Data stream classification with artificial endocrine system

Due to concept drifts, maintaining an up-to-date model is a challenging task for most of the current classification approaches used in data stream mining. Both the incremental classifiers and the ensemble classifiers spend most of their time in updating their temporary models and at the same time, a big sample buffer for training a classifier is necessary for most of them. These two drawbacks constrain further application in classifying a data stream. In this paper, we present a hormone based nearest neighbor classification algorithm for data stream classification, in which the classifier is updated every time a new record arrives. The records could be seen as locations in the feature space, and each location can accommodate only one endocrine cell. The classifier consists of endocrine cells on the boundaries of different classes. Every time a new record arrives, the cell that resides in the most unfit location will move to the new arrived record. In this way, the changing boundaries between different classes are recorded by the locations where endocrine cells reside in. The main advantages of the proposed method are the saving of the sample buffer and the improving of the classification accuracy. It is very important for conditions where the hardware resources are very expensive or the main memory is limited. Experiments on synthetic and real life data sets show that the proposed algorithm is able to classify data streams with less memory space and classification error.     

Fingerprint matching,spoof and liveness detection: classification and literature review

Fingerprint matching,spoof mitigation and liveness detection are the trendiest biometric techniques,mostly because of their stability through life,uniqueness and their least risk of invasion.In recent decade,several techniques are presented to address these challenges over well-known data-sets.This study provides a comprehensive review on the fingerprint algorithms and techniques which have been published in the last few decades.It divides the research on fingerprint into nine different approaches including feature based,fuzzy logic,holistic,image enhancement,latent,conventional machine learning,deep learning,template matching and miscellaneous tech-niques.Among these,deep learning approach has outperformed other approaches and gained significant attention for future research.By reviewing fingerprint literature,it is historically divided into four eras based on 106 referred papers and their cumulative citations.     

Adversarial example detection for DNN models: a review and experimental comparison

Deep learning (DL) has shown great success in many human-related tasks, which has led to its adoption in many computer vision based applications, such as security surveillance systems, autonomous vehicles and healthcare. Such safety-critical applications have to draw their path to success deployment once they have the capability to overcome safety-critical challenges. Among these challenges are the defense against or/and the detection of the adversarial examples (AEs). Adversaries can carefully craft small, often imperceptible, noise called perturbations to be added to the clean image to generate the AE. The aim of AE is to fool the DL model which makes it a potential risk for DL applications. Many test-time evasion attacks and countermeasures, i.e., defense or detection methods, are proposed in the literature. Moreover, few reviews and surveys were published and theoretically showed the taxonomy of the threats and the countermeasure methods with little focus in AE detection methods. In this paper, we focus on image classification task and attempt to provide a survey for detection methods of test-time evasion attacks on neural network classifiers. A detailed discussion for such methods is provided with experimental results for eight state-of-the-art detectors under different scenarios on four datasets. We also provide potential challenges and future perspectives for this research direction.

     

Pattern classification with missing data: a review

Pattern classification has been successfully applied in many problem domains, such as biometric recognition, document classification or medical diagnosis. Missing or unknown data are a common drawback that pattern recognition techniques need to deal with when solving real-life classification tasks. Machine learning approaches and methods imported from statistical learning theory have been most intensively studied and used in this subject. The aim of this work is to analyze the missing data problem in pattern classification tasks, and to summarize and compare some of the well-known methods used for handling missing values.     

Fingerprint classification: a review

Biometrics is the automatic identification of an individual that is based on physiological or behavioural characteristics. Due to its security-related applications and the current world political climate, biometrics is currently the subject of intense research by both private and academic institutions. Fingerprints are emerging as the most common and trusted biometric for personal identification. The main objective of this paper is to review the extensive research that has been done on fingerprint classification over the last four decades. In particular, it discusses the fingerprint features that are useful for distinguishing fingerprint classes and reviews the methods of classification that have been applied to the problem. Finally, it presents empirical results from the state of the art fingerprint classification systems that have been tested using the NIST Special Database 4.     

Performance evaluation of classification trees for building detection from aerial images and LiDAR data: a comparison of classification trees models

This study assesses the performance of three classification trees (CT) models (entropy, gain ratio and gini) for building detection by the fusion of airborne laser scanner data and multispectral aerial images. Data from four study areas with different sensors and scene characteristics were used to assess the performance of the models. The process of performance evaluation is based on four criteria: model validation and testing, classification accuracies, relative importance of input variables, as well as transferability of CT derived from one data set to another. The LiDAR point clouds were filtered to generate a digital terrain model (DTM) based on the orthogonal polynomials, and then a digital surface model (DSM) and the normalized digital surface model (nDSM) were generated. A set of 26 uncorrelated feature attributes were derived from the original aerial images, LiDAR intensity image, DSM and nDSM. Finally, the three CT models were used to classify buildings, trees, roads and ground from aerial images, LiDAR data and the generated attributes, with the most accurate average classifications of 95% being achieved. The entropy splitting algorithm proved to be a preferable algorithm for building detection from aerial images and LiDAR data.     

News recommender system: a review of recent progress,challenges, and opportunities

Nowadays, more and more news readers read news online where they have access to millions of news articles from multiple sources. In order to help users find the right and relevant content, news recommender systems (NRS) are developed to relieve the information overload problem and suggest news items that might be of interest for the news readers. In this paper, we highlight the major challenges faced by the NRS and identify the possible solutions from the state-of-the-art. Our discussion is divided into two parts. In the first part, we present an overview of the recommendation solutions, datasets, evaluation criteria beyond accuracy and recommendation platforms being used in the NRS. We also talk about two popular classes of models that have been successfully used in recent years. In the second part, we focus on the deep neural networks as solutions to build the NRS. Different from previous surveys, we study the effects of news recommendations on user behaviors and try to suggest possible remedies to mitigate those effects. By providing the state-of-the-art knowledge, this survey can help researchers and professional practitioners have a better understanding of the recent developments in news recommendation algorithms. In addition, this survey sheds light on the potential new directions.

     

Deep learning models for predictive maintenance: a survey,comparison, challenges and prospects

Applied Intelligence - Given the growing amount of industrial data in the 4th industrial revolution, deep learning solutions have become popular for predictive maintenance (PdM) tasks, which...     

Virtualization layer security challenges and intrusion detection/prevention systems in cloud computing: a comprehensive review

Virtualization plays a vital role in the construction of cloud computing. However, various vulnerabilities are existing in current virtualization implementations, and thus there are various security challenges at virtualization layer. In this paper, we investigate different vulnerabilities and attacks at virtualization layer of cloud computing. We examine the proposals of cloud intrusion detection system (IDS) and intrusion detection and prevention system frameworks. We recommend the cloud IDS requirements and research scope to achieve desired level of security at virtualization layer of cloud computing.     

Deployment techniques in wireless sensor networks: a survey,classification, challenges,and future research issues

The Journal of Supercomputing - Wireless sensor networks (WSNs) have been considered as one of the fine research areas in recent years because of vital role in numerous applications. To process the...     

Anomaly-based network intrusion detection: Techniques,systems and challenges

The Internet and computer networks are exposed to an increasing number of security threats. With new types of attacks appearing continually, developing flexible and adaptive security oriented approaches is a severe challenge. In this context, anomaly-based network intrusion detection techniques are a valuable technology to protect target systems and networks against malicious activities. However, despite the variety of such methods described in the literature in recent years, security tools incorporating anomaly detection functionalities are just starting to appear, and several important problems remain to be solved. This paper begins with a review of the most well-known anomaly-based intrusion detection techniques. Then, available platforms, systems under development and research projects in the area are presented. Finally, we outline the main challenges to be dealt with for the wide scale deployment of anomaly-based intrusion detectors, with special emphasis on assessment issues.     

A novel block intensity comparison code for video classification and retrieval

Appropriate organization of video databases is essential for pertinent indexing and retrieval of visual information. This paper proposes a new feature called block intensity comparison code (BICC) for video classification and retrieval. Block intensity comparison code represents the average block intensity difference between blocks of a frame. The extracted feature is further processed using principal component analysis (PCA) to reduce the redundancy while exploiting the correlations between the feature elements. The temporal nature of video is modeled by hidden Markov model (HMM) with BICC as the features. It is found that, BICC outperforms other visual features such as edge, motion and histogram which are commonly used for video classification.     

Business process modelling challenges and solutions: a literature review

We have presented a review of the challenges facing business PM. These challenges are categorized into three challenges: (1) between business and IT, difficulty of deriving IT goals from business goals challenges; (2) security issues on business PM challenges; and (3) managing customer power, the rapidly changing business environment and business process (BP) challenges. Also, it presents the limitations of existing business PM frameworks. For example, in the first challenge, the existing literature is limited because they fail to capture the real business environment. Also, it is hard for IT analysts to understand BPs. In the second challenges, the existing methods of IS development fail to successfully integrate security during all development process stages and only deal with specific security requirements, goals and constraints. In the third challenges, no research has been conducted in the area of separating customers into different priority groups to provide services according to their required delivery time, payment history and feedback. Finally, we outline possible further research directions in the business PM domain. A systematic literature review method was used. Our review reports on academic publications on business PM challenges over the 13 years from 2000 to 2012. There are 31 journals as well as the IEEE and ACM databases being searched to identify relevant papers. Our systematic literature review results in that there are 53 journal papers as being the most relevant to our topic. In conclusion, it is not easy to create a good business PM. However, the research have to pay much attention on the area of creating successful business PM by creating secure business PM, manage customer power and create business PM where IT goals can be easily derived from business goals.     

Performance comparison of feature extraction algorithms for target detection and classification

This paper addresses the problem of target detection and classification, where the performance is often limited due to high rates of false alarm and classification error, possibly because of inadequacies in the underlying algorithms of feature extraction from sensory data and subsequent pattern classification. In this paper, a recently reported feature extraction algorithm, symbolic dynamic filtering (SDF), is investigated for target detection and classification by using unmanned ground sensors (UGS). In SDF, sensor time series data are first symbolized to construct probabilistic finite state automata (PFSA) that, in turn, generate low-dimensional feature vectors. In this paper, the performance of SDF is compared with that of two commonly used feature extractors, namely Cepstrum and principal component analysis (PCA), for target detection and classification. Three different pattern classifiers have been employed to compare the performance of the three feature extractors for target detection and human/animal classification by UGS systems based on two sets of field data that consist of passive infrared (PIR) and seismic sensors. The results show consistently superior performance of SDF-based feature extraction over Cepstrum-based and PCA-based feature extraction in terms of successful detection, false alarm, and misclassification rates.     

User involvement: a review of the benefits and challenges

User involvement is a widely accepted principle in development of usable systems. However, it is a vague concept covering many approaches. This study first clarifies the nature of user involvement and its expected benefits, and secondly reviews three streams of research, to evaluate the benefits and problems of varied user involvement approaches in practice. The particular focus of this study is on the early activities in the development process. An analysis of the literature suggests that user involvement has generally positive effects, especially on user satisfaction, and some evidence exists to suggest that taking users as a primary information source is an effective means of requirements capture. However, the role of users must be carefully considered and more cost-efficient practices are needed for gathering users' implicit needs and requirements in real product development contexts.     

Fault detection,location and classification of a transmission line

Neural Computing and Applications - Transient stability is very important in power system. Large disturbances like fault in a transmission line are a concern which needs to be disconnected as...     

Tasks for agent-based negotiation teams: Analysis,review, and challenges

An agent-based negotiation team is a group of interdependent agents that join together as a single negotiation party due to their shared interests in the negotiation at hand. The reasons to employ an agent-based negotiation team may vary: (i) more computation and parallelization capabilities; (ii) unite agents with different expertise and skills whose joint work makes it possible to tackle complex negotiation domains; (iii) the necessity to represent different stakeholders or different preferences in the same party (e.g., organizations, countries, and married couple). The topic of agent-based negotiation teams has been recently introduced in multi-agent research. Therefore, it is necessary to identify good practices, challenges, and related research that may help in advancing the state-of-the-art in agent-based negotiation teams. For that reason, in this article we review the tasks to be carried out by agent-based negotiation teams. Each task is analyzed and related with current advances in different research areas. The analysis aims to identify special challenges that may arise due to the particularities of agent-based negotiation teams.