1,720,984 research outputs found
A deep learning approach for designing a cloud intrusion detection service
Full text linkFen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Ana Bilim DalıSaldırı tespiti, siber güvenliğin temel taşı olarak kabul edilir. Erken ve etkili saldırı tespiti, son on yılda araştırmacılardan büyük ilgi görmüştür. Bununla birlikte, siber güvenliğe saldırı tespiti için derin öğrenme modellerinin kullanımı konusunda derin ve yeterli bir çalışmanın varlığı nadiren mümkündür. Bu tez çalışmasında kişisel bilgisayar, ağ ve bulut bilişim olmak üzere üç farklı ortamda saldırı saptama problemini araştırdık. Kişisel bilgisayar ve ağ ortamları ile ilgili olarak, sırasıyla maskeli ve ağ saldırı tespiti için bir dizi derin öğrenme modeli geliştirdik. Ayrıca, hem özellik hem de hiperparametre seçimi için yeni ve etkili bir çift Parçacık Sürü Optimizasyonu (PSO) tabanlı bir algoritma önerdik. Eski algoritmayı, derin öğrenme modelinin antrenman öncesi aşamasında, verilen antrenman setinin optimum özellik alt kümesi ve azaltılmış antrenman setinin doğruluğunu en üst düzeye çıkartan modelin optimum hipermetreleri elde edileceği şekilde kullandık. eğitim aşamasına. Ayrıca, geliştirilen derin öğrenme modellerinin saldırı tespitinde iyi bilinen bir dizi veri seti ve çeşitli analizler kullanarak etkinliğini doğruladık. Deneysel sonuçlar, çift PSO tabanlı algoritmayı kullanarak ön eğitimli derin öğrenme modellerinin performans açısından geleneksel makine öğrenme yöntemlerinden daha iyi performans gösterdiğini, tespit oranını 1% ile 10% arasında artırdığını ve yanlış alarm oranını 1% ıle 5% arasında azalttığını çoğu durumda göstermiştir. Kişisel bilgisayar ve ağ ortamları için saldırı tespitindeki bulgularımız, dinamik, karma ve çok iş parçacıklı bir bulut tabanlı saldırı algılama sistemi tasarlamak için kullanılır. Buna ek olarak, üçüncü taraf bir bulut hizmeti, önerilen bir bulut tabanlı saldırı algılama sistemini izlemek ve yönetmek, ayrıca bir saldırı alarmı verildiğinde bulut kullanıcıları ve bulut hizmeti sağlayıcısıyla iletişim kurmak için de tasarlanmıştır.Intrusion detection is deemed to be a cornerstone of cyber security. Early and effective intrusion detection has been attracted much attention from researchers in the last decade. However, the existence of a deep and adequate study in using deep learning models for intrusion detection in cyber security is still seldom. In this thesis, we have investigated the problem of intrusion detection in three different environments, namely, personal computer, network and cloud computing. Regarding personal computer and network environments, we have developed a set of deep learning models for masquerade and intrusion detection, respectively. Furthermore, we proposed a novel and efficient double Particle Swarm Optimization (PSO)-based algorithm for both feature and hyperparameter selection. We utilized the former algorithm in the pre-training phase of the deep learning model in such a way that the optimal feature subset of the given training set and the optimal hyperparameters of the model which maximizes the accuracy over the reduced training set, are obtained prior to training phase. Moreover, we validated the effectiveness of the developed deep learning models in intrusion detection using a set of well-known datasets and various analyses. The experimental results demonstrated that the deep learning models with pre-training using the double PSO-based algorithm outperformed the traditional machine learning methods in terms of performance, increased the detection rate between 1% to 10%, and decreased the false alarm rate between 1% to 5% in most cases. Our findings in intrusion detection for personal computer and network environments are exploited to design an integrated cloud-based intrusion detection system which is dynamic, hybrid and multithreaded. In addition to that, a third party cloud service is also designed to monitor and manage the proposed cloud-based intrusion detection system as well as communicate with cloud users and cloud service provider when an alert of attack is raised
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Comparison of Five Different Distributions based onThree Metaheuristics to Model Wind Speed Distribution
Full text linkWind energij Modelling is crucial in studijing anij site s feasibilitij. Wind energij Modelling principallij depends on wind speed distribution. Determining wind speed distribution is fundamentallij based on the used distribution functions. This paper examines five different distributions to describe the wind speed pattern, such as T Location-Scale, Logistic, Extreme Value, and Raijleigh distributions. Besides, alternative optimization algorithms like Multi-Verse Optimizer, Marine Predators Algorithm, and Greij Wolf Optimization are applied to the pre-described distributions to determine the best parameters. Five error measures are investigated and compared to test the accuracij of the presented distributions and optimization methods. Catalca site in Istanbul, Turkeij, is chosen for this analijsis. The analijzed results verifij the applicabilitij of the proposed approach to characterize the wind speed pattern. It was observed from the experimental results that the Raijleigh distribution occupied the highest rank, whereas the Extreme Value distribution was the worst. Manij invaluable conclusions are also discussed based on the results and deep investigations
Statistical analysis of wind energy potential using different estimation methods for Weibull parameters: a case study
No full textAccurate estimation of wind speed distributions is a challenging task in wind power planning and operation. The selection of convenient functions for describing wind speed distribution is a crucial requisite. In this paper, remarkable bi-parameter Weibull function is presented to estimate the wind energy potential. Weibull parameters based on different six estimation methods, namely graphical, method of moment, energy pattern factor, mean standard deviation, power density methods, and genetic algorithm are evaluated. Besides, the goodness of fit of the estimation methods is investigated via mean absolute error, root mean square error, normalized mean absolute error, Chi-square error, and regression coefficient. To plainly identify the best matching estimation method, Net Fitness test is also presented. Catalca in the Marmara region in Istanbul, Republic of Turkey, is selected to be the underlying site. The experimental results show the effectiveness of the estimation methods in modeling wind distribution but with relatively small differences in terms of performance. However, the genetic algorithm and energy pattern factor accomplish the best and worst matching estimation methods, respectively
EDLA-EFDS: A novel ensemble deep learning approach for electrical fault detection systems
No full textEarly detection of electrical faults is a very essential research area due to its positive influence on network stability and customer satisfaction. Despite of the electrical fault detection problem has been researched during the last decade, the existence of an intelligent fault detection system is still rare in real-world applications. Therefore, this study proposes a novel Ensemble Deep Learning Approach for Electrical Fault Detection Systems (EDLA-EFDS) that resolves the limitations of existing systems such as automation, validation, and overfitting. The proposed approach benefits from two phases prior to the training phase, namely, data preprocessing and pre-training. Whereas the data preprocessing phase manages data by executing all elementary operations on the raw data, the pre-training phase selects both optimal features and hyperparameters by exploiting a double Particle Swarm Optimization (PSO) metaheuristic. Thereafter, a bagging ensemble system is deployed from three different deep learning paradigms, namely, Deep Neural Networks (DNN), Long Short-Term Memory recurrent Neural Networks (LSTM-RNN), and Deep Belief Networks (DBN). The ensemble system is followed by a majority voting engine to produce the final decision. Moreover, the performance of the ensemble system leveraged by the proposed approach is measured on the VSB dataset which is a modern and realistic dataset for power line fault detection. Finally, the analysis of the results using various scenarios and aspects such as the Receiver Operating Characteristic (ROC) curves and Friedman test is provided. The experimental results confirm the effectiveness of the proposed approach in solving the electrical fault detection problem. © 2022 Elsevier B.V
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Enhanced anomaly-based fault detection system in electrical power grids
No full textEarly and accurate fault detection in electrical power grids is a very essential research area because of its positive influence on network stability and customer satisfaction. Although many electrical fault detection techniques have been introduced during the past decade, the existence of an effective and robust fault detection system is still rare in real-world applications. Moreover, one of the main challenges that delays the progress in this direction is the severe lack of reliable data for system validation. Therefore, this paper proposes a novel anomaly-based electrical fault detection system which is consistent with the concept of faults in the electrical power grids. It benefits from two phases prior to training phase, namely, data preprocessing and pretraining. While the data preprocessing phase executes all elementary operations on the raw data, the pretraining phase selects the optimal hyperparameters of the model using a particle swarm optimization (PSO)-based algorithm. Furthermore, the one-class support vector machines (OC-SVMs) and the principal component analysis (PCA) anomaly-based detection models are exploited to validate the proposed system on the VSB dataset which is a modern and realistic electrical fault detection dataset. Finally, the results are thoroughly discussed using several quantitative and statistical analyses. The experimental results confirm the effectiveness of the proposed system in improving the detection of electrical faults
8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024
No full text▪️ Date of Conference: 21-22 September 2024.The 'Psychological Assistant' presents a groundbreaking approach to remote emotion assessment by integrating video analysis techniques, computer vision, speech recognition, and Natural Language Processing (NLP). Leveraging pre-trained models such as Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), and advanced NLP algorithms, the system analyzes facial expressions, voice signals, and Text Classification to provide mental health practitioners with comprehensive insights during remote consultations. Through the use of methods such as averaging and combining over time, the system ensures a thorough emotion evaluation, promising high accuracy and reliability in mood identification. This innovative integration of NLP enhances the system's capability to understand and interpret textual cues, allowing for a more holistic assessment of patients' mental states. The technology holds the potential for early intervention, personalized treatment plans, and an elevated standard of care in remote mental health services, representing a significant advancement in digital healthcare solutions. © 2024 IEEE
- …
