WEKA Classifiers Research Articles

A Comparison of Convolutional Neural Networks and Traditional Feature-Based Classification Applied to Leukaemia Image Analysis.

The accuracy of smear test image classification is a fundamental aspect in differentiating the type of leukaemia and determining the right treatment to improve the patient's chances of survival and recovery. Image Classification has lately become a very effective tool in detecting and analysing the right type of leukaemia as each type of the disease looks differently when evaluated under microscope. This paper is evaluating and comparing the efficiency and performance of feature extraction techniques (colour descriptors and Haralick texture descriptors) and a CNN (Convolutional Neural Network) built and trained by using the TensorFlow packages for classifying leukaemia images. Extracting texture and colour features from a given set of leukaemia images through computation was successful in detecting the type of disease and the results analysed with Weka Classifiers were giving the highest accuracy of 93.58%. TensorFlow tested with Cross-Validation proves efficient in training and customising the system, but the accuracy was median 56% and was not greatly improved by addressing the class imbalance issue from the data set with SMOTE. Further studies will investigate increasing the number of images by using a segmentation and image manipulation/augmentation techniques and increasing the accuracy of CNN through the addition of the investigated traditional features.

Monophonic Musical Instrument Sound Classification Using Impulse Response Modeling

The field of music has promising commercial and social applications. Hence it has attracted the attention of researchers, engineers, sociologists and health care peoples. Therefore this particular research area has been selected.
 In this manuscript the monophonic musical classificationsystem using impulse response of the system is presented. In this research work 19 musical instruments monophonic sounds from 4 families are classified using WEKA classifier. The impulse response is of all musical instruments and families are computed in Cepstral Domain. AsImpulse response is used to model the body response of the musical instruments and helps to capture the information. It is different for different instruments. The features are extracted from impulse response and presented to WEKA Classifier.
 The Musical instrument classification for individual instruments and family is verified using impulse response modeling. It is found that the impulse response is different for different instruments. It helps to easily distinguish between instrument to instrument and family to family. For individual instruments, the average classification accuracy has been obtained is 83.23% and 85.55% for family classification.

Performance Analysis of Classification Techniques in Data Mining using WEKA

To place similar objects together in to one group and separate the different ones are done with the help of data mining algorithms. In the present days, retrieval of information for decision making is very crucial task. The interdisciplinary field of computer science that deals with this task is known as data mining. Data mining is used to discover the knowledge that is hidden in large volume of data stored in data repositories. So, many researchers attracted towards data mining for decision making. There are number of tools available for data mining also such as ORANGE, WEKA and KNIME etc. But whenever there is discussion of some classification model then WEKA seems as a strong data mining tool. In this paper, various machine learning algorithms of classification are analysed by using the diabetes data set. WEKA tool is used for the same purpose. The purpose of this paper is to present the comparative evaluation of WEKA classifiers in the context of diabetes dataset. These algorithms are compared by using their results calculations received on WEKA.

AERIAL IMAGE SEGMENTATION IN URBAN ENVIRONMENT FOR VEGETATION MONITORING

Abstract. Urban forests are crucial for the population well-being and improvement of the quality of life. For example, they contribute to the rain damping and to the improvement of the local climate. Therefore a correct and accurate mapping of this resource is fundamental for its correct management. We investigated a method that combines machine learning and SLIC superpixel techniques using different Superpixels (k) number to map trees in the metropolitan region of the municipality of Campo Grande-MS, Brazil with aerial orthoimages with GSD (Ground Sample Distance) of 10 cm. The combination of superpixels and machine learning algorithms were checked out with a set of weka classifiers and achieved good results i.e. F-1 %98.2, MCC %88.4 and Accuracy of %96.8, supporting that this method is efficient when used for urban trees mapping.

Wearable Internet-of-Things platform for human activity recognition and health care

We propose to perform wearable sensors-based human physical activity recognition. This is further extended to an Internet-of-Things (IoT) platform which is based on a web-based application that integrates wearable sensors, smartphones, and activity recognition. To this end, a smartphone collects the data from wearable sensors and sends it to the server for processing and recognition of the physical activity. We collect a novel data set of 13 physical activities performed both indoor and outdoor. The participants are from both the genders where their number per activity varies. During these activities, the wearable sensors measure various body parameters via accelerometers, gyroscope, magnetometers, pressure, and temperature. These measurements and their statistical are then represented in features vectors that used to train and test supervised machine learning algorithms (classifiers) for activity recognition. On the given data set, we evaluate a number of widely known classifiers such random forests, support vector machine, and many others using the WEKA machine learning suite. Using the default settings of these classifiers in WEKA, we attain the highest overall classification accuracy of 90%. Consequently, such a recognition rate is encouraging, reliable, and effective to be used in the proposed platform.

Multivariate Data Analysis and Machine Learning for Prediction of MCI-to-AD Conversion.

There has always been a need for discovering efficient and dependable Alzheimer's disease (AD) diagnostic biomarkers. Like the majority of diseases, the earlier the diagnosis, the most effective the treatment. (Semi)-automated structural magnetic resonance imaging (MRI) processing approaches are very popular in AD research. Mild cognitive impairment (MCI) is considered to be a stage between normal cognitive ageing and dementia. MCI can often be the prodromal stage of AD. Around 10-15% of MCI patients convert to AD per year. In this study, we used three supervised machine learning (ML) techniques to differentiate MCI converters (MCIc) from MCI non-converters (MCInc) and predict their conversion rates from baseline MRI data (cortical thickness (CTH) and hippocampal volume (HCV)). A total of 803 participants from the ADNI cohort were included in this study (188 AD, 107 MCIc, 257 MCInc and 156 healthy controls (HC)). We studied the classification abilities of three different WEKA classifiers (support vector machine (SVM), decision trees (J48) and Naive Bayes (NB)). We built six different classification models, three models based on CTH and three based on HCV (CTH-SVM, CTH-J48, CTH-NB, HCV-SVM, HCV-J48 and HCV-NB). For the classification experiments, we obtained up to 71% sensitivity and up to 56% specificity. The prediction of conversion showed accuracy for up to 84%. The value of certain multivariate models derived from the classification experiments has exhibited robust and effective results in MCIc identification. However, there was a limitation in this study since we could not compare the CTH with the HCV models seeing as the data used originated from different subjects. As future direction, we propose the creation of a model that would combine various features with data originating from the same subjects, thus being a far more reliable and accurate prognostic tool.

A SURVEY ON DIFFERENT MACHINE LEARNING ALGORITHMS AND WEAK CLASSIFIERS BASED ON KDD AND NSL-KDD DATASETS

Network intrusion detection often finds a difficulty in creating classifiers that could handle unequal distributed attack categories. Generally, attacks such as Remote to Local (R2L) and User to Root (U2R) attacks are very rare attacks and even in KDD dataset, these attacks are only 2% of overall datasets. So, these result in model not able to efficiently learn the characteristics of rare categories and this will result in poor detection rates of rare attack categories like R2L and U2R attacks. We even compared the accuracy of KDD and NSL-KDD datasets using different classifiers in WEKA.

Evaluation of wheat kernels infected by fungi of the genus Fusarium based on morphological features

AbstractThe aim of this study was to propose a nondestructive method for evaluating wheat kernels infected by fungi of the genus Fusarium based on the morphological features of kernels and for distinguishing infected kernels from healthy kernels. Images were acquired with a flatbed scanner to determine 59 geometric parameters (linear dimensions and shape factors). Wheat kernels were classified as infected or healthy with the use of Decision trees, Rules, Bayes, Lazy, Meta, and Functions classifiers in WEKA 3.9 software. The classification accuracy of the model based on 59 attributes ranged from 58.12% to 73.37%. The selection of the best attributes shortened the time of the analysis and improved classification results. Linear Forward Selection and MLP classifiers were characterized by the highest classification accuracy.Practical applicationsThe infection of cereal grains by fungi of the genus Fusarium is a food security challenge that can compromise the quantity and quality of yields in many agricultural regions. Selected fungi produce mycotoxins with carcinogenic, mutagenic, teratogenic, and immunotoxic effects for humans and animals. In this study, a nondestructive method was applied to evaluate wheat kernels infected by fungi of the genus Fusarium based on the morphological features of kernels and to distinguish infected kernels from healthy kernels. The proposed method can be used for rapid, inexpensive, and effective detection of fungal infections in cereal grain.

Data Fusion for Real-time Multimodal Emotion Recognition through Webcams and Microphones in E-Learning

This article describes the validation study of our software that uses combined webcam and microphone data for real-time, continuous, unobtrusive emotion recognition as part of our FILTWAM framework. FILTWAM aims at deploying a real-time multimodal emotion recognition method for providing more adequate feedback to the learners through an online communication skills training. Herein, timely feedback is needed that reflects on the intended emotions they show and which is also useful to increase learners’ awareness of their own behavior. At least, a reliable and valid software interpretation of performed face and voice emotions is needed to warrant such adequate feedback. This validation study therefore calibrates our software. The study uses a multimodal fusion method. Twelve test persons performed computer-based tasks in which they were asked to mimic specific facial and vocal emotions. All test persons’ behavior was recorded on video and two raters independently scored the showed emotions, which were contrasted with the software recognition outcomes. A hybrid method for multimodal fusion of our multimodal software shows accuracy between 96.1% and 98.6% for the best-chosen WEKA classifiers over predicted emotions. The software fulfils its requirements of real-time data interpretation and reliable results.

Artificial Intelligence (AI) Techniques Applied for the Development of a Clinical Decision Support System (CDSS) for Diagnosing Ischemic Heart Disease (IHD)

Heart Disease (IHD) is difficult to diagnose since most of the symptoms and clinical presentations are similar to other diseases. It is a very common, harmful disease, which is identified mostly during the mortality of an individual. The objective is to build a clinical decision support system, which will diagnose the presence of IHD with an integrated automated classifier using Artificial Intelligence (AI) techniques. A retrospective data set that included 800 clinical cases was taken for the work. A total of 88 sets were discarded during pre-processing. Tests were run on 712 cases using the Weka classifiers available in Weka 3.7.0. Out of 113 classifiers, 16 were identified to be the best based on the following parameters: sensitivity, specificity, accuracy, F- measure, kappa statistic, correctly classified cases, time taken to run the model, and the Receiver Operating Characteristic (ROC) curve. The diagnoses made by the Clinical Decision Support System (CDSS) were compared with those made by physicians during patient consultations. The KSTAR algorithm showed the best diagnoses with the highest accuracy 97.32%, sensitivity 98%, specificity 97% kappa 0.95, and ROC 0.995. The authors thus conclude that a CDSS can be developed to assist expert physicians in separating the positive and the negative cases of heart disease.

The Prediction of Disulphide Bonding in HIV and other lenti-viruses by Machine Learning Techniques

The introduction of disulphide bonds into proteins is an important mechanism by which they have evolved and are evolving. Most protein disulphide bonds are motifs that stabilize the tertiary and quaternary protein structure. These bonds also thought to assist protein folding by decreasing the entropy of the unfolded form. Amino acid cysteine plays a fundamental role in formation of disulphide bonds. In the present study, proteomics of disulphide bonding in HIV is studied through a machine learning model which has been developed to classify disulphide bonds from different species of lentiviruses like bovine immunodeficiency virus (BIV), simian immunodeficiency virus (SIV), Feline immunodeficiency virus, murine infectious virus (MIV) and equine infectious anaemia virus (EIV) and Human immunodeficiency virus (HIV). Phylogenetic relationship is also studied by the prediction of disulphide bonding among these viruses. Hence by different algorithms of WEKA classifier J48 predicts better classification with an accuracy of 89.6104%.

Annotation Framework for the Physical Activity Evaluation in Real-Time

Objectives: Work aims to create a portable tool with a decision support, providing relevant methods for purposes of physical activity evaluation in real-time. Methods: We have utilized accelerometer equipped ez430Chronos watch in conjunction with a preconfigured RaspberryPi-based setup. Wireless transmission of accelerometer data into a running web application instance, which served as a user frontend, is provided through the WebSocket protocol. Decision support is based on a Weka classifier. Results: The proposed framework is ready to be used for the annotation and basic evaluation of physical activity data in a Wi-Fi covered areas. Minor issues are related to the occasional instability of data transmission, which has to be handled consequently. Conclusions: We found the overall framework architecture robust enough to serve its purpose. Next steps in the development will lead to an expansion of outlined functionality.

Dynamic categorization of clinical research eligibility criteria by hierarchical clustering

Objective To semi-automatically induce semantic categories of eligibility criteria from text and to automatically classify eligibility criteria based on their semantic similarity. Design The UMLS semantic types and a set of previously developed semantic preference rules were utilized to create an unambiguous semantic feature representation to induce eligibility criteria categories through hierarchical clustering and to train supervised classifiers. Measurements We induced 27 categories and measured the prevalence of the categories in 27,278 eligibility criteria from 1578 clinical trials and compared the classification performance (i.e., precision, recall, and F1-score) between the UMLS-based feature representation and the “bag of words” feature representation among five common classifiers in Weka, including J48, Bayesian Network, Naïve Bayesian, Nearest Neighbor, and instance-based learning classifier. Results The UMLS semantic feature representation outperforms the “bag of words” feature representation in 89% of the criteria categories. Using the semantically induced categories, machine-learning classifiers required only 2000 instances to stabilize classification performance. The J48 classifier yielded the best F1-score and the Bayesian Network classifier achieved the best learning efficiency. Conclusion The UMLS is an effective knowledge source and can enable an efficient feature representation for semi-automated semantic category induction and automatic categorization for clinical research eligibility criteria and possibly other clinical text.

Echocardiographic determinants of successful balloon dilation in pulmonary atresia with intact ventricular septum

Pulmonary atresia with intact ventricular septum (PA-IVS) is a complex congenital heart malformation with multitude therapeutic approaches. Recently, balloon valvotomy has been used as an alternative to primary surgery. This study aimed to identify echocardiographic markers of balloon dilation success in PA-IVS. The echocardiograms of 26 patients diagnosed with PA-IVS who underwent primary pulmonary balloon valvotomy were reviewed. Tricuspid annulus Z-score, pulmonary annulus Z-score, right ventricular (RV) to left ventricular (LV) length ratio, RV to LV transverse diameter ratio, and tricuspid valve (TV) to mitral valve (MV) annulus diameter ratio were measured. The tricuspid Z-score, pulmonary Z-score, RV/LV length ratio, RV/LV diameter ratio, and the TV/MV ratio were significantly different in the group which had successful balloon dilation compared with that failed. Based on decision trees using the Weka classifier package, only RV/LV diameter ratio >0.76 predicts a 92.3% success rate. In contrast, an RV/LV diameter ratio < or =0.76 associated with RV/LV length ratio < or =0.70 predicts 100% failure. Successful balloon dilation in membranous type PA-IVS can be predicted by a scoring system using RV/LV diameter ratio and RV/LV length ratio.