Search

Author's accepted manuscript Industrial cooling systems consume large quantities of energy with highly variable power demand. To reduce environmental impact and overall energy consumption, and to stabilize the power requirements, it is recommended to recover surplus heat, store energy, and integrate renewable energy production. To control these operations continuously in a complex energy system, an intelligent energy management system can be employed using operational data and machine learning. In this work, we have developed an artificial neural network based technique for modelling operational CO2 refrigerant based industrial cooling systems for embedding in an overall energy management system. The operating temperature and pressure measurements, as well as the operating frequency of compressors, are used in developing operational model of the cooling system, which outputs electrical consumption and refrigerant mass flow without the need for additional physical measurements. The presented model is superior to a generalized theoretical model, as it learns from data that includes individual compressor type characteristics. The results show that the presented approach is relatively precise with a Mean Average Percentage Error (MAPE) as low as 5%, using low resolution and asynchronous data from a case study system. The developed model is also tested in a laboratory setting, where MAPE is shown to be as low as 1.8%.

Mitigating misinformation on social media is an unresolved challenge, particularly because of the complexity of information dissemination. To this end, Multivariate Hawkes Processes (MHP) have become a fundamental tool because they model social network dynamics, which facilitates execution and evaluation of mitigation policies. In this paper, we propose a novel light-weight intervention-based misinformation mitigation framework using decentralized Learning Automata (LA) to control the MHP. Each automaton is associated with a single user and learns to what degree that user should be involved in the mitigation strategy by interacting with a corresponding MHP, and performing a joint random walk over the state space. We use three Twitter datasets to evaluate our approach, one of them being a new COVID-19 dataset provided in this paper. Our approach shows fast convergence and increased valid information exposure. These results persisted independently of network structure, including networks with central nodes, where the latter could be the root of misinformation. Further, the LA obtained these results in a decentralized manner, facilitating distributed deployment in real-life scenarios.

A wide range of applications in marine ecology extensively uses underwater cameras. Still, to efficiently process the vast amount of data generated, we need to develop tools that can automatically detect and recognize species captured on film. Classifying fish species from videos and images in natural environments can be challenging because of noise and variation in illumination and the surrounding habitat. In this paper, we propose a two-step deep learning approach for the detection and classification of temperate fishes without pre-filtering. The first step is to detect each single fish in an image, independent of species and sex. For this purpose, we employ the You Only Look Once (YOLO) object detection technique. In the second step, we adopt a Convolutional Neural Network (CNN) with the Squeeze-and-Excitation (SE) architecture for classifying each fish in the image without pre-filtering. We apply transfer learning to overcome the limited training samples of temperate fishes and to improve the accuracy of the classification. This is done by training the object detection model with ImageNet and the fish classifier via a public dataset (Fish4Knowledge), whereupon both the object detection and classifier are updated with temperate fishes of interest. The weights obtained from pre-training are applied to post-training as a priori. Our solution achieves the state-of-the-art accuracy of 99.27\% on the pre-training. The percentage values for accuracy on the post-training are good; 83.68\% and 87.74\% with and without image augmentation, respectively, indicating that the solution is viable with a more extensive dataset., Comment: arXiv admin note: substantial text overlap with arXiv:1904.02768

Author's accepted manuscript. © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Indoor space classification is an important part of localization that helps in precise location extraction, which has been extensively utilized in industrial and domestic domain. There are various approaches that employ Bluetooth Low Energy (BLE), Wi-Fi, magnetic field, object detection, and Ultra Wide Band (UWB) for indoor space classification purposes. Many of the existing approaches need extensive pre-installed infrastructure, making the cost higher to obtain reasonable accuracy. Therefore, improvements are still required to increase the accuracy with minimum requirements of infrastructure. In this paper, we propose an approach to classify the indoor space using geomagnetic field (GMF) and radio signal strength (RSS) as the identity. The indoor space is an open big test bed divided into different indiscernible subspace. We collect GMF and RSS at each subspace and classify it using cascaded Long Short Term Memory (LSTM). The experimental results show that the accuracy is significantly improved when GMF and RSS are combined to make distinct features. In addition, we compare the performance of the proposed model with the state-of-the-art machine learning methods.

Whenever a disaster occurs, users in social media, sensors, cameras, satellites, and the like generate vast amounts of data. Emergency responders and victims use this data for situational awareness, decision-making, and safe evacuations. However, making sense of the generated information under time-bound situations is a challenging task as the amount of data can be significant, and there is a need for intelligent systems to analyze, process, and visualize it. With recent advancements in Artificial Intelligence (AI), numerous researchers have begun exploring AI, machine learning (ML), and deep learning (DL) techniques for big data analytics in managing disasters efficiently. This paper adopts a systematic literature approach to report on the application of AI, ML, and DL in disaster management. Through a systematic review process, we identified one relevant hundred publications. After that, we analyzed all the identified papers and concluded that most of the reviewed articles used AI, ML, and DL methods on social media data, satellite data, sensor data, and historical data for classification and prediction. The most common algorithms are support vector machines (SVM), Naive Bayes (NB), Random Forest (RF), Convolutional Neural Networks (CNN), Artificial neural networks (ANN), Natural language processing techniques (NLP), Latent Dirichlet Allocation (LDA), K-nearest neighbor (KNN), and Logistic Regression (LR).

Most of the Nordic holiday resorts are in rural area with low capacity distributed network. The rural area network is weak and needs capacity expansion planning as the load demand of this area are going to increase due to penetration of electric vehicles and heat pumps. Such type of rural network can also be operated as a micro-grid, and therefore load analysis is required for appropriate operation. The load analysis will also be useful for finding proper sizing of distributed energy resources including energy storage. In this work, load demand analysis of a typical Nordic holiday resorts, connected in rural grid, is presented to find out the load variation during the usage periods. The load analysis is targeted for demand prediction. The demand forecasting has been considered through integrating Regression Tools with Artificial Neural Networks due to the low amount of data available from the Holiday Resorts. Collected data is from a rural area in Norway consisting of 125 holiday cabins, with maximum load of 478 kW in the period of 2014 to 2018. This work is presenting the analysis on the total electric load consumption of cabins during typical short and long term holidays. It is observed, during the longer time holiday period, the loads are significantly higher compared to shorter time holiday period. Prediction analysis shows that the MAPE is relatively higher compare to predicted results in higher load area. Through analysis, it is observed that the curvature of the maximum peak demand is unfitting the predictive outcome. To overcome this problem the finite gradient by autoregression, has been used in this work.

Teeth are some of the most resilient tissues of the human body. Because of their placement, teeth often yield intact indicators even when other metrics, such as finger prints and DNA, are missing. Forensics on dental identification is now mostly manual work which is time and resource intensive. Systems for automated human identification from dental X-ray images have the potential to greatly reduce the necessary efforts spent on dental identification, but it requires a system with high stability and accuracy so that the results can be trusted. This paper proposes a new system for automated dental X-ray identification. The scheme extracts tooth and dental work contours from the X-ray images and uses the Hausdorff-distance measure for ranking persons. This combination of state-of-the-art approaches with a novel lowest cost path-based method for separating a dental X-ray image into individual teeth, is able to achieve comparable and better results than what is available in the literature. The proposed scheme is fully functional and is used to accurately identify people within a real dental database. The system is able to perfectly separate 88.7% of the teeth in the test set. Further, in the verification process, the system ranks the correct person in top in 86% of the cases, and among the top five in an astonishing 94% of the cases. The approach has compelling potential to significantly reduce the time spent on dental identification.

Predicting and mitigating demand peaks in electrical networks has become a prevalent research topic. Demand peaks pose a particular challenge to energy companies because these are difficult to foresee and require the net to support abnormally high consumption levels. In smart energy grids, time-differentiated pricing policies that increase the energy cost for the consumers during peak periods, and load balancing are examples of simple techniques for peak regulation. In this paper, we tackle the task of predicting power peaks prior to their actual occurrence in the context of a pilot Norwegian smart grid network.

The Norwegian rural distributed power network is mainly designed for Holiday Cabins with limited electrical loading capacity. Load prediction analysis, within such type of network, is necessary for effective operation and to manage the increasing demand of new appliances (e. g. electric vehicles and heat pumps). In this paper, load prediction of a distributed power network (i.e. a typical Norwegian rural area power network of 125 cottages with 478 kW peak demand) is carried out using regression analysis techniques for establishing autocorrelations and correlations among weather parameters and occurrence time in the period of 2014–2018. In this study, the regression analysis for load prediction is done considering vertical and continuous time approach for day-ahead prediction. The vertical time approach uses seasonal data for training and inference, compared to continuous time approach which utilizes all data in a continuum from the start of the dataset until the time period used for inference. The vertical approach does this with even fewer data than continuous approach. The regression tools can perform using the low amount of data, and the prediction accuracy matches with other techniques. It is observed through load predictive analysis that the autocorrelation by vertical approach with kNN-regressor gives a low Symmetric Mean Absolute Percentage Error. The kNN-regressor is compared with Random Forest Regressor, and it uses autoregression. Autoregression is the simplest and the most straightforward predictive model based on the targeted vector itself. The autoregression indicates the decline and incline of the time-series, and thus gives a finite gradient for the curvature of load profile. It is observed that joint learning of regression tools with autoregression can predict time-series components of the different load profile characteristics. The presented load prediction analysis is going to be useful for distributed network operation, demand-side management, integration of renewable energy sources and distributed generators.

Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, for the first time, a text categorization approach that leverages the recently introduced Tsetlin Machine. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "rash" and "reaction" and "penicillin" then Allergy. The Tsetlin Machine learns these formulae from a labelled text, utilizing conjunctive clauses to represent the particular facets of each category. Indeed, even the absence of terms (negated features) can be used for categorization purposes. Our empirical comparison with Na\"ive Bayes, decision trees, linear support vector machines (SVMs), random forest, long short-term memory (LSTM) neural networks, and other techniques, is quite conclusive. The Tsetlin Machine either performs on par with or outperforms all of the evaluated methods on both the 20 Newsgroups and IMDb datasets, as well as on a non-public clinical dataset. On average, the Tsetlin Machine delivers the best recall and precision scores across the datasets. Finally, our GPU implementation of the Tsetlin Machine executes 5 to 15 times faster than the CPU implementation, depending on the dataset. We thus believe that our novel approach can have a significant impact on a wide range of text analysis applications, forming a promising starting point for deeper natural language understanding with the Tsetlin Machine., Comment: 10 pages, 4 figures

Relying simply on bitwise operators, the recently introduced Tsetlin machine (TM) has provided competitive pattern classification accuracy in several benchmarks, including text understanding. In this paper, we introduce the regression Tsetlin machine (RTM), a new class of TMs designed for continuous input and output, targeting nonlinear regression problems. In all brevity, we convert continuous input into a binary representation based on thresholding, and transform the propositional formula formed by the TM into an aggregated continuous output. Our empirical comparison of the RTM with state-of-the-art regression techniques reveals either superior or on par performance on five datasets. This article is part of the theme issue ‘Harmonizing energy-autonomous computing and intelligence’.

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use attention modules that perform channel and spatial attention together. We use some data augmentation techniques to further boost performance. Our model is able to achieve state-of-the-art performance on all three benchmark environment sound classification datasets, i.e. the UrbanSound8K (97.52%), ESC-10 (95.75%) and ESC-50 (88.50%). To the best of our knowledge, this is the first time that a single environment sound classification model is able to achieve state-of-the-art results on all three datasets. For ESC-10 and ESC-50 datasets, the accuracy achieved by the proposed model is beyond human accuracy of 95.7% and 81.3% respectively., Comment: Re-checking results

When any kind of disaster occurs, victims who are directly and indirectly affected by the disaster often post vast amount of data (e.g., images, text, speech, video) using numerous social media platforms. This is because social media has recently become a primary communication channel among people to report either to public or to emergency responders (ERs). ERs, who are from various emergency response organizations (EROs), usually consider to gain awareness of the situation in order to respond to occurred disaster. However, with the occurrence of the disaster, within minutes, the social media platforms are flooded with various kinds of data which become overwhelmed for ERs with big data. Further, in this posted data, there may be majority of the data consist of redundant and irrelevant content. With this, it becomes challenging for ERs to make sense and take decisions of/on the available big data. Despite recent advances in the technology, processing and analyzing of the disaster related social media big data remains a challenging task. Hence, in this paper, we focus on presenting an initial analysis of a systematic literature review on application of artificial intelligence to analyze/process social media big data for efficient disaster management. During a systematic review process 68 publications were identified. Thereafter, we analyzed all the identified papers. From our analysis, we conclude that the most of the reviewed papers are on text and image classification and mostly convolutional neural networks have been employed for the classification.

Being capable of online learning in unknown stochastic environments, Tsetlin Automata (TA) have gained considerable interest. As a model of biological systems, teams of TA have been used for solving complex problems in a decentralized manner, with low computational complexity. For many domains, decentralized problem solving is an advantage, however, also may lead to coordination difficulties and unstable learning. To combat this negative effect, this paper proposes a novel TA coordination scheme designed for learning problems with continuous input and output. By saving and updating the best solution that has been chosen so far, we can avoid having the overall system being led astray by spurious erroneous actions. We organize this process hierarchically by a principal-teacherclass structure. We further propose a binary representation of continuous actions (coefficients). Each coefficient in the cost function is represented by 8 TA. TA teams at different classes produce different solutions. They are trained to find the global optimum with the help of their own best and the overall best solutions. The proposed algorithm is tested first with an artificial dataset and later used to forecast dengue haemorrhagic fever in the Philippines. Results of the novel procedure are compared with results from two traditional TA approaches. The training error of the novel TA scheme is lower approx. 50 and 62 times compared to the considered two traditional Tsetlin Automata approaches and testing error is approx. 31 and 21 times lower for the new scheme. These improvements not only highlight the effectiveness of the proposed scheme, but also the importance of old, simple, yet powerful concepts in the Artificial Intelligence techniques.

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast capabilities of convolutional neural networks, that can extract useful features from noisy and complex data. Games are excellent tools to test and push the boundaries of novel RL algorithms because they give valuable insight into how well an algorithm can perform in isolated environments without the real-life consequences. Real-time strategy games (RTS) is a genre that has tremendous complexity and challenges the player in short and long-term planning. There is much research that focuses on applied RL in RTS games, and novel advances are therefore anticipated in the not too distant future. However, there are to date few environments for testing RTS AIs. Environments in the literature are often either overly simplistic, such as microRTS, or complex and without the possibility for accelerated learning on consumer hardware like StarCraft II. This paper introduces the Deep RTS game environment for testing cutting-edge artificial intelligence algorithms for RTS games. Deep RTS is a high-performance RTS game made specifically for artificial intelligence research. It supports accelerated learning, meaning that it can learn at a magnitude of 50 000 times faster compared to existing RTS games. Deep RTS has a flexible configuration, enabling research in several different RTS scenarios, including partially observable state-spaces and map complexity. We show that Deep RTS lives up to our promises by comparing its performance with microRTS, ELF, and StarCraft II on high-end consumer hardware. Using Deep RTS, we show that a Deep Q-Network agent beats random-play agents over 70% of the time. Deep RTS is publicly available at https://github.com/cair/DeepRTS., Comment: Proceedings of the IEEE International Conference on Computational Intelligence and Games (CIG 2018)

Ant Colony Optimisation for classification has mostly been limited to rule based approaches where artificial ants walk on datasets in order to extract rules from the trends in the data, and hybrid approaches which attempt to boost the performance of existing classifiers through guided feature reductions or parameter optimisations. A recent notable example that is distinct from the mainstream approaches is PolyACO, which is a proof of concept polygon-based classifier that resorts to ant colony optimisation as a technique to create multi-edged polygons as class separators. Despite possessing some promise, PolyACO has some significant limitations, most notably, the fact of supporting classification of only two classes, including two features per class.This paper introduces PolyACO+, which is an extension of PolyACO in three significant ways: (1) PolyACO+ supports classifying multiple classes, (2) PolyACO+ supports polygons in multiple dimensions enabling classification with more than two features, and (3) PolyACO+ substantially reduces the training time compared to PolyACO by using the concept of multi-leveling. This paper empirically demonstrates that these updates improve the algorithm to such a degree that it becomes comparable to state-of-the-art techniques such as SVM, Neural Networks, and AntMiner+. nivå1

The purpose of this paper is to propose a solution to an extremely pertinent problem, namely, that of identifying unreliable sensors (in a domain of reliable and unreliable ones) without any knowledge of the ground truth. This fascinating paradox can be formulated in simple terms as trying to identify stochastic liars without any additional information about the truth. Though apparently impossible, we will show that it is feasible to solve the problem, a claim that is counterintuitive in and of itself. One aspect of our contribution is to show how redundancy can be introduced, and how it can be effectively utilized in resolving this paradox. Legacy work and the reported literature (for example, in the so-called weighted majority algorithm) have merely addressed assessing the reliability of a sensor by comparing its reading to the ground truth either in an online or an offline manner. Unfortunately, the fundamental assumption of revealing the ground truth cannot be always guaranteed (or even expected) in many real life scenarios. While some extensions of the Condorcet jury theorem [9] can lead to a probabilistic guarantee on the quality of the fused process, they do not provide a solution to the unreliable sensor identification problem. The essence of our approach involves studying the agreement of each sensor with the rest of the sensors, and not comparing the reading of the individual sensors with the ground truth—as advocated in the literature. Under some mild conditions on the reliability of the sensors, we can prove that we can, indeed, filter out the unreliable ones. Our approach leverages the power of the theory of learning automata (LA) so as to gradually learn the identity of the reliable and unreliable sensors. To achieve this, we resort to a team of LA, where a distinct automaton is associated with each sensor. The solution provided here has been subjected to rigorous experimental tests, and the results presented are, in our opinion, both novel and conclusive. Nivå2

With the increasing popularity of online learning, intelligent tutoring systems are regaining increased attention. In this paper, we introduce adaptive algorithms for personalized assignment of learning tasks to student so that to improve his performance in online learning environments. As main contribution of this paper, we propose a a novel Skill-Based Task Selector (SBTS) algorithm which is able to approximate a student's skill level based on his performance and consequently suggest adequate assignments. The SBTS is inspired by the class of multi-armed bandit algorithms. However, in contrast to standard multi-armed bandit approaches, the SBTS aims at acquiring two criteria related to student learning, namely: which topics should the student work on, and what level of difficulty should the task be. The SBTS centers on innovative reward and punishment schemes in a task and skill matrix based on the student behaviour. To verify the algorithm, the complex student behaviour is modelled using a neighbour node selection approach based on empirical estimations of a students learning curve. The algorithm is evaluated with a practical scenario from a basic java programming course. The SBTS is able to quickly and accurately adapt to the composite student competency --- even with a multitude of student models., 6th International Conference on Web Intelligence

In many applications, data from different sensors are aggregated in order to obtain more reliable information about the process that the sensors are monitoring. However, the quality of the aggregated information is intricately dependent on the reliability of the individual sensors. In fact, unreliable sensors will tend to report erroneous values of the ground truth, and thus degrade the quality of the fused information. Finding strategies to identify unreliable sensors can assist in having a counter-effect on their respective detrimental influences on the fusion process, and this has has been a focal concern in the literature. The purpose of this paper is to propose a solution to an extremely pertinent problem, namely, that of identifying which sensors are unreliable without any knowledge of the ground truth . This fascinating paradox can be formulated in simple terms as trying to identify stochastic liars without any additional information about the truth. Though apparently impossible, we will show that it is feasible to solve the problem, a claim that is counter-intuitive in and of itself . To the best of our knowledge, this is the first reported solution to the aforementioned paradox. Legacy work and the reported literature have merely addressed assessing the reliability of a sensor by comparing its reading to the ground truth either in an online or an offline manner. The informed reader will observe that the so-called Weighted Majority Algorithm is a representative example of a large class of such legacy algorithms. The essence of our approach involves studying the agreement of each sensor with the rest of the sensors, and not comparing the reading of the individual sensors with the ground truth – as advocated in the literature. Under some mild conditions on the reliability of the sensors, we can prove that we can, indeed, filter out the unreliable ones. Our approach leverages the power of the theory of Learning Automata (LA) so as to gradually learn the identity of the reliable and unreliable sensors. To achieve this, we resort to a team of LA , where a distinct automaton is associated with each sensor. The solution provided here has been subjected to rigorous experimental tests, and the results presented are, in our opinion, both novel and conclusive.

This paper deals with the extremely pertinent problem of web crawling, which is far from trivial considering the magnitude and all-pervasive nature of the World-Wide Web. While numerous AI tools can be used to deal with this task, in this paper we map the problem onto the combinatorially-hard stochastic non-linear fractional knapsack problem, which, in turn, is then solved using Learning Automata (LA). Such LA-based solutions have been recently shown to outperform previous state-of-the-art approaches to resource allocation in Web monitoring. However, the ever growing deployment of distributed systems raises the need for solutions that cope with a distributed setting. In this paper, we present a novel scheme for solving the non-linear fractional bin packing problem. Furthermore, we demonstrate that our scheme has applications to Web crawling, i.e., Distributed resource allocation, and in particular, to distributed Web monitoring. Comprehensive experimental results demonstrate the superiority of our scheme when compared to other classical approaches.

Stochastic point location (SPL) deals with the problem of a learning mechanism (LM) determining the optimal point on the line when the only input it receives are stochastic signals about the direction in which it should move. One can differentiate the SPL from the traditional class of optimization problems by the fact that the former considers the case where the directional information, for example, as inferred from an Oracle (which possibly computes the derivatives), suffices to achieve the optimization-without actually explicitly computing any derivatives. The SPL can be described in terms of a LM (algorithm) attempting to locate a point on a line. The LM interacts with a random environment which essentially informs it, possibly erroneously, if the unknown parameter is on the left or the right of a given point. Given a current estimate of the optimal solution, all the reported solutions to this problem effectively move along the line to yield updated estimates which are in the neighborhood of the current solution(1) This paper proposes a dramatically distinct strategy, namely, that of partitioning the line in a hierarchical tree-like manner, and of moving to relatively distant points, as characterized by those along the path of the tree. We are thus attempting to merge the rich fields of stochastic optimization and data structures. Indeed, as in the original discretized solution to the SPL, in one sense, our solution utilizes the concept of discretization and operates a uni-dimensional controlled random walk (RW) in the discretized space, to locate the unknown parameter. However, by moving to nonneighbor points in the space, our newly proposed hierarchical stochastic searching on the line (HSSL) solution performs such a controlled RW on the discretized space structured on a superimposed binary tree. We demonstrate that the HSSL solution is orders of magnitude faster than the original SPL solution proposed by Oommen. By a rigorous analysis, the HSSL is shown to be optimal if the effectiveness (or credibility) of the environment, given by p , is greater than the golden ratio conjugate. The solution has been both analytically solved and simulated, and the results obtained are extremely fascinating, as this is the first reported use of time reversibility in the analysis of stochastic learning. The learning automata extensions of the scheme are currently being investigated. As we shall see later, hierarchical solutions have been proposed in the field of LA.

Published version of a chapter in the book: Recent Trends in Applied Artificial Intelligence. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-38577-3_7 Managing the uncertainties that arise in disasters – such as ship fire – can be extremely challenging. Previous work has typically focused either on modeling crowd behavior or hazard dynamics, targeting fully known environments. However, when a disaster strikes, uncertainty about the nature, extent and further development of the hazard is the rule rather than the exception. Additionally, crowd and hazard dynamics are both intertwined and uncertain, making evacuation planning extremely difficult. To address this challenge, we propose a novel spatio-temporal probabilistic model that integrates crowd with hazard dynamics, using a ship fire as a proof-of-concept scenario. The model is realized as a dynamic Bayesian network (DBN), supporting distinct kinds of crowd evacuation behavior – both descriptive and normative (optimal). Descriptive modeling is based on studies of physical fire models, crowd psychology models, and corresponding flow models, while we identify optimal behavior using Ant-Based Colony Optimization (ACO). Simulation results demonstrate that the DNB model allows us to track and forecast the movement of people until they escape, as the hazard develops from time step to time step. Furthermore, the ACO provides safe paths, dynamically responding to current threats.

Published version of a chapter from the volume: Recent Trends in Applied Artificial Intelligence. Also available on SpringerLink: http://dx.doi.org/10.1007/978-3-642-38577-3_6 An emergency requiring evacuation is a chaotic event filled with uncertainties both for the people affected and rescuers. The evacuees are often left to themselves for navigation to the escape area. The chaotic situation increases when a predefined escape route is blocked by a hazard, and there is a need to re-think which escape route is safest. This paper addresses automatically finding the safest escape route in emergency situations in large buildings or ships with imperfect knowledge of the hazards. The proposed solution, based on Ant Colony Optimisation, suggests a near optimal escape plan for every affected person — considering both dynamic spread of hazards and congestion avoidance.The solution can be used both on an individual bases, such as from a personal smart phone of one of the evacuees, or from a remote location by emergency personnel trying to assist large groups.

Published version of a chapter in the book: Computers Helping People with Special Needs. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-31522-0_63 This paper presents a conceptual analysis of how the Web Content Accessibility Guidelines (WCAG) 2.0 and its accompanying documents can be used as a basis for the implementation of an automatic checking tool and the definition of a web accessibility metric. There are two major issues that need to be resolved to derive valid and reliable conclusions from the output of individual tests. First, the relationship of Sufficient Techniques and Common Failures has to be taken into account. Second, the logical combination of the techniques related to a Success Criterion must be represented in the results. The eGovMon project has a lot of experience in specifying and implementing tools for automatic checking of web accessibility. The project is based on the belief that web accessibility evaluation is not an end in itself. Its purpose is to promote web accessibility and initiate improvements.

Equal access to public information and services for all is an essential part of the United Nations (UN) Declaration of Human Rights. Today, the Web plays an important role in providing information and services to citizens. Unfortunately, many government Web sites are poorly designed and have accessibility barriers that prevent people with disabilities from using them. This article combines current Web accessibility benchmarking methodologies with a sound strategy for comparing Web accessibility among countries and continents. Furthermore, the article presents the first global analysis of the Web accessibility of 192 United Nation Member States made publically available. The article also identifies common properties of Member States that have accessible and inaccessible Web sites and shows that implementing antidisability discrimination laws is highly beneficial for the accessibility of Web sites, while signing the UN Rights and Dignity of Persons with Disabilities has had no such effect yet. The article demonstrates that, despite the commonly held assumption to the contrary, mature, high-quality Web sites are more accessible than lower quality ones. Moreover, Web accessibility conformance claims by Web site owners are generally exaggerated.

Published version of a chapter from the book: Computers Helping People with Special Needs.The original publication is available at www.springerlink.com: http://dx.doi.org/10.1007/978-3-642-14097-6_75 Accessibility benchmarking is efficient to raise awareness and initiate competition. However, traditional benchmarking is of little avail when it comes to removing barriers from eGovernment web sites in practice. Regulations and legal enforcement may be helpful in a long-term perspective. For more rapid progress both vendors and web site maintainers are willing to take short-term action towards improvements, provided that clear advise is available. The approach of the eGovernment Monitoring project (eGovMon) integrates benchmarking as a central activity in a user-driven project. In addition to benchmarking results, several other services and background information are provided to enable the users – in this case a group of Norwegian municipalities who want to improve the accessibility of their web sites – to gain real added value from benchmarking.

This paper makes a range of comparisons between e-government developments and performance worldwide. In order to make such comparisons, it is necessary to use a set of indicators. This paper examines the evolution of indicators used by three widely referenced international e-government studies, from the early days of e-government benchmarking until today. Some critical remarks related to the current state-of-the-art are given. The authors conclude that all three studies have their strengths and weaknesses, and propose automatic assessment of e-government services as a potential solution to some of the problems experienced by current benchmarking studies.

The most adequate approach for benchmarking web accessibility is manual expert evaluation supplemented by automatic analysis tools. But manual evaluation has a high cost and is impractical to be applied on large websites. In reality, there is no choice but to rely on automated tools when reviewing large web sites for accessibility. The question is: to what extent the results from automatic evaluation of a web site and individual web pages can be used as an approximation for manual results? This paper presents the initial results of an investigation aimed at answering this question. He have performed both manual and automatic evaluations of the accessibility of web pages of two sites and we have compared the results. In our data set automatically retrieved results could most definitely be used as an approximation manual evaluation results. L'enfocament més adequat per l'accessibilitat web de referència és l'avaluació manual d'experts complementada amb eines d'anàlisi automàtiques. Tot i així, l'avaluació manual té un cost elevat i no és pràctic que s'apliqui a grans llocs web. En realitat, no hi ha més remei que confiar amb les eines automatitzades en la revisió de l'accessibilitat dels llocs web de major grandària. La pregunta és: en quina mesura els resultats de l'avaluació automàtica d'un lloc web i de pàgines individuals es poden utilitzar com una aproximació als resultats manuals? Aquest treball presenta els resultats inicials d'una investigació dirigida a respondre aquesta pregunta. S'han realitzat dues avaluacions manuals i automàtiques de l'accessibilitat de dues pàgines web i s'han comparat els resultats. A la nostra base de dades els resultats recuperats automàticament es podrien utilitzar com una aproximació manual als resultats de l'avaluació. El enfoque más adecuado para la accesibilidad web de referencia es la evaluación manual de expertos complementada con herramientas de análisis automático. Sin embargo, la evaluación manual tiene un alto costo y no es práctico que se aplique en los sitios web de gran tamaño. En realidad, no hay más remedio que confiar en las herramientas automatizadas en la revisión de la accesibilidad de los sitios web de gran tamaño. La pregunta es: ¿en qué medida los resultados de la evaluación automática de un sitio web y páginas web individuales pueden ser utilizados como una aproximación a los resultados manuales? Este trabajo presenta los resultados iniciales de una investigación dirigida a responder a esta pregunta. Se han realizado dos evaluaciones manuales y automáticas de la accesibilidad de las páginas web de dos sitios diferentes y se han comparado los resultados. En nuestra base de datos los resultados recuperados automáticamente podrían ser utilizados como una aproximación manual a los resultados de la evaluación.

The European Internet Accessibility project (EIAO) has developed an Observatory for performing large scale automatic web accessibility evaluations of public sector web sites in Europe. The architecture includes a distributed web crawler that crawls web sites for links until either a given budget of web pages have been identified or the web site has been crawled exhaustively. Subsequently, a uniform random subset of the crawled web pages is sampled and sent for accessibility evaluation and the evaluation results are stored in a Resource Description Format (RDF) database that is later loaded into the EIAO data warehouse using an Extract-Transform-Load (ETL) tool. The aggregated indicator results in the data warehouse are finally presented in a Plone based online reporting tool. This paper describes the final version of the EIAO architecture and outlines some of the technical and architectural challenges that the project faced and the solutions developed towards building a system capable of regular large-scale accessibility evaluations with sufficient capacity and stability. It also outlines some possible future architectural improvements.

Previous approaches to resource allocation in Web monitoring target optimal performance under restricted capacity constraints (Pandey et al., 2003; Wolf et al., 2002). The resource allocation problem is generally modelled as a knapsack problem with known deterministic properties. However, for practical purposes the Web must often be treated as stochastic and unknown. Unfortunately, estimating unknown knapsack properties (e.g., based on an estimation phase (Pandey et al., 2003; Wolf et al., 2002)) delays finding an optimal or near-optimal solution. Dynamic environments aggravate this problem further when the optimal solution changes with time. In this paper, we present a novel solution for the nonlinear fractional knapsack problem with a separable and concave criterion function (Bretthauer and Shetty, 2002). To render the problem realistic, we consider the criterion function to be stochastic with an unknown distribution. At every time instant, our scheme utilizes a series of informed guesses to move, in an online manner, from a "current" solution, towards the optimal solution. At the heart of our scheme, a game of deterministic learning automata performs a controlled random walk on a discretized solution space. Comprehensive experimental results demonstrate that the discretization resolution determines the precision of our scheme. In order to yield a required precision, the current resource allocation solution is consistently improved, until a near-optimal solution is found. Furthermore, our proposed scheme quickly adapts to periodically switching environments. Thus, we believe that our scheme is qualitatively superior to the class of estimation-based schemes

Masteroppgave i informasjons- og kommunikasjonsteknologi 2005 - Høgskolen i Agder, Grimstad There is no doubt that the World Wide Web has lived up to it’s hype of being the world’s central information highway through the past years. An increasing amount of versatile services keeps finding their way onto the Web as information providers continue to embrace the possibilities that the Web can offer. Especially the possibility of producing dynamic content has been an accelerant factor and is the reason why we now conveniently can participate in online auctions or see the latest development of our favorite stocks in near real-time from our own living rooms. However, for automated data mining applications that deploy crawlers to continuously capture the information provided by this new breed of services, the highly dynamic nature of the content is not convenient at all. As a matter of fact, a complete new set of challenges emerges where traditional crawling strategies are shown to be sub-optimal. Accordingly a new class of methods for crawling operations are clearly needed. Nonetheless, the problem area has so far been given limited attention in literature. In this thesis we address the new problem area of monitoring highly dynamic data sources of different importance. We use the concept of an incremental web crawler as a basis for our novel approach where we consider the incremental crawling task as a continuous learning problem where scheduling of monitoring tasks is combined with parameter estimation in an on-line manner. By mapping the problem to two variants of the so called knapsack problem we propose two solutions based on a machine learning technique known as learning automata. We show empirically that our proposed solutions continuously improve their performance through a learning process and that they are capable of operating in non-stationary environments. We also show their performance in comparison to alternative algorithms where, most notably, our schemes are shown to outdo the traditional uniform crawling scheme by factors up to 550% in certain situations.