Arabic open information extraction system using dependency parsing

<p>Arabic is a Semitic language and one of the most natural languages distinguished by the richness in morphological enunciation and derivation. This special and complex nature makes extracting information from the Arabic language difficult and always needs improvement. Open information extraction systems (OIE) have been emerged and used in different languages, especially in English. However, it has almost not been used for the Arabic language. Accordingly, this paper aims to introduce an OIE system that extracts the relation tuple from Arabic web text, exploiting Arabic dependency parsing and thinking carefully about all possible text relations. Based on clause types' propositions as extractable relations and constituents' grammatical functions, the identities of corresponding clause types are established. The proposed system named Arabic open information extraction(AOIE) can extract highly scalable Arabic text relations while being domain independent. Implementing the proposed system handles the problem using supervised strategies while the system relies on unsupervised extraction strategies. Also, the system has been implemented in several domains to avoid information extraction in a specific field. The results prove that the system achieves high efficiency in extracting clauses from large amounts of text.</p>

A decade of research on patterns and architectures for IoT security

Security of the Internet of Things (IoT)-based Smart Systems involving sensors, actuators and distributed control loop is of paramount importance but very difficult to address. Security patterns consist of domain-independent time-proven security knowledge and expertise. How are they useful for developing secure IoT-based smart systems? Are there architectures that support IoT security? We aim to systematically review the research work published on patterns and architectures for IoT security (and privacy). Then, we want to provide an analysis on that research landscape to answer our research questions. We follow the well-known guidelines for conducting systematic literature reviews. From thousands of candidate papers initially found in our search process, we have systematically distinguished and analyzed thirty-six (36) papers that have been peer-reviewed and published around patterns and architectures for IoT security and privacy in the last decade (January 2010–December 2020). Our analysis shows that there is a rise in the number of publications tending to patterns and architectures for IoT security in the last three years. We have not seen any approach of applying systematically architectures and patterns together that can address security (and privacy) concerns not only at the architectural level, but also at the network or IoT devices level. We also explored how the research contributions in the primary studies handle the different issues from the OWASP Internet of Things (IoT) top ten vulnerabilities list. Finally, we discuss the current gaps in this research area and how to fill in the gaps for promoting the utilization of patterns for IoT security and privacy by design.

Interfaces for Searching and Triaging Large Document Sets: An Ontology-Supported Visual Analytics Approach

We investigate the design of ontology-supported, progressively disclosed visual analytics interfaces for searching and triaging large document sets. The goal is to distill a set of criteria that can help guide the design of such systems. We begin with a background of information search, triage, machine learning, and ontologies. We review research on the multi-stage information-seeking process to distill the criteria. To demonstrate their utility, we apply the criteria to the design of a prototype visual analytics interface: VisualQUEST (Visual interface for QUEry, Search, and Triage). VisualQUEST allows users to plug-and-play document sets and expert-defined ontology files within a domain-independent environment for multi-stage information search and triage tasks. We describe VisualQUEST through a functional workflow and culminate with a discussion of ongoing formative evaluations, limitations, future work, and summary.

Mining Domain Terminologies Using Search Engine's Query Log

Domain terminologies are a basic resource for various natural language processing tasks. To automatically discover terminologies for a domain of interest, most traditional approaches mostly rely on a domain-specific corpus given in advance; thus, the performance of traditional approaches can only be guaranteed when collecting a high-quality domain-specific corpus, which requires extensive human involvement and domain expertise. In this article, we propose a novel approach that is capable of automatically mining domain terminologies using search engine's query log—a type of domain-independent corpus of higher availability, coverage, and timeliness than a manually collected domain-specific corpus. In particular, we represent query log as a heterogeneous network and formulate the task of mining domain terminology as transductive learning on the heterogeneous network. In the proposed approach, the manifold structure of domain-specificity inherent in query log is captured by using a novel network embedding algorithm and further exploited to reduce the need for the manual annotation efforts for domain terminology classification. We select Agriculture and Healthcare as the target domains and experiment using a real query log from a commercial search engine. Experimental results show that the proposed approach outperforms several state-of-the-art approaches.

A Domain-Independent Generative Adversarial Network for Activity Recognition Using WiFi CSI Data

Over the past years, device-free sensing has received considerable attention due to its unobtrusiveness. In this regard, context recognition using WiFi Channel State Information (CSI) data has gained popularity, and various techniques have been proposed that combine unobtrusive sensing and deep learning to accurately detect various contexts ranging from human activities to gestures. However, research has shown that the performance of these techniques significantly degrades due to change in various factors including sensing environment, data collection configuration, diversity of target subjects, and target learning task (e.g., activities, gestures, emotions, vital signs). This problem, generally known as the domain change problem, is typically addressed by collecting more data and learning the data distribution that covers multiple factors impacting the performance. However, activity recognition data collection is a very labor-intensive and time consuming task, and there are too many known and unknown factors impacting WiFi CSI signals. In this paper, we propose a domain-independent generative adversarial network for WiFi CSI based activity recognition in combination with a simplified data pre-processing module. Our evaluation results show superiority of our proposed approach compared to the state of the art in terms of increased robustness against domain change, higher accuracy of activity recognition, and reduced model complexity.

Particle Swarm Optimization and Fuzzy C-means for Domain-independent Noisy Image Segmentation

<p>Image segmentation is considered to be one of the foremost image analysis techniques for high-level real-world applications in computer vision. Its task is to change or simplify the representation of an image in order to make it easier to understand or analyze. Although image segmentation has been studied for many years, evolving technology and transformation of demands make image segmentation a continuing challenge. Noise as a side effect of imaging devices is an inevitable part of images in many computer vision applications. Therefore, an important topic in image segmentation is noisy image segmentation which requires extra effort to deal with image segmentation in the presence of noise. Generally, different strategies are needed for different noisy images with different levels/types of noise. Therefore, many approaches in the literature are domain-dependent and applicable only to specific images. A well-recognized approach in noisy image segmentation uses clustering algorithms, among which Fuzzy C-Means (FCM) is one of the most popular. FCM is unsupervised, efficient, and can deal with uncertainty and complexity of information in an image. Dealing with uncertainties is easier with the fuzzy characteristic of FCM, and complexity of information is being taken care of by utilizing different features in FCM, and also combining FCM with other techniques. Many modifications have been introduced to FCM to deal with noisy image segmentation more effectively. Common approaches include, adding spatial information into the FCM process, addressing the FCM initialization problem, and enhancing features used for segmentation. However, existing FCM-based noisy image segmentation approaches in the literature generally suffer from three drawbacks. First, they are applicable to specific domains and images, and impotent in others. Second, they don’t perform well on severely noisy image segmentation. Third, they are effective on specific type and level of noise, and they don’t explore the effect of noise level variation. Recently, evolutionary computation techniques due to their global search abilities have been used in hybridization with FCM, mostly to address FCM stagnation in local optima. Particle Swarm Optimization (PSO) is particularly of interest because of its lower computational costs, easy implementation, and fast convergence, but its potential in this area has not been fully investigated. This thesis develops new domain-independent PSO-based algorithms for an automatic non-supervised FCM-based segmentation of severely noisy images which are capable of extracting the main coherent/homogeneous regions while preserving details and being robust to noise variation. The key approach taken in the thesis is to explore the use of PSO to manipulate and enhance local spatial and spatial-frequency information. This thesis introduces a new PSO feature enhancement approach in wavelet domain for noisy image segmentation. This approach applies adaptive wavelet shrinkage using evaluation based on FCM clustering performance. The results show great accuracy in the case of severe noise because of the enhanced features. Also, due to adaptivity, no parameter-tuning is required according to the type or volume of noise, and the performance is consistent under noise level variation. This thesis presents a scheme under which a fusion of two different denoising algorithms for more effective segmentation is possible. This fusion retains the advantages of each algorithm while leaving out their drawbacks. The fusion scheme uses the noisy image segmentation system introduced above and anisotropic diffusion, the edge-preserving denoising algorithm. Results show greater accuracy and stability in comparison to the individual algorithms on a variety of noisy images. This thesis introduces another PSO-based edge-preserving adaptive wavelet shrinkage system using wavelet packets, bilateral filtering, and a detail-respecting shrinkage scheme. The analysis of the results provide a comparison between the two feature enhancement systems. The first system uses wavelets and the second uses wavelet packets as a domain to enhance features for an FCM-based noisy image segmentation. Also, the highest segmentation accuracy among all the algorithms introduced in this thesis on some benchmarks belong to this system.</p>

Particle Swarm Optimization and Fuzzy C-means for Domain-independent Noisy Image Segmentation

<p>Image segmentation is considered to be one of the foremost image analysis techniques for high-level real-world applications in computer vision. Its task is to change or simplify the representation of an image in order to make it easier to understand or analyze. Although image segmentation has been studied for many years, evolving technology and transformation of demands make image segmentation a continuing challenge. Noise as a side effect of imaging devices is an inevitable part of images in many computer vision applications. Therefore, an important topic in image segmentation is noisy image segmentation which requires extra effort to deal with image segmentation in the presence of noise. Generally, different strategies are needed for different noisy images with different levels/types of noise. Therefore, many approaches in the literature are domain-dependent and applicable only to specific images. A well-recognized approach in noisy image segmentation uses clustering algorithms, among which Fuzzy C-Means (FCM) is one of the most popular. FCM is unsupervised, efficient, and can deal with uncertainty and complexity of information in an image. Dealing with uncertainties is easier with the fuzzy characteristic of FCM, and complexity of information is being taken care of by utilizing different features in FCM, and also combining FCM with other techniques. Many modifications have been introduced to FCM to deal with noisy image segmentation more effectively. Common approaches include, adding spatial information into the FCM process, addressing the FCM initialization problem, and enhancing features used for segmentation. However, existing FCM-based noisy image segmentation approaches in the literature generally suffer from three drawbacks. First, they are applicable to specific domains and images, and impotent in others. Second, they don’t perform well on severely noisy image segmentation. Third, they are effective on specific type and level of noise, and they don’t explore the effect of noise level variation. Recently, evolutionary computation techniques due to their global search abilities have been used in hybridization with FCM, mostly to address FCM stagnation in local optima. Particle Swarm Optimization (PSO) is particularly of interest because of its lower computational costs, easy implementation, and fast convergence, but its potential in this area has not been fully investigated. This thesis develops new domain-independent PSO-based algorithms for an automatic non-supervised FCM-based segmentation of severely noisy images which are capable of extracting the main coherent/homogeneous regions while preserving details and being robust to noise variation. The key approach taken in the thesis is to explore the use of PSO to manipulate and enhance local spatial and spatial-frequency information. This thesis introduces a new PSO feature enhancement approach in wavelet domain for noisy image segmentation. This approach applies adaptive wavelet shrinkage using evaluation based on FCM clustering performance. The results show great accuracy in the case of severe noise because of the enhanced features. Also, due to adaptivity, no parameter-tuning is required according to the type or volume of noise, and the performance is consistent under noise level variation. This thesis presents a scheme under which a fusion of two different denoising algorithms for more effective segmentation is possible. This fusion retains the advantages of each algorithm while leaving out their drawbacks. The fusion scheme uses the noisy image segmentation system introduced above and anisotropic diffusion, the edge-preserving denoising algorithm. Results show greater accuracy and stability in comparison to the individual algorithms on a variety of noisy images. This thesis introduces another PSO-based edge-preserving adaptive wavelet shrinkage system using wavelet packets, bilateral filtering, and a detail-respecting shrinkage scheme. The analysis of the results provide a comparison between the two feature enhancement systems. The first system uses wavelets and the second uses wavelet packets as a domain to enhance features for an FCM-based noisy image segmentation. Also, the highest segmentation accuracy among all the algorithms introduced in this thesis on some benchmarks belong to this system.</p>

Genetic Programming for Automatically Synthesising Robust Image Descriptors with A Small Number of Instances

<p>Image classification is a core task in many applications of computer vision, including object detection and recognition. It aims at analysing the visual content and automatically categorising a set of images into different groups. Performing image classification can largely be affected by the features used to perform this task. Extracting features from images is a challenging task due to the large search space size and practical requirements such as domain knowledge and human intervention. Human intervention is usually needed to identify a good set of keypoints (regions of interest), design a set of features to be extracted from those keypoints such as lines and corners, and develop a way to extract those features. Automating these tasks has great potential to dramatically decrease the time and cost, and may potentially improve the performance of the classification task. There are two well-recognised approaches in the literature to automate the processes of identifying keypoints and extracting image features. Designing a set of domain-independent features is the first approach, where the focus is on dividing the image into a number of predefined regions and extracting features from those regions. The second approach is synthesising a function or a set of functions to form an image descriptor that aims at automatically detecting a set of keypoints such as lines and corners, and performing feature extraction. Although employing image descriptors is more effective and very popular in the literature, designing those descriptors is a difficult task that in most cases requires domain-expert intervention. The overall goal of this thesis is to develop a new domain independent Genetic Programming (GP) approach to image classification by utilising GP to evolve programs that are capable of automatically detecting diverse and informative keypoints, designing a set of features, and performing feature extraction using only a small number of training instances to facilitate image classification, and are robust to different image changes such as illumination and rotation. This thesis focuses on incorporating a variety of simple arithmetic operators and first-order statistics (mid-level features) into the evolutionary process and on representation of GP to evolve programs that are robust to image changes for image classification. This thesis proposes methods for domain-independent binary classification in images using GP to automatically identify regions within an image that have the potential to improve classification while considering the limitation of having a small training set. Experimental results show that in over 67% of cases the new methods significantly outperform the use of existing hand-crafted features and features automatically detected by other methods. This thesis proposes the first GP approach for automatically evolving an illumination-invariant dense image descriptor that detects automatically designed keypoints, and performs feature extraction using only a few instances of each class. The experimental results show improvement of 86% on average compared to two GP-based methods, and can significantly outperform domain-expert hand-crafted descriptors in more than 89% of the cases. This thesis also considers rotation variation of images and proposes a method for automatically evolving rotation-invariant image descriptors through integrating a set of first-order statistics as terminals. Compared to hand-crafted descriptors, the experimental results reveal that the proposed method has significantly better performance in more than 83% of the cases. This thesis proposes a new GP representation that allows the system to automatically choose the length of the feature vector side-by-side with evolving an image descriptor. Automatically determining the length of the feature vector helps to reduce the number of the parameters to be set. The results show that this method has evolved descriptors with a very small feature vector which yet still significantly outperform the competitive methods in more than 91% of the cases. This thesis proposes a method for transfer learning by model in GP, where an image descriptor evolved on instances of a related problem (source domain) is applied directly to solve a problem being tackled (target domain). The results show that the new method evolves image descriptors that have better generalisability compared to hand-crafted image descriptors. Those automatically evolved descriptors show positive influence on classifying the target domain datasets in more than 56% of the cases.</p>

Genetic Programming for Automatically Synthesising Robust Image Descriptors with A Small Number of Instances

<p>Image classification is a core task in many applications of computer vision, including object detection and recognition. It aims at analysing the visual content and automatically categorising a set of images into different groups. Performing image classification can largely be affected by the features used to perform this task. Extracting features from images is a challenging task due to the large search space size and practical requirements such as domain knowledge and human intervention. Human intervention is usually needed to identify a good set of keypoints (regions of interest), design a set of features to be extracted from those keypoints such as lines and corners, and develop a way to extract those features. Automating these tasks has great potential to dramatically decrease the time and cost, and may potentially improve the performance of the classification task. There are two well-recognised approaches in the literature to automate the processes of identifying keypoints and extracting image features. Designing a set of domain-independent features is the first approach, where the focus is on dividing the image into a number of predefined regions and extracting features from those regions. The second approach is synthesising a function or a set of functions to form an image descriptor that aims at automatically detecting a set of keypoints such as lines and corners, and performing feature extraction. Although employing image descriptors is more effective and very popular in the literature, designing those descriptors is a difficult task that in most cases requires domain-expert intervention. The overall goal of this thesis is to develop a new domain independent Genetic Programming (GP) approach to image classification by utilising GP to evolve programs that are capable of automatically detecting diverse and informative keypoints, designing a set of features, and performing feature extraction using only a small number of training instances to facilitate image classification, and are robust to different image changes such as illumination and rotation. This thesis focuses on incorporating a variety of simple arithmetic operators and first-order statistics (mid-level features) into the evolutionary process and on representation of GP to evolve programs that are robust to image changes for image classification. This thesis proposes methods for domain-independent binary classification in images using GP to automatically identify regions within an image that have the potential to improve classification while considering the limitation of having a small training set. Experimental results show that in over 67% of cases the new methods significantly outperform the use of existing hand-crafted features and features automatically detected by other methods. This thesis proposes the first GP approach for automatically evolving an illumination-invariant dense image descriptor that detects automatically designed keypoints, and performs feature extraction using only a few instances of each class. The experimental results show improvement of 86% on average compared to two GP-based methods, and can significantly outperform domain-expert hand-crafted descriptors in more than 89% of the cases. This thesis also considers rotation variation of images and proposes a method for automatically evolving rotation-invariant image descriptors through integrating a set of first-order statistics as terminals. Compared to hand-crafted descriptors, the experimental results reveal that the proposed method has significantly better performance in more than 83% of the cases. This thesis proposes a new GP representation that allows the system to automatically choose the length of the feature vector side-by-side with evolving an image descriptor. Automatically determining the length of the feature vector helps to reduce the number of the parameters to be set. The results show that this method has evolved descriptors with a very small feature vector which yet still significantly outperform the competitive methods in more than 91% of the cases. This thesis proposes a method for transfer learning by model in GP, where an image descriptor evolved on instances of a related problem (source domain) is applied directly to solve a problem being tackled (target domain). The results show that the new method evolves image descriptors that have better generalisability compared to hand-crafted image descriptors. Those automatically evolved descriptors show positive influence on classifying the target domain datasets in more than 56% of the cases.</p>

Automatically Producing Semantically Tagged Bilingual Terminologies

Even though many NLP resources and tools claim to be domain independent, their application to specific tasks is restricted to some specific domain, otherwise their performance degrade notably. As the accuracy of NLP resources drops heavily when applied in environments different from which they were built a tuning to the new environment is needed. This paper proposes a method for automatically compile terminologies from potentially any domain. The proposed method takes as reference the set of domains defined by Magnini, the Multilingual Central Repository (a resource based on WordNet 3.0) together with DBpedia, an open knowledge source that had proven to be reliable for restricted domains. Using the method described in this article, we have produced a big set of reliable terminologies for 164 domains and 2 languages totalling 635,527 terms. The proposed method has been applied to English and Spanish languages but it is potentially applicable to any language that has its own a DBpedia evolved enough. The obtained results have been intensively evaluated in several ways.