Comparison of Resampling Techniques for Imbalanced Datasets in Machine Learning: Application to Epileptogenic Zone Localization From Interictal Intracranial EEG Recordings in Patients With Focal Epilepsy

Aim: In neuroscience research, data are quite often characterized by an imbalanced distribution between the majority and minority classes, an issue that can limit or even worsen the prediction performance of machine learning methods. Different resampling procedures have been developed to face this problem and a lot of work has been done in comparing their effectiveness in different scenarios. Notably, the robustness of such techniques has been tested among a wide variety of different datasets, without considering the performance of each specific dataset. In this study, we compare the performances of different resampling procedures for the imbalanced domain in stereo-electroencephalography (SEEG) recordings of the patients with focal epilepsies who underwent surgery.Methods: We considered data obtained by network analysis of interictal SEEG recorded from 10 patients with drug-resistant focal epilepsies, for a supervised classification problem aimed at distinguishing between the epileptogenic and non-epileptogenic brain regions in interictal conditions. We investigated the effectiveness of five oversampling and five undersampling procedures, using 10 different machine learning classifiers. Moreover, six specific ensemble methods for the imbalanced domain were also tested. To compare the performances, Area under the ROC curve (AUC), F-measure, Geometric Mean, and Balanced Accuracy were considered.Results: Both the resampling procedures showed improved performances with respect to the original dataset. The oversampling procedure was found to be more sensitive to the type of classification method employed, with Adaptive Synthetic Sampling (ADASYN) exhibiting the best performances. All the undersampling approaches were more robust than the oversampling among the different classifiers, with Random Undersampling (RUS) exhibiting the best performance despite being the simplest and most basic classification method.Conclusions: The application of machine learning techniques that take into consideration the balance of features by resampling is beneficial and leads to more accurate localization of the epileptogenic zone from interictal periods. In addition, our results highlight the importance of the type of classification method that must be used together with the resampling to maximize the benefit to the outcome.

Download Full-text

Localizing Epileptogenic Zone from High Density EEG Data Using Machine Learning

International Journal of Online and Biomedical Engineering (iJOE) ◽

10.3991/ijoe.v17i06.18653 ◽

2021 ◽

Vol 17 (06) ◽

pp. 73

Author(s):

Sehresh Khan ◽

Aunsia Khan ◽

Nazia Hameed ◽

Muhammad Aleem Taufiq ◽

Saba Riaz

Keyword(s):

Machine Learning ◽

Human Brain ◽

Antiepileptic Drugs ◽

Focal Epilepsy ◽

Brain Regions ◽

High Density ◽

Machine Learning Algorithms ◽

Epileptogenic Zone ◽

Drug Resistant ◽

Time Frequency

Drug-resistant focal epilepsy is the failure of antiepileptic drugs scheduled to obtain epileptic free brain activities. In human brain, cerebral hemispheres are the most commonly involved brain regions in epilepsy. In case of antiepileptic drugs failure, surgical treatment is the best cure possible. However, correct localization of epileptogenic region is a challenging task for neurologists, while for computer scientists, automatic localization is. This research work’s aim is to explore the functional activities of all brain regions in drug-resistant focal epileptic patients and achieve high accuracy for the classification of epileptogenic region (ER) with the high-density electroencephalographic (hdEEG) data. The proposed system includes frequency analysis for feature extractions followed by individual subject’s registration of hdEEG signals with anatomical brain images for most precise localization of ER possible. The datasets attained from feature extraction process are then preprocessed for class imbalanced and then evaluated using different machine learning algorithms including the techniques under Bayesian networks, Lazy networks, Meta techniques, Rule based systems and Tree structured algorithms. Considering human brain as stationary object as well as dynamic object, frequency-based and time-frequency based features were considered in 12 subjects respectively. Through this novel approach, 99.70% accuracy is achieved to classify ER from healthy regions using KSTAR and using IBK algorithm, 91.60% accuracy has been achieved to classify generator from propagator.

Download Full-text

Comparative Study of Machine Learning Algorithms on Prediction of Diabetes Mellitus Disease

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2020.8651 ◽

2020 ◽

Vol 17 (1) ◽

pp. 201-205

Author(s):

Gina George ◽

Anisha M. Lal ◽

P. Gayathri ◽

Niveditha Mahendran

Keyword(s):

Diabetes Mellitus ◽

Machine Learning ◽

Learning Algorithms ◽

Ensemble Methods ◽

Classification Problem ◽

Disease Diagnosis ◽

The Body ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Related Data

Diabetes Mellitus disease is said to occur when there is not proper generation of insulin in the body which is needed for proper regulation of glucose in the body. This health disorder leads to whole degradation of several organs including the heart, kidneys, eyes, nerves. Hence diabetes disease diagnosis by means of accurate prediction is vital. When such disease related data is given as input to several machine learning techniques it becomes an important classification problem. The purpose of the work done in this paper is to compare several classic machine learning algorithms including decision tree, logistic regression and ensemble methods to identify the more accurate classification algorithm for better prediction of the diabetes mellitus disease. This in turn would help for better and effective treatment.

Download Full-text

Comparison of Machine Learning Techniques Powering Flood Early Warning Systems. Application to a catchment located in the Tropical Andes of Ecuador.

10.5194/egusphere-egu2020-4243 ◽

2020 ◽

Author(s):

Paul Munoz ◽

Johanna Orellana-Alvear ◽

Jörg Bendix ◽

Rolando Célleri

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Early Warning ◽

Lead Time ◽

Geometric Mean ◽

Classification Problem ◽

Early Warning Systems ◽

Machine Learning Techniques ◽

Warning Systems ◽

Tropical Andes

Flood Early Warning Systems have globally become an effective tool to mitigate the adverse effects of this natural hazard on society, economy and environment. A novel approach for such systems is to actually forecast flood events rather than merely monitoring the catchment hydrograph evolution on its way to an inundation site. A wide variety of modelling approaches, from fully-physical to data-driven, have been developed depending on the availability of information describing intrinsic catchment characteristics. However, during last decades, the use of Machine Learning techniques has remarkably gained popularity due to its power to forecast floods at a minimum of demanded data and computational cost. Here, we selected the algorithms most commonly employed for flood prediction (K-nearest Neighbors, Logistic Regression, Random Forest, Na&#239;ve Bayes and Neural Networks), and used them in a precipitation-runoff classification problem aimed to forecast the inundation state of a river at a decisive control station. These are &#8220;No-alert&#8221;, &#8220;Pre-alert&#8221;, and &#8220;Alert&#8221; of inundation with varying lead times of 1, 4, 8 and 12 hours. The study site is a 300-km2 catchment in the tropical Andes draining to Cuenca, the third most populated city of Ecuador. Cuenca is susceptible to annual floods, and thus, the generated alerts will be used by local authorities to inform the population on upcoming flood risks. For an integral comparison between forecasting models, we propose a scheme relying on the F1-score, the Geometric mean and the Log-loss score to account for the resulting data imbalance and the multiclass classification problem. Furthermore, we used the Chi-Squared test to ensure that differences in model results were due to the algorithm applied and not due to statistical chance. We reveal that the most effective model according to the F1-score is using the Neural Networks technique (0.78, 0.62, 0.51 and 0.46 for the test subsets of the 1, 4, 8 and 12-hour forecasting scenarios, respectively), followed by the Logistic Regression algorithm. For the remaining algorithms, we found F1-score differences between the best and the worse model inversely proportional to the lead time (i.e., differences between models were more pronounced for shorter lead times). Moreover, the Geometric mean and the Log-log score showed similar patterns of degradation of the forecast ability with lead time for all algorithms. The overall higher scores found for the Neural Networks technique suggest this algorithm as the engine for the best forecasting Early Warning Systems of the city. For future research, we recommend further analyses on the effect of input data composition and on the architecture of the algorithm for full exploitation of its capacity, which would lead to an improvement of model performance and an extension of the lead time. The usability and effectiveness of the developed systems will depend, however, on the speed of communication to the public after an inundation signal is indicated. We suggest to complement our systems with a website and/or mobile application as a tool to boost the preparedness against floods for both decision makers and the public.Keywords: Flood; forecasting; Early Warning; Machine Learning; Tropical Andes; Ecuador.

Download Full-text

Brain Activity-Based Metrics for Assessing Learning States in VR under Stress among Firefighters: An Explorative Machine Learning Approach in Neuroergonomics

Brain Sciences ◽

10.3390/brainsci11070885 ◽

2021 ◽

Vol 11 (7) ◽

pp. 885

Author(s):

Maher Abujelala ◽

Rohith Karthikeyan ◽

Oshin Tyagi ◽

Jing Du ◽

Ranjana K. Mehta

Keyword(s):

Machine Learning ◽

Environmental Conditions ◽

Brain Activity ◽

Memory Task ◽

Classification Problem ◽

Brain Regions ◽

Training Data ◽

Information Encoding ◽

Machine Learning Approach ◽

Encoding And Retrieval

The nature of firefighters` duties requires them to work for long periods under unfavorable conditions. To perform their jobs effectively, they are required to endure long hours of extensive, stressful training. Creating such training environments is very expensive and it is difficult to guarantee trainees’ safety. In this study, firefighters are trained in a virtual environment that includes virtual perturbations such as fires, alarms, and smoke. The objective of this paper is to use machine learning methods to discern encoding and retrieval states in firefighters during a visuospatial episodic memory task and explore which regions of the brain provide suitable signals to solve this classification problem. Our results show that the Random Forest algorithm could be used to distinguish between information encoding and retrieval using features extracted from fNIRS data. Our algorithm achieved an F-1 score of 0.844 and an accuracy of 79.10% if the training and testing data are obtained at similar environmental conditions. However, the algorithm’s performance dropped to an F-1 score of 0.723 and accuracy of 60.61% when evaluated on data collected under different environmental conditions than the training data. We also found that if the training and evaluation data were recorded under the same environmental conditions, the RPM, LDLPFC, RDLPFC were the most relevant brain regions under non-stressful, stressful, and a mix of stressful and non-stressful conditions, respectively.

Download Full-text

Stock Market Prediction Using Machine Learning Techniques: A Decade Survey on Methodologies, Recent Developments, and Future Directions

Electronics ◽

10.3390/electronics10212717 ◽

2021 ◽

Vol 10 (21) ◽

pp. 2717

Author(s):

Nusrat Rouf ◽

Majid Bashir Malik ◽

Tasleem Arif ◽

Sparsh Sharma ◽

Saurabh Singh ◽

...

Keyword(s):

Machine Learning ◽

Stock Market ◽

Digital Libraries ◽

Stock Price ◽

Ensemble Methods ◽

Machine Learning Techniques ◽

Learning Approaches ◽

Stock Market Prediction ◽

Research Areas ◽

Recent Developments

With the advent of technological marvels like global digitization, the prediction of the stock market has entered a technologically advanced era, revamping the old model of trading. With the ceaseless increase in market capitalization, stock trading has become a center of investment for many financial investors. Many analysts and researchers have developed tools and techniques that predict stock price movements and help investors in proper decision-making. Advanced trading models enable researchers to predict the market using non-traditional textual data from social platforms. The application of advanced machine learning approaches such as text data analytics and ensemble methods have greatly increased the prediction accuracies. Meanwhile, the analysis and prediction of stock markets continue to be one of the most challenging research areas due to dynamic, erratic, and chaotic data. This study explains the systematics of machine learning-based approaches for stock market prediction based on the deployment of a generic framework. Findings from the last decade (2011–2021) were critically analyzed, having been retrieved from online digital libraries and databases like ACM digital library and Scopus. Furthermore, an extensive comparative analysis was carried out to identify the direction of significance. The study would be helpful for emerging researchers to understand the basics and advancements of this emerging area, and thus carry-on further research in promising directions.

Download Full-text

Analysis of Kinase Inhibitors and Druggability of Kinase-Targets Using Machine Learning Techniques

Pattern Discovery Using Sequence Data Mining ◽

10.4018/978-1-61350-056-9.ch009 ◽

2012 ◽

pp. 155-165

Author(s):

S. Prasanthi ◽

S.Durga Bhavani ◽

T. Sobha Rani ◽

Raju S. Bapi

Keyword(s):

Machine Learning ◽

Decision Tree ◽

Kinase Inhibitors ◽

Kinase Inhibitor ◽

Classification Problem ◽

Machine Learning Techniques ◽

Learning Approaches ◽

Decision Tree Classifier ◽

Data Set ◽

Learning Techniques

Vast majority of successful drugs or inhibitors achieve their activity by binding to, and modifying the activity of a protein leading to the concept of druggability. A target protein is druggable if it has the potential to bind the drug-like molecules. Hence kinase inhibitors need to be studied to understand the specificity of a kinase inhibitor in choosing a particular kinase target. In this paper we focus on human kinase drug target sequences since kinases are known to be potential drug targets. Also we do a preliminary analysis of kinase inhibitors in order to study the problem in the protein-ligand space in future. The identification of druggable kinases is treated as a classification problem in which druggable kinases are taken as positive data set and non-druggable kinases are chosen as negative data set. The classification problem is addressed using machine learning techniques like support vector machine (SVM) and decision tree (DT) and using sequence-specific features. One of the challenges of this classification problem is due to the unbalanced data with only 48 druggable kinases available against 509 non-drugggable kinases present at Uniprot. The accuracy of the decision tree classifier obtained is 57.65 which is not satisfactory. A two-tier architecture of decision trees is carefully designed such that recognition on the non-druggable dataset also gets improved. Thus the overall model is shown to achieve a final performance accuracy of 88.37. To the best of our knowledge, kinase druggability prediction using machine learning approaches has not been reported in literature.

Download Full-text

Predicting Takeover Success Using Machine Learning Techniques

Journal of Business & Economics Research (JBER) ◽

10.19030/jber.v10i10.7264 ◽

2012 ◽

Vol 10 (10) ◽

pp. 547

Author(s):

Mei Zhang ◽

Gregory Johnson ◽

Jia Wang

Keyword(s):

Machine Learning ◽

Learning Community ◽

Binary Classification ◽

Classification Problem ◽

Machine Learning Techniques ◽

Success Prediction ◽

Support Vector ◽

Font Size ◽

Network Support ◽

Learning Techniques

A takeover success prediction model aims at predicting the probability that a takeover attempt will succeed by using publicly available information at the time of the announcement. We perform a thorough study using machine learning techniques to predict takeover success. Specifically, we model takeover success prediction as a binary classification problem, which has been widely studied in the machine learning community. Motivated by the recent advance in machine learning, we empirically evaluate and analyze many state-of-the-art classifiers, including logistic regression, artificial neural network, support vector machines with different kernels, decision trees, random forest, and Adaboost. The experiments validate the effectiveness of applying machine learning in takeover success prediction, and we found that the support vector machine with linear kernel and the Adaboost with stump weak classifiers perform the best for the task. The result is consistent with the general observations of these two approaches.

Download Full-text

A Hybrid Meta-Learner Technique for Credit Scoring of Banks’ Customers

Engineering, Technology & Applied Science Research ◽

10.48084/etasr.1361 ◽

2017 ◽

Vol 7 (5) ◽

pp. 2073-2082 ◽

Cited By ~ 1

Author(s):

A. G. Armaki ◽

M. F. Fallah ◽

M. Alborzi ◽

A. Mohammadzadeh

Keyword(s):

Machine Learning ◽

Hybrid Model ◽

Credit Scoring ◽

Clustering Algorithms ◽

Real Life ◽

Ensemble Methods ◽

Scoring Systems ◽

Error Rates ◽

Machine Learning Algorithms ◽

Machine Learning Techniques

Financial institutions are exposed to credit risk due to issuance of consumer loans. Thus, developing reliable credit scoring systems is very crucial for them. Since, machine learning techniques have demonstrated their applicability and merit, they have been extensively used in credit scoring literature. Recent studies concentrating on hybrid models through merging various machine learning algorithms have revealed compelling results. There are two types of hybridization methods namely traditional and ensemble methods. This study combines both of them and comes up with a hybrid meta-learner model. The structure of the model is based on the traditional hybrid model of ‘classification + clustering’ in which the stacking ensemble method is employed in the classification part. Moreover, this paper compares several versions of the proposed hybrid model by using various combinations of classification and clustering algorithms. Hence, it helps us to identify which hybrid model can achieve the best performance for credit scoring purposes. Using four real-life credit datasets, the experimental results show that the model of (KNN-NN-SVMPSO)-(DL)-(DBSCAN) delivers the highest prediction accuracy and the lowest error rates.

Download Full-text

Data Analytics: Intelligent Anti-Phishing Techniques Based on Machine Learning

Journal of Information & Knowledge Management ◽

10.1142/s0219649219500059 ◽

2019 ◽

Vol 18 (01) ◽

pp. 1950005 ◽

Cited By ~ 1

Author(s):

Said Baadel ◽

Joan Lu

Keyword(s):

Machine Learning ◽

Computer Security ◽

Work Group ◽

Classification Problem ◽

Machine Learning Techniques ◽

Network Dynamic ◽

Phishing Attacks ◽

Learning Techniques ◽

Neural Network Dynamic ◽

International Body

According to the international body Anti-Phishing Work Group (APWG), phishing activities have skyrocketed in the last few years and more online users are becoming susceptible to phishing attacks and scams. While many online users are vulnerable and naive to the phishing attacks, playing catch-up to the phishers’ evolving strategies is not an option. Machine Learning techniques play a significant role in developing effective anti-phishing models. This paper looks at phishing as a classification problem and outlines some of the recent intelligent machine learning techniques (associative classifications, dynamic self-structuring neural network, dynamic rule-induction, etc.) in the literature that is used as anti-phishing models. The purpose of this review is to serve researchers, organisations’ managers, computer security experts, lecturers, and students who are interested in understanding phishing and its corresponding intelligent solutions. This will equip individuals with knowledge and skills that may prevent phishing on a wider context within the community.

Download Full-text