Showing papers in "IEEE Computational Intelligence Magazine in 2014"

Jumping NLP Curves: A Review of Natural Language Processing Research [Review Article]

Abstract: Natural language processing (NLP) is a theory-motivated range of computational techniques for the automatic analysis and representation of human language. NLP research has evolved from the era of punch cards and batch processing (in which the analysis of a sentence could take up to 7 minutes) to the era of Google and the likes of it (in which millions of webpages can be processed in less than a second). This review paper draws on recent developments in NLP research to look at the past, present, and future of NLP technology in a new light. Borrowing the paradigm of `jumping curves? from the field of business management and marketing prediction, this survey article reinterprets the evolution of NLP research as the intersection of three overlapping curves-namely Syntactics, Semantics, and Pragmatics Curves- which will eventually lead NLP research to evolve into natural language understanding.

Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum]

Abstract: "Big Data" as a term has been among the biggest trends of the last three years, leading to an upsurge of research, as well as industry and government applications. Data is deemed a powerful raw material that can impact multidisciplinary research endeavors as well as government and business performance. The goal of this discussion paper is to share the data analytics opinions and perspectives of the authors relating to the new opportunities and challenges brought forth by the big data movement. The authors bring together diverse perspectives, coming from different geographical locations with different core research expertise and different affiliations and work experiences. The aim of this paper is to evoke discussion rather than to provide a comprehensive survey of big data research.

The Emerging Big Dimensionality

Abstract: The world continues to generate quintillion bytes of data daily, leading to the pressing needs for new efforts in dealing with the grand challenges brought by Big Data. Today, there is a growing consensus among the computational intelligence communities that data volume presents an immediate challenge pertaining to the scalability issue. However, when addressing volume in Big Data analytics, researchers in the data analytics community have largely taken a one-sided study of volume, which is the "Big Instance Size" factor of the data. The flip side of volume which is the dimensionality factor of Big Data, on the other hand, has received much lesser attention. This article thus represents an attempt to fill in this gap and places special focus on this relatively under-explored topic of "Big Dimensionality", wherein the explosion of features (variables) brings about new challenges to computational intelligence. We begin with an analysis on the origins of Big Dimensionality. The evolution of feature dimensionality in the last two decades is then studied using popular data repositories considered in the data analytics and computational intelligence research communities. Subsequently, the state-of-the-art feature selection schemes reported in the field of computational intelligence are reviewed to reveal the inadequacies of existing approaches in keeping pace with the emerging phenomenon of Big Dimensionality. Last but not least, the "curse and blessing of Big Dimensionality" are delineated and deliberated.

Frame-Based Detection of Opinion Holders and Topics: A Model and a Tool

Abstract: Sentilo is a model and a tool to detect holders and topics of opinion sentences. Sentilo implements an approach based on the neo-Davidsonian assumption that events and situations are the primary entities for contextualizing opinions, which makes it able to distinguish holders, main topics, and sub-topics of an opinion. It uses a heuristic graph mining approach that relies on FRED, a machine reader for the Semantic Web that leverages Natural Language Processing (NLP) and Knowledge Representation (KR) components jointly with cognitively-inspired frames. The evaluation results are excellent for holder detection (F1: 95%), very good for subtopic detection (F1: 78%), and good for topic detection (F1: 68%).

A Probabilistic Generative Model for Mining Cybercriminal Networks from Online Social Media

Abstract: There has been a rapid growth in the number of cybercrimes that cause tremendous financial loss to organizations. Recent studies reveal that cybercriminals tend to collaborate or even transact cyber-attack tools via the "dark markets" established in online social media. Accordingly, it presents unprecedented opportunities for researchers to tap into these underground cybercriminal communities to develop better insights about collaborative cybercrime activities so as to combat the ever increasing number of cybercrimes. The main contribution of this paper is the development of a novel weakly supervised cybercriminal network mining method to facilitate cybercrime forensics. In particular, the proposed method is underpinned by a probabilistic generative model enhanced by a novel context-sensitive Gibbs sampling algorithm. Evaluated based on two social media corpora, our experimental results reveal that the proposed method significantly outperforms the Latent Dirichlet Allocation (LDA) based method and the Support Vector Machine (SVM) based method by 5.23% and 16.62% in terms of Area Under the ROC Curve (AUC), respectively. It also achieves comparable performance as the state-of-the-art Partially Labeled Dirichlet Allocation (PLDA) method. To the best of our knowledge, this is the first successful research of applying a probabilistic generative model to mine cybercriminal networks from online social media.

Benchmarking Optimization Algorithms: An Open Source Framework for the Traveling Salesman Problem

Abstract: We introduce an experimentation procedure for evaluating and comparing optimization algorithms based on the Traveling Salesman Problem (TSP). We argue that end-of-run results alone do not give sufficient information about an algorithm's performance, so our approach analyzes the algorithm's progress over time. Comparisons of performance curves in diagrams can be formalized by comparing the areas under them. Algorithms can be ranked according to a performance metric. Rankings based on different metrics can then be aggregated into a global ranking, which provides a quick overview of the quality of algorithms in comparison. An open source software framework, the TSP Suite, applies this experimental procedure to the TSP. The framework can support researchers in implementing TSP solvers, unit testing them, and running experiments in a parallel and distributed fashion. It also has an evaluator component, which implements the proposed evaluation process and produces detailed reports. We test the approach by using the TSP Suite to benchmark several local search and evolutionary computation methods. This results in a large set of baseline data, which will be made available to the research community. Our experiments show that the tested pure global optimization algorithms are outperformed by local search, but the best results come from hybrid algorithms.

Computational Intelligence Challenges and Applications on Large-Scale Astronomical Time Series Databases

Abstract: Time-domain astronomy (TDA) is facing a paradigm shift caused by the exponential growth of the sample size, data complexity and data generation rates of new astronomical sky surveys. For example, the Large Synoptic Survey Telescope (LSST), which will begin operations in northern Chile in 2022, will generate a nearly 150 Petabyte imaging dataset of the southern hemisphere sky. The LSST will stream data at rates of 2 Terabytes per hour, effectively capturing an unprecedented movie of the sky. The LSST is expected not only to improve our understanding of time-varying astrophysical objects, but also to reveal a plethora of yet unknown faint and fast-varying phenomena. To cope with a change of paradigm to data-driven astronomy, the fields of astroinformatics and astrostatistics have been created recently. The new data-oriented paradigms for astronomy combine statistics, data mining, knowledge discovery, machine learning and computational intelligence, in order to provide the automated and robust methods needed for the rapid detection and classification of known astrophysical objects as well as the unsupervised characterization of novel phenomena. In this article we present an overview of machine learning and computational intelligence applications to TDA. Future big data challenges and new lines of research in TDA, focusing on the LSST, are identified and discussed from the viewpoint of computational intelligence/machine learning. Interdisciplinary collaboration will be required to cope with the challenges posed by the deluge of astronomical data coming from the LSST.

Muscle Fatigue Tracking with Evoked EMG via Recurrent Neural Network: Toward Personalized Neuroprosthetics

Abstract: -One of the challenging issues in computational rehabilitation is that there is a large variety of patient situations depending on the type of neurological disorder. Human characteristics are basically subject specific and time variant; for instance, neuromuscular dynamics may vary due to muscle fatigue. To tackle such patient specificity and time-varying characteristics, a robust bio-signal processing and a precise model-based control which can manage the nonlinearity and time variance of the system, would bring break-through and new modality toward computational intelligence (CI) based rehabilitation technology and personalized neuroprosthetics. Functional electrical stimulation (FES) is a useful technique to assist restoring motor capability of spinal cord injured (SCI) patients by delivering electrical pulses to paralyzed muscles. However, muscle fatigue constraints the application of FES as it results in the time-variant muscle response. To perform adaptive closedloop FES control with actual muscle response feedback taken into account, muscular torque is essential to be estimated accurately. However, inadequacy of the implantable torque sensor limits the direct measurement of the time-variant torque at the joint. This motivates the development of methods to estimate muscle torque from bio-signals that can be measured. Evoked electromyogram (eEMG) has been found to be highly correlated with FES-induced torque under various muscle conditions, indicating that it can be used for torque/force prediction. A nonlinear ARX (NARX) type model is preferred to track the relationship between eEMG and stimulated muscular torque. This paper presents a NARX recurrent neural network (NARX-RNN) model for identification/prediction of FES-induced muscular dynamics with eEMG. The NARX-RNN model may possess novelty of robust prediction performance. Due to the difficulty of choosing a proper forgetting factor of Kalman filter for predicting time-variant torque with eEMG, the presented NARX-RNN could be considered as an alternative muscular torque predictor. Data collected from five SCI patients is used to evaluate the proposed NARX-RNN model, and the results show promising estimation performances. In addition, the general importance regarding CI-based motor function modeling is introduced along with its potential impact in the rehabilitation domain. The issue toward personalized neuroprosthetics is discussed in detail with the potential role of CI-based identification and the benefit for motor-impaired patient community.

An Adaptive Variable Neighborhood Search for a Heterogeneous Fleet Vehicle Routing Problem with Three-Dimensional Loading Constraints

Abstract: The paper addresses the heterogeneous fleet vehicle routing problem with three-dimensional (3D) loading constraints (3L-HFVRP), a new practical variant of the combined routing and loading problem. In this problem, the loads consist of a set of three-dimensional, rectangular shaped items. The fleet is composed of heterogeneous vehicles with different weight and space capacities. The objective is to serve all customers by selecting a set of vehicles such that the total transportation cost is minimized. The cost consists of the fixed cost of the selected vehicles and their travel cost. In addition, loading sequence related constraints frequently encountered in realistic applications are respected when loading and unloading the items. To solve this challenging problem, we develop an adaptive variable neighborhood search (AVNS) which utilizes an extreme point based first fit heuristic to find a feasible loading pattern for each route. We design two strategies to accelerate the loading and routing processes. The Trie data structure is used to record the loading information of routes already visited and to control the computational effort spent for each route. The Fibonacci heap data structure is used to maintain all of the possible moves and vehicle type assignments, which avoids the duplicated evaluation of some moves and unnecessary loading check of unpromising solutions. The robustness and effectiveness of the proposed algorithm is validated by computational tests performed both on some newly generated 3L-HFVRP instances and well-known benchmark instances from the literature for two simplified VRP variants: the capacitated vehicle routing problem with 3D loading constraints (3L-CVRP) and the pure heterogeneous fleet vehicle routing problem (HFVRP). The numerical experiments show that the proposed AVNS outperforms other algorithms in 3L-CVRP and improves several best known solutions reported in the literature. The results obtained for the pure HFVRP are very close to the best known solutions.

A Hybrid Metaheuristic Optimization Algorithm for Strategic Planning of 4D Aircraft Trajectories at the Continental Scale

Abstract: Global air-traffic demand is continuously increasing. To handle such a tremendous traffic volume while maintaining at least the same level of safety, a more efficient strategic trajectory planning is necessary. In this work, we present a strategic trajectory planning methodology which aims to minimize interaction between aircraft at the European-continent scale. In addition, we propose a preliminary study that takes into account uncertainties of aircraft positions in the horizontal plane. The proposed methodology separates aircraft by modifying their trajectories and departure times. This route/departuretime assignment problem is modeled as a mixed-integer optimization problem. Due to the very high combinatorics involved in the continent-scale context (involving more than 30,000 flights), we develop and implement a hybrid-metaheuristic optimization algorithm. In addition, we present a computationallyefficient interaction detection method for large trajectory sets. The proposed methodology is successfully implemented and tested on a full-day simulated air traffic over the European airspace, yielding to an interaction-free trajectory plan.

Context-Aware Personal Information Retrieval From Multiple Social Networks

Abstract: -People use a variety of social networking services to collect and organize web information for future reuse. When such contents are actually needed as reference to reply a post in an online conversation, however, the user may not be able to retrieve them with proper cues or may even forget their existence at all. In this paper, we study this problem in the online conversation context and investigate how to automatically retrieve the most context-relevant previously-seen web information without user intervention. We propose a Context-aware Personal Information Retrieval (CPIR) algorithm, which considers both the participatory and implicit-topical properties of the context to improve the retrieval performance. Since both the context and the user's web information are usually short and ambiguous, the participatory context is utilized to formulate and expand the query. Moreover, the implicit-topical context is exploited to implicitly determine the importance of each web information of the targeting user in the given context. The experimental results using real-world dataset demonstrate that CPIR can achieve significant improvements over several baselines.

On Solving WCDMA Network Planning Using Iterative Power Control Scheme and Evolutionary Multiobjective Algorithm [Application Notes]

Abstract: Due to the increasing demand for mobile radio services, 3G wireless network planning has been becoming one of the most important research f ields. 3G system, e.g. WCDMA, is based on Code Division Multiple Access [1], which is quite different from Time Division Multiple Access (TDMA) as used in 2G system.In the 3G network planning, not only are coverage, capacity and quality of the signal interrelated, but multi-rate and mixed-business also utilize the common carrier at the same time. As a result, it makes the 3G network planning become more challenging. In this paper, we will only concentrate on the WCDMA network planning. Since the WCDMA systems have self-interference and the effects of cell-breathing, it makes the coverage, capacity and interference of the base stations (BSs) restrain each other [2], [3]. That is, the area actually covered by a BS depends on the Quality of Service (QoS) and the traffic demand distribution. Therefore, the relationship between coverage, capacity and interference should be fully taken into account in the planning process.

A Chaotic Theorectical Approach to ECG-Based Identity Recognition [Application Notes]

Abstract: Sophisticated technologies realized from applying the idea of biometric identification are increasingly applied in the entrance security management system, private document protection, and security access control Common biometric identification involves voice, attitude, keystroke, signature, iris, face, palm or finger prints, etc Still, there are novel identification technologies based on the individual's biometric features under development [1-4]

Computational Intelligence in Big Data [Guest Editorial]

Abstract: To react to the drastic developments in Big Data, the IEEE Computational Intelligence Society (IEEE CIS) has taken several measures, including setting up the First IEEE Symposium on Computational Intelligence in Big Data, which is going to be held within the SSCI 2014 in December 2014 in Florida, USA, and revising the name of the Technical Committee on Data Mining to expand its scope to cover Big Data Analytics. This special issue of the IEEE Computational Intelligence Magazine is one in a series of reactions of the IEEE CIS to the boom in Big Data Analytics research that aims to publish selected research articles presenting most recent advances and discussing challenges and opportunities in the application of CI techniques to Big Data. After a peer-review procedure, two papers have been selected from 12 manuscripts submitted to the Special Issue to be present in this Special Issue, representing the highest quality work on CI techniques in understanding Big Data challenges. Both papers are briefly summarized. Both papers are of review nature discussing the opportunities and promises of CI techniques along with challenges. They have raised more questions than answers, which is actually the aim of this Special Issue to trigger a wider range of interests in the CI community.

Computational Intelligence for Natural Language Processing [Guest Editorial]

Abstract: The articles in this special section focus on the use of computational modeling for natural language processing applications

Extracting Urban Occupational Plans Using Cultural Algorithms [Application Notes]

Abstract: Cultural Algorithms can be used to evolve structural functional models of urban centers. The population of the Cultural Algorithm is a set of urban planning agents, each of whom competes to build up a high level model of the site from a set of building blocks. These building blocks are produced through the use of techniques from Data Mining and Complex Systems. The best model is compared with existing models of modern cities in order to identify the similarities and differences between ancient and modern cities. The resultant comparison suggests that early Monte Alb?n exhibited a sector-based model that is characteristic of some modern cities. In addition, the plan generated by the Cultural Algorithm is able to add insight into the plan generated by a site expert. This suggests that such an approach can be generalized to other urban sites and foster a new understanding of the urbanization process.

Landmark-Based Methods for Temporal Alignment of Human Motions

Abstract: -Considerable current research is focusing on the subject of "Wellbeing and aging", which covers a wide range of solutions to help encourage elderly people to engage on routine physical exercise. In particular, elderly communities in nursing homes are usually involved in activities on rehabilitation, daily exercises and health tracking. In order to implement an automated system for elderly exercise monitoring, human motion analysis should be efficiently performed in an affordable way, and delivered in a way that the users understand. In this paper, a general framework for comparison of fitness performances in the context of basic stand-up physical activities is presented. The Microsoft Kinect device is used for motion capture. A method for key body pose prediction on human activities based on multi-class C4.5, SVM, Naive Bayes and AdaBoost classifiers is first introduced, followed by a cluster analysis to refine the obtained results. The performances achieved with the different techniques and parameters are then analyzed and the best configuration compares favorably against the DTW and HACA algorithms.

A Memetic Algorithm for Resource Allocation Problem Based on Node-Weighted Graphs [Application Notes]

Abstract: Resource allocation problems usually seek to find an optimal allocation of a limited amount of resources to a number of activities. The allocation solutions of different problems usually optimize different objectives under constraints [1, 2]. If the activities and constraints among them are presented as nodes and edges respectively, the resource allocation problem can be modeled as a k-coloring problem with additional optimization objectives [3, 4]. Since the amount of resources is limited, it is common that some of the activities (nodes) cannot obtain a resource (color). Because the importance of the nodes is usually different, let the weight of a node denote the cost if it cannot obtain a resource, then the resource allocation problem can be described by a node-weighted graph G(E,V), where E and V are the edge and node set, respectively. Some of the nodes that cannot obtain a resource will incur cost to the allocation solution. The optimization objective of the resource allocation problem formulated in this paper is to minimize the total cost of all the nodes that do not obtain a resource. If the total cost is zero, the obtained solution is a k-coloring of the graph; otherwise, the obtained solution is a k -coloring of the graph after removing the nodes that do not obtain a resource. So the resource allocation problem is a generalization of the k-coloring problem.

The Next Technological Wave: Intelligence Technology for Intelligence Super Agent [Research Frontier]

Abstract: Since the industrial revolution, technological evolution has been the defining aspect of societal progress. Among all the technologies that have emerged over the years, information technology is the one that truly revolutionized the modern lifestyle. To take information technology beyond information mining and communication, intelligence technology (InT) is required to manipulate the information and knowledge with human-like intelligence. However, transforming InT into the next technological wave requires a medium to actualize InT with all its potential. Therefore, in this paper, we propose an intelligence super agent (iSA) as an autonomous entity equipped with all categories of intelligence, i.e. cognitive, social, behavioral, ambient, collective, and genetic intelligences. To realize the iSA, we also present a modular architecture, named intelligence operating architecture (iOA), capable of implementing all aspects of InT along with a biologically-inspired thought process. As a novel implementation platform for the iSA, we present user-centered development of robots enacted through agent based modularization (UDREAM). The effectiveness of UDREAM is shown through some application-specific experiments with individual robots. Although the current iSA is for a limited number of services with a standalone robot, it can be extended to a more complex iSA.

A Metaheuristic-Based Approach for the Capacitated Supply Chain Network Design Problem Including Imperfect Quality and Rework

Abstract: -A growing number of organizations have realized the importance of quantifying costs associated to product quality and optimizing their supply chains based not only on operational and logistics costs but also on quality-related costs or Cost of Quality (COQ). This paper presents a novel capacitated Supply Chain Network Design (SCND) model, known as the SCND-COQ model, which quantifies the overall economic profit of the supply chain while accounting for quality-related costs. Quality-related costs are computed from analytical expressions for tracking the Supply Chain (SC) quality level and quantifying the prevention, inspection, rework, failure and opportunity costs, which, in turn, depend on the internal operational decisions within the manufacturing plants. Two metaheuristic solution procedures, based on the Simulated Annealing (SA) and the Genetic Algorithm (GA), with calls to a nonlinear solver are proposed for identifying near-optimal SCNDs since maximizing the output of the SCNDCOQ model can be classified as an NPO-complete problem. The effectiveness of the proposed solution procedures is demonstrated through comprehensive numerical experiments. Based on computational results, the GA-based procedure outperformed the SA-based procedure for all the tested instances in terms of solution quality. The results show that quality-related costs may account up to 11% of the overall profit and the selected business entities differ when including quality-related costs in the SCND decision-making process.

Computational intelligence in production and logistics systems: solving vehicle routing, supply chain network, and air-traffic trajectory planning problems [guest editorial]

Abstract: The three articles in this special section focus on the use of logistics and computational intelligence in the fields of intelligent vehicle routing, supply chain management, and air traffic control trajectory planning.

Intelligence for Embedded Systems: A Methodological Approach [Book Review]

Abstract: It is felt that as intelligence plays a key role in future embedded systems, this book will have broader impacts and far-reaching applications. The presented methods are technology independent and can be suitably adapted to software and or hardware implementations, depending on the application constraints. The book will also be an important resource for practitioners working on embedded systems and applications. The book is multidisciplinary and crosses several disciplines, from measurements and metrology to machine learning, from computer science to probability and system identification. The book forms a suitable reference text for a course on "advanced embedded systems" at the Master and Ph.D. level as well presenting concepts that could complement any course in the disciplines of electronics and computer science. To conclude, this book presents a breakthrough in research and opens new directions for investigation of intelligent embedded systems, where computational intelligence techniques can be used to enhance intelligence in the next generation of embedded systems.

Special Issue on Computational Intelligence for Community-Centric Systems [Guest Editorial]

Abstract: The articles in this special section focus on computational intelligence applications for use with community-centric systems and social network services.