教学课程资源库 更多>>

关键词： Feature extraction   Training   Metaheuristics   Intrusion detection   Classification algorithms   Computer science   Artificial neural networks   Intrusion detection system (IDS)   bat algorithm (BAT)   metaheuristic algorithm (MA)   feature selection (FS)   multi-objective optimization (MOO)   multilayer perceptron (MLP)  

摘要： The staggering development of cyber threats has propelled experts, professionals and specialists in the field of security into the development of more dependable protection systems, including effective intrusion detection system (IDS) mechanisms which are equipped for boosting accurately detected threats and limiting erroneously detected threats simultaneously. Nonetheless, the proficiency of the IDS framework depends essentially on extracted features from network traffic and an effective classifier of the traffic into abnormal or normal traffic. The prime impetus of this study is to increase the performance of the IDS on networks by building a two-phase framework to reinforce and subsequently enhance detection rate and diminish the rate of false alarm. The initial stage utilizes the developed algorithm of a proficient wrapper-approach-based feature selection which is created on a multi-objective BAT algorithm (MOBBAT). The subsequent stage utilizes the features obtained from the initial stage to categorize the traffic based on the newly upgraded BAT algorithm (EBAT) for training multilayer perceptron (EBATMLP), to improve the IDS performance. The resulting methodology is known as the (MOB-EBATMLP). The efficiency of our proposition has been assessed by utilizing the mainstream benchmarked datasets: NLS-KDD, ISCX2012, UNSW-NB15, KDD CUP 1999, and CICIDS2017 which are established as standard datasets for evaluating IDS. The outcome of our experimental analysis demonstrates a noteworthy advancement in network IDS above other techniques.

关键词： Risk assessment   Software testing   Training   Random forests   Predictive models   Machine learning   Computer science   Risk in requirements   risk dataset for requirements   tree family machine learning technique  

摘要： Risk prediction is the most sensitive and critical activity in the Software Development Life Cycle (SDLC). It might determine whether the project succeeds or fails. To increase the success probability of a software project, the risk should be predicted at the early stages. This study proposed a novel model based on the requirement risk dataset to predict software requirement risks using Tree-Family -Machine-Learning (TF-ML) approaches. Moreover, the proposed model is compared with the state-of-the-art models to determine the best-suited methodology based on the nature of the dataset. These strategies are assessed and evaluated using a variety of metrics. The findings of this study may be reused as a baseline for future studies and research, allowing the results of any proposed approach, model, or framework to be benchmarked and easily checked.

关键词： General \u0026 Introductory Computer Science  

ISBN: (数字)9781394163830;9781394163823 ISBN: (纸本)9781786307552

摘要： This book serves as a guide to help the reader develop an awareness of security vulnerabilities and attacks, and encourages them to be circumspect when using the various computer resources and tools available today. For experienced users, Computer Science Security presents a wide range of tools to secure legacy software and hardware. Computing has infiltrated all fields nowadays. No one can escape this wave and be immune to security attacks, which continue to evolve, gradually reducing the level of expertise needed by hackers. It is high time for each and every user to acquire basic knowledge of computer security, which would enable them to mitigate the threats they may face both personally and professionally. It is this combined expertise of individuals and organizations that will guarantee a minimum level of security for families, schools, the workplace and society in general.

关键词： Music   Recommender systems   Task analysis   Context modeling   Computer science   Collaboration   Real-time systems   Recommender system   temporal point process   attention mechanism   user profiling   music recommendation  

摘要： Recommender systems, which aim to provide personalized suggestions for users, have proven to be an effective approach to cope with the information overload problem existing in many online applications and services. In this paper, we target two specific sequential recommendation tasks, next music recommendation and next new music recommendation, to predict the next (new) music piece that users would like based on their historical listening records. In current music recommender systems, various kinds of auxiliary/side information, e.g., item contents and users' contexts, have been taken into account to facilitate user/item preference modeling and have yielded comparable performance improvement. Despite the gained benefits, it is still a challenging and important problem to fully exploit sequential music listening records due to the complexity and diversity of interactions and temporal contexts among users and music, as well as the dynamics of users' preferences. To this end, this paper proposes a novel Attentive Temporal Point Process (ATPP) approach for sequential music recommendation, which is mainly composed of a temporal point process model and an attention mechanism. Our ATPP can effectively capture the long- and short-term preferences from the sequential behaviors of users for sequential music recommendation. Specifically, ATPP is able to discover the complex sequential patterns from the interaction between users and music with the temporal point process, as well as model the dynamic impact of historical music listening records on next (new) music pieces adaptively with an attention mechanism. Comprehensive experiments on four real-world music datasets demonstrate that the proposed approach ATPP outperforms state-of-the-art baselines in both next and next new music recommendation tasks.

关键词： perseverance   technology   acceptance   COVID-19   under-developed countries  

摘要： A study is conducted with 368 teachers teaching various undergraduate Computer Science and Computer Engineering courses in an under-developed country - Pakistan, during the COVID-19 pandemic. A teaching model is presented in this research, suggesting that the grit had played an important role in technology adoption for online teaching during the COVID-19. It is found that although the absence of technological support such as high speed Internet and consistent, robust and useful LMS, teachers were still adopting and using technologies such as Google Classroom, Zoom and WhatsApp groups for teaching the students in real-time or through recorded videos. This behavior is explained by the teacher's grit that has also motivated the adoption of online teaching related technologies. The lack of technology such as LMS does affect the user satisfaction, however, it didn't affect the usage behavior of the adoption and use of technology. The initial research model had components from non-cognitive learner characteristics, and from various popular technology usage and acceptance models such as an Information System success model, and Unified Theory of Acceptance and Use of Technology. A quantitative questionnaire survey is conducted to assess the proposed research model. The resultant research model had components only from non-cognitive learner characteristics and Unified Theory of Acceptance and Use of Technology model. The data is analyzed using SEM PLS, K-means clustering and Decision Tree classification method.

关键词： Encryption   Privacy   Data privacy   Companies   Cloud computing   Servers   Computer science   Cloud storage   services computing   reverse nearest neighbor query   order-preserving encryption  

摘要： With the advent of cloud computing, it has become more and more popular to outsource various services to the cloud for releasing the burden of local data storage and maintenance. However, it may cause serious privacy problems because the cloud may be untrusted. In this article, we study the privacy-preserving reverse nearest neighbor (PPRNN) query over encrypted spatial data. First, we introduce the concept of reference-locked order-preserving encryption (RL-OPE) with its construction and security proof, which reveals less information than traditional order-preserving encryption (OPE). Then, we present a novel PPRNN scheme in static setting based on structured encryption (SE) and the proposed RL-OPE, called sPPRNN. After that, we design a generic method that extends a PPRNN scheme in static setting to the counterpart in dynamic setting, called dPPRNN. Furthermore, we present a thorough privacy analysis of our proposal. Finally, we demonstrate its efficiency and effectiveness for practical deployment through extensive experiments.

关键词： Diseases   Medical diagnostic imaging   Semantics   Medical diagnosis   Encoding   Learning systems   Computer science   Representation learning   information fusion   disease prediction   network embedding  

摘要： Online medical consult and offline medical check-in have generated a large amount of health-related data in medical forums and patient records. However, exploiting the user-generated content for orienting patients online and assisting medical checkup offline is nontrivial due to the sparsity of symptom-disease associations. The serious sparsity is caused by the informal/chatty expressions of symptoms in the data.

关键词： Image reconstruction   Spatial resolution   Optimization   Computer science   Training   Spectral analysis   Sparse matrices   Hyperspectral image super-resolution (SR)   pixel-aware refinement   unsupervised deep learning  

摘要： Unsupervised fusion-based hyperspectral imagery (HSI) super-resolution (SR) is an essential task of HSI processing, which aims to reconstruct a high-resolution (HR) HSI using only an observed low-resolution HSI and a conventional HR image. Although a large number of unsupervised HSI SR methods have been proposed, the heuristic handcrafted image priors adopted by the majority of these methods restrict their capacity to capture specific characteristics of the HSI, as well as their ability to generalize to noisy observation images. In this study, we investigate a fusion-based HSI SR framework with the deep image prior, in which the deep neural network (rather than a heuristic handcrafted image prior) is exploited to capture plenty of image statistics. Within this framework, we further propose an unsupervised recurrence-based HSI SR method using pixel-aware refinement, which utilizes the intermediate reconstruction results to self-supervise unsupervised learning. Due to containing the information of the image-specific characteristic, the proposed method achieves better performance, in terms of both accuracy and robustness to noise, compared with the existing methods. Extensive experiments on four HSI data sets demonstrate the effectiveness of the proposed method.

关键词： STEM   computer science   data science   modelling and integration  

摘要： Currently STEM education evolves rapidly towards a higher integration either among separate constituents (Science, Technology, Engineering and Mathematics) or by adding the new aspects, such as social. This paper aims at extending the science dimension in STEM-driven Computer Science (CS) education by integrating (through modelling) Data Science (DS) concepts into the high school curriculum. Three types of models and modelling (conceptual, feature-based, and physical modelling) incorporated into a coherent methodology form the background of the proposed approach. Models and modelling, as well processes with data, are essential attributes of engineering education too. The core result of this paper is a novel three-layered framework outlining a series of modelling processes to support integration along with the assessment model. The latter includes the Revised Bloom's taxonomy combined with computational and scientific thinking skills. The use of this approach in the real educational setting and provided experiments show that discovered models ensure a seamless integration of the DS component into STEM-driven CS education. This approach contributes to the increased students' motivation to learn due to the interesting real-world task and active learning of engineering aspects through constructing and testing own experimental system and data processing. The approach also enforces the learner's interdisciplinary knowledge by computational, scientific, and designing skills so important for engineering activities.