MOTIVATION: Large-scale bioinformatics analyses increasingly require collaboration across multiple cohorts and institutions, yet existing workflows often rely on data co-localization, which is slow, difficult to scale, and raises privacy concerns. We present a privacy-preserving federated analytics framework that enables secure statistical analysis across distributed datasets without transferring raw data, by performing all computations on encrypted data via cryptographic methods. RESULTS: We evaluate the framework by validating polygenic risk scores and conducting meta-analyses on two real-world cohorts. The proposed solution achieves over 99.9% accuracy relative to plaintext analyses, while maintaining scalable runtime performance with increasing data size and number of participating sites. These results demonstrate the feasibility of secure federated analytics for practical bioinformatics applications involving sensitive data.

Explainable Artificial Intelligence methods have gained significant traction for their ability to elucidate the decision-making processes of black-box models, particularly in high-stakes fields such as healthcare and finance. Among these, Local Interpretable Model-agnostic Explanations (LIME) stands out as a widely adopted post-hoc, model-agnostic approach that interprets black-box predictions by constructing an interpretable surrogate model on perturbed instances to approximate the local behavior of the original model around a given instance. However, the effectiveness of LIME can depend on the quality of the training data used by the black-box model. When trained on limited or low-quality data, the black-box model may yield inaccurate predictions for perturbed samples, resulting in poorly defined local decision boundaries and consequently unreliable explanations. This limitation is especially problematic in data-scarce settings. To overcome this challenge, we propose TransLIME, a novel end-to-end explainable transfer learning framework that improves the local fidelity and stability of LIME on limited tabular datasets by transferring relevant explainability knowledge from a related auxiliary source domain with a shifted distribution. Also, in TransLIME, only representative source prototype explanations obtained through clustering are transferred to the target domain, thereby reducing cross-domain exposure of both data and explanatory information during transfer. Experimental evaluations on real-world datasets demonstrate the effectiveness of the proposed framework in improving explanation quality in target domains with limited data.

Speech Emotion Recognition (SER) is a method of identifying emotional states from the human voice. Automatic SER (ASER) is a research domain where Machine Learning (ML) is used to extract and analyze speech features to predict emotional states. Using ML in a sensitive area like SER requires transparency and reliability of the models. For instance, ASER is crucial to understanding the underlying decision-making in real-world applications such as mental health monitoring systems. Researchers, therefore, have focused attention on advancing the interpretability and explainability of ASER models. Interpretability maximizes human understanding of complex processes by providing meaningful insights. Explainability presents the interpretable insights in a clear and human-understandable manner. Some standard interpretability methods include feature importance, feature selection methods, and attention models. Explainability methods include SHapley Additive exPlanations (SHAP), visualizations using embedding plots, saliency maps, etc., and feature importance analysis. The current systematic review explores the different interpretability and explainability methods for speech emotion features. The current review paper aims to identify the progress in the area, identify potential research gaps, and motivate future research.

Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic variations and samples that deviate from the true data manifold. Consequently, the surrogate model may fail to accurately approximate the complex decision boundary of the original model. To address these challenges, we propose a novel Instance-based Transfer Learning LIME framework (ITL-LIME) that enhances explanation fidelity and stability in data-constrained environments. ITL-LIME introduces instance transfer learning into the LIME framework by leveraging relevant real instances from a related source domain to aid the explanation process in the target domain. Specifically, we employ clustering to partition the source domain into clusters with representative prototypes. Instead of generating random perturbations, our method retrieves pertinent real source instances from the source cluster whose prototype is most similar to the target instance. These are then combined with the target instance's neighboring real instances. To define a compact locality, we further construct a contrastive learning-based encoder as a weighting mechanism to assign weights to the instances from the combined set based on their proximity to the target instance. Finally, these weighted source and target instances are used to train the surrogate model for explanation purposes. Experimental evaluation with real-world datasets demonstrates that ITL-LIME greatly improves the stability and fidelity of LIME explanations in scenarios with limited data. Our code is available at https://github.com/rehanrazaa/ITL-LIME.

Question answering over knowledge graphs (KGQA) seeks to automatically answer natural language questions by retrieving triples within the knowledge graph (KG). In the context of multi-hop KGQA, reasoning across multiple edges of the KG becomes crucial for obtaining answers. Existing methods align with either the path-searching-based mainstream, emphasizing structural KG analysis, or the subgraph-based mainstream, focusing on semantic KG embeddings. Both streams have two primary challenges: (1) KG incompleteness, where path searching or subgraph construction faces limitations in the absence of links between entities; (2) candidate answer selection, wherein most approaches employ pre-defined searching sizes or heuristics. Many recent studies incorporate Graph Convolutional Network (GCN) to encode KGs, yet they overlook the potential over-smoothing issue inherent in GCNs. The over-smoothing problem arises from the tendency of closely connected nodes to exhibit similar embeddings within the deep convolutional architecture of GCNs. To address these challenges, this paper proposes a two-stage framework named ComPath, leveraging insights from both mainstreams. ComPath utilizes GCN to tackle KG incompleteness and introduces a path analyser to mitigate the over-smoothing issue associated with GCN. Candidate answers are selected using semantic similarity. The ablation studies and comparative experiments on the three KGQA benchmark datasets shown that the proposed ComPath performed better than the other KGQAs.

CiRA CORE is a central hub designed to connect AI technology creation with practical application, making it easier to work with ROS (Robot Operating System) and link different systems through a user-friendly drag-and-drop interface. This approach removes the need for extensive coding, making the platform accessible to those with minimal programming experience. CiRA CORE offers a comprehensive suite of features for AI development and robot control, including algorithm creation, AI model training, and device integration commonly used in industrial settings. It supports tasks like image recognition and facilitates data storage, labeling, and integration with other systems for data-driven AI development. Overall, CiRA CORE aims to democratize AI development and robot control, simplifying AI development for Industry 4.0 applications, and leading to increased efficiency, reduced costs, and improved safety in industrial processes. This paper reports the progress of the CiRA CORE training modules funded by the SMCS TEAM Program Award. The project has completed the design of a 6-axis robot 3D training kit and simulation models for CiRA CORE training modules. The next steps involve developing 3D-printed robots and training materials. The main goal is to democratize advanced robotics and AI by simplifying integration through a visual, node-based programming interface. This approach reduces the need for complex coding, making these technologies accessible to users with limited programming experience. This initiative aims to foster widespread adoption in business and industrial settings, aligning with IEEE SMC's mission to promote professional growth and innovation in robotics and AI.

Abstract Drug repurposing is a technique for probing new usages of existing medicines, but its traditional methods, such as computational approaches, can be time-consuming and laborious. Recently, knowledge graphs (KGs) have emerged as a powerful approach for graph-based representation in drug repurposing, encoding entities and relations to predict new connections and facilitate drug discovery. As COVID-19 has become a major public health concern, it is critical to establish an appropriate COVID-19 KG for drug repurposing to combat the spread of the virus. However, most publicly available COVID-19 KGs lack support for multi-relations and comprehensive entity types. Moreover, none of them originates from COVID-19-related drugs, making it challenging to identify effective treatments. To tackle these issues, we developed Drug-CoV, a drug-origin and multi-relational COVID-19 KG. We evaluated the quality of Drug-CoV by performing link prediction and comparing the results to another publicly available COVID-19 KG. Our results showed that Drug-CoV outperformed the comparing KG in predicting new links between entities. Overall, Drug-CoV represents a valuable resource for COVID-19 drug repurposing efforts and demonstrates the potential of KGs for facilitating drug discovery.

Abstract Recent advances in digital technologies have lowered the costs and improved the quality of digital pathology Whole Slide Images (WSI), opening the door to apply Machine Learning (ML) techniques to assist in cancer diagnosis. ML, including Deep Learning (DL), has produced impressive results in diverse image classification tasks in pathology, such as predicting clinical outcomes in lung cancer and inferring regional gene expression signatures. Despite these promising results, the uptake of ML as a common diagnostic tool in pathology remains limited. A major obstacle is the insufficient labelled data for training neural networks and other classifiers, especially for new sites where models have not been established yet. Recently, image synthesis from small, labelled datasets using Generative Adversarial Networks (GAN) has been used successfully to create high-performing classification models. Considering the domain shift and complexity in annotating data, we investigated an approach based on GAN that minimized the differences in WSI between large public data archive sites and a much smaller data archives at the new sites. The proposed approach allows the tuning of a deep learning classification model for the class of interest to be improved using a small training set available at the new sites. This paper utilizes GAN with the one-class classification concept to model the class of interest data. This approach minimizes the need for large amounts of labelled data from the new site to train the network. The GAN generates synthesized one-class WSI images to jointly train the classifier with WSIs available from the new sites. We tested the proposed approach for follicular lymphoma data of a new site by utilizing the data archives from different sites. The synthetic images for the one-class data generated from the data obtained from different sites with minimum amount of data from the new site have resulted in a significant improvement of 15% for the Area Under the curve (AUC) for the new site that we want to establish a new follicular lymphoma classifier. The test results have shown that the classifier can perform well without the need to obtain more training data from the test site, by utilizing GAN to generate the synthetic data from all existing data in the archives from all the sites.

Abstract Gated Recurrent Neural Networks (RNNs) such as LSTM and GRU have been highly effective in handling sequential time series data in recent years. Although Gated RNNs have an inherent ability to learn complex temporal dynamics, there is potential for further enhancement by enabling these deep learning networks to directly use time information to recognise time-dependent patterns in data and identify important segments of time. Synonymous with time series data in real-world applications are missing values, which often reduce a model’s ability to perform predictive tasks. Historically, missing values have been handled by simple or complex imputation techniques as well as machine learning models, which manage the missing values in the prediction layers. However, these methods do not attempt to identify the significance of data segments and therefore are susceptible to poor imputation values or model degradation from high missing value rates. This paper develops Cyclic Gate enhanced recurrent neural networks with learnt waveform parameters to automatically identify important data segments within a time series and neglect unimportant segments. By using the proposed networks, the negative impact of missing data on model performance is mitigated through the addition of customised cyclic opening and closing gate operations. Cyclic Gate Recurrent Neural Networks are tested on several sequential time series datasets for classification performance. For long sequence datasets with high rates of missing values, Cyclic Gate enhanced RNN models achieve higher performance metrics than standard gated recurrent neural network models, conventional non-neural network machine learning algorithms and current state of the art RNN cell variants.

Over the last few years, there have been many significant advances in the use of deep learning in digital pathology. Deep learning has been reported to assist with registration, segmentation, classification, and diagnosis tasks in digital pathology. However, the development of scalable, adaptable, and accurate deep learning-based models often relies on collecting large amounts of high-quality annotated training data from various sources or from different sites. Given that the medical data are normally linked to a site and/or within an organization, assembling large-scale datasets has historically required data transfer between them. Patient privacy could be an issue by such transfers, especially if data are to be shared between countries. This poses ethical and legal issues. Therefore, privacy and ownership issues affecting multi-institutional collaborations focused on centrally shared patient data, could affect the translation of deep learning techniques for real-world application. Federated learning has recently emerged as a new paradigm for data-private multi-institutional collaborations, in which model-learning uses all available data without exchanging data between institutions by distributing model training to data-owners and aggregating their outcomes. This paper aims to investigate the possible use of the federated learning method in digital pathology and examine the advantages of using federated learning for real world digital pathology workflow. We have performed our study on the Breast Cancer Histopathological Database, which consists of data from different sites. The case study results presented in this paper have demonstrated that federated learning can be used effectively in the digital pathology area.

Representation learning of knowledge graphs aims to embed entities and relations into low-dimensional vectors. Most existing works only consider the direct relations or paths between an entity pair. It is considered that such approaches disconnect the semantic connection of multi-relations between an entity pair, and we propose a convolutional and multi-relational representation learning model, ConvMR. The proposed ConvMR model addresses the multi-relation issue in two aspects: (1) Encoding the multi-relations between an entity pair into a unified vector that maintains the semantic connection. (2) Since not all relations are necessary while joining multi-relations, we propose an attention-based relation encoder to automatically assign weights to different relations based on semantic hierarchy. Experimental results on two popular datasets, FB15k-237 and WN18RR, achieved consistent improvements on the mean rank. We also found that ConvMR is efficient to deal with less frequent entities.

Deep learning (DL) has achieved superior classification in many applications due to its capability of extracting features from the data. However, the success of DL comes with the tradeoff of possible overfitting. The bias towards the data it has seen during the training process leads to poor generalisation. One way of solving this issue is by having enough training data so that the classifier is invariant to many data patterns. In the literature, data augmentation has been used as a type of regularisation method to reduce the chance for the model to overfit. However, most of the relevant works focus on image, sound or text data. There is not much work on numerical data augmentation, although many real-world problems deal with numerical data. In this paper, we propose using a technique based on Fuzzy C-Means clustering and fuzzy membership grades. Fuzzy-related techniques are used to address the variance problem by generating new data items based on fuzzy numbers and each data item's belongings to different fuzzy clusters. This data augmentation technique is used to improve the generalisation of a Deep Neural Network that is suitable for numerical data. By combining the proposed fuzzy data augmentation technique with the Dropout regularisation technique, we manage to balance the classification model's bias-variance tradeoff. Our proposed technique is evaluated using four popular data sets and is shown to provide better regularisation and higher classification accuracy compared with popular regularisation approaches.

Video games are often designed around puzzles and problem-solving, leading to challenging yet engaging experiences for players. However, it is hard to measure or compare the challenge level of puzzles in video games. This can make designing appropriately challenging puzzles problematic. This study collates previous work to present refined definitions for challenge and difficulty within the context of video games. We present the Puzzle Challenge Analysis tool which can be used to determine the best metrics for analysing the challenge level of puzzles within video games. Previous research has focused on measuring the difficulty of simple action video games, such as Pac-Man, which can be easily modified for research purposes. Existing methods to measure challenge or difficulty include measuring player brain activity, examining game features and player scores. However, some of these approaches cannot be applied to puzzles or puzzle games. For example, approaches relying on game scores will not work for puzzle games with no scoring system, where puzzles are either solved or not. This paper describes the design and development of the Puzzle Challenge Analysis tool using two case studies of commercial video games The Witness and Untitled Goose Game. The tool is also tested for generalisability on a third commercial puzzle video game, Baba Is You. This proposed tool can help game designers and researchers to objectively analyse and compare puzzle challenge and produce more in-depth insights into the player experience. This has implications for designing challenging and engaging games for a range of player abilities.

Extreme learning machines (ELMs) has been theoretically and experimentally proved to achieve promising performance at a fast learning speed for supervised classification tasks. However, it does not perform well on imbalanced binary classification tasks and tends to get biased toward the majority class. Besides, since a large amount of training data with labels are not always available in the real world, there is an urgent demand to develop an efficient semi-supervised version of ELM for imbalanced binary classification tasks. In this article, owing to the distinct insensitivity of area under the ROC curve (AUC) to both class skews and changes of class distributions, we focus the study on integrating AUC maximization into the ELM framework to tackle with imbalanced binary classification tasks well. By demystifying the AUC metric with the ELM framework, we develop a new AUC-based ELM called AUC-ELM for imbalanced binary classification, which essentially is revealed to be equivalent to an ELM on another transformed data space. Accordingly, its semi-supervised version called SAUC-ELM is also developed. Both AUC-ELM and SAUC-ELM have the distinctive merits: 1) they share the advantage of ELM in both generalization capability and training efficiency, and further uniquely tailored for imbalanced binary classification tasks and 2) in contrast to the existing imbalanced variants of ELM, such as class-specific cost regulation ELM and semi-supervised ELM, they have fewer parameters to tune, thereby reducing the computational cost for model selection. Experiments on a heap of datasets show that both AUC-ELM and SAUC-ELM outperform the other comparative methods in terms of both classification performance and training speed.

The performance of classification algorithms with highly imbalanced streaming data depends upon efficient balancing strategy. Some techniques of balancing strategy have been applied using static batch data to resolve the class imbalance problem, which is difficult if applied for massive data streams. In this paper, a new Piece-Wise Incremental Data re-Balancing (PWIDB) framework is proposed. The PWIDB framework combines automated balancing techniques using Racing Algorithm (RA) and incremental rebalancing technique. RA is an active learning approach capable of classifying imbalanced data and can provide a way to select an appropriate re-balancing technique with imbalanced data. In this paper, we have extended the capability of RA for handling imbalanced data streams in the proposed PWIDB framework. The PWIDB accumulates previous knowledge with increments of re-balanced data and captures the concept of the imbalanced instances. The PWIDB is an incremental streaming batch framework, which is suitable for learning with streaming imbalanced data. We compared the performance of PWIDB with a well-known FLORA technique. Experimental results show that the PWIDB framework exhibits an improved and stable performance compared to FLORA and accumulative re-balancing techniques.

The pervasiveness of social media and user-generated content has triggered an exponential increase in global data. However, due to collection and extraction challenges, data in embedded comments, reviews and testimonials are largely inaccessible to a knowledge management system. This article describes a KM framework for the end-to-end knowledge management and value extraction from such content. This framework embodies solutions to unlock the potential of UGC as a rich, real-time data source. Three contributions are described in this article. First, a method for automatically navigating webpages to expose UGC for collection is presented. This is evaluated using browser emulation integrated with automated collection. Second, a method for collecting data without any a priori knowledge of the sites is introduced. Finally, a new testbed is developed to reflect the current state of internet sites and shared publicly to encourage future research. The discussion benchmarks the new algorithm alongside existing techniques, providing evidence of the increased amount of UGC data extracted.

Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), and Memory Networks which contain memory are popularly used to learn patterns in sequential data. Sequential data has long sequences that hold relationships. RNN can handle long sequences but suffers from the vanishing and exploding gradient problems. While LSTM and other memory networks address this problem, they are not capable of handling long sequences (50 or more data points long sequence patterns). Language modelling requiring learning from longer sequences are affected by the need for more information in memory. This paper introduces Long Term Memory network (LTM), which can tackle the exploding and vanishing gradient problems and handles long sequences without forgetting. LTM is designed to scale data in the memory and gives a higher weight to the input in the sequence. LTM avoid overfitting by scaling the cell state after achieving the optimal results. The LTM is tested on Penn treebank dataset, and Text8 dataset and LTM achieves test perplexities of 83 and 82 respectively. 650 LTM cells achieved a test perplexity of 67 for Penn treebank, and 600 cells achieved a test perplexity of 77 for Text8. LTM achieves state of the art results by only using ten hidden LTM cells for both datasets.

Text clustering is an effective way that helps crime investigation through grouping of crime-related documents. This paper proposes a Memetic Algorithm Feature Selection (MAFS) approach to enhance the performance of document clustering algorithms used to partition crime reports and criminal news as well as some benchmark text datasets. Two clustering algorithms have been selected to demonstrate the effectiveness of the proposed MAFS method; they are the k-means and Spherical k-means (Spk). The reason behind using these clustering methods is to observe the performance of these algorithms before and after applying a hybrid FS that uses a Memetic scheme. The proposed MAFS method combines a Genetic Algorithm-based wrapper FS with the Relief-F filter. The performance evaluation was based on the clustering outcomes before and after applying the proposed MAFS method. The test results showed that the performance of both k-means and spk improved after the MAFS.

With the evolution of technology and the major role that technology now plays in the diagnosis and identification of disorders and difficulties, improving the accuracy of diagnostic systems is paramount. Improving and evaluating the way in which patterns of results are identified and classified may help uncover answers that are not always obvious. This paper attempts to discover such patterns found in brainwave signals in adults who have been diagnosed with dyslexia using classifiers. Electroencephalogram (EEG) signals captured during real-word and nonsense-word reading activities from adults with dyslexia were compared with normal controls. The classification was performed using Linear Support Vector Machine (LSVM) and Cubic Support Vector Machine (CSVM) on different lobes of the brain. The study revealed that the nonsense-words classifiers produced higher validation accuracies compared to real-words classifiers, confirming difficulties in phonological decoding skills seen in individuals with dyslexia are reflected in the brainwave patterns.

A hybrid sampling technique is proposed by combining Complementary Fuzzy Support Vector Machine (CMTFSVM) and Synthetic Minority Oversampling Technique (SMOTE) for handling the imbalanced classification problem. The proposed technique uses an optimised membership function to enhance the classification performance and it is compared with three different classifiers. The experiments consisted of four standard benchmark datasets and one real world data of plant cells. The results revealed that implementing CMTFSVM followed by SMOTE provided better result over other FSVM classifiers for the benchmark datasets. Furthermore, it presented the best result on real world dataset with 0.9589 of G-mean and 0.9598 of AUC. It can be concluded that the proposed techniques work well with imbalanced benchmark and real world data.

This paper proposes a methodology to create an interpretable fuzzy model for monthly rainfall time series prediction. The proposed methodology incorporates the advantages of artificial neural network, fuzzy logic and genetic algorithm. In the first step, the differences between the time series data are calculated and they are used to define the interval between the membership functions of a Mamdani-type fuzzy inference system. Next, artificial neural network is used to develop the model from input-output data and the established model is then used to extract the fuzzy rules. The parameters of the created fuzzy model are then optimized by using genetic algorithm. The proposed model was applied to eight monthly rainfall time series data in the northeast region of Thailand. The experimental results showed that the proposed model provided satisfactory prediction accuracy when compared to other commonly-used prediction models. Due to the interpretability nature of the model, human analysts can gain insight knowledge of the data to be modeled.

Feature selection is an important step in processing the images especially for applications such as content based image retrieval. In large multimedia databases, it may not be practical to search through the entire database in order to retrieve similar images from a query. Good data structures for similarity search and indexing are needed, and the existing data structures do not scale well for the high dimensional multimedia descriptors. Thus feature selection is an important step. Fuzzy rough feature selection method has many advantages in determining the relevant features. In this paper, five feature selection methods are compared with the fuzzy rough method. These five feature selection methods are Relief-F, Information Gain, Gain Ratio, OneR and the statistical measure χ2. The main purpose of the comparison is to rank the image features and see which method provides better results. An image retrieval dataset (COREL dataset) was used in the comparison. In order to evaluate the performance of the six methods, ranking of the important features is defined. This is then used to compare with the automated ranking produced by the aforesaid feature selection methods. Results show that the retrieval system using fuzzy rough feature selection has better retrieval accuracy and provide good Precision Recall performance. The advantages of the use of fuzzy rough feature selection will also be discussed in the paper.

In water management systems, accurate rainfall forecasting is indispensable for operation and management of reservoir, and flooding prevention because it can provide an extension of lead-time of the flow forecasting. In general, time series prediction has been widely applied to predict rainfall data. The conventional time series prediction models or artificial neural networks can be used to perform this task. However, such models are difficult to interpret by human analyst. From a hydrologist's point of view, the accuracy of the prediction and understanding the prediction model are equally important. This study proposes the use of a Modular Fuzzy Inference System (Mod FIS) to predict monthly rainfall data in the northeast region of Thailand. The experimental results show that the proposed model can be a good alternative method to provide both accurate results and human-understandable prediction mechanism.

In data classification, the problem of imbalanced class distribution has attracted many attentions. Most efforts have used to investigate the problem mainly for binary classification. However, research solutions for the imbalanced data on binary-class problems are not directly applicable to multi-class applications. Therefore, it is a challenge to handle the multi-class problem with imbalanced data in order to obtain satisfactory results. This problem can indirectly affect how human visualise the data. In this paper, an algorithm named One-Against-All with Data Balancing (OAA-DB) is developed to enhance the classification performance in the case of the multi-class imbalanced data. This algorithm is developed by combining the multi-binary classification technique called One-Against-All (OAA) and a data balancing technique. In the experiment, the three multi-class imbalanced data sets used were obtained from the University of California Irvine (UCI) machine learning repository. The results show that the OAA-DB algorithm can enhance the classification performance for the multi-class imbalanced data without reducing the overall classification accuracy.

To overcome the problem of information overloading in mobile communication, a recommendation system can be used to help mobile device users. However, there are problems relating to sparsity of information from a first-time user in regard to initial rating of the content and the retrieval of relevant items. In order for the user to experience personalized content delivery via the mobile recommendation system, content filtering is necessary. This paper proposes an integrated method by using classification and association rule techniques for extracting knowledge from mobile content in a user's profile. The knowledge can be used to establish a model for new users and first rater on mobile content. The model recommends relevant content in the early stage during the connection based on the user's profile. The proposed method also facilitates association to be generated to link the first rater items to the top items identified from the outcomes of the classification and clustering processes. This can address the problem of sparsity in initial rating and new user's connection for non-interactive recommendation systems.

The classical approaches for the traditional problems of text mining, such as document indexing, document clustering or text classification, represent the text as bag-of-words. Words, the units of the representation, are determined by tokenization, using e.g. whitespace and punctuation characters as separator. The bag-of-word based methods face problem with non-segmented text typical for some Asian languages, since the tokenization based solution cannot be applied anymore to determine the representation units. Several solutions were proposed so far, among them frequent max substring mining is adopted here because of its language-independency and favourable speed and store requirements. We present in this paper a fuzzy signature based solution using frequent max substring for non-segmented document representation, and propose how it could be applied for some typical text mining tasks. We show how the flexibility of fuzzy signatures can be exploited for text mining tasks. With the use of this proposed concept, complex decision models in text mining may be constructed more effectively in future.

This paper presents a class of fuzzy cognitive modeling which can handle granulation, organisation and causation. This cognitive modeling technique consists of multiple levels where the lowest level includes details required to make a decision or to transfer to the next stage. At the lowest level, fuzzy signatures are used to represent the concepts or knowledge.

This paper investigates the possible use of fuzzy system and linear assignment problem (LAP) for resource allocation for massively multiplayer online games (MMOGs). Due to the limitation of design capacity of such complex MMOGs, resources available in the game cannot be unlimited. Resources in this context refer to items used to support the game play and activities in the MMOGs, also known as in-game resources. As for network resources, it is also one of the important research areas for MMOGs due to the increasing number of players. One of the main objectives is to ensure the quality of service (QoS) in the MMOGs environment for each player. Regardless, which context the resource is defined, the proposed method can still be used. Simulated results based on the network resources to ensure QoS shows that the proposed method could be an alternative.

Fuzzy Cognitive Map (FCM) has commonly been used as a prediction tool. The FCM forward chains have been used to find answers to what-if questions. The process starts with the encoding of the what-if question into a stimulus vector. The vector goes through a series of vector-matrix multiplication until the FCM converges to one of the FCM attractors. The attractor is the answer to the initial question. There are several types of FCM attractors. The usefulness of the different types of attractors relies heavily on the user’s objectives and interpretations. This paper presents the theoretical discussion on distance measurement among the various FCM attractor distances. Subsequently the FCM Attractor Distance (FCMAD) based on genetic algorithm is proposed. The use of this distance in FCM goal oriented analysis and FCM learning is discussed. Experiment results have confirmed the effectiveness of the proposed technique.

In most fuzzy systems, the completeness of the fuzzy rule base is required to generate meaningful output when classical fuzzy reasoning methods are applied. This means, in other words, that the fuzzy rule base has to cover all possible inputs. Regardless of the way of rule base construction, be it created by human experts or by an automated manner, often incomplete rule bases are generated. One simple solution to handle sparse fuzzy rule bases and to make infer reasonable output is the application of fuzzy rule interpolation (FRI) methods. In this paper, we present a Fuzzy Rule Interpolation Matlab Toolbox, which is freely available. With the introduction of this Matlab Toolbox, different FRI methods can be used for different real time applications, which have sparse or incomplete fuzzy rule base.

This paper presents an efficient fuzzy cognitive modeling which can handle granulation, organisation and causation. This cognitive modeling technique consists of multiple levels where the lowest level includes details required to make a decision or to transfer to the next stage. This fuzzy cognitive modeling will enhance the usability of fuzzy theory in modeling complex systems as well as facilitating complex decision making process based on ill structured or missing information or data.

Use of relevance feedback (RF) in the feature vector model has been one of the most popular approaches to fine tune query for content-based image retrieval (CBIR) systems. This paper proposes a framework that extends the RF approach to capture the inter-query relationship between current and previous queries. By using the feature vector model, this approach avoids the need of "memorizing" actual retrieval relationship between the actual image indexes and the previous queries. This implies that the approach is more suitable for image database application where images are frequently added and removed. The proposed inter-query relationship is presented using a data cluster that is defined by a transformation matrix, a centroid point and the reference boundary value. These parameters are captured in a file commonly known as the user log. The file however will grow rapidly after successive retrieval sessions. In order to reduce the size of the user log, this paper introduces a merging approach to combine clusters that are close-by and similar in their characteristics. Experiments have shown that the proposed framework has out performed the short term learning approach and yet without the burden of the complex database maintenance strategies required in long-term learning approach.

Quantification of uncertainty in mineral prospectivity prediction is an important process to support decision making in mineral exploration. Degree of uncertainly can identify level of quality in the prediction. This paper proposes an approach to predict degrees of favourability for gold deposits together with quantification of uncertainty in the prediction. Geographic information systems (GIS) data is applied to the integration of ensemble neural networks and interval neutrosophic sets, three different neural network architectures are used in this paper. The prediction and its uncertainty are represented in the form of truth-membership, indeterminacy-membership, and false-membership values. Two networks arc created for each network architecture to predict degrees of favourability for deposit and non deposit, which are represented by truth and false membership values respectively. Uncertainty or indeterminacy-membership values are estimated from both truth and false membership values, The results obtained using different neural network ensemble techniques are discussed in this paper.

Adaptation of parameters and operators represents one of the recent most important and promising areas of research in evolutionary computations; it is a form of designing self-configuring algorithms that acclimatize to suit the problem in hand. Here, our interests are on a recent breed of hybrid evolutionary algorithms typically known as adaptive memetic algorithms (MAs). One unique feature of adaptive MAs is the choice of local search methods or memes and recent studies have shown that this choice significantly affects the performances of problem searches. In this paper, we present a classification of memes adaptation in adaptive MAs on the basis of the mechanism used and the level of historical knowledge on the memes employed. Then the asymptotic convergence properties of the adaptive MAs considered are analyzed according to the classification. Subsequently, empirical studies on representatives of adaptive MAs for different type-level meme adaptations using continuous benchmark problems indicate that global-level adaptive MAs exhibit better search performances. Finally we conclude with some promising research directions in the area.

Fuzzy rule based systems have been very popular in many engineering applications. However, when generating fuzzy rules from the available information, this may result in a sparse fuzzy rule base. Fuzzy rule interpolation techniques have been established to solve the problems encountered in processing sparse fuzzy rule bases. In most engineering applications, the use of more than one input variable is common, however, the majority of the fuzzy rule interpolation techniques only present detailed analysis to one input variable case. This paper investigates characteristics of two selected fuzzy rule interpolation techniques for multidimensional input spaces and proposes an improved fuzzy rule interpolation technique to handle multidimensional input spaces. The three methods are compared by means of application examples in the field of petroleum engineering and mineral processing. The results show that the proposed fuzzy rule interpolation technique for multidimensional input spaces can be used in engineering applications.

This paper proposes and examines a new approach using fuzzy logic to vehicle fleet deployment. Fleet deployment is viewed as a fuzzy linear assignment problem. It assigns each travel request to an available service vehicle through solving a linear assignment matrix of defuzzied cost entries. Each cost entry indicates the cost value of a travel request that "fuzzily aggregates" multiple criteria in simple rules incorporating human dispatching expertise. The approach is examined via extensive simulations anchored in a representative scenario of taxi deployment, and compared to the conventional case of using only distances (each from the taxi position to the source point and finally destination point of a travel request) as cost entries. Discussion in the context of related work examines the performance and practicality of the proposed approach.

There are many areas where objects with very complex and sometimes interdependent features are to be classified; similarities and dissimilarities are to be evaluated. This makes a complex decision model difficult to construct effectively. Fuzzy signatures are introduced to handle complex structured data and interdependent feature problems. Fuzzy signatures can also be used in cases where data is missing. This work presents the concept of a fuzzy signature and how its flexibility can be used to quickly construct a medical pre-clinical diagnosis system. A severe acute respiratory syndrome (SARS) pre-clinical diagnosis system using fuzzy signatures is constructed as an example to show many advantages of the fuzzy signature. With the use of this fuzzy signature structure, complex decision models in the medical field should be able to be constructed more effectively.

Customer relationship management (CRM) initiatives have gained much attention in recent years. With the aid of data mining technology, businesses can formulate specific strategies for different customer bases more precisely. Additionally, personalisation is another important issue in CRM - especially when a company has a huge product range. This paper presents a case model and investigates the use of computational intelligent techniques for CRM. These techniques allow the complex functions of relating customer behaviour to internal business processes to be learned more easily and the industry expertise and experience from business managers to be integrated into the modelling framework directly. Hence, they can be used in the CRM framework to enhance the creation of targeted strategies for specific customer bases.

This paper proposes an extended version of a previously developed low cost parallel computation platform called Para Worker. The new system is termed Para Worker 2 which differentiates from the early system. The new proposed system adds enhanced features of improved dynamic object reallocation, adaptive consistency protocols, and location transparency as compared to the original system. The proposal is particularly useful for the implementation and execution of computational intelligence techniques such as evolutionary computing for engineering applications.

We propose a histogram-based rule extraction technique using straightforward histogram-based clustering that produces trapezoidal clusters that are well suited for the rule extraction purpose. Two experiments were carried out to validate the feasibility and effectiveness of the proposed technique and show that the rule base generated by the proposed technique is reasonably accurate.

Fuzzy rule based systems have been very popular in many control applications. However, when fuzzy control systems are used in real problems, many rules may be required. The number of rules required depends on the number of inputs and the number of fuzzy linguistic terms used. This exponential explosion of fuzzy rules can take too much computing time to solve any but the simplest problems. This paper proposes a hierarchical fuzzy system that partitions a problem for more efficient computation. The hierarchical fuzzy rule base algorithm constructs rules from data for the purpose of performing fuzzy classification. Illustration examples are also generated and the results show that this hierarchical fuzzy system can be successfully used for classification applications.