Search

A critical aspect of software engineering is Software fault prediction which aims to identify and prevent errors in software systems before their release which can cause failures or issues for its users. Various techniques and tools have been developed to detect software faults, including static code analysis, dynamic testing, and machine learning-based approaches. In past few years, the world has seen a growing interest in the use of ML models for predicting software faults, as they can effectively analyse high dimensional datasets and detect complex patterns which are difficult for human experts to detect. However, developing accurate and reliable software fault detection models requires careful selection of data, feature engineering, and model evaluation. This purpose of this paper is to present a comprehensive analysis of potential applications and future research directions in the field of software fault detection. The study emphasizes the importance of identifying and addressing software faults to ensure the reliability and efficiency of software systems. Additionally, the paper outlines various approaches and techniques that can be employed for effective software fault detection. [ABSTRACT FROM AUTHOR]

One of the most dangerous threats in WSNs is botnet attacks, in which attackers use mutual communications between IoT devices to launch large-scale malicious activities. In this regard, developments in the field of effective and reliable means of defence against this type of threat, in particular, reliable methods for detecting, identifying, and countering botnet attacks, are becoming increasingly important and relevant. This paper presents a comprehensive study that applies machine learning techniques, namely Random Forest and XGBoost, to identify botnet attacks on IoT effectively. These algorithms are analyzed, compared, and shown to be highly effective in detecting complex patterns indicative of botnet activity, thus achieving a significant improvement in IoT security. The conducted research aims to make a useful contribution to the problem of securing WSNs and IoT in general. The results of the study demonstrated high accuracy in detecting attacks with an accuracy of 99.18% for XGBoost and Random Forest showed an accuracy of 99.21%. Thus, it was shown that the significance of applying machine learning techniques such as Random Forest and XGBoost can be one of the key approaches in combating botnet attacks and securing the IoT. The results of the work emphasize the promising application of machine learning techniques for effective defense against cyber threats and highlight the importance of further. [ABSTRACT FROM AUTHOR]

Product recommendation systems are an important aspect of retailing because of the improved shopping experience provided for customers. Due to the wide range of products offered by retailers, recommendation systems provide an optimal approach for displaying only relevant products to customers by forming associations that exist between products. Still, it is also important to understand the characteristics of customers connected to different product associations. Conventional approaches for product recommendation systems apply association algorithms and unsupervised classification of customers based on product ratings. However, it is not clear what demographic properties of customers are linked to which different product associations. This paper applies a hybrid system of machine learning (ML) association and clustering algorithms to implement a product recommendation system that shows associations that exist in products and unique customer profiles linked to these associations. The method described in this paper is evaluated with a case of a hygiene product retailer in Austria. [ABSTRACT FROM AUTHOR]

Techniques for classifying data using data mining are now a day prevalent in agriculture. The method of classifying seeds involves grouping various seed varieties according to their morphological characteristics. To accomplish categorization of the typical Charotar region (generally comprising Anand and Kheda districts of the Gujarat State of India) Gujarat Wheat (GW) varieties (TRITICUM – AESTIVUM) viz. GW 273, GW 496, GW 322, LOK-1, and GDW 1255 (TRITICUM – DURUM), Weka Explorer was used. The features used are area, perimeter, solidity, aspect ratio, major and minor axis of seed kernel, Hue, Saturation, Value, and SF1 (empirical). Features reduction was done using Information Gain (IG) and its modified version Gain Ratio (GR). This paper compares performance of Tree based data mining algorithms in classifying wheat varieties. For classification we used purely tree-based machine learning algorithms viz. J48, Random Forest, Hoeffding Tree, Logistic Model Tree (LMT), and REPTree. LMT- logistics regression method gives higher accuracy 96.4% compared to other classifiers. Hoeffding Tree classifiers stood second with 96% accuracy. For validation 10-fold cross validation was used. By reducing the number of folds in cross validation performance of most algorithms decreased except J48. The percentage of correctly classified instance increased for all algorithms when features were selected by GR except for J48. [ABSTRACT FROM AUTHOR]

Stock market trading is a major and predominant activity when one talks about the financial markets. With the inevitable uncertainty and volatility in the prices of the stocks, an investor keeps looking for ways to predict the future trends in order to dodge the losses and make the maximum possible profits. However, it cannot be denied that as of yet there is no such technique to predict the upcoming trends in the markets with complete accuracy, while multiple methods are being explored to improve the predictive performance of models to an extent as large as possible. With the advancement in Machine Learning (ML) and Deep Learning (DL) over the past few years, many algorithms are being deployed for stock price prediction. This paper researches 5 algorithms namely K-Nearest Neighbors, Linear Regression, Support Vector Regression, Decision Tree Regression, and Long Short-Term Memory for predicting stock prices of 12 leading companies of the Indian stock market. After exhaustive research of the various aspects related to the application of ML in stock market, a data extensive implementation has been carried out as a part of this research work wherein the stock price dataset of 12 companies over the last 7 years was collected and used. The paper also highlights some more efficient and robust techniques that are used to forecast trends in the stock market. In detail, the methodology followed, to acquire the results, has been talked about step-wise. Furthermore, a detailed comparative analysis of the performances of the aforementioned algorithms for stock price prediction has been carried out with the results displayed in a legible tabulated and graphical form to analyze them better. The conclusions from this novel, data comprehensive research work have been presented and it has been inferred that the DL algorithm outperforms all the other algorithms for stock price or time series prediction and provides results with extensive accuracy. [ABSTRACT FROM AUTHOR]

The evolution and civilization development lead us to the progress next important step - the creation of AGI. More "intelligent" tasks are successfully solved by machine learning methods using neural network algorithms. Not only the solved problems quantitative increase in the number and accuracy are important, but also a qualitative transition to the tasks of obtaining "truly" new knowledge and building "truly" new goals on their basis. This transition can serve as a criterion for determining AGI. The paper shows necessity of using existing knowledge to advance into the field of more and more diverse "truly" new knowledge. Also, the paper shows usefulness of implementing proposed ideas on a scalable hierarchical structure which has two main modes of operation: "intuition" and "thinking", and structure of vector control of these and other operation modes, similar to animal hormonal control. [ABSTRACT FROM AUTHOR]

With the fast-moving deployment of IoT (Internet of Things) applications, a large amount of data is generated and the data is in need for processing to be able contribute to the user's requirements. All of the IoT applications require low latency and certain bandwidth to provide us with new features which are Time-Dependent. Thus, it would be advantageous to redesign the current IoT architecture by understanding the unique properties of communications and computational power to support intelligent processing of IoT data and its analysis. The paper is focused on topics such as characteristics of IoT data, trends in IoT network architecture, problems in IoT data analysis and their solutions. Thus, in particular, the paper is a discussion that Edge software-defined computing and CEP (Complex Event Processing) based fog computing as a architecture that promises to support the different requirements of IoT data analytics. And also, the paper is a discussion about how machine learning, deep learning are useful in removing data processing anomalies. The leader node election for data processing at cloud is also a time consuming task, the proposed genetic based Genetic based Leader Election Algorithm (GLEA) algorithm in the paper show promising results for the solution. [ABSTRACT FROM AUTHOR]

Clustering is one of the most common technologies in data mining. The size, dimension and sparsity of data are all different aspects that restrict clustering analysis. Clustering machine learning is called unsupervised learning, which is different from classification in that the data objects used in clustering analysis have no class marks, so they need to be calculated by the clustering learning algorithm, while the classified data objects need class marks. At present, most of the sparse data algorithms with high attribute dimensions are oriented to binary data, and there is no evaluation method of clustering results, which brings great limitations to their application. The BP neural network, RBF neural network and Elman neural network model with feedback function, which are mature and widely used in pest prediction models, are studied. The purpose of this paper is to study diseases and pests based on sparse clustering algorithm. In this paper, algorithm formulas, models and data graphs are established to study. From the research, it can be seen that the damage index of pests and diseases is very high, reaching about 50. 54%. Through the research in this paper, we can know that the future will lay a certain foundation for the research of diseases and pests. [ABSTRACT FROM AUTHOR]

Intelligent machines are an important carrier of artificial intelligence, which are widely used not only in the industrial field, but also in various fields of daily life and work. Path planning is an important research direction for studying machine intelligence. The main purpose is to search for a feasible path so that the robot can walk along the searched path in a complex environment. This paper aims to study the evolutionary algorithm of intelligent machines based on artificial intelligence. On the basis of introducing the characteristics of artificial potential field algorithm, the concept and characteristics of genetic algorithm, using genetic algorithm as the framework, the artificial potential field algorithm is combined with the crossover of genetic algorithm. In the operator, the optimization performance of the crossover operator is improved. The research results show that the length of the path obtained by the improved algorithm is shorter and better than that of the genetic algorithm of the single-point crossover operator. [ABSTRACT FROM AUTHOR]

This paper presents a Text similarity detection method based on artificial intelligence and natural language processing. The method combines statistical machine learning and deep learning techniques and designs six models from three perspectives: character-level, word-level, and semantic-level. These models include the diff model based on machine learning, cosine similarity model, Jaccard model, TF-IDF model, as well as the SimCSE and SBERT models based on deep learning methods. To fully leverage the characteristics of these models, three scenarios are designed to calculate the similarity scores based on experience and multiple experimental results. The results show that calculating the similarity scores using these three scenarios not only achieves high accuracy but also requires fewer computational resources. As deep learning and natural language processing technologies continue to advance, Text similarity detection methods based on artificial intelligence and natural language processing will continue to be improved and play a more significant role in practice. Future research can explore more models and algorithms to enhance the accuracy and robustness of plagiarism detection. [ABSTRACT FROM AUTHOR]

With the advancement of science and technology, metallographic research on metal materials has made remarkable progress. In this paper, the authors processed metallographic images using machine learning algorithms to classify the different elements in the images. The classification results divide the elements into three categories, which are metal elements, non-metal elements and metal-nonmetal combination elements. On the basis of this research, a metallographic compression algorithm based on adaptive threshold is also explored, and grayscale experiments are carried out on carbon steel samples. The recognition rate is 98.3%, and the compression rate is 1.06. Experimental results verify the effectiveness of the algorithm in processing metallographic compressed images of metal materials in power grids. [ABSTRACT FROM AUTHOR]

The paper focuses on the problem of instance selection. Instance selection is currently crucial to enhance the efficacy and efficiency of machine-learning tools when they are used to solve a data-mining task and when the data are large and they are seen through the prism of the big data phenomenon. Instance selection eliminates redundant instances and thus reduces the size of the training data set. The training data, with redundant cases removed, can be more useful and ensure better performance of the final classification models. The instance selection problem belongs to the NP-hard class, so it can be solved with an approximation tool. In this paper the firefly algorithm is proposed for solving the instance selection problem. This paper is one paper, where the firefly algorithm has been used to solve a discrete optimisation problem, when in more cases previously it has been used for solving continuous optimisation problems. The firefly-based instance selection algorithm is presented and its validation is carried out. The results of the computational experiment show that the algorithm is competitive with others. The results obtained are discussed and conclusions are formulated. [ABSTRACT FROM AUTHOR]

The paper presents a description of the research methodology dedicated to a two-step discretisation process applied to the input numeric data, with combining the characteristics of selected supervised and unsupervised algorithms, which leads to extended processing of some attributes in train and test sets. The methodology was illustrated with the investigations carried out in the domain of stylometric analysis of texts, for two datasets prepared for the task of binary authorship attribution. The several variants of transformed input data obtained were subjected to exploration using two selected machine learning methods capable of inducing knowledge from both continuous and categorical forms, namely the PART and J48 classifiers. The results from the experiments indicate that, as can be expected, supervised transformations of data work well enough, however, they do not always return the best outcome. The two-step processing of some attributes shows sufficient promise to warrant a closer study, as opposed to always unconditionally relying only on supervised algorithms as outperforming all other approaches. [ABSTRACT FROM AUTHOR]

In a dynamic world, data streams are continuously generated, which poses immense challenges for machine learning (ML) algorithms to adapt to changing statistical properties that are subject to a non-stationary context. The underlying scenario is defined as concept drift (CD), where changes in the relationship between response and prediction variables (real CD) or a change in input data (virtual CD) are accompanied by a significant degradation in the predictive performance of the models, causing ML models to reach unacceptable levels of system accuracy. In this paper, the state of the art for CD algorithms is analyzed and compared. For this purpose, a systematic literature review was performed. Then, the 10 most popular CD algorithms were extracted from the literature using a newly-developed metric. Subsequently, the algorithms were analyzed and compared with respect to their functionality and limitations. Based on these, the optimization potentials were systematically derived. This work presents a summarized overview of CD algorithms and provides the basis for algorithm optimization in this domain. [ABSTRACT FROM AUTHOR]

In this paper, the problem of imbalanced data stream classification is considered. To eliminate the problem of imbalanced data, over- and under-sampling procedures are implemented within a dedicated framework called Weighted Ensemble with one-class Classification and Over-sampling and Instance selection (WECOI). To increase the quality of synthetic instance generation (carried out under the umbrella of an over-sampling procedure), an agent-based population algorithm is proposed. The problem is defined, and the agent-based algorithm is presented. A discussion of selected computational results is also included. [ABSTRACT FROM AUTHOR]

The development of quantum machine learning (QML) has received a lot of interest recently thanks to developments in both quantum computing (QC) and machine learning (ML). One of the ML paradigms that can be utilized to address challenging sequential decision-making issues is reinforcement learning (RL). It has been demonstrated that classical RL can successfully complete many difficult tasks. A leading method of building quantum RL agents relies on the variational quantum circuits (VQC). However, training QRL algorithms with VQCs requires significant amount of computational resources. This issue hurdles the exploration of various QRL applications. In this paper, we approach this challenge through asynchronous training of QRL agents. Specifically, we choose the asynchronous training of advantage actor-critic variational quantum policies. We demonstrate the results via numerical simulations that within the tasks considered, the asynchronous training of QRL agents can reach performance comparable to or superior to classical agents with similar model sizes and architectures. [ABSTRACT FROM AUTHOR]

K-Nearest Neighbors (KNN) are very popular supervised machine learning algorithm which can be effectively used for both multi-class classification and regression utilizing multiple features of the dataset. It trains extremely fast, that is with time complexity of O(n). However, the time complexity for generating results with KNN is O(n3dk) (where k=number of neighbours, d=dimension of data, n=number of training points) and hence it becomes very difficult to work with larger dataset. Although there are parallelizing and distributed computing techniques available for speeding up KNN, it still have limitations on horizontal scalability, fault tolerance and incremental learning capabilities. To solve these issues, the paper presents a KNN inspired novel Supervised Machine Learning algorithm called Distributed Nearest Hash utilizing unique usage of hashmap and primary key clustering order with help of wide column store databases facilitating easy incremental near-realtime scalability to train unlimited datapoints with O(n) time complexity and also predict them in near realtime with O(1) time complexity considering n >> d. This can be readily integrated in any system that uses KNN as a base classifier or regressor. The experimental results shows that the proposed DNH model is 25% faster than state of the art distributed KNN algorithm. Integrating with fuzzy logic the algorithm can be used for several class classification. Using this could aid in building very powerful smart decision making systems with very little computational power. [ABSTRACT FROM AUTHOR]

The performance of classification algorithms with highly imbalanced streaming data depends upon efficient balancing strategy. Some techniques of balancing strategy have been applied using static batch data to resolve the class imbalance problem, which is difficult if applied for massive data streams. In this paper, a new Piece-Wise Incremental Data re-Balancing (PWIDB) framework is proposed. The PWIDB framework combines automated balancing techniques using Racing Algorithm (RA) and incremental rebalancing technique. RA is an active learning approach capable of classifying imbalanced data and can provide a way to select an appropriate re-balancing technique with imbalanced data. In this paper, we have extended the capability of RA for handling imbalanced data streams in the proposed PWIDB framework. The PWIDB accumulates previous knowledge with increments of re-balanced data and captures the concept of the imbalanced instances. The PWIDB is an incremental streaming batch framework, which is suitable for learning with streaming imbalanced data. We compared the performance of PWIDB with a well-known FLORA technique. Experimental results show that the PWIDB framework exhibits an improved and stable performance compared to FLORA and accumulative re-balancing techniques. [ABSTRACT FROM AUTHOR]

The amount of network traffic generated from the Internet of Things (IoT) devices is massive which leads to Big data. In present scenario, IoT devices has taken a leap ahead in terms of growing technology and insecure network traffic flow. The sensitivity of the data in the IoT network is becoming very high, which concern the security in legal and privacy issues. Traditional Intrusion Detection System (IDS) is used as a primary line security to differentiate between the attack and benign network traffic flow. As the size of the network traffic capture increases, it becomes more important to handle such big data. Similarly, when the number of classes and instances increases, the complexity of the data also increases. In this paper, we propose a big data platform based intrusion detection system which can differentiate between the types of network traffic flow generated from the IoT devices. We compared the performance of deep learning algorithms with machine learning algorithms on Apache Spark platform and found that machine learning algorithms outperform deep learning algorithms with greater accuracy and less training time for the model. We evaluated our research based on real world network traffic dataset BoT-IoT [1] for an improved intrusion detection system in IoT network traffic. [ABSTRACT FROM AUTHOR]

The quest for learning more about the minute intricacies of the universe has fascinated mankind since ages. From stars to planets and asteroids to exoplanets, each research endeavor in astronomy has supplemented our knowledge about the cosmos. NASA's Kepler Mission is one monumental step in this direction wherein, telescopes conduct a survey of the Milky Way galaxy and try to identify thousands of earth-size and other smaller planets in or near the habitable zone, so as to determine the thousands or even millions of stars in our galaxy that might have such orbiting planets. Exoplanet is any new planet outside the solar system which orbits a star. Identifying new exoplanets gives us a chance to precisely understand the planet formation processes. Earlier, it was a laborious endeavour to mine the mission data using traditional algorithms and churn out the possible exoplanets. Ever since the advent of various machine learning algorithms, this process has become quite seamless. However, not all algorithms give equal and promising results when it comes to analysing different types of data. A comparative study of algorithms helps in this regard, thereby identifying the pros and cons of different algorithms for analysing certain forms of data. In this paper, we initially focus on feature set reduction using principal component analysis and thereafter make a detailed comparative analysis of ML algorithms for the identification of exoplanets, in the NASA Kepler mission data. [ABSTRACT FROM AUTHOR]

This paper presents optimization techniques for automatic personality recognition (APR) based on Twitter in Bahasa Indonesia, the mother tongue of Indonesians. Foremost, we discuss Twitter and its utilization as a resource for many types of research. Several previous studies have been attempted to predict users’ personality automatically. However, only a few of them have done their research for Bahasa Indonesia data. Therefore, this paper discusses the optimization of APR in Bahasa Indonesia. We evaluate a series of techniques implementing hyperparameter tuning, feature selection, and sampling to improve the machine learning algorithms used. The personality prediction system is built on machine learning algorithms. There are three machine learning algorithms used in this study, namely Stochastic Gradient Descent (SGD), and two ensemble learning algorithms, Gradient Boosting (XGBoost), and stacking (super learner). By implementing this series of optimization techniques, the current study’s evaluation results show huge improvement by achieving 1.0 ROC AUC score with SGD and Super Learner. [ABSTRACT FROM AUTHOR]

Intrusion Detection Systems (IDS) are used in computer networks to safeguard the integrity and confidentiality of sensitive data. In recent years, network traffic has become sizeable enough to be considered under the big data domain. Current machine learning based techniques used in IDS are largely defined on eager learning paradigms which lose performance efficiency by trying to generalize training data before receiving queries thereby incurring overheads for trivial computations. This paper, proposes the use of lazy learning methodologies to improve overall performance of IDS. A novel heuristic weight based indexing technique has been used to overcome the drawback of high search complexity inherent in lazy learning. IBk and LWL, two popular lazy learning algorithms have been compared and applied on the NSL-KDD dataset for simulating a real-world like scenario and comparing their relative performances with hw-IBk. The results of this paper clearly indicate lazy algorithms as a viable solution for real-world network intrusion detection. [ABSTRACT FROM AUTHOR]

Email spam has been a big issue in recent years. As the percentage of internet users grows, so does the number of spam emails. Technologies are being used for illegitimate and immoral activities, such as phishing and robbery. As a consequence, it is essential to identify fraudulent spammers by employing machine learning techniques. This paper presents a novel spam classification technique that integrates the Harris Hawks optimizer (HHO) algorithm with the k-Nearest Neighbors algorithm (k-NN). The Harris Hawks Optimization (HHO) algorithm is a new metaheuristic algorithm motivated by Harris' Hawks' cooperative relations and surprises pounce pursue technique in nature. According to empirical results on the dataset, the suggested model can handle high-dimensional data (Spambase). The suggested model's spam detection accuracy is compared to the numerous algorithms, including the Binary Dragonfly Algorithm (BDA), Equilibrium Optimizer (EO), Teaching-Learning-based Optimization, Seagull Optimization Algorithm (SO), and Marine Predators Algorithm (MPA). We found that the proposed technique trumps the other spam detection techniques investigated in this study in terms of classification accuracy. The experimental results showed that the proposed technique accuracy reaches %94.3. [ABSTRACT FROM AUTHOR]

Hybrid quantum machine learning (QML) algorithms have potentials for current quantum computing technologies since only part of the model is computed by a quantum device. This paper proposes a novel hybrid quantum-classical deep learning model for cybersecurity application: domain generation algorithms (DGA)-based botnet detection. We analyzed our hybrid model's performance compared with the classical model counterpart to investigate the quantum circuit's effectivity as a layer in a deep learning model. We used four features of the Botnet DGA dataset: MinREBotnets, CharLength, TreeNewFeature, and nGramReputation_Alexa. The hybrid model's quantum circuit is a combination of Pennylane's embedding (Angle Embedding and IQP Embedding) and layers circuit (Basic Entangler Layers, Random Layers, and Strongly Entangling Layers). Also, we implemented noise models for assessing the applicability of the model for current Noisy Intermediate Scale Quantum (NISQ) technology. We found that in some cases, the hybrid model reached high performance (maximum accuracy up to 94,7% using n= 100; 93,9% using n= 1,000). We discovered that the combination of Angle Embedding and Strongly Entangled delivers high accuracy, superior to the classical deep learning model in n= 100 experiments). However, the overall performance is still inferior for the rest cases compared to the classical deep learning model counterpart. [ABSTRACT FROM AUTHOR]

In today's world, the amount of information is increasing drastically. There are 2.5 quintillion bytes of data generated each day at a current time. With this rapid increase of data, it is important to filter the huge amount of data from the existing unnecessary available storage. To handle this issue, the researchers have incorporated the concept of recommender system. Recommender system tries to filter the users' data to come up with the exact amount of information required according to the needs and preferences of the users. Hence there is an increase in the demand of recommender system to tackle the data overload. However, the existing recommender systems do perform well but face some issues in the corporate world. Cold start, user bias, precision and speed are some of the major problems faced by recommender system which are yet to be addressed. To minimize such issues, we incorporate the concept of randomization such that random factor can be integrated in design of recommender systems. In this paper, we have also outlined the advantages as well as the procedure of using a randomized algorithm for recommender system. The proposed approach would provide a platform for researchers to enhance the recommender system using the randomized algorithms in the future. [ABSTRACT FROM AUTHOR]

The primary objective of the present work is two-fold. First, to compare the different filtering techniques namely BayesNet, Decision Table, Logistic, k-NN, JRip, LibSVM, Randomized Filtered Classifier, Random Forest, Random Tree and OneR on the basis of six evaluation metrics including Kappa Statistic, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), F- Measure, ROC Area and Accuracy. Second, to improve the accuracy with the resampling mechanism. To determine the most appropriate algorithm, we have compared them using WEKA tool on a large sample of MovieLens dataset. The performance of ten different training algorithms has been analyzed and presented in this paper. It is found that random forest has received better results in comparison with other techniques with 99.39% accuracy. In addition to this, we have also incorporated the discussion of on-going researches and related works carried in the domain of recommendation systems. The present research shall help the researchers in exploring the best classification techniques for improving accuracy. [ABSTRACT FROM AUTHOR]

The paper presents an approach to machine learning involving the use of a hybrid method in Neural ODE. The authors consider a way of the Neural ODE application with an embedded hybrid method for intelligent manipulator control in a non-deterministic environment. To reduce computational resources, the number of layers of the neural network using ODE is reduced, the solution of which is carried out by a hybrid transformation method. The hybrid method includes normalizing the system, linear transformation, and polynomial transformation. Using the hybrid method in Neural ODE can increase the learning and computation speed. The transformation method has high accuracy with low computational complexity of the algorithm. As a result of applying the hybrid method, the original nonlinear system is transformed to a simpler form. To solve the simplified transformed system, the scheme of the numerical Runge-Kutta method of the third order with an adaptive step is used. The results of the computational experiment show an increase in the speed and accuracy of the calculation. The presented approach to implementing the hybrid method in Neural ODE allows faster training of the neural network of the world model on limited data obtained from the real environment. After training on the data generated by the model of the world, a robotic arm always successfully reaches the object during subsequent interaction with the real environment. This solves the problem of the limited ability of the agent to interact when learning with the real environment in robotic systems. [ABSTRACT FROM AUTHOR]

Time-series modeling is a well-studied topic of classical analysis and machine learning. However, large datasets are required to obtain the model with a better prediction quality with the increasing model complexity. Therefore, some applications demand synthetic datasets that are preserving modeling-sensitive properties. Another application of synthetic data is data anonymization. The synthetic data generation algorithm may be split into two parts: the time-series modeling and the synthetic data generation parts. The model must be interpretable to obtain the synthetic data with good quality. The model parameter interpretation allows controlling generation by adding noise to different groups of parameters. In the paper, the evolutionary multi-objective closed-form algebraic expressions discovery approach that allows obtaining the model in the form that may be analyzed using the mathematics is proposed. The analysis allows the interpretation of the model parameters for the controllable generation of the synthetic data. The notion of synthetic data quality is discussed. The examples of the synthetic time-series generation based on two datasets with different properties are shown. [ABSTRACT FROM AUTHOR]

Feature selection (FS) is considered a challenging machine learning problem that handles the large size of features. The main purpose of FS is to remove irrelevant and redundant variables to improve the performance of the learning algorithms. Consequently, the FS process is considered as an optimization problem where metaheuristics approaches prove efficiency in solving it. In this paper, we propose new binary versions of a new ancient inspired metaheuristic approach called Giza Pyramids Construction (GPC) to select the most relevant subset of features. The proposed binary versions of the algorithm called BGPC-S and BGPC-V are implemented with two transfer functions, with the main objective of maximizing classification accuracy and minimizing the number of selected features. The two versions of BGPC were compared to six well-known binary metaheuristics for feature selection problem, namely Binary Atom Search Optimisation (BASO), Binary Bat Algorithm (BBA), Binary Differential Evolution (BDE), Binary Grey Wolf Optimizer (BGWO), Binary Particle Swarm Optimization (BPSO), and Binary Harris Hawks Optimizer (BHHO), and evaluated over 20 datasets from the UCI repository. Experiments have demonstrated that the proposed approaches outperformed the other algorithms in terms of classification accuracy and the number of selected features. [ABSTRACT FROM AUTHOR]

The increasingly noticeable effects of climate change require action to reduce greenhouse gas emissions. In the transport sector, the increase in electromobility is an important tool for reducing CO 2 emissions. In order to meet the essential requirements, a particularly detailed system knowledge, for example on energy efficiency in the powertrain, is needed for the development and improvement of electric vehicles. The present work contributes to this by mapping the efficiency of a planetary gearbox for an electric vehicle. The mapping is done by experimental modelling with machine learning methods based on a standard efficiency description. The data necessary for the neural network training is generated by efficiency experiments on the powertrain test rig. For suitable results the data was pre-processed by applying relevant low-pass filters. A comparison of the Bayesian-Regularization algorithm, the Levenberg-Marquardt algorithm and the scaled-conjugate-gradient algorithm for training exhibited the strengths and weaknesses of the individual algorithms for the efficiency mapping. By comparing each algorithms performance metrics, the one matching the requirements best is chosen for the efficiency mapping. The result is a continuous function that determines the efficiency based on speed- and torque-inputs. Based on a key performance indicator, statistical validation by evaluating the standard deviations is used to ensure the quality of the results. In this paper the suitable algorithm for the given use case was determined. It can be applied for further research due to the significant results shown. [ABSTRACT FROM AUTHOR]

A vehicular network underpinned by the 3-tier vehicle-edge-cloud infrastructure enables an efficient and safer travel experience. The compute-intensive vehicular applications are often offloaded to the edge and/or cloud servers to enhance the applications' Quality of Services (QoS). The underlying edge-cloud servers consume a high among of energy. Consequently, it becomes crucial to optimizing energy consumption in the offloading process. Current energy-efficient offloading strategies in 2-tier vehicle-edge infrastructure, do not account for cloud computing energy consumption. In this paper, we address this void by proposing a machine learning-based energy-aware offloading algorithm, which optimizes the energy of the edge-cloud computing platform. The offloading strategy is enabled by the Support Vector Machine (SVM) regression model machine learning algorithm used for the edge-cloud power prediction. The experimental results show that the proposed algorithm is a promising approach in energy savings. [ABSTRACT FROM AUTHOR]

The sentiment classification method is a research field that is proliferating in Indonesia since it is fast in extracting public opinion and provides essential and valuable information for stakeholders. Of the best-performing sentiment classification approaches, machine learning is one of them that has excellent performance. However, the method has several problems, such as noisy features and high dimensionality of features that significantly affect the sentiment classification performance. Therefore, to overcome the problems, this paper presents a novel feature selection using a combination of Query Expansion Ranking (QER) and Genetic Algorithm-Support Vector Machine (GA-SVM) for improving sentiment classification performance. Based on the experimental results, the proposed method could significantly improve sentiment classification performance, outperform all state-of-the-art algorithms, and decrease computational time. The method achieved the best performance in average precision, recall, and f-measure with the value of 96.78%, 96.76%, and 96.75%, respectively. [ABSTRACT FROM AUTHOR]

The primary objective of IEEE 802.22 standard is to determine vacant spectrum bands available in Digital Television channel (DTV) and to utilize them for wireless rural broadband connectivity. Cognitive Radio aims at maximizing the utilization of the limited radio bandwidth while accommodating the increasing number of services and applications in Wireless networks. For cognitive radio networks to operate efficiently, Secondary Users (SU) should be able to exploit radio spectrum that is unused by the primary user. A critical component of cognitive radio is thus spectrum sensing. The secondary user should sense the spectrum efficiently, utilize the opportunities for transmission, and vacate the channel once primary user reoccupies it. In this paper, we propose approaches for cooperative spectrum sensing as per the IEEE 802.22 standard. This paper describes several simulation scenarios that can be used to evaluate spectrum sensing by single SU unit (local sensing) and multiple SUs in a cooperative setup. The detection accuracy and performance of the proposed algorithms are described using performance metrics called probability of detection and probability of false-alarm through extensive simulations using Matlab. [ABSTRACT FROM AUTHOR]

In this paper, we propose an evolutionary learning approach for flexible identification of custom composite models for classification problems. To solve this problem in an efficient way, the problem-specific evolutionary operators are proposed and the effectiveness of different modifications of the common genetic programming algorithm is investigated. Also, several implementations of caching for the fitted models were compared from the performance point of view. To verify the proposed algorithm, both synthetic and real-world classification cases are examined. The implemented solution can identify the structure of the composite models from scratch, as well as be used as a part of automated machine learning solutions. [ABSTRACT FROM AUTHOR]

The article describes the automated formatting verification technique of docx document elements which were the basis for developed online service. Checking the document formatting correctness is an important task when writing various research papers, explanatory notes for course projects, and other scientific works. The article describes the approach for identifying design features of text document elements. The structure of the client-server interaction of the service, the operation of which was simulated, is also given. Such a machine learning algorithm as gradient boosting on decision trees CatBoost was chosen as the primary tool for multi-classification. Empirically refined parameters of the algorithm that increase its accuracy are described. Special attention is paid to the developed method of checking the results of classification of elements, the sequence of which has different regularities. This approach allows us to identify the formatting classes of docx files elements that were incorrectly identified by the classifier. Sometimes, it is possible to override the results of the classifier to increase the accuracy of checking the elements formatting in docx files. [ABSTRACT FROM AUTHOR]

Graph analytics are now considered the state-of-the-art in many applications of communities detection. The combination between the graph's definition in mathematics and the graphs in computer science as an abstract data structure is the key behind the success of graph-based approaches in machine learning. Based on graphs, several approaches have been developed such as shortest path first (SPF) algorithms, subgraphs extraction, social media analytics, transportation networks, bioinformatic algorithms, etc. While SPF algorithms are widely used in optimization problems, Spectral clustering (SC) algorithms have overcome the limits of the most state-of-art approaches in communities detection. The purpose of this paper is to introduce a graph-based approach of communities detection in the novel coronavirus Covid-19 countries' datasets. The motivation behind this work is to overcome the limitations of multiclass classification, as SC is an unsupervised clustering algorithm, there is no need to predefine the output clusters as a preprocessing step. Our proposed approach is based on a previous contribution on an automatic estimation of the k number of the output clusters. Based on dynamic statistical data for more than 200 countries, each cluster is supposed to group countries having similar behaviors of Covid-19 propagation. [ABSTRACT FROM AUTHOR]

The article deals with the subject of mini-models (MMs) based on clustering algorithms. The mini-model method is a local regression algorithm that operates on some part of the input space called the mini-model domain (MM domain). MM domain can be created as a multidimensional polytope in the input space. Another possible solution is to divide the input space with clustering algorithms. As a result of this process, each data cluster is treated as a separate mini-model domain. The main aim of the article is to create an exhaustive comparison of mini-model methods based on the most well-known clustering algorithms. The work introduces new versions of the mini-model method based on clustering algorithms such as DBSCAN, OPTICS, Mean Shift, spectral clustering and several hierarchical methods. The paper also compares the results with other versions of the MM-method and instance-based learning algorithms. [ABSTRACT FROM AUTHOR]

Intrusion detection has been the subject of numerous studies in industry and academia. Still, Cybersecurity analysts always want greater precision and global threat analysis to secure their systems in cyberspace. To improve the intrusion detection system, the visualization of the security events in the form of graphs and diagrams is significant to improve the accuracy of alerts. In this paper, we propose an approach of an IDS based on cloud computing, big data technique and, using a machine learning graph algorithm which can detect in real-time different attacks as early as possible. We use the MAWILab intrusion detection dataset. We choose Microsoft Azure as a unified cloud environment to load our dataset on Azure blob storage. We implement the k2 algorithm, which is a graphical machine learning algorithm to classify attacks. Our system showed a great performance due to the graphical machine learning algorithm and Apache Spark structured streaming engine. [ABSTRACT FROM AUTHOR]

In this paper an Online Monitoring System is presented, which enables a universal condition monitoring of electrical household appliances. The approach involves recording the power consumption of the respective device and evaluating the measured data using machine learning methods and tools. Thereby an artificial intelligence learns the normal condition of the examined device and can subsequently perform a monitoring. A k -Means algorithm is used for clustering and a One-class Support Vector Machine for classification. This makes it possible to detect anomalies in the operating modes and behavior of the device during subsequent operation. In addition to the methodology, the design and real application of a prototype is presented, in which a suitable sensor technology and a software with artificial intelligence are implemented. [ABSTRACT FROM AUTHOR]

This paper presents the design and a prototypical implementation of a tool for short-term energy demand forecasting in prosumer scenarios in local energy systems. The prototype combines explainable machine learning and visual analytics to facilitate the forecasting and analysis of energy demand and supply in a way usable for small utilities not used to complex analytical approaches. It applies a kNN (k-Nearest Neighbour) algorithm to forecast energy demand and supply and presents the results in an interactive visual dashboard that allows the user to analyze different forecast alternatives, to understand how they relate to the input parameters and identify consumption and production patterns. Initial assessment of the forecasting accuracy (MAPE 5.77%) on a limited dataset and the feedback from target users support the feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Failure of machinery and equipment in factories, plants, etc. is a great loss to the operator. Various studies have been conducted for a long time to solve this problem, and many solutions have recently been developed to perform real-time health monitoring by attaching sensors to facilities. In addition, machine learning has allowed more accurate diagnosis of the condition to be carried out on these collected data. However, real-time fault detection is accompanied by a number of difficulties. Class imbalance issues are considered one of the most representative factors that makes it difficult to apply machine learning models in real-world locations. Class imbalance means that when it comes to classification problems, the amount of data in one class is greater than that in another class. In this case, the machine learning model is overfitted to a class with a lot of data, causing performance degradation. In real-world sites, the performance degradation of the model due to class imbalance is very serious because most data occurs in normal state, while fault data does not occur very well. Several prior studies have proposed ways to overcome this class imbalance, but each has several limitations. In this paper, an algorithm solution method and computing architecture solution method are introduced together as methodologies to overcome class imbalance, and a robust classification model is designed for class imbalance. [ABSTRACT FROM AUTHOR]

As a popular traditional Chinese exercise, Tai Chi is of great benefit to physical and mental health. Professional and face-to-face guidance is a traditional and effective way to learn Tai Chi, but it is restricted by factors such as site and time. Although the way to learn Tai Chi by watching videos is not limited by time or place, it is not convenient for learners to observe learning from multiple perspectives since it shows sequences of actions that have been recorded from fixed viewpoints. This paper proposes a real-time interactive Tai Chi learning system based on VR and motion capture technology, in which the learner wears the head-mounted display to follow the virtual coach in the scene, and can watch the demonstration of the virtual coach in all directions; the learner can also drive and watch his own avatar, and can operate the menu by natural interaction in the virtual environment in real time through wearable motion capture device, so that he can know the effects of his training and learning of each action. The actions of the avatar and virtual coach are also compared by using a motion similarity matching algorithm, to evaluate the quality of learning and training and guide the learner to adjust his motion in real time. With the help of our system, learners can practice Tai Chi in the same way as in the real environments and drive their avatars in virtual scenes, so as to achieve effective self-learning and evaluation. [ABSTRACT FROM AUTHOR]

Article presents the relevance of creating Smart Grid for public power networks and industrial enterprises. The article describes an experiment in which data were collected from current and voltage sensors from several different consumers of electric energy, using the created Smart Socket - Smart Energy device. The methods and algorithms of intellectual and spectral analysis were used to analyze and process experimental data. In this paper, we developed an algorithm for identifying the type of consumer of electric energy in the network of general power supply using the machine learning model XGBoost - extreme gradient boosted decision trees. [ABSTRACT FROM AUTHOR]

In the current age of high competition and risk in markets, technological advancements are a must for better growth and sustainability. The same applies to the agriculture industry. Every farmer has high stakes on the crops, their yield and quality. Rising water issues and need for proper methodologies for farm maintenance is a hot issue that needs to be tackled at utmost propriety. An automation of irrigation systems in farms is proposed in this research. The proposed solution is based on the Internet of Things (IoT), which would be a cheaper and more precise solution to the farm needs. A Monitoring system whose main purpose is to solve the over irrigation, soil erosion and crop-specific irrigation problem will be developed to ease and efficiently manage Irrigation problems. Since it is a well-known fact that the water is a scarce resource and over wastage of such an essential resource should be minimized. The proposed solution will be developed by establishing a distributed wireless sensor network (WSN), wherein each region of the farm would be covered by various sensor modules which will be transmitting data on a common server. Machine learning (ML) algorithms will support predictions for irrigation patterns based on crops and weather scenarios. So, a sustainable approach to irrigation is provided in this paper. [ABSTRACT FROM AUTHOR]

In this paper, a study to protect Java Card source codes against fuzzing attacks is presented. This work is based on the tool ChuckyJava. This tool aims at automatically detecting anomalies in Java source codes in a Machine Learning way, without the knowledge of their specification. First, we propose a definition of neighbor methods. Based on this same definition, this study focuses on the improvement of the neighborhood discovery step for the tool ChuckyJava. To achieve this task, we have created a new Machine Learning tool: JavaNeighbors. It is based on different Natural Language Processing techniques: both local and global weighting schemes adjustement for term extraction and Latent Semantic Analysis to mitigate the curse of dimensionality. As a result, JavaNeighbors solves four limitations of ChuckyJava and it performs faster and with a better accuracy. [ABSTRACT FROM AUTHOR]

Abstract The world is moving exponential towards the technical growth in every field. The most obliging and gifted is the field of Healthcare and medical diagnosis with the advanced techniques of Artificial Intelligence and Machine Learning; it's a boon to the patients affected by cancer. Brain Tumor is one of the severe syndrome causes for the death of Human beings. Magnetic Resonance Imaging is vital medical diagnosis tool for revealing of tumors. Precise segmentation and classification of the tumors yet relics a puzzling task because of its large structural and spatial erraticism among tumors. In this paper an effort is made to discuss and implement the different Machine Learning classification algorithms on Brain Tumor MR Images for 20 Patients i.e 150*20 Slices of MR Sequences (MR Images) for thirteen attributes (statistical features), using the Dataset of BRATS 2015. Contribution to the heart of technology that can be used for tumor classification exhausting the machine learning algorithms namely the Naive Bayes, Logistic Regression, Multi-layer Perceptron, Support Vector Machine and Decision tree using the Waikato Environment for Knowledge Analysis tool and MATLAB. The experimental outcomes of proposed technique have been assessed for performance and quality examination on magnetic resonance brain images. [ABSTRACT FROM AUTHOR]

Abstract Drug Named Entity Recognition (DNER) is the process of identifying drug names from unstructured biomedical text. Most of the research works in this area make use of the available benchmark biomedical corpus to train and test the DNER system. In this paper, we propose an interactive biomedical text mining framework to access the scientific abstracts online, to pre-process and to extract drug entity through state – of – art machine learning techniques. This framework facilitates recognizing new drug names from real time biomedical abstracts from PubMed as well as from existing benchmark test datasets. [ABSTRACT FROM AUTHOR]

Abstract The emergence of machine learning algorithms enhanced the effectiveness of satellite image applications. On account of the high variability in-born in satellite data, a large portion of the present classification proposals are not sensible for handling satellite datasets. In this paper, we assessed profound learning systems in view of Convolutional Neural Networks for the precise order of multispectral remote sensing information. The Normalized Difference Vegetation Index (NDVI) is a solitary parameter for detecting landcover by utilizing the red and near-infrared band (NIR) information of the electromagnetic spectrum. NDVI is used to break down remote detecting images and survey the presence or absence of live green vegetation. The experiment is conducted on new publicaly available SAT-4 dataset, where the classes involved are types of vegetation. As NDVI computation require just two band data, it takes the benefit of both RED and NIR band information to classify diverse land covers. In the present work, the AlexNet architecture with two band information along with the reduced number of filters were trained and high-level features obtained from tested model managed to classify different land cover classes in the dataset. The proposed architecture is compared against the benchmark and results are estimated in terms of accuracy, precision and total number of trainable parameters. The proposed design brings about the aggregate diminishment of trainable parameters, while retaining high accuracy and precision, when compared against the existing architecture, which utilizes four bands. [ABSTRACT FROM AUTHOR]

Abstract Metocean modeling with short output fields timestep, for example, hourly average fields output, generates a large number of pictures and requires extended computational power. Often, during the simulation different types of artifacts can appear due to the inappropriate model tuning or errors in boundary and initial data and, therefore, expert's supervision and validation are required. When the number of images is increasing it becomes difficult or even impossible to check all output images manually. Therefore, it is required to use machine learning algorithms to reduce a time for expert's validation. Thereby, it would be useful to develop a system that allows detecting anomalies in generated data automatically during the experiment. In the paper, we provide a method of anomalies detection for the geospatial data. Data in climatographic archives is available in restricted amount and therefore, full Arctic images are divided into sub-zones, which allows one to increase training set. Moreover, this division can be used to account for the spatial dependency, which is required for ice images. An advantage of the approach is the ability to detect anomalies completely in automatic mode without involving a domain expert and manual labeling. [ABSTRACT FROM AUTHOR]

Surface Mount Device (SMD) is widely used in an automated Printed Circuit Board (PCB) assembling plant. Soldering SMD is a tedious and time-consuming process when it is done using bare hands. Industries require bulk production and hence it cannot be achieved by manual labour. For this fully automated SMD Pick and Place (P&P) machines are available in the market but the cheapest one starts at INR 15 Lakh (Yamaha yv-100x—Refurbished) and they are proprietary. Start-ups especially India based, find it difficult to afford such machine. In this paper, this issue is addressed and built an automated SMD P&P machine which is open source and far cheaper than the cheapest one in the market. However, the algorithm of the developed SMD P&P Machine and the one in the market remains the same but it functions differently and the steps are as follows; (i) Component are loaded onto the feeder tray (ii) Centroid file( machine file in ASCII format which comprise reference designator, X, Y, rotation, top or bottom side of the PCB board) is fed to the machine (iii) From the feeder tray component is picked by placement head using vacuum suction (iv) If the component is available in the placement head then correcting of component’s orientation and alignment using image processing is done else placement head is made to re-pick the component from feeder tray (v) Properly aligned and oriented component is placed on the PCB by releasing the vacuum. The proposed model is open source in both hardware (Raspberry Pi & Arduino) and software which is user friendly and easy to customize as per requirements. [ABSTRACT FROM AUTHOR]