant stomps. Twin Algorithms' level of performance should be superior to that of allure parents'.  The improvements worthy time of TELM and TWSVM are praiseworthy and have given assurance to the researchers. The twin models that followed Extreme Learning Machine (ELM) and the sole-hidden-coating learning example both attempted to overcome any of their parents' drawbacks. Artificial intelligence will advance thanks to repetitive single-hidden-tier models and their reliable depictions. In this chapter, few of the works in twin learning algorithms that are either technically sound or better in the accomplishments are taken for the study. The current developments in twin algorithms, particularly in the single hidden flaky models, found more drawing attention because of the underlined knowledge procedure than the performance. The active principle and accomplishment of the algorithms are detailed by way of published works and judgments.

Author(s) Details:

Vidhya Mohan,
Department of Computer Science, University of Kerala, India.

Please see the link here: https://stm.bookpi.org/RATMCS-V3/article/view/11570

Genetic Algorithm and Support Vector Machine for DNS Tunneling Detection: A Hybrid Method Approach | Chapter 10 | Novel Research Aspects in Mathematical and Computer Science Vol. 5

In order to find the best characteristics that may maximise the detection of DNS tunnelling, this research suggests a hybrid technique of genetic algorithm feature selection approach with the support vector machine classifier. Corporations are increasingly spending a lot of money developing web applications as online commerce expands. On the other hand, such dangers can leave companies open to future attacks. One of these dangers is DNS tunnelling, which sends dangerous information through the domain name protocol. As a result, confidential data would be exposed and violated. Machine learning has been the subject of several studies to develop a detecting technique. The strategies used by authors comprised a wide range of characteristics, such as domain length, Bytes, content, DNS traffic volume, hostnames per domain, location, and domain history are all factors. Evidently, there is a critical need for feature selection tasks to be supported in order to discover the finest features. A benchmark dataset for DNS tunnelling was used to assess the proposed method. The new method surpassed the classic SVM by receiving an F-measure of 0.946, proving that it was superior.

Author (s) Details:

Fuqdan A. Al-Ibraheemi,
College of Dentistry, University of Al-Ameed, Iraq.

Sattar Al-Ibraheemi,
Education Ministry, Iraq.

Haleh Amintoosi,
Faculty of Engineering, Ferdowsi University of Mashhad, Iran.

Please see the link here: https://stm.bookpi.org/NRAMCS-V5/article/view/7487

Attendance Capturing and Consolidation Mechanism Using Image Processing and Machine Learning Technique | Chapter 11 | Innovations in Science and Technology Vol. 5

 

Microwave ovens had a crucial role in the twentieth century. This frequency also sees a lot of application development. Microwave tube advancements have aided numerous growths in the recent past. Based on the RF field phase velocity, microwave tubes can be classed as slow-wave or fast-wave devices. A high-power source and amplifier are necessary for millimetre and sub-millimeter wave applications, which can be obtained by designing fast-wave devices. The interaction of the electron with the RF wave in fast wave tubes differs from slow-wave devices, as will be explained further. A brief history is discussed, as well as the many types of fast-wave tubes and their dispersion relationships.

Author(S) Details

Rajib Bag
Department of Computer Engineering, Dr. B.R. Ambedkar Institute of Technology, Port Blair, Andaman & Nicobar Islands, India.

Gautam .
Department of Computer Engineering, Dr. B.R. Ambedkar Institute of Technology, Port Blair, Andaman & Nicobar Islands, India

Komal Das
Department of Computer Engineering, Dr. B.R. Ambedkar Institute of Technology, Port Blair, Andaman & Nicobar Islands, India.

P. Mohini Amma
Department of Computer Engineering, Dr. B.R. Ambedkar Institute of Technology, Port Blair, Andaman & Nicobar Islands, India.

View Book:- https://stm.bookpi.org/IST-V5/article/view/5706

Machine Learning Algorithms for Heart Disease Prediction: A Comparative Analysis | Chapter 16 | New Visions in Science and Technology Vol. 7

 Machine learning has grown in popularity as a result of the widespread application of its algorithms in numerous data science projects across many industries, particularly in the health-care industry. Machine learning technologies must be used to assist researchers and medical professionals in the early diagnosis of diseases such as heart disease, which is one of the world's leading causes of death. Correct heart disease prediction can save lives and avoid health problems, but inaccurate heart disease prediction can be fatal. Machine learning algorithms excel at learning from data, and because healthcare providers collect massive amounts of data on a regular basis, these algorithms have a lot of room to grow in this industry. A comparative analytical technique was used in this research study to determine which algorithm works better under the specified conditions. Various tests were carried out using 5 and 10 fold cross validation to confirm that the models produced were sufficiently generalizable. The data for this study comes from a machine learning database at the University of California, Irvine (UCI), which contains 303 instances with 14 attributes. The obtained data is normalised using the Min-Max method. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Nave Bayes (NB), Random Forest (RF), and Gradient Boosting ensemble approach are some of the common models developed utilising supervised machine learning classification algorithms on scaled data. Standard performance criteria such as accuracy, recall, and F1-score are also used to evaluate these methods. Based on the results of the studies, it can be determined that SVM outperforms the other algorithms.

Author(S) Details

Isreal Ufumaka
Department of Computer Science, University of Benin, Nigeria.

View Book:- https://stm.bookpi.org/NVST-V7/article/view/4433

Novel and Efficient Hybrid Model for Classification of Heart Disease | Chapter 3 | Current Approaches in Science and Technology Research Vol. 9

 Propose an effective cardiac disease categorization method that can predict disease early on and cut death rates. The study used a hybrid intelligence model of Genetic Algorithm (GA) and Support Vector Machine (SVM) for prediction, and the Cleveland dataset from the UCI machine learning library was used. SVM and GA were used to predict coronary artery disease by maximising the hyper parameters of SVM: ‘C' and ‘gamma.' Implementing meta-heuristics improved the performance of heart disease classification and resulted in a 91 percent accuracy when compared to SVM without GA. In terms of accuracy, a method of optimising SVM parameters using GA outperforms SVM and SVM with k-cross validation for predicting heart disorders. It points in the direction of making machine learning algorithms more efficient.

Author (S) Details

Mittal Desai
CMPICA, Charotar Univerity of Science and Technology (CHARUSAT), Gujarat, India.

Atul Patel
CMPICA, Charotar Univerity of Science and Technology (CHARUSAT), Gujarat, India.

View Book :- https://stm.bookpi.org/CASTR-V9/article/view/1975

Hybridized Swarm Optimization Classifiers with Ensemble Feature Ranking Techniques: Recent Study | Chapter 8 | Emerging Trends in Engineering Research and Technology Vol. 6

Intrusion Detection System (IDS) is a security support mechanism which has become an essential component of security infrastructure to detect attacks, identify and track the intruders. Intrusion Detection Systems are implemented in order to detect malicious activities and it functions behind the firewall, observing for patterns in network traffic that might indicate malicious action. The extreme development of the internet, the high occurrence of the threats over the internet has been the cause in recognizing the need for both IDS and firewall to help in securing a network. Currently many researchers have shown an increasing interest in intrusion detection based on data mining techniques and swarm intelligence techniques. Also, recent research focuses more on the hybridization of techniques to improve the performance of classifiers and it has become commonplace in IDSs which allows researchers to exploit the benefits of individual techniques and approaches. In intrusion detection, the quantity of data is huge that includes thousands of traffic records with number of various features. Selecting a subset of informative features can lead to improved classification accuracy. In this paper ensemble of feature ranking techniques are used to select the most relevant features that can represent the pattern of the network traffic. The efficiency of the presented method is validated on KDDCUP’99 dataset using hybrid swarm based classifier, Simplified Swarm Optimization (SSO) with Ant Colony Optimization (ACO). The performance of the proposed method is compared with the basic classifiers, SSO and hybridization of SSO with Support Vector Machine (SVM). It is shown that the hybridization of SSO with ACO using hybrid feature ranking method outperformed other algorithms and can be efficient in the detection of intrusive behaviour.

Author(s) Details

P. Amudha
Department of CSE, School of Engineering, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, India

S. Sivakumari
Department of CSE, School of Engineering, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, India.

View Book :-  http://bp.bookpi.org/index.php/bpi/catalog/book/200