A hybrid approach to interactive global illumination and soft shadows

We present a hybrid approach to simulate global illumination and soft shadows at interactive frame rates. The strengths of hardware-accelerated GPU techniques are combined with CPU methods to achieve physically consistent results while maintaining reasonable performance. The process of image synthesis is subdivided into multiple passes accounting for the different illumination effects. While direct lighting is rendered efficiently by rasterization, soft shadows are simulated using a novel approach combining the speed of shadow mapping and the accuracy of visibility ray tracing. A shadow refinement mask is derived from the result of the direct lighting pass and from a small number of shadow maps to identify the penumbral region of an area light source. This region is accurately rendered by ray tracing. For diffuse indirect illumination, we introduce radiosity photons to profit from the flexibility of a point-based sampling while maintaining the benefits of interpolation over scattered data approximation or density estimation. A sparse sampling of the scene is generated by particle tracing. An area is approximated for each point sample to compute the radiosity solution using a relaxation approach. The indirect illumination is interpolated between neighboring radiosity photons, stored in a multidimensional search tree. We compare different neighborhood search algorithms in terms of image quality and performance. Our method yields interactive frame rates and results consistent with path tracing reference solutions.     

An efficient algorithm for learning to rank from preference graphs

In this paper, we introduce a framework for regularized least-squares (RLS) type of ranking cost functions and we propose three such cost functions. Further, we propose a kernel-based preference learning algorithm, which we call RankRLS, for minimizing these functions. It is shown that RankRLS has many computational advantages compared to the ranking algorithms that are based on minimizing other types of costs, such as the hinge cost. In particular, we present efficient algorithms for training, parameter selection, multiple output learning, cross-validation, and large-scale learning. Circumstances under which these computational benefits make RankRLS preferable to RankSVM are considered. We evaluate RankRLS on four different types of ranking tasks using RankSVM and the standard RLS regression as the baselines. RankRLS outperforms the standard RLS regression and its performance is very similar to that of RankSVM, while RankRLS has several computational benefits over RankSVM.     

A multicriteria approach to two-level hierarchy scheduling in grids

In this paper we address a multicriteria scheduling problem for computational Grid systems. We focus on the two-level hierarchical Grid scheduling problem, in which at the first level (the Grid level) a Grid broker makes scheduling decisions and allocates jobs to Grid nodes. Jobs are then sent to the Grid nodes, where local schedulers generate local schedules for each node accordingly. A general approach is presented taking into account preferences of all the stakeholders of Grid scheduling (end-users, Grid administrators, and local resource providers) and assuming a lack of knowledge about job time characteristics. A single-stakeholder, single-criterion version of the approach has been compared experimentally with the existing approaches.     

A new numerical learning approach to solve general Falkner–Skan model

A new numerical learning approach namely Rational Gegenbauer Least Squares Support Vector Machines (RG_LS_SVM), is introduced in this paper. RG_LS_SVM method is a combination of collocation method based on rational Gegenbauer functions and LS_SVM method. This method converts a nonlinear high order model on a semi-infinite domain to a set of linear/nonlinear equations with equality constraints which decreases computational costs. Blasius, Falkner–Skan and MHD Falkner–Skan models and the effects of various parameters over them are investigated to satisfy accuracy, validity and efficiency of the proposed method. Both Primal and Dual forms of the problems are considered and the nonlinear models are converted to linear models by applying quasilinearization method to get the better results. Comparing the results of RG_LS_SVM method with available analytical and numerical solutions show that the present methods are efficient and have fast convergence rate and high accuracy.

     

Distance learning success – a perspective from socio-technical systems theory

With widespread adoption of computer-based distance education as a mission-critical component of the institution's educational program, the need for evaluation has emerged. In this research, we aim to expand on the systems approach by offering a model for evaluation based on socio-technical systems theory addressing a stated need in the literature for comprehensive models for evaluating e-learning environments (Holsapple, C.W. and Lee-Post, A., 2006 Holsapple, C. W. and Lee-Post, A. 2006. Defining, assessing, and promoting e-learning success: an information systems perspective. Decision Sciences Journal of Innovative Education, 4(1): 67–85. [Crossref] , [Google Scholar]. Defining, assessing, and promoting e-learning success: an information systems perspective. Decision Sciences Journal of Innovative Education, 4(1), 67–85). The proposed systems model evaluates distance learning success from the instructor's perspective. It defines and develops measures for course quality, system quality and corresponding impacts. The model is tested based on the data collected from 548 instructors of seven universities in the Midwest region of the USA. The results suggest that the proposed multi-dimensional system flexibility scale is reliable. The course quality significantly affects both system flexibility and faculty perceived impacts of distance education. The system flexibility also significantly affects both course quality and faculty perceived impacts.     

A novel approach to visualize web anomaly attacks in pervasive computing environment

These days, a pervasive computing environment is a rapidly changing trend towards increasingly always-on connected computing devices in the convergence environment. In a pervasive computing environment, there are various multimedia web services and communications for various devices in order to provide interesting and invaluable information to users. Meanwhile, providing a wide variety of the web-based multimedia services and communications may cause various security threats and abnormal behaviors. In this paper, a multimedia visualization approach for pervasive computing environment is proposed which analyzes HTTP request and response header information to detect and visualize multimedia web attacks based on the Bayesian method. We conducted a few cases’ experiment for the verification of the proposed approach in a real environment. The experimental results such as web attack detection visualization, scanning and password attack visualization, and attacker’s position tracking visualization verify the usability of the proposed approach.     

A novel unsupervised classification approach for network anomaly detection by k-Means clustering and ID3 decision tree learning methods

This paper presents a novel host-based combinatorial method based on k-Means clustering and ID3 decision tree learning algorithms for unsupervised classification of anomalous and normal activities in computer network ARP traffic. The k-Means clustering method is first applied to the normal training instances to partition it into k clusters using Euclidean distance similarity. An ID3 decision tree is constructed on each cluster. Anomaly scores from the k-Means clustering algorithm and decisions of the ID3 decision trees are extracted. A special algorithm is used to combine results of the two algorithms and obtain final anomaly score values. The threshold rule is applied for making the decision on the test instance normality. Experiments are performed on captured network ARP traffic. Some anomaly criteria has been defined and applied to the captured ARP traffic to generate normal training instances. Performance of the proposed approach is evaluated using five defined measures and empirically compared with the performance of individual k-Means clustering and ID3 decision tree classification algorithms and the other proposed approaches based on Markovian chains and stochastic learning automata. Experimental results show that the proposed approach has specificity and positive predictive value of as high as 96 and 98%, respectively.     

Can past failures help identify vulnerable bridges to extreme events? A biomimetical machine learning approach

With limited resources to properly maintain and upgrade transportation infrastructure, bridges often end up exceeding their expected service lifespan; thus, becoming vulnerable to the adverse effects of aging and extreme loading conditions. In order to better assess the vulnerability of these structures, this study showcases the outcome of an observational analysis that utilizes biomimetical (bio-inspired) machine learning algorithms to predict the vulnerability and expected degree of damage in bridges in the aftermath of an extreme loading event (such as fire, flood, earthquake, etc.). These algorithms comprise deep learning, decision tree, genetic algorithm and genetic programing and were trained and validated using 299 international incidents covering a wide variety of bridge systems/configurations, traffic demands, etc. Based on this analysis, user-friendly assessment tools that can be used to evaluate propensity of a given bridge to undergo high levels of damage and/or collapse are developed. These tools can aid designers and decision-makers in evaluating performance of new or existing bridges against a variety of hazards, as well as in developing relevant design strategies for mitigating disaster-induced failures as to minimize disruptions to supply chain operations and/or evacuations during an emergency.

     

Interactive reconstructive student modeling: A machine‐learning approach

Reconstructive bug modeling is a well‐known approach to student modeling in intelligent tutoring systems, suitable for modeling procedural tasks. Domain knowledge is decomposed into the set of primitive operators and the set of conditions of their applicability. Reconstructive modeling is capable of describing errors that come from irregular application of correct operators. The main obstacle to successfulness of this approach is such decomposition of domain knowledge to primitive operators with a very low level of abstraction so that bugs could never occur within them. The other drawback of this modeling scheme is its efficiency because it is usually done offline, due to vast search spaces involved.

This article reports a novel approach to reconstructive modeling based on machine‐learning techniques for inducing procedures from traces. The approach overcomes the problems of reconstructive modeling by its interactive nature. It allows online model generation by using domain knowledge and knowledge about the student to focus the search on the portion of the problem space the student is likely to traverse while solving the problem. Furthermore, the approach is not only incremental, but also truly interactive because it involves the student in explicit dialogs about his or her goals. In such a way, it is possible to determine whether the student knows the operator he or she is trying to apply. Pedagogical actions and the student model are generated interchangeably, thus allowing for dynamic adaptation of instruction, problem generation, and immediate feedback on student's errors. The approach presented is examined in the context of the symbolic integration tutoring system (SINT), an intelligent tutoring system (ITS) for the domain of symbolic integration.     

A combined CLP-MILP approach for scheduling commodities in a pipeline

This paper addresses the problem of developing an optimization model to aid the operational scheduling in a real-world pipeline scenario. The pipeline connects refinery and harbor, conveying different types of commodities (gasoline, diesel, kerosene, etc.). An optimization model was developed to determine pipeline scheduling with improved efficiency. This model combines constraint logic programming (CLP) and mixed integer linear programming (MILP) in a CLP-MILP approach. The proposed model uses decomposition strategies, continuous time representation, intervals that indicate time constraints (time windows), and a series of operational issues, such as the seasonal and hourly cost of electric energy (on-peak demand hours). Real cases were solved in a matter of seconds. The computational results have demonstrated that the model is able to define new operational points to the pipeline, providing significant cost savings. Indeed the CLP-MILP model is an efficient tool to aid operational decision-making within this real-world pipeline scenario.     

YAARC: yet another approach to further reducing the rate of conflict misses

Traditional set associative caches are seriously prone to conflict misses. We propose an adapted new skewed associative architecture as an attempt to alleviate this problem. It has already been shown that skewed associative caches can reduce the rate of conflict misses by using different hash functions to index different banks. Building on this observation, we propose yet another approach to further reduce the rate of conflict misses, nicknamed YAARC (Yet Another Approach to Reducing Conflicts) that uses different hash functions to index into a single bank. Mathematical modeling and simulation results are exploited to evaluate the impact of YAARC on the rate of conflict misses. Mathematical analysis show the superiority of YAARC caches over set and skewed associative caches from the conflict miss point of view. Simulations, using some benchmarks from SPEC CPU2000 benchmark suit that former researchers have reported them as the best candidates for cache performance evaluation, also show nearly 43% conflict miss rate improvement for the skewed associative cache over the set associative cache, and nearly 31% improvement for the YAARC cache over the skewed associative cache. This implies that YAARC caches considerably outperform set and skewed associative caches from the conflict miss point of view. Since production of YAARC caches require a dispensable amount of hardware overhead, they can be considered as a cost effective approach to minimize the rate of conflict misses.

Hybrid unsupervised web-attack detection and classification – A deep learning approach

Web requests made by users of web applications are manipulated by hackers to gain control of web servers. Moreover, detecting web attacks has been increasingly important in the distribution of information over the last few decades. Also, several existing techniques had been performed on detecting vulnerable web attacks using machine learning and deep learning techniques. However, there is a lack in achieving attack detection ratio owing to the utilization of supervised and semi-supervised learning approaches. Thus to overcome the aforementioned issues, this research proposes a hybrid unsupervised detection model a deep learning-based anomaly-based web attack detection. Whereas, the encoded outputs of De-Noising Autoencoder (DAE), as well as Stacked Autoencoder (SAE), are integrated and given to the Generative adversarial network (GAN) as input to improve the feature representation ability to detect the web attacks. Consequently, for classifying the type of attacks, a novel DBM-Bi LSTM-based classification model has been introduced. Which incorporates DBM for binary classification and Bi-LSTM for multi-class classification to classify the various attacks. Finally, the performance of the classifier in terms of recall, precision, F1-Score, and accuracy are evaluated and compared. The proposed method achieved high accuracy of 98%.     

A lightweight clustering–based approach to discover different emotional shades from social message streams

With the explosion of social media, automatic analysis of sentiment and emotion from user-generated content has attracted the attention of many research areas and commercial-marketing domains targeted at studying the social behavior of web users and their public attitudes toward brands, social events, and political actions. Capturing the emotions expressed in the written language could be crucial to support the decision-making processes: the emotion resulting from a tweet or a review about an item could affect the way to advertise or to trade on the web and then to make predictions about future changes in popularity or market behavior. This paper presents an experience with the emotion-based classification of textual data from a social network by using an extended version of the fuzzy C-means algorithm called extension of fuzzy C-means. The algorithm shows interesting results due to its intrinsic fuzzy nature that reflects the human feeling expressed in the text, often composed of a mix of blurred emotions, and at the same time, the benefits of the extended version yield better classification results.     

Brave induction: a logical framework for learning from incomplete information

This paper introduces a novel logical framework for concept-learning called brave induction. Brave induction uses brave inference for induction and is useful for learning from incomplete information. Brave induction is weaker than explanatory induction which is normally used in inductive logic programming, and is stronger than learning from satisfiability, a general setting of concept-learning in clausal logic. We first investigate formal properties of brave induction, then develop an algorithm for computing hypotheses in full clausal theories. Next we extend the framework to induction in nonmonotonic logic programs. We analyze computational complexity of decision problems for induction on propositional theories. Further, we provide examples of problem solving by brave induction in systems biology, requirement engineering, and multiagent negotiation.     

A novel intrusion detection approach learned from the change of antibody concentration in biological immune response

Inspired by the relationship between the antibody concentration and the intrusion network traffic pattern intensity, we present a Novel Intrusion Detection Approach learned from the change of Antibody Concentration in biological immune response (NIDAAC) to reduce false alarm rate without affecting detection rate. In NIDAAC, the concepts and formal definitions of self, nonself, antibody, antigen and detector in the intrusion detection domain are given. Then, in initial IDS, new detectors are generated from the gene library and tested by the negative selection. In every effective IDS node, according to the intrusion network traffic pattern intensity, the change of antibody number is recorded from the process of clone proliferation based on the detector evolution. Finally, building upon the above works, a probabilistic calculation model for intrusion alarm production, which is based on the correlation between the antibody concentration and the intrusion network traffic pattern intensity, is proposed. Compared with Naive Bayes (NB), Multilevel Classifier (AdaBoost) and Hidden Markov Model (HMM), the false alarm rate of NIDAAC is reduced by 8.66%, 4.93% and 6.36%, respectively. Our theoretical analysis and experimental results show that NIDAAC has a better performance than previous approaches.     

Emotion recognition using deep learning approach from audio–visual emotional big data

This paper proposes an emotion recognition system using a deep learning approach from emotional Big Data. The Big Data comprises of speech and video. In the proposed system, a speech signal is first processed in the frequency domain to obtain a Mel-spectrogram, which can be treated as an image. Then this Mel-spectrogram is fed to a convolutional neural network (CNN). For video signals, some representative frames from a video segment are extracted and fed to the CNN. The outputs of the two CNNs are fused using two consecutive extreme learning machines (ELMs). The output of the fusion is given to a support vector machine (SVM) for final classification of the emotions. The proposed system is evaluated using two audio–visual emotional databases, one of which is Big Data. Experimental results confirm the effectiveness of the proposed system involving the CNNs and the ELMs.     

Const—A constructive approach to information modelling

An approach to information modelling is presented which is based on the principles of a constructive theory and employs the formalism of production rules. In the paper a constructive approach is taken concerning the nature and representation of abstract objects (here referred to as quasi objects). The cognitive, formal and metaphysical advantages are presented and discussed, and examples employing the constructive approach are presented with comments.     

An integrative approach to assess qualitative and quantitative consumer feedback

The increasing availability of consumer feedback on the web provides a wealth of information that organizations can use for product and service improvement. Many consumer feedback sites allow users to enter both a quantitative rating and a qualitative critique. Previous research has used this information disjunctively. This work proposes an innovative approach that integrates the two types of information to identify words that are related to positive or negative consumer ratings. A case study shows that this approach does raise some issues not identified using existing analytical approaches.