In this paper, we propose an intrusion detection dataset for nuclear power plant systems, which consists of processed and labeled network traffic data collected from real nuclear power plant systems. Through Pearson c...
详细信息
The role of consumer shopping demand in the operation forecast of e-commerce platforms is very important, but there is the problem of incomplete data estimation. The k-NN nearest neighbor algorithm cannot accurately p...
详细信息
machinelearning models, ubiquitous in domains like natural language processing and image recognition, are vulnerable to adversarial poisoning attacks, where malicious actors manipulate training data to induce erroneo...
详细信息
Consumer shopping behavior is changing due to the explosive growth of e-commerce, which brings both benefits and challenges. E-commerce enterprises must comprehend the shopping behavior of their clients to enhance use...
详细信息
The peripheral psychophysiological signals (EMG, ECG and GSR) of 13 participants were recorded in the well planned Cognition and Robotics lab at BTH University and 9 participants data were taken for further processing...
详细信息
The peripheral psychophysiological signals (EMG, ECG and GSR) of 13 participants were recorded in the well planned Cognition and Robotics lab at BTH University and 9 participants data were taken for further processing. Thirty(30) pictures of IAPS were shown to each participant individually as stimuli, and each picture was displayed for five- second intervals. Signal preprocessing, feature extraction and selection, models, datasets formation and data analysis and interpretation were done. The correlation between a combination of EMG, ECG and GSR signal and emotional states were investigated. 2- Dimensional valence-arousal model was used to represent emotional states. Finally, accuracy comparisons among selected machinelearning classification algorithms have performed. Context: Psychophysiological measurement is one of the recent and popular ways to identify emotions when using computers or robots. It can be done using peripheral signals: Electromyography (EMG), Electrocardiography (ECG) and Galvanic Skin Response (GSR). The signals from these measurements are considered as reliable signals and can produce the required data. It is further carried out by preprocessing of data, feature selection and classification. Classification of EMG, ECG and GSR data can be conducted with appropriate machine learning algorithms for better accuracy results. Objectives: In this study, we investigate and analyzed with psychophysiological (EMG, ECG and GSR) data to find best classifier algorithm. Our main objective is to classify those data with appropriate machinelearning techniques. Classifications of psychophysiological data are useful in emotion recognition. Therefore, our ultimate goal is to provide validated classified psychological measures for the automated adoption of human robot performance. Methods: We conducted a literature review in order to answer RQ1. The sources used are Inspec/ Compendex, IEEE, ACM Digital Library, Google Scholar and Springer Link. This helps us to id
The classification of protein sequences is a subfield in the area of Bioinformatics that attracts a substantial interest today. machine learning algorithms are here believed to be able to improve the performance of th...
详细信息
The classification of protein sequences is a subfield in the area of Bioinformatics that attracts a substantial interest today. machine learning algorithms are here believed to be able to improve the performance of the classification phase. This thesis considers the application of different machine learning algorithms to the classification problem of a data set of short-chain dehydrogenases/reductases (SDR) proteins. The classification concerns both the division of the proteins into the two main families, Classic and Extended, and into their different sub- families. The results of the different algorithms are compared to select the most appropriate algorithm for this particular classification problem.
Due to the existence of a double-sided asymmetric information problem on the labour marketcharacterized by a mutual lack of trust by employers and unemployed people, not enough job matchesare facilitated by public emp...
详细信息
Due to the existence of a double-sided asymmetric information problem on the labour marketcharacterized by a mutual lack of trust by employers and unemployed people, not enough job matchesare facilitated by public employment services (PES), which seem to be caught in a low-end equilibrium. In order to act as a reliable third party, PES need to build a good and solid reputation among their mainclients by offering better and less time consuming pre-selection services. The use of machine-learning, data-driven relevancy algorithms that calculate the viability of a specific candidate for a particular jobopening is becoming increasingly popular in this field. Based on the Portuguese PES databases (CVs, vacancies, pre-selection and matching results), complemented by relevant external data published byStatistics Portugal and the European Classification of Skills/Competences, Qualifications andOccupations (ESCO), the current thesis evaluates the potential application of models such as RandomForests, Gradient Boosting, Support Vector machines, Neural Networks Ensembles and other tree-basedensembles to the job matching activities that are carried out by the Portuguese PES, in order tounderstand the extent to which the latter can be improved through the adoption of automatedprocesses. The obtained results seem promising and point to the possible use of robust algorithms suchas Random Forests within the pre-selection of suitable candidates, due to their advantages at variouslevels, namely in terms of accuracy, capacity to handle large datasets with thousands of variables, including badly unbalanced ones, as well as extensive missing values and many-valued categoricalvariables.
The current Ethiopian market is conducted in a traditional manner and market drivers are still not used for prediction of future market price. Although, large amount of market data have been gathered throughout years ...
详细信息
The current Ethiopian market is conducted in a traditional manner and market drivers are still not used for prediction of future market price. Although, large amount of market data have been gathered throughout years by both governmental and non-governmental organizations, yet little have been done to analyze the data for future market price prediction. Moreover, the analysis methods were often manual creating inefficiency in time and quality of market prediction. Analyzing valuable data will show us what the future holds and accelerate the development goals of the country in the sector. The study examines features of current Ethiopian market attributes to find out most valuable features for predicting market price. Eighteen technical indicators are taken and tested for their individual ability of prediction and redundancy. From the feature selection of commodity marke, we have found that features like Stochastic %K, Stochastic %D, Close gain/loss, High, close price, Opening Price, Low, RSI, Ton and Moving Average Convergence/ divergence (MACD) founded to be in the top ten of individual performance evaluation. Moreover features namely Stochastic %K, Relative Strength Index (RSI), Bollinger Bands-Upper, Highest-High, close gain/loss, Simple Moving Average (SMA), Closing price, MACD-Fast, Exponential Moving Average (EMA), MACD-Slow and Low founded to be less redundant. The study also compares four machinelearning models for their prediction ability of Ethiopian commodity market price. The outcomes of feature selection were used to compare the models. Two experiments were conducted; the first was comparison of the models with 10 fold cross validation using feature of high individual predictive ability and less redundancy. The second one was a comparison of models with separate train and test data using features of high individual predictive ability and less redundancy. From the models (Support Vector machine (SVM), Artificial Neural Network (ANN), K-Nearest Neighbor (
In this paper, we introduce an experiment evaluating performance of football players in countermovement jumps (CMJs). Three methods including time domain, frequency domain, and machine learning algorithms are proposed...
详细信息
ISBN:
(纸本)9781538636749
In this paper, we introduce an experiment evaluating performance of football players in countermovement jumps (CMJs). Three methods including time domain, frequency domain, and machine learning algorithms are proposed for performance evaluation. Correlation coefficients and p-values are given for time domain and frequency domain methods, and prediction errors are given for different machine learning algorithms.
This work focuses on developing an electronic nose system with machinelearning algorithm for detection of trimethylamine (TMA). Pure and Ga-doped In2O3 nanotubes are synthesized by a simple electrospinning method, an...
详细信息
ISBN:
(纸本)9780738124292
This work focuses on developing an electronic nose system with machinelearning algorithm for detection of trimethylamine (TMA). Pure and Ga-doped In2O3 nanotubes are synthesized by a simple electrospinning method, and four kinds of gas sensors (pristine, 1% Ga, 10% Ga, and 20% Ga-doped In2O3) are fabricated to form a sensor array. Results show that the sensor array can classify TMA effectively from interference gases (xylene, ethanol, hydrogen sulfide) by a support vector machine (SVM) algorithm. Several algorithms, including radial basis function neural network (RBFNN), back propagation neural network (BPNN) and principal component analysis combined with linear regression (PCA-LR), are used to predict the concentration level of each gas. For TMA gas, the trained algorithms can predict its concentration with average relative errors of 1.22% for RBFNN, 2.5% for BPNN and 13.34% for PCA-LR. Furthermore, the binary mixtures of TMA and ethanol are measured and used to train the above algorithms, and the lowest average relative error of 1.74% is achieved in the case of RBFNN algorithm.
暂无评论