A survey of applied machine learning techniques for optical orthogonal frequency division multiplexing based networks

BACKGROUND Arthritis is a common condition, which frequently involves the hands. Patients with inflammatory arthritis have been shown to experience significant delays in diagnosis. OBJECTIVE We sought to develop and test a screening tool combining an image of a patient’s hands, a short series of questions, and a single examination technique, to determine the most likely diagnosis in a patient presenting with hand arthritis. Machine learning techniques were used to develop separate algorithms for each component, which were combined to produce a diagnosis. METHODS 280 consecutive new patients presenting to a Rheumatology practice with hand arthritis were enrolled. Each patient completed a 9-part questionnaire, had photographs taken of each hand, and had a single examination result recorded. The Rheumatologist diagnosis was recorded following a 45-minute consultation. The photograph algorithm was developed from a library of 1000 images, and machine learning techniques were applied to the questionnaire results, training several models against the diagnosis from the Rheumatologist. RESULTS The combined algorithms in this study were able to predict inﬂammatory arthritis with an accuracy, precision, recall and specificity of 96·8%, 97·2%, 98·6% and 90·5% respectively. Similar results were found when inflammatory arthritis was subclassified into rheumatoid arthritis and psoriatic arthritis. The corresponding figures for osteoarthritis were 79·6%, 85·9%, 61·9% and 92·6%. CONCLUSIONS This study demonstrates a novel application of a combined image-processing and a patient questionnaire with applied machine-learning methods, to facilitate the diagnosis of patients presenting with hand arthritis. Preliminary results are encouraging for the application of such techniques in clinical practice. CLINICALTRIAL Not applicable.

Download Full-text

Applied Machine Learning Techniques on Selection and Positioning of Human Resources in the Public Sector

Open Journal of Business and Management ◽

10.4236/ojbm.2021.92030 ◽

2021 ◽

Vol 09 (02) ◽

pp. 536-556

Author(s):

Panagiota Pampouktsi ◽

Spyridon Avdimiotis ◽

Manolis Μaragoudakis ◽

Markos Avlonitis

Keyword(s):

Machine Learning ◽

Public Sector ◽

Human Resources ◽

Machine Learning Techniques ◽

The Public ◽

Applied Machine Learning ◽

Learning Techniques

Download Full-text

Machine Learning Methods to Classify Mushrooms for Edibility-A Review

International Journal for Modern Trends in Science and Technology - RTT2020 ◽

10.46501/ijmtst060909 ◽

2020 ◽

Vol 06 (09) ◽

pp. 54-58

Author(s):

Rakesh Kumar Y and Dr. V. Chandrasekhar

Keyword(s):

Neural Network ◽

Machine Learning ◽

Literature Review ◽

Edible Mushroom ◽

Machine Learning Techniques ◽

Support Vector ◽

Applied Machine Learning ◽

Learning Techniques ◽

Artificial Neural Network Ann

There are thousands of species of Mushrooms in the world; they are edible and non-edible being poisonous. It is difficult for non-expertise person to Identify poisonous and edible mushroom of all the species manually. So a computer aided system with software or algorithm is required to classify poisonous and nonpoisonous mushrooms. In this paper a literature review is presented on classification of poisonous and nonpoisonous mushrooms. Most of the research works to classify the type of mushroom have applied, machine learning techniques like Naïve Bayes, K-Neural Network, Support vector Machine(SVM), Artificial Neural Network(ANN), Decision Tree techniques. In this literature review, a summary and comparisons of all different techniques of mushroom classification in terms of its performance parameters, merits and demerits faced during the classification of mushrooms using machine learning techniques.

Download Full-text

Ensemble of SVM Classifiers for Spam Filtering

Encyclopedia of Artificial Intelligence ◽

10.4018/978-1-59904-849-9.ch086 ◽

2011 ◽

pp. 561-566

Author(s):

Ángela Blanco ◽

Manuel Martín-Merino

Keyword(s):

Machine Learning ◽

False Positive ◽

Machine Learning Techniques ◽

Support Vector ◽

Applied Machine Learning ◽

Internet Users ◽

Learning Techniques ◽

Svm Algorithm ◽

Misclassification Errors ◽

Voting Strategy

Unsolicited commercial email also known as Spam is becoming a serious problem for Internet users and providers (Fawcett, 2003). Several researchers have applied machine learning techniques in order to improve the detection of spam messages. Naive Bayes models are the most popular (Androutsopoulos, 2000) but other authors have applied Support Vector Machines (SVM) (Drucker, 1999), boosting and decision trees (Carreras, 2001) with remarkable results. SVM has revealed particularly attractive in this application because it is robust against noise and is able to handle a large number of features (Vapnik, 1998). Errors in anti-spam email filtering are strongly asymmetric. Thus, false positive errors or valid messages that are blocked, are prohibitively expensive. Several authors have proposed new versions of the original SVM algorithm that help to reduce the false positive errors (Kolz, 2001, Valentini, 2004 & Kittler, 1998). In particular, it has been suggested that combining non-optimal classifiers can help to reduce particularly the variance of the predictor (Valentini, 2004 & Kittler, 1998) and consequently the misclassification errors. In order to achieve this goal, different versions of the classifier are usually built by sampling the patterns or the features (Breiman, 1996). However, in our application it is expected that the aggregation of strong classifiers will help to reduce more the false positive errors (Provost, 2001 & Hershop, 2005). In this paper, we address the problem of reducing the false positive errors by combining classifiers based on multiple dissimilarities. To this aim, a diversity of classifiers is built considering dissimilarities that reflect different features of the data. The dissimilarities are first embedded into an Euclidean space where a SVM is adjusted for each measure. Next, the classifiers are aggregated using a voting strategy (Kittler, 1998). The method proposed has been applied to the Spam UCI machine learning database (Hastie, 2001) with remarkable results.

Download Full-text

Has the Flood Entered the Basement? A Systematic Literature Review about Machine Learning in Laboratory Medicine

Diagnostics ◽

10.3390/diagnostics11020372 ◽

2021 ◽

Vol 11 (2) ◽

pp. 372

Author(s):

Luca Ronzio ◽

Federico Cabitza ◽

Alessandro Barbaro ◽

Giuseppe Banfi

Keyword(s):

Machine Learning ◽

Literature Review ◽

Systematic Literature Review ◽

Laboratory Medicine ◽

Machine Learning Techniques ◽

Prognostic Performance ◽

Applied Machine Learning ◽

Previous Review ◽

Learning Techniques

This article presents a systematic literature review that expands and updates a previous review on the application of machine learning to laboratory medicine. We used Scopus and PubMed to collect, select and analyse the papers published from 2017 to the present in order to highlight the main studies that have applied machine learning techniques to haematochemical parameters and to review their diagnostic and prognostic performance. In doing so, we aim to address the question we asked three years ago about the potential of these techniques in laboratory medicine and the need to leverage a tool that was still under-utilised at that time.

Download Full-text

Fast and accurate primary user detection with machine learning techniques for cognitive radio networks

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v21.i1.pp472-478 ◽

2021 ◽

Vol 21 (1) ◽

pp. 472

Author(s):

G. A. Pethunachiyar ◽

B. Sankaragomathi

Keyword(s):

Machine Learning ◽

Spectrum Sensing ◽

Orthogonal Frequency Division Multiplexing ◽

Signal To Noise Ratio ◽

Energy Detection ◽

Primary User ◽

Detection Algorithm ◽

Machine Learning Techniques ◽

Support Vector ◽

Learning Techniques

<p class="IJASEITAbtract"><span>Spectrum decision is an important and crucial task for the secondary user to avail the unlicensed spectrum for transmission. Managing the spectrum is an efficient one for spectrum sensing. Determining the primary user presence in the spectrum is an essential work for using the licensed spectrum of primary user. The information which lacks in managing the spectrum are the information about the primary user presence, accuracy in determining the existence of user in the spectrum, the cost for computation and difficult in finding the user in low signal-to noise ratio (SNR) values. The proposed system overcomes the above limitations. In the proposed system, the various techniques of machine learning like decision tree, support vector machines, naive bayes, ensemble based trees, nearest neighbour’s and logistic regression are used for testing the algorithm. As a first step, the spectrum sensing is done in two stages with Orthogonal Frequency Division Multiplexing and Energy Detection algorithm at the various values of SNR. The results generated from the above algorithm is used for database generation. Next, the different machine learning techniques are trained and compared for the results produced by different algorithms with the characteristics like speed, time taken for training and accuracy in prediction. The accuracy and finding the presence of the user in the spectrum at low SNR values are achieved by all the algorithms. The computation cost of the algorithm differs from each other. Among the tested techniques, k-nearest neighbour (KNN) algorithm produces the better performance in a minimized time.</span></p>

Download Full-text

Dimensioning an FPGA for Real-Time Implementation of State of the Art Neural Network-Based HPA Predistorter

Electronics ◽

10.3390/electronics10131538 ◽

2021 ◽

Vol 10 (13) ◽

pp. 1538

Author(s):

Abdelhamid Louliej ◽

Younes Jabrane ◽

Víctor P. Gil Jiménez ◽

Frédéric Guilloud

Keyword(s):

Power Efficiency ◽

Orthogonal Frequency Division Multiplexing ◽

Average Power ◽

Digital Signal ◽

Travelling Wave ◽

Ultra Wideband ◽

Machine Learning Techniques ◽

Frequency Division Multiplexing ◽

Frequency Division ◽

Non Linear

Orthogonal Frequency Division Multiplexing (OFDM) is one of the key modulations for current and novel broadband communications standards. For example, Multi-band Orthogonal Frequency Division Multiplexing (MB-OFDM) is an excellent choice for the ECMA-368 Ultra Wideband (UWB) wireless communication standard. Nevertheless, the high Peak to Average Power Ratio (PAPR) of MB-OFDM UWB signals reduces the power efficiency of the key element in mobile devices, the High Power Amplifier (HPA), due to non-linear distortion, known as the non-linear saturation of the HPA. In order to deal with this limiting problem, a new and efficient pre-distorter scheme using a Neural Networks (NN) is proposed and also implemented on Field Programmable Gate Array (FPGA). This solution based on the pre-distortion concept of HPA non-linearities offers a good trade-off between complexity and performance. Some tests and validation have been conducted on the two types of HPA: Travelling Wave Tube Amplifiers (TWTA) and Solid State Power Amplifiers (SSPA). The results show that the proposed pre-distorter design presents low complexity and low error rate. Indeed, the implemented architecture uses 10% of DSP (Digital Signal Processing) blocks and 1% of LUTs (Look up Table) in case of SSPA, whereas it only uses 1% of LUTs in case of TWTA. In addition, it allows us to conclude that advanced machine learning techniques can be efficiently implemented in hardware with the adequate design.

Download Full-text

Application of Machine Learning Techniques in Drug-Target Interactions Prediction

Current Pharmaceutical Design ◽

10.2174/1381612826666201125105730 ◽

2020 ◽

Vol 26 ◽

Author(s):

Shengli Zhang ◽

Jiesheng Wang ◽

Zhenhui Lin ◽

Yunyun Liang

Keyword(s):

Machine Learning ◽

Drug Target ◽

Drug Repositioning ◽

Machine Learning Techniques ◽

Data Sets ◽

Machine Learning Methods ◽

Applied Machine Learning ◽

Lab Experiments ◽

Learning Techniques ◽

Supervised Methods

Background: Drug-Target interactions are vital for drug design and drug repositioning. However, traditional lab experiments are both expensive and time-consuming. Various computational methods which applied machine learning techniques performed efficiently and effectively in the field. Results: The machine learning methods can be divided into three categories basically: Supervised methods, SemiSupervised methods and Unsupervised methods. We reviewed recent representative methods applying machine learning techniques of each category in DTIs and summarized a brief list of databases frequently used in drug discovery. In addition, we compared the advantages and limitations of these methods in each category. Conclusion: Every prediction model has its both strengths and weaknesses and should be adopted in proper ways. Three major problems in DTIs prediction including the lack of nonreactive drug-target pairs data sets, overoptimistic results due to the biases and the exploiting of regression models on DTIs prediction should be seriously considered.

Download Full-text