Decision Tree Forest Research Articles

Application of the Acousto-ultrasonics technique to bridge cables in their anchorages.

The objective of this research is to evaluate the state of health of civil engineering cable structures using the acousto-ultrasonics method. More specifically, the element to be examined is the cable in its non-accessible part inside the anchor base. Cables in anchor caps are sensitive areas subject to various types of damage, such as water infiltration, which causes corrosion inside the anchor, or fretting fatigue. Such degradation cannot currently be assessed using NDT techniques. A number of challenges need to be overcome, including the complex geometry of the anchors, which limits the installation of sensors, the diversity of damage that may be present, the sensitivity to the defects being sought and the reproducibility of the measurements. Once the acoustic signals have been acquired, data analysis is crucial, requiring the use of unsupervised or supervised techniques such as principal component analysis, or more advanced techniques such as decision tree forests. These approaches aim to determine the state of health of anchor caps from the analysis of acoustic signals, providing a reliable diagnostic for the assessment of these parts of engineering structures. This development could have major implications for the preventive maintenance and sustainability of cable infrastructures, by giving us a reliable and accurate method for assessing cable state.

Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays

We present an interpretable implementation of the autoencoding algorithm, used as an anomaly detector, built with a forest of deep decision trees on FPGA, field programmable gate arrays. Scenarios at the Large Hadron Collider at CERN are considered, for which the autoencoder is trained using known physical processes of the Standard Model. The design is then deployed in real-time trigger systems for anomaly detection of unknown physical processes, such as the detection of rare exotic decays of the Higgs boson. The inference is made with a latency value of 30 ns at percent-level resource usage using the Xilinx Virtex UltraScale+ VU9P FPGA. Our method offers anomaly detection at low latency values for edge AI users with resource constraints.

Mining, refining, and QSAR analysing the nanoinformatics in EPA NaKnowBase.

Concerns about the safety of manufacturing and using engineered nanomaterials (ENMs) have been increasing as the technology continues to expand. Efforts have been underway to investigate the potentially harmful effects of ENMs without carrying out the challenging empirical studies. To make such investigations possible, the US EPA Office of Research and Development (ORD) developed the nanomaterial database NaKnowBase (NKB) containing the detail of hundreds of assays conducted and published by ORD scientists experimentally investigating the environmental health and safety effects of ENMs (nanoEHS). This article describes specifics of the effort to mine, refine, and analyse the NKB. Here we use a quantitative structure activity relationship (QSAR) analysis, using a random forest of decision trees to predict the in vitro cell viability effects that occur upon exposure to ENMs that are similar in composition and structure and implement a set of laboratory conditions. These predictions are confirmed using the Jaqpot cloud platform developed by the National Technical University of Athens, Greece (NTUA) where nanoEHS effects are investigated with scientists working together globally.

Wine quality analysis by the structural causal model (SCM)

Bayes network modelling for structural causal analysis between wine physicochemical data and quantitative human quality blind assessments is applied. The large dataset of white and red "Vinho Verde'' wine samples from Portugal, which was available from an open data repository for machine learning at the University of California at Irving, was analysed. The dataset contains 4898 white and 1599 red samples evaluated by blind tastes by a minimum of 3 sensory assessors and 12 physicochemical properties. The casual effects of wine analytic data on human quality evaluations are evaluated numerically by Bayes neural networks for adjusted sets of the covariates as marginal distributions and presented graphically as partial dependence plots. Structural causal analysis revealed important differences between the most important variables for quality predictions and the individual causal effects. Bayes neural network models of the partial dependencies show more pronounced nonlinear effects for red wines compared to white wine quality. The artificial intelligence models with boosted random decision tree forests for untrained wine samples yield a 5% relative standard error of predictions compared to 12% for the linear models and ordinary least squares estimation. For red wine, the most important direct causal quality effects are caused by alcohol, volatile acidity, and sulphates. Alcohol improves quality with a maximum plateau at 14%, while volatile acidity has a strong proportional negative effect. The effect of sulphates is highly nonlinear with maximum positive effect at a concentration of 1 g/L of K2SO4. For the white wine samples causal effects are linear with positive effects of alcohol and negative effects of volatile and fixed acidity. The developed structural causal model enables evaluation of targeted wine production interventions, named as “doing x, do(x) models”, as restructured adjusted Bayes networks. It leads to potential applications of artificial intelligence in wine production technology and process quality control.

Power Flow Control of the Grid-Integrated Hybrid DG System using an ARFMF Optimization

A power flow control scheme for a grid-integrated Hybrid DG System (HDGS) is presented in this work, utilizing an advanced random forest algorithm combined with the moth-flame optimization (ARFMF) approach. The proposed control scheme combines the random forest algorithm (RFA) and moth-flame optimization algorithm (MFO) for consolidated execution. The random forest algorithm (RFA), an AI technique, is well-suited for nonlinear systems due to its accurate interpolation and extrapolation capabilities. It is an ensemble learning method that combines multiple decision trees to make predictions. The algorithm constructs a forest of decision trees and aggregates their predictions to produce the final output. The moth-flame optimization (MFO) process is a meta-heuristic optimization procedure inspired by the transverse orientation of moths in nature. It improves initial random solutions and converges to superior positions in the search area. Similarly, the MFO is effective in nonlinear systems as it accurately interpolates and extrapolates arbitrary information. In the proposed technique, the RFA performs the calculation process to determine precise control gains for the HDGS through online implementation based on power variation between the source side and the load side. The recommended dataset is used to implement the AI approach for online execution, reducing optimization process time. The learning process of the RFA is guided by the MFO optimization algorithm. The MFO technique defines the objective function using system information based on equal and unequal constraints, including the accessibility of renewable energy sources, power demand, and state of charge (SOC) of storage systems. Storage devices such as batteries stabilize the energy generated by renewable energy systems to maintain a constant, stable output power. The proposed model is implemented on the MATLAB/Simulink platform, and its execution is compared to previous approaches.

Using Ensembles of Machine Learning Techniques to Predict Reference Evapotranspiration (ET0) Using Limited Meteorological Data

To maximize crop production, reference evapotranspiration (ET0) measurement is crucial for managing water resources and planning crop water needs. The FAO-PM56 method is recommended globally for estimating ET0 and evaluating alternative methods due to its extensive theoretical foundation. Numerous meteorological parameters, needed for ET0 estimation, are difficult to obtain in developing countries. Therefore, alternative ways to estimate ET0 using fewer climatic data are of critical importance. To estimate ET0 with alternative methods, difference climatic parameters of temperatures, relative humidity (maximum and minimum), sunshine hours, and wind speed for a period of 20 years from 1996 to 2015 were used in the study. The data were recorded by 11 meteorological observatories situated in various climatic regions of Pakistan. The significance of the climatic parameters used was evaluated using sensitivity analysis. The machine learning techniques of single decision tree (SDT), tree boost (TB) and decision tree forest (DTF) were used to perform sensitivity analysis. The outcomes indicated that DTF-based models estimated ET0 with higher accuracy and fewer climatic variables as compared to other ML techniques used in the study. The DTF technique, with Model 15 as input, outperformed other techniques for the most part of the performance metrics (i.e., NSE = 0.93, R2 = 0.96 and RMSE = 0.48 mm/month). The results indicated that the DTF with fewer climatic variables of mean relative humidity, wind speed and minimum temperature could estimate ET0 accurately and outperformed other ML techniques. Additionally, a non-linear ensemble (NLE) of ML techniques was further used to estimate ET0 using the best input combination (i.e., Model 15). It was seen that the applied non-linear ensemble (NLE) approach enhanced modelling accuracy as compared to a stand-alone application of ML techniques (R2 Multan = 0.97, R2 Skardu = 0.99, R2 ISB = 0.98, R2 Bahawalpur = 0.98 etc.). The study results affirmed the use of an ensemble model for ET0 estimation and suggest applying it in other parts of the world to validate model performance.

Parallel Multistage Wide Neural Network.

Deep learning networks have achieved great success in many areas, such as in large-scale image processing. They usually need large computing resources and time and process easy and hard samples inefficiently in the same way. Another undesirable problem is that the network generally needs to be retrained to learn new incoming data. Efforts have been made to reduce the computing resources and realize incremental learning by adjusting architectures, such as scalable effort classifiers, multi-grained cascade forest (gcForest), conditional deep learning (CDL), tree CNN, decision tree structure with knowledge transfer (ERDK), forest of decision trees with radial basis function (RBF) networks, and knowledge transfer (FDRK). In this article, a parallel multistage wide neural network (PMWNN) is presented. It is composed of multiple stages to classify different parts of data. First, a wide radial basis function (WRBF) network is designed to learn features efficiently in the wide direction. It can work on both vector and image instances and can be trained in one epoch using subsampling and least squares (LS). Second, successive stages of WRBF networks are combined to make up the PMWNN. Each stage focuses on the misclassified samples of the previous stage. It can stop growing at an early stage, and a stage can be added incrementally when new training data are acquired. Finally, the stages of the PMWNN can be tested in parallel, thus speeding up the testing process. To sum up, the proposed PMWNN network has the advantages of: 1) optimized computing resources; 2) incremental learning; and 3) parallel testing with stages. The experimental results with the MNIST data, a number of large hyperspectral remote sensing data, and different types of data in different application areas, including many image and nonimage datasets, show that the WRBF and PMWNN can work well on both image and nonimage data and have very competitive accuracy compared to learning models, such as stacked autoencoders, deep belief nets, support vector machine (SVM), multilayer perceptron (MLP), LeNet-5, RBF network, recently proposed CDL, broad learning, gcForest, ERDK, and FDRK.

Application of Pseudo-Random Numbers in System Design

The purpose of the article is to study and search for optimal strategies for modelling information systems using pseudo-random numbers to improve the performance of information systems and to determine the optimal parameters of random number distributions; to analyze efficient algorithms for generating pseudo-random numbers. The research methods are based on the application of a systematic approach to analyzing the benefits of using pseudorandom numbers in the design of information systems. Scientific novelty. The article analyses the advantages of stochastic modelling of information systems using different approaches to generating pseudorandom numbers, and for the first time considers the application of a random decision tree forest for modelling queuing systems. Conclusions. The application of pseudorandom numbers in system design is an urgent problem that requires further research and development of methods. The design of efficient algorithms for generating, validating, and using pseudorandom values plays an essential role in many fields of science and technology. This approach allows for optimization and planning in the process of designing the system and is essential for validating and testing the system. By generating random variables, you can create different test scenarios and check how the system reacts to various conditions, which helps to identify potential errors, flaws, and problems in the system and ensures the quality of the design. Thus, the use of pseudo-random numbers in system design allows for randomness, risk analysis, optimization and planning, validation, and testing. This is an important aspect of system development that helps to ensure their reliability, performance, and efficiency.

Partial Decision Tree Forest: A Machine Learning Model for the Geosciences

As a result of the continuous growth in the amount of geological data, machine learning (ML) offers an opportunity to contribute to solving problems in geosciences. However, digital geology applications introduce new challenges for machine learning due to the unique geoscience properties encountered in each problem, requiring novel research in ML. This paper proposes a novel machine learning method, entitled “Partial Decision Tree Forest (PART Forest)”, to overcome these challenges introduced by geoscience problems and offers potential advancements in both machine learning and geoscience disciplines. The effectiveness of the proposed PART Forest method was illustrated in mineral classification. This study aims to build an intelligent ML model that automatically classifies the minerals in terms of their crystal structures (triclinic, monoclinic, orthorhombic, tetragonal, hexagonal, and trigonal) by taking into account their chemical compositions and their physical and optical properties. In the experiments, the proposed PART Forest method demonstrated its superiority over one of the well-known ensemble learning methods, random forest, in terms of accuracy, precision, recall, f-score, and AUC (area under the curve) metrics.

Intercomparison and Assessment of Stand-Alone and Wavelet-Coupled Machine Learning Models for Simulating Rainfall-Runoff Process in Four Basins of Pothohar Region, Pakistan

The science of hydrological modeling has continuously evolved under the influence of rapid advancements in software and hardware technologies. Starting from simple rational formulae for estimating peak discharge and developing into sophisticated univariate predictive models, accurate conversion of rainfall into runoff and the assessment of inherent uncertainty has been a prime focus for researchers. Therefore, alternative data-driven methods have gained widespread attention in hydrology. Moreover, scientists often couple conventional machine learning models with data pre-processing techniques, i.e., wavelet transformation (WT), to enhance modelling accuracy. In this context, this research work attempts to explore the latent linkage between rainfall and runoff in Pothohar region of Pakistan by developing a novel linkage of five streamline techniques of machine learning, including single decision tree (SDT), decision tree forest (DTF), tree boost (TB), multilayer perceptron (MLP), and gene expression modeling (GEP), with a more sophisticated variant of WT, i.e., maximal overlap discrete wavelet transformation (MODWT), for boundary correction of the transformed components of timeseries data. This study also implements these machine learning models in a stand-alone mode for a more comprehensive comparative analysis of performances. Furthermore, the study uses a combined-basin approach that divides Pothohar region into two basins to compensate for the complex topographic division of the study area. The results indicate that MODWT-based DTF outperformed other stand-alone and hybrid models in terms of modeling accuracy. In the first scenario, considering the Bunha-Kahan River basin, MODWT-DTF yielded the highest NSE (0.86) and the lowest RMSE (220.45 mm) and R2 (0.92 at lag order 3 (Lo3)) when transformed with daubechies4 (db4) at level three. While in the Soan-Haro River basin, MODWT-DTF produced the highest accuracy modeling at lag order 4 (Lo4) (NSE = 0.88, RMSE = 21.72 m3/s, and R2 = 0.91). The highly accurate performance of 3- and 4-days lagged models reflects the temporal consistency in hydrological response of the study area. The comparison of simple and hybrid model performance indicates up to a 55% increase in modeling accuracy due to data pre-processing with wavelet transformation.

Detection of oil spills based on gray level co-occurrence matrix and support vector machine

Accurate reconnaissance of Marine oil spill is very important for emergency management of Marine oil spill accidents. Unmanned aerial vehicles (UAV) is a suitable carrier for offshore oil spill reconnaissance because of its fast deployment speed and low cost. Aiming at the identification accuracy of small oil spill accident in offshore port area and the problem of day and night reconnaissance, this study takes thermal infrared remote sensing images of oil leakage captured by UAV as the research object and proposes an oil spill detection method based on a Gray Level Co-occurrence Matrix (GLCM) and Support Vector Machine (SVM) method. Firstly, the extraction steps of image GLCM feature and the basic principle of SVM classification are studied. Then, the thermal infrared image data collected by UAV is preprocessed, including image filtering, clipping and rotation, and the sample database is generated. Subsequently, GLCM features of the samples were extracted, and the energy and correlation in GLCM were selected as classification features and sent to the SVM classifier to complete the oil spill detection of real-time thermal infrared images. The experimental results show that, compared with Classification and Regression Tree algorithm (CART) and Random Forests of Decision Trees (RF) algorithm, the detection accuracy of the method proposed in this paper reaches 95%, which were 10 and 2 percentage points higher than them respectively. The proposed method in this paper has fast recognition speed and high accuracy, and can provide all-weather recognition of oil spills for the detection of small oil spills in the offshore port area.

Ensembled Approach to Heterogeneous Data Streams

Principal component analysis-based decision tree forest (PDTF) can improve the variety in base classifiers while generating the forest of decision trees. All the trees in the forest have a very low correlation. In this research work, an algorithm is proposed to select the important features from the original data by applying them to the PDTF algorithm and then the selected features are used with long and short-term memory (LSTM) networks for improving the classification accuracy of heterogeneous data streams. This reduces the load on the active classification system and improves the per record classification time. In addition to thirty-five different datasets, Indian National stock exchange data feeds are used for experimentation. This real-time data feed is used as a base for calculating the values of twenty-five technical indicators. Technical indicators statistically forecast the market movement. Since the movement of stock is not only governed by its past values and it simply cannot be predicted with technical indicators alone. Therefore, heterogeneous data related to various domains that could probably impact the performance of the market is also considered. This approach is evaluated against the benchmark methods against a total of thirty-five datasets and livestock feeds and from the results, it is evident that this approach is better than previously used approaches.

Runoff Estimation Using Advanced Soft Computing Techniques: A Case Study of Mangla Watershed Pakistan

A precise rainfall-runoff prediction is crucial for hydrology and the management of water resources. Rainfall-runoff prediction is a nonlinear method influenced by simulation model inputs. Previously employed methods have some limitations in predicting rainfall-runoff, such as low learning speed, overfitting issues, stopping criteria, and back-propagation issues. Therefore, this study uses distinctive soft computing approaches to overcome these issues for modeling rainfall-runoff for the Mangla watershed in Pakistan. Rainfall-runoff data for 29 years from 1978–2007 is used in the study to estimate runoff. The soft computing approaches used in the study are Tree Boost (TB), decision tree forests (DTFs), and single decision trees (SDTs). Using various combinations of past rainfall datasets, these soft computing techniques are validated and tested for the security of efficient results. The evaluation criteria for the models are some statistical measures consisting of root means square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). The outcomes of these computing techniques were evaluated with the multilayer perceptron (MLP). DTF was found to be a more accurate soft computing approach with the average evaluation parameters R2, NSE, RMSE, and MAE being 0.9, 0.8, 1000, and 7000 cumecs. Regarding R2 and RMSE, there are about 57% and 17% of improvement in the results of DTF compared to other techniques. Flow duration curves (FDCs) were employed and revealed that DTF performed better than other techniques. This assessment revealed that DTF has potential; researchers may consider it an alternative approach for rainfall-runoff estimations in the Mangla watershed.

A hybrid approach for noise reduction-based optimal classifier using genetic algorithm: A case study in plant disease prediction

Plant diseases can cause significant losses to agricultural productivity; therefore, their early prediction is much needed. So far, many machine learning-based plant disease prediction models have been recommended, but these models face a problem of noisy class label dataset that degrades the performance. Noisy class label dataset results from the improper assignment of positive class labels into negative class data samples or vice versa. Hence, a precise and noise-free plant disease model is required for a better prediction. The current study proposes noise reduction-based hybridized classifiers for plant disease prediction. One tomato and four soybean disease datasets have been selected to conduct the proposed research. The Adaptive Sampling-based Class Label Noise Reduction (AS-CLNR) method has been used along with the Support Vector Machine (SVM) approach for noise reduction. The noise-minimized datasets have been fed into the Extreme Learning Machine (ELM), Decision Tree (DT), and Random Forest (RF) classifiers whose parameters are optimized using Genetic Algorithm (GA) for developing plant disease prediction models. The performances of all these models viz. Hybrid SVM-GA-ELM, Hybrid SVM-GA-DT, and Hybrid SVM-GA-RF have been evaluated using Accuracy, Area under ROC Curve, and F1-Score metrics. Further, these classifiers have been ranked using the statistical Friedman Test in which the Hybrid SVM-GA-RF classifier performed the best. Lastly, the Nemenyi test has also been performed to find out if significant differences exist between various classifiers or not. It was found that 33.33% of the total pairs of hybrid classifiers show a remarkably different performance from one another.

Detection of Credit Card Fraud Transactions using Machine Learning based Algorithm

The rapid growth in E-Commerce industry has lead to an exponential increase in the use of credit cards for online purchases and consequently they has been surge in the fraud related to it .In recent years, For banks has become very difficult for detecting the fraud in credit card system. Machine learning plays a vital role for detecting the credit card fraud in the transactions. For predicting these transactions banks make use of various machine learning methodologies, past data has been collected and new features are been used for enhancing the predictive power. The performance of fraud detecting in credit card transactions is greatly affected by the sampling approach on data-set, selection of variables and detection techniques used. This paper investigates the performance of SVM, decision tree and random forest for credit card fraud detection. Dataset of credit card transactions is collected from kaggle and it contains a total of 2,84,808 credit card transactions of a European bank data set. It considers fraud transactions as the “positive class” and genuine ones as the “negative class” .The data set is highly imbalanced, it has about 0.172% of fraud transactions and the rest are genuine transactions. The author has been done oversampling to balance the data set, which resulted in 60% of fraud transactions and 40% genuine ones. The three techniques are applied for the dataset and work is implemented in R language. The performance of the techniques is evaluated for different variables based on sensitivity, specificity, accuracy and error rate. The result shows of accuracy for SVM, Decision tree and random forest classifier are 90.0, 94.3, 95.5 respectively. The comparative results show that the Random forest performs better than the SVM and decision tree techniques.

Analysis of risk factors associated with acute respiratory infections among under-five children in Uganda

BackgroundGlobally, infectious diseases are the major cause of death in children under the age of 5 years. Sub-Saharan Africa and South Asia account for 95% of global child mortalities every year, where acute respiratory infections (ARI) remain the leading cause of child morbidity and mortality. The aim of this study is to analyze the risk factors of ARI disease symptoms among children under the age of 5 years in Uganda.MethodsA cross-sectional design was used to analyze 2016 Uganda Demographic and Health Survey (UDHS) data collected on 13,493 children under the age of 5 years in Uganda. Various methods, such as logistic regression, elastic net logistic regression, decision tree, and random forest, were compared and used to predict 75% of the symptom outcomes of ARI disease. Well-performing methods were used to determine potential risk factors for ARI disease symptoms among children under the age of 5 years.ResultsIn Uganda, about 40.3% of children were reported to have ARI disease symptoms in the 2 weeks preceding the survey. Children under the age of 24 months were found to have a high prevalence of ARI disease symptoms. By considering 75% of the sample, the random forest was found to be a well-performing method (accuracy = 88.7%; AUC = 0.951) compared to the logistic regression method (accuracy = 62.0%; AUC = 0.638) and other methods in predicting childhood ARI symptoms. In addition, one-year old children (OR: 1.27; 95% CI: 1.12–1.44), children whose mothers were teenagers (OR: 1.28; 95% CI: 1.06–1.53), and farm workers (1.25; 95% CI: 1.11–1.42) were most likely to have ARI disease symptoms than other categories. Furthermore, children aged 48–59 months (OR: 0.69; 95% CI: 0.60–0.80), breastfed children (OR: 0.83; 95% CI: 0.76–0.92), usage of charcoal in cooking (OR: 0.77; 95% CI: 0.69–0.87), and the rainy season effect (OR: 0.66; 95% CI: 0.61–0.72) showed a low risk of developing ARI disease symptoms among children under the age of 5 years in Uganda.ConclusionPolicy-makers and health stakeholders should initiate target-oriented approaches to address the problem regarding poor children’s healthcare, improper environmental conditions, and childcare facilities. For the sake of early child care, the government should promote child breastfeeding and maternal education.

Disease Prediction Based on Symptoms By Using Decision Tree And Random Forest In Machine Learning

The medical care space is one of the unmistakable examination fields in the ongoing situation with the fast improvement of innovation and information. Dealing with the colossal measure of information of the patients is troublesome. Taking care of this information through Big Data Analytics is simpler. There are a ton of methodology for the treatment of different infections across the world. AI is an arising approach that aides in expectation, determination of an illness. This venture portrays the expectation of illness in light of side effects utilizing AI. AI calculations, for example, Support Vector Machine, Decision Tree and Random Forest are utilized on the gave dataset and anticipate the sickness. Its execution is finished through the python programming language. The task exhibits the best calculation in light of their exactness. The exactness of a not entirely set in stone by the presentation on the given dataset.

Diabetes mellitus prediction: An efficient pipeline of data imputation and oversampling

Diabetes is a chronic disease which indicates the high level of body glucose level. As per the World Health Organization (WHO), 422 million people were diabetic until 2014. This paper develops an accurate classification machine learning model and an efficient usage of data pre-processing pipeline to improve overall accuracy. For the purpose, six algorithms: Support Vector Machine with Linear kernel (Linear-SVM), Support Vector Machine with RBF kernel (RBF-SVM), K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Decision Tree and Random Forest are used for classification purpose and their comparative accuracy is analyzed. Data Imputation, Oversampling and Feature scaling techniques are the constituents of Data preprocessing pipeline. Experiments are performed on a well-known dataset of National Institute of Diabetes and Digestive and Kidney Diseases, the PIMA diabetes dataset. The data preprocessing techniques, data imputation and Synthetic Minority Oversample Technique (SMOTE) analysis improved classification accuracy from 77% on raw data, to 88.12% (on Random Forest Classifier) and 91% (on ANN Classifier), respectively. Furthermore, a new feature generation approach is applied and performance is analyzed using the SVM model. Original data attributes BMI and Insulin are replaced with new features BMI_NORMAL and INSULIN_NORMAL, respectively. The significant improvement by proposed technique is confirmed by statistical testing followed by post-hoc analysis.

Machine learning-based authorship attribution using token n-grams and other time tested features

Authorship Attribution is a process to determine and/or identify the author of a given text document. The relevance of this research area comes to the fore when two or more writers claim to be the prospective authors of an unidentified or anonymous text document or are unwilling to accept any authorship. This research work aims to utilize various Machine Learning techniques in order to solve the problem of author identification. In the proposed approach, a number of textual features such as Token n-grams, Stylometric features, bag-of-words and TF-IDF have been extracted. Experimentation has been performed on three datasets viz. Spooky Author Identification dataset, Reuter_50_50 dataset and Manual dataset with 3 different train-test split ratios viz. 80-20, 70-30 and 66.67-33.33. Models have been built and tested with supervised learning algorithms such as Naive Bayes, Support Vector Machine, K-Nearest Neighbor, Decision Tree and Random Forest. The proposed system yields promising results. For the Spooky dataset, the best accuracy score obtained is 84.14% with bag-of-words using Naïve Bayes classifier. The best accuracy score of 86.2% is computed for the Reuter_50_50 dataset with 2100 most frequent words when the classifier used is Support Vector Machine. For the Manual dataset, the best score of 96.67% is obtained using the Naïve Bayes Classification Model with both 5-fold and 10-fold cross validation when both syntactic features and 600 most frequent unigrams are used in combination.

Evaluating the Effectiveness of Complexity Features of Eye Movement on Computer Activities Detection.

Recently, tools developed for detecting human activities have been quite prominent in contributing to health issue prevention and long-term healthcare. For this occasion, the current study aimed to evaluate the performance of eye-movement complexity features (from multi-scale entropy analysis) compared to eye-movement conventional features (from basic statistical measurements) on detecting daily computer activities, comprising reading an English scientific paper, watching an English movie-trailer video, and typing English sentences. A total of 150 students participated in these computer activities. The participants’ eye movements were captured using a desktop eye-tracker (GP3 HD Gazepoint™ Canada) while performing the experimental tasks. The collected eye-movement data were then processed to obtain 56 conventional and 550 complexity features of eye movement. A statistic test, analysis of variance (ANOVA), was performed to screen these features, which resulted in 45 conventional and 379 complexity features. These eye-movement features with four combinations were used to build 12 AI models using Support Vector Machine, Decision Tree, and Random Forest (RF). The comparisons of the models showed the superiority of complexity features (85.34% of accuracy) compared to conventional features (66.98% of accuracy). Furthermore, screening eye-movement features using ANOVA enhances 2.29% of recognition accuracy. This study proves the superiority of eye-movement complexity features.