Search

Cyberbullying detection is a rising research topic due to its paramount impact on social media users, especially youngsters and adolescents. While there has been an enormous amount of progress in utilising efficient machine learning and NLP techniques for tackling this task, recent methods have not fully addressed contextualizing the textual content to the highest possible extent. The textual content of social media posts and comments is normally long, noisy and mixed with lots of irrelevant tokens and characters, and therefore utilizing an attention-based approach that can focus on more relevant parts of the text can be quite pertinent. Moreover, social media information is normally multi-modal in nature and may contain various metadata and contextual information that can contribute to enhancing the Cyberbullying prediction system. In this research, we propose a novel machine learning method that, (i) fine tunes a variant of BERT, a deep attention-based language model, which is capable of detecting patterns in long and noisy bodies of text; (ii)~extracts contextual information from multiple sources including metadata information, images and even external knowledge sources and uses these features to complement the learner model; and (iii) efficiently combines textual and contextual features using boosting and a wide-and-deep architecture. We compare our proposed method with state-of-the-art methods and highlight how our approach significantly outperforming the quality of results compared to those methods in most cases.

Intelligent Transportation Systems (ITS), especially Autonomous Vehicles (AVs), are vulnerable to security and safety issues that threaten the lives of the people. Unlike manual vehicles, the security of communications and computing components of AVs can be compromised using advanced hacking techniques, thus barring AVs from the effective use in our routine lives. Once manual vehicles are connected to the Internet, called the Internet of Vehicles (IoVs), it would be exploited by cyber-attacks, like denial of service, sniffing, distributed denial of service, spoofing and replay attacks. In this article, we present a deep learning-based Intrusion Detection System (IDS) for ITS, in particular, to discover suspicious network activity of In-Vehicles Networks (IVN), vehicles to vehicles (V2V) communications and vehicles to infrastructure (V2I) networks. A Deep Learning architecture-based Long-Short Term Memory (LSTM) autoencoder algorithm is designed to recognize intrusive events from the central network gateways of AVs. The proposed IDS is evaluated using two benchmark datasets, i.e., the car hacking dataset for in-vehicle communications and the UNSW-NB15 dataset for external network communications. The experimental results demonstrated that our proposed system achieved over a 99% accuracy for detecting all types of attacks on the car hacking dataset and a 98% accuracy on the UNSW-NB15 dataset, outperforming other eight intrusion detection techniques.

Knowledge of the underlying anatomy of the left atrium can promote improved diagnostic protocols and clinical interventions. Hence, an automatic segmentation of the left atrium on magnetic resonance imaging (MRI) can support diagnosis, treatment and surgery planning of heart. However, due to the small size of left atrium with respect to the whole MRI volume, accurate segmentation of left atrium is challenging. Most of the existing deep learning approaches are based on cropping or cascading networks. In this work, we present a novel deep learning architecture for the segmentation of left atrium from MRI volume which incorporates the residual learning based encoder-decoder network. We introduce a loss function and parameter adjustments to deal with the issue of class imbalance and unavailability of large medical imaging dataset. To facilitate the high quality segmentation, we present a three-dimensional multi-scale residual learning based architecture that maintains coarse and fine level features throughout the network. Experimental results have shown a considerable improvement in segmentation performance by surpassing the current benchmarks (especially the winner of Left Atrial Segmentation Challenge-2018) with fewer parameters compared to the state-of-the-art approaches, thus potentially supporting cardiac diagnosis and surgery without adding any extensive pre-processing of input volumes or any post-processing on the base network’s output.

Corrosion is known as the gradual destruction of materials, leading to structural integrity loss and deteriorates the surface function. Regarding sewage pipelines, corrosion is vital due to its substantial financial, health, and safety costs for society, and it is considered as one of the biggest problems facing water and wastewater infrastructure. Also, it is the primary cause of chemical property alteration, efficiency loss, life span reduction, etc. To overcome the resulting problems, various researches have been performed to understand not only the effective parameters leading to corrosion in sewer pipes but also monitoring the infrastructure conditions. Studies have depicted that developments in sensing systems to detect effective parameters in pipe corrosion such as temperature, H2S, and pH, have significantly reduced damage to the industrial equipment of sewage pipelines caused by corrosion. This paper presents a critical review of the effective factors resulting in sewer pipeline corrosion and discusses advanced sensing systems utilized for relevant monitoring. Also, microbiologically induced corrosion and effective factors are individually discussed. Moreover, various data analysis techniques adopted to evaluate outputs of the sensors for corrosion prediction have been explored. Finally, recommendations and future directions for improving sensing accuracy and robustness are detailed.

Rule-based systems have been used increasingly to augment learning algorithms for annotating data. Rules alleviate many of the shortcomings inherent in pure algorithmic approaches, in cases algorithms are not working well or lack from enough training data. However, in dynamic curation environments where data are constantly changing, there is a need to craft and adapt rules to keep them applicable and precise. Rule adaptation has been proven to be painstakingly difficult and error-prone, as an analyst is needed for examining the precision of rules and applying different modifications to adapt the imprecise ones. In this paper, we present an autonomic and conceptual approach to adapt data annotation rules. Our approach offloads analysts from adapting rules; it boosts rules to annotate a larger number of items using a set of high-level conceptual features, e.g. topic. We utilize a Bayesian multi-armed-bandit algorithm, an online learning algorithm that adapts rules based on the feedback collects from the curation environment over time. We propose a summarization technique, which offers a set of high-level conceptual features for annotating items by identifying the semantical relationships among them. We conduct experiments on different curation domains and compare the performance of our approach with systems relying on analysts for adapting rules. The experimental results show that our approach has a comparative performance to analysts in adapting rules.

[EN] In cloud computing, service providers rent heterogeneous servers from cloud providers, i.e., Infrastructure as a Service (IaaS), to meet requests of consumers. The heterogeneity of servers and impatience of consumers pose great challenges to service providers for profit maximization. In this article, we transform this problem into a multi-queue model where the optimal expected response time of each queue is theoretically analyzed. A multi-queue request scheduling algorithm framework is proposed to maximize the total profit of service providers, which consists of three components: request stream splitting, requests allocation, and server assignment. A request stream splitting algorithm is designed to split the arriving requests to minimize the response time in the multi-queue system. An allocation algorithm, which adopts a one-step improvement strategy, is developed to further optimize the response time of the requests. Furthermore, an algorithm is developed to determine the appropriate number of required servers of each queue. After statistically calibrating parameters and algorithm components over a comprehensive set of random instances, the proposed algorithms are compared with the state-of-the-art over both simulated and real-world instances. The results indicate that the proposed multi-queue request scheduling algorithm outperforms the other algorithms with acceptable computational time., This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFB1400800, in part by the National Natural Science Foundation of China under Grants 61872077 and 61832004, and in part by the Collaborative InnovationCenter of Wireless Communications Technology. The work of Quan Z. Sheng was supported in part by Australian Research Council Future Fellowship under Grant FT140101247 and in part by Discovery Project under Grant DP180102378. The work of Ruben Ruiz was supported in part by the Spanish Ministry of Science, Innovation, and Universities through the project OPTEP-Port Terminal Operations Optimization under Grant RTI2018-094940-B-I00 financed with FEDER funds

Influence maximization, i.e., the problem of finding a small subset of nodes in a social network which can maximize the propagation of influence, has the potential to become a vital asset to identify and predict mental health related issues such as, predicting suicide, bulling, and radicalization. For example, predictive analytics in mental health can enable analyzing and exploring the factors involved in influencing people to participate in extremist activities. To address this challenge, in this paper, we analyze the influence maximization in mental health from effectiveness, efficiency, and scalability viewpoints. We present a social data analytics pipeline to enable analysts to engage with social data to explore the potential online radicalization. According to the predictive analytics, a particle swarm optimization influence maximization algorithm is proposed to facilitate selecting potential influential nodes. A context analytics algorithm is proposed to analyze the social data and the user activity patterns to learn how influence flows in social networks. We conducted intensive experiments based on real dataset and illustrate the effectiveness and efficiency of the proposed algorithms.

Reducing instructors workload in online and large-scale learning environments could be one of the most important factors in educational systems. To address this challenge, techniques such as Artificial Intelligence has been considered in tutoring systems and automatic essay scoring tasks. In this paper, we construct a novel model to enable learning distributed representations of assessments namely Assessment2Vec and mark assessments automatically with Supervised Contrastive Learning loss which will effectively reduce instructors’ workload in marking large number of assessments. The experimental results based on the real-world datasets show the effectiveness of the proposed approach.

We present a vision for the next generation of process technology based on cognitive augmentation. Starting from current process technology, we show how by augmenting layers of cognitive intelligence to combine advances in machine-automation, crowdsourcing and more importantly adaptation and reasoning, we can advance support for emerging requirements of highly changing environments. We believe the challenges lie in the synergy between human and machine, in understanding how to orchestrate and combine their contributions. This vision paper sets forth a roadmap for future research by introducing a framework for cognitive augmentation, identifying the relevant research and technologies, and discussing its application amidst real-world use cases.

The data economy is inevitably rising while data is becoming the ‘new fuel’ driving the world economy as discussed in many studies from a number of viewpoints including economics, technology development, digitisation, and data analytic technologies. Although the significance of data trading is recognised as a critical part of data economy, how data should be described, protected, packaged and priced as data product for trading has not been fully explored. In this chapter we present a service-based approach for data resources to data product transformation and mechanism for data product trading.

With the advent of Industry 4.0, the Internet of Things (IoT) and Artificial Intelligence (AI), smart entities are now able to read the minds of users via extracting cognitive patterns from electroencephalogram (EEG) signals. Such brain data may include users' experiences, emotions, motivations, and other previously private mental and psychological processes. Accordingly, users' cognitive privacy may be violated and the right to cognitive privacy should protect individuals against the unconsented intrusion by third parties into the brain data as well as against the unauthorized collection of those data. This has caused a growing concern among users and industry experts that laws to protect the right to cognitive liberty, right to mental privacy, right to mental integrity, and the right to psychological continuity. In this paper, we propose an AI-enabled EEG model, namely Cognitive Privacy, that aims to protect data and classifies users and their tasks from EEG data. We present a model that protects data from disclosure using normalized correlation analysis and classifies subjects (i.e., a multi-classification problem) and their tasks (i.e., eye open and eye close as a binary classification problem) using a long-short term memory (LSTM) deep learning approach. The model has been evaluated using the EEG data set of PhysioNet BCI, and the results have revealed its high performance of classifying users and their tasks with achieving high data privacy.

The rapid and vast adoption of social media and the 21st century technologies is changing the bullying process., i.e., deliberate misuse of power in relationships through social behavior that intends to cause social and psychological harm. In this context, Cyberbullying can be defined as the process of using technology to hurt someone else by sending hurtful messages, pictures, or comments. A successful Cyberbullying detection technique requires an effective combination of big data (generated from social, open, and private data islands), features, and algorithms. While many Cyberbullying detection techniques exist for working with machine learning data and algorithms, support for thinking of new features (to be extracted from images, images' metadata, and textual information generated around images) remains poor. In this paper, we present an intelligent Cyberbullying detection pipeline to: (i) extract features (from an image, image meta-data and textual content generate); (ii) contextualize the extracted features by developing a crowdsourced feedback loop and drawing on human knowledge; and (iii) combining features using a Neural Network to identify and build potentially useful features. We adopt a typical scenario for analyzing social media content generated on Instagram and Twitter to identify Cyberbullying activities. We discuss how the proposed approach significantly improves the quality of extracted knowledge compared to classical natural language analysis techniques.

Trust can be employed for finding reliable information in Online Social Networks (OSNs). Since users in OSNs may intentionally change their behavior over time (in some cases for deceiving other users), modeling (pair-wise) trust relations in such complex environment is a challenging task. However, most of the existing trust prediction approaches assume that trust relations are fixed over time and they fail to capture the dynamic behavior of users in OSNs. In this paper, we propose a dynamic deep trust prediction model. As the impact of incidental emotions on trust has been proven in psychology studies, in this paper, we also study this impact on our trust prediction approach. First, we propose a novel deep structure that incorporates users' emotions and their textual contents in OSNs. Second, we use embeddings to represent the users and their self-descriptions provided. Finally, considering different time windows, we dynamically predict pair-wise trust relations. To evaluate our approach, we collected a large twitter dataset. The evaluation results demonstrate the effectiveness of our approach compared to the state-of-the-art approaches.

Business process monitoring techniques have been investigated in depth over the last decade to enable organizations to deliver process insight. Recently, a new stream of work in predictive business process monitoring leveraged deep learning techniques to unlock the potential business value locked in process execution event logs. These works use Recurrent Neural Networks, such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), and suffer from misinformation and accuracy as they use the last hidden state (as the context vector) for the purpose of predicting the next event. On the other hand, in operational processes, traces may be very long, which makes the above methods inappropriate for analyzing them. In addition, in predicting the next events in a running case, some of the previous events should be given a higher priority. To address these shortcomings, in this paper, we present a novel approach inspired by the notion of attention mechanism, utilized in Natural Language Processing and, particularly, in Neural Machine Translation. Our proposed approach uses all hidden states to accurately predict future behavior and the outcome of individual activities. Experimental evaluation of real-world event logs revealed that the use of attention mechanisms in the proposed approach leads to a more accurate prediction.

One of the essential tasks in Business Process Management (BPM) is Predictive Business Process Monitoring. This task aims to predict the behavior of an ongoing process based on the historical data stored in event logs. Since feed-forward neural networks do not consider the order of events for the prediction, they may not be helpful in predictive process monitoring. Recent research shows that using Recurrent Neural Networks such as LSTM and GRU may not be also helpful in predictive process monitoring. Because these networks use only the last hidden state as the context vector, and may lose some of past information, especially in long sequences. In addition, many existing approaches just use the activity name of each event as the representative of that event. In this context, they may ignore other events’ attributes in generating the feature vector. Some works have utilized these attributes simply by concatenating all of them together. While we need to use all event attributes to predict the next activity, it should be noted that not all of them are equally important. In this paper, we use two layers of attention mechanism on top of LSTM: (i) at the attribute level, to determine which attributes have more importance; and (ii) at the event level, to identify important events in predicting the next activity. Experimental evaluation of the real-world event logs showed that the use of hierarchical attention mechanisms in the proposed approach could effectively predict the next activity of an ongoing process.

Criminal Investigation (CI) plays an important role in policing, where police use various traditional techniques to investigate criminal activities such as robbery and assault. However, the techniques should hybrid with the use of artificial intelligence to analyze and determine different crime types for taking actions in real-time. In contrast with the manual process of investigating a large amount of data collected related to a criminal investigation. In this paper, we present a novel Cognitive Computing enabled Convolution Neural Networks (CC-CNN) approach for identifying crime types, such as robbery and assault, collected from unstructured textual data. We develop learning algorithms and provide a cognitive assistant to assist a police investigator in easily understanding crime types. We train and validate the CC-CNN technique on two datasets including handcrafted text-crime dataset and sentiment polarity dataset of negative and positive reviews. The experimental results show that our approach performs at a high level in terms of accuracy, error rate and time processing using both datasets.

Intelligence is the ability to learn from experience and use domain experts&rsquo, knowledge to adapt to new situations. In this context, an intelligent Recommender System should be able to learn from domain experts&rsquo, knowledge and experience, as it is vital to know the domain that the items will be recommended. Traditionally, Recommender Systems have been recognized as playlist generators for video/music services (e.g., Netflix and Spotify), e-commerce product recommenders (e.g., Amazon and eBay), or social content recommenders (e.g., Facebook and Twitter). However, Recommender Systems in modern enterprises are highly data-/knowledge-driven and may rely on users&rsquo, cognitive aspects such as personality, behavior, and attitude. In this paper, we survey and summarize previously published studies on Recommender Systems to help readers understand our method&rsquo, s contributions to the field in this context. We discuss the current limitations of the state of the art approaches in Recommender Systems and the need for our new approach: A vision and a general framework for a new type of data-driven, knowledge-driven, and cognition-driven Recommender Systems, namely, Cognitive Recommender Systems. Cognitive Recommender Systems will be the new type of intelligent Recommender Systems that understand the user&rsquo, s preferences, detect changes in user preferences over time, predict user&rsquo, s unknown favorites, and explore adaptive mechanisms to enable intelligent actions within the compound and changing environments. We present a motivating scenario in banking and argue that existing Recommender Systems: (i) do not use domain experts&rsquo, knowledge to adapt to new situations, (ii) may not be able to predict the ratings or preferences a customer would give to a product (e.g., loan, deposit, or trust service), and (iii) do not support data capture and analytics around customers&rsquo, cognitive activities and use it to provide intelligent and time-aware recommendations.

Automatic classification algorithms are an important component of expert decision support systems that are used in a number of medical applications including diagnostic radiology and disease detection. This study proposes a deep learning-based framework for medical image classification using wavelet features. Convolutional neural networks are incorporated to discover informative latent patterns and features from a set of X-ray images pertaining to human body parts. The features are then passed to a classifier for labelling the respective X-ray images. The experimental results show that the low-pass filter wavelet-based convolutional model outperforms the original convolutional network and some models for classifying X-ray images. The performance of the proposed method implies that it can be implemented effectively in practice for disease detection using radiological images.

The production of knowledge from ever increasing amount of social data is seen by many organizations as an increasingly important capability that can complement the traditional analytics sources. Examples include extracting knowledge and deriving insights from social data to improve government services, predict intelligence activities, personalize the advertisements in elections and improve national security and public health. Understanding social data can be challenging as the analysis goal can be subjective. In this context, storytelling is considered as an appropriate metaphor as it facilitates understanding and surfacing insights which is embedded within the data. In this paper, we focus on the research problem of ‘understanding the social data’ in general and more particularly the curation, summarization and presentation of large amounts of social data. The goal is to enable intelligent narrative construction based on the important features (extracted and ranked automatically) and enable storytelling at multiple levels and from different views using novel summarization techniques. We implement an interactive storytelling dashboard, namely iStory, and focus on a motivating scenario for analyzing Urban Social Issues from Twitter as it relates to the Australian Government Budget, to highlight how storytelling can significantly facilitate understanding social data.

Enabling the analysis of behavioral disorders over time in social networks, can help in suicide prevention, (school) bullying detection and extremist/criminal activity prediction. In this paper, we present a novel data analytics pipeline to enable the analysis of patterns of behavioral disorders on social networks. We present a Social Behavior Graph (sbGraph) model, to enable the analysis of factors that are driving behavior disorders over time. We use the golden standards in personality, behavior and attitude to build a domain specific Knowledge Base (KB). We use this domain knowledge to design cognitive services to automatically contextualize the raw social data and to prepare them for behavioral analytics. Then we introduce a pattern-based word embedding technique, namely personality2vec, on each feature extracted to build the sbGraph. The goal is to use mathematical embedding from a space with a dimension per feature to a continuous vector space which can be mapped to classes of behavioral disorders (such as cyber-bullying and radicalization) in the domain specific KB. We implement an interactive dashboard to enable social network analysts to analyze and understand the patterns of behavioral disorders over time. We focus on a motivating scenario in Australian government's office of the e-Safety commissioner, where the goal is to empowering all citizens to have safer, more positive experiences online.

The continuous improvement in connectivity, storage and data processing capabilities allow access to a data deluge from the big data generated on open, private, social and IoT (Internet of Things) data islands. Data Lakes introduced as a storage repository to organize this raw data in its native format until it is needed. The rationale behind a Data Lake is to store raw data and let the data analyst decide how to curate them later. Previously, we introduced the novel notion of Knowledge Lake, i.e., a contextualized Data Lake, and proposed algorithms to turn the raw data (stored in Data Lakes) into contextualized data and knowledge using extraction, enrichment, annotation, linking and summarization techniques. In this tutorial, we introduce Intelligent Knowledge Lakes to facilitate linking Artificial Intelligence (AI) and Data Analytics. This will enable AI applications to learn from contextualized data and use them to automate business processes and develop cognitive assistance for facilitating the knowledge intensive processes or generating new rules for future business analytics.

Customer reviews are now increasingly available on Online Social Networks (OSNs) for a wide range of products and services. Trust in the review's author is a crucial basis for believing in the reliability of reviews generated on such networks. In this context, the main challenge is to predict the unknown trust relationship between two users. Existing trust prediction approaches fail to incorporate textual footprint of users. To address this challenge, we present a deep learning-based graph analytics model to predict trust relations in OSNs. We leverage and extend GraphSAGE, a method for computing node representations in an inductive manner, to develop a deep classifier. We present our experiment with datasets from review websites to train classifiers that predict trust relations between pairs of users, and highlight how our approach significantly improves the quality of predicted trust relations compared to the state-of-the-art approaches.

The confluence of technological and societal advances, and more specifically, engagement with Web, social media, and smart devices has the potential to affect the mental behavior of the individuals. Examples include extremist and criminal behaviors such as radicalization and cyber-bullying, which are causing serious issues for humanity. Major barriers to the effective understanding of behavioral disorders on social networks includes the ability to understand the content and context of social documents, as well as the activity of social users. Understanding the patterns of behavioral disorders (e.g., criminal and extremist activities) on social networks, is challenging and requires techniques to contextualize the content of social documents based on the time-aware analysis of personality, behaviour and past activities of social users. In this context, semantic information extraction and enrichment from social documents has the potential to become a vital asset to explore the sign of behavioral disorders and prevent serious issues such as cyber-bullying, suicidal related behavior and radicalization. To address this challenge, in this paper, we present a novel social document analysis pipeline to enable analysts engage with social documents (e.g., a Tweet in Twitter or a post on Facebook) to explore cognitive aspects of behavioral disorders. We implement the pipeline as an extensible and scalable architecture and present the evaluation results.

Social data analytics have become a vital asset for organizations and governments. For example, over the last few years, governments started to extract knowledge and derive insights from vastly growing open data to personalize the advertisements in elections, improve government services, predict intelligence activities, as well as to improve national security and public health. A key challenge in analyzing social data is to transform the raw data generated by social actors into curated data, i.e., contextualized data and knowledge that is maintained and made available for use by end-users and applications. To address this challenge, we present the notion of knowledge lake, i.e., a contextualized Data Lake, to provide the foundation for big data analytics by automatically curating the raw social data and to prepare them for deriving insights. We present a social data curation foundry, namely DataSynapse, to enable analysts engage with social data to uncover hidden patterns and generate insight. In DataSynapse, we present a scalable algorithm to transform social items (e.g., a Tweet in Twitter) into semantic items, i.e., contextualized and curated items. This algorithm offers customizable feature extraction to harness desired features from diverse data sources. To link contextualized information items to the domain knowledge, we present a scalable technique which leverages cross document coreference resolution assisting analysts to derive targeted insights. DataSynapse is offered as an extensible and scalable microservice-based architecture that are publicly available on GitHub supporting networks such as Twitter, Facebook, GooglePlus and LinkedIn. We adopt a typical scenario for analyzing urban social issues from Twitter as it relates to the government budget, to highlight how DataSynapse significantly improves the quality of extracted knowledge compared to the classical curation pipeline (in the absence of feature extraction, enrichment and domain-linking contextualization).

With Data Science continuing to emerge as a powerful differentiator across industries, organisations are now focused on transforming their data into actionable insights. This task is challenging as in today's knowledge-, service-, and cloud-based economy, businesses accumulate massive amounts of raw data from a variety of sources. Data Lakes introduced as a storage repository to organize this raw data in its native format (supporting from relational to NoSQL DBs) until it is needed. The rationale behind a Data Lake is to store raw data and let the data analyst decide how to cook/curate them later. In this paper, we present the notion of Knowledge Lake, i.e. a contextualized Data Lake. The Knowledge Lake will provide the foundation for big data analytics by automatically curating the raw data in the Data Lake and to prepare them for deriving insights. We present CoreKG-an open source Data and Knowledge Lake service- which offers researchers and developers a single REST API to organize, curate, index and query their data and metadata in the Lake and over time. CoreKG manages multiple database technologies (from Relational to NoSQL) and offers a built-in design for data curation, security and provenance.

Perceiving data can be challenging as the analysis goal is subjective. Storytelling approaches try to address this challenge by focusing on the research problem of understanding the data in general and, more particularly in curation, summarization, and presentation of the big data, i.e., a massive number of small data islands from personal, shared, and business data. In this context, summarization can facilitate understanding and surfacing insights that are embedded within the data. In this paper, we propose a general hierarchical personalized summarization framework, called Narrative Summaries (NARS), to improve the drawbacks of traditional summarization methods in various aspects. We proposed two variants of NARS: a semi-structured summarization approach (SNARS) and a fully-structured summarization approach (FNARS). The goal is to enable intelligent narrative construction of summaries based on the important features extracted from users' engagement. To achieve this goal, we propose a hierarchical structure to prevent users from being overwhelmed with less important information at first glance and to facilitate the selection process. Afterward, instead of providing a short static summary, we present an intelligent and interactive summarization approach to enable users to navigate through the hierarchy to gain more elaborated information upon request. Our approach aims to: (i) engage users in the summarization process, to guarantee the interactive speed even for extensive text collections, and (ii) eliminate the need for reference summaries, which is one of the most challenging issues in the summarization problem. The results demonstrate that our approach fabricates a summary that helps the users understand the topic better and faster compared to the existing state-of-the-art methods.

In a large information space a user needs to iteratively investigate the data to formulate her preferences for IR systems. In recent years several visualization techniques have been proposed to help a user to better formulate her preferences. However, using these solutions a user needs to explicitly specify her preferences for IR systems in forms of keywords or phrases. In this paper we present ConceptMap, a system that takes the advantage of deep learning and a knowledge lake to provide a conceptual summary of the information space. ConceptMap allows a user to specify her preferences implicitly as a set of concepts without the need to iteratively investigate the information space. It provides a 2D Radial Map of concepts where a user can rank items relevant to her preferences through dragging and dropping. Our experiment results shows that ConceptMap can help users to better formulate their preferences when they need to retrieve varied and comprehensive list of information across a large amount of data.

Business world is getting increasingly dynamic. Information processing using knowledge-, service-, and cloud-based systems makes the use of complex, dynamic and often knowledge-intensive activities an inevitable task. Knowledge-intensive processes contain a set of coordinated tasks and activities, controlled by knowledge workers to achieve a business objective or goal. Recruitment process - i.e., the process of attracting, shortlisting, selecting and appointing suitable candidates for jobs within an organization - is an example of a knowledge-intensive process, where recruiters (i.e., knowledge workers who have the experience, understanding, information, and skills) control various tasks from advertising positions to analyzing the candidates’ Curriculum Vitae. Attracting and recruiting right talent is a key differentiator in modern organizations. In this paper, we put the first step towards automating the recruitment process. We present a framework and algorithms (namely iRecruit) to: (i) imitate the knowledge of recruiters into the domain knowledge; and (ii) extract data and knowledge from business artifacts (e.g., candidates’ CV and job advertisements) and link them to the facts in the domain Knowledge Base. We adopt a motivating scenario of recruitment challenges to find the right fit for Data Scientists role in an organization.

Rule-based systems have been used to augment machine learning based algorithms for annotating data in unstructured and dynamic environments. Rules can alleviate many of shortcomings inherent in pure algorithmic approaches. Rule adaptation is a challenging and error-prone task: in a rule-based system, there is a need for an analyst to adapt rules in order to keep them applicable and precise. In this paper, we present an approach for adapting data annotation rules in unstructured and constantly changing environments. Our approach offloads analysts from adapting rules and autonomically identifies the optimal modification for rules using a Bayesian multi-armed-bandit algorithm. We conduct experiments on different curation domains and compare the performance of our approach with systems relying on analysts. The experimental results show a comparative performance of our approach compared to analysts in adapting rules.

In the era of big data, the quality of services any organization provides largely depends on the quality of their data-driven processes. In this context, the goal of process data science, is to enable innovative forms of information processing that enable enhanced insight and decision making. For example, consider the data-driven and knowledge-intensive processes in Australian government’s office of the e-Safety commissioner, where the goal is to empowering all citizens to have safer, more positive experiences online. An example process, is to analyze the large amount of data generated every second on social networks to understand patterns of suicidal thoughts, online bullying and criminal/exterimist behaviour. Current processes leverage machine learning systems, e.g., to perform automatic mental-health-disorders detection from social networks. This approach is challenging for knowledge workers (end-user analysts) who have little knowledge of computer science to use machine learning solutions in their data-driven processes. In this paper, we present a novel platform, namely iSheets, that makes it easy for knowledge workers of all skill levels to use machine learning technology, the way people use spreadsheet. We present and develop a Machine Learning (ML) as a service framework and a spreadsheet-based ML development platform to enable knowledge workers in data-driven processes engage with ML tasks and uncover hidden insights through learning in an easy way.

Analyzing data-driven and knowledge intensive business processes is a key endeavor for today’s enterprises. Recently, the Internet of Things (IoT) has been widely adopted for the implementation and integration of data-driven business processes within and across enterprises. For example, in law enforcement agencies, various IoT devices such as CCTVs, police cars and drones are augmented with Internet-enabled computing devices to sense the real world. This in turn, has the potential to change the nature of data-driven and knowledge intensive processes, such as criminal investigation, in policing. In this paper, we present a framework and a set of techniques to assist knowledge workers (e.g., a criminal investigator) in knowledge intensive processes (e.g., criminal investigation) to benefit from IoT-enabled processes, collect large amounts of evidences and dig for the facts in an easy way. We focus on a motivating scenario in policing, where a criminal investigator will be augmented by smart devices to collect data and to identify devices around the investigation location and communicate with them to understand and analyze evidences. We present iCOP, IoT-enabled COP assistant system, to enable IoT in policing and to accelerate the investigation process.

Bioinformatics and computational biology have significantly contributed to the generation of vast and important knowledge that can lead to great improvements and advancements in biology and its related fields. Over the past three decades, a wide range of tools and methods have been developed and proposed to enhance performance, diagnosis, and throughput while maintaining feasibility and convenience for users. Here, we propose a new user-friendly comprehensive tool called VIRMOTIF to analyze DNA sequences. VIRMOTIF brings different tools together as one package so that users can perform their analysis as a whole and in one place. VIRMOTIF is able to complete different tasks, including computing the number or probability of motifs appearing in DNA sequences, visualizing data using the matplotlib and heatmap libraries, and clustering data using four different methods, namely K-means, PCA, Mean Shift, and ClusterMap. VIRMOTIF is the only tool with the ability to analyze genomic motifs based on their frequency and representation (D-ratio) in a virus genome.

Rule-based techniques are gaining importance with their ability to augment large scale data processing systems. However, there still remain key challenges amongst current rule-based techniques, including rule monitoring, adapting and evaluation. Among these challenges, monitoring the precision of rules is highly important as it enables analysts to maintain the accuracy of a rule-based system. In this paper, we propose an Adaptive Rule Monitoring System (ARMS) for monitoring the precision of rules. The approach employs a combination of machine learning and crowdsourcing techniques. ARMS identifies rules deteriorating the performance of a rule based system, using the feedback receives from the crowd. To enable analysts identifying the imprecise rules, ARMS leverage machine learning algorithms to analyze the crowd's feedback. The evaluation results show that ARMS can identify the imprecise rules more successfully compared to the default practice of the system, which rely exclusively on analysts.

The Internet of Things (IoT), the network of physical objects augmented with Internet-enabled computing devices to enable those objects sense the real world, has the potential to transform many industries. This includes harnessing real-time intelligence to improve risk-based decision making and supporting adaptive processes from core to edge. For example, modern police investigation processes are often extremely complex, data-driven and knowledge-intensive. In such processes, it is not sufficient to focus on data storage and data analysis; and the knowledge workers (e.g., investigators) will need to collect, understand and relate the big data (scattered across various systems) to process analysis: in order to communicate analysis findings, supporting evidences and to make decisions. In this paper, we present a scalable and extensible IoT-Enabled Process Data Analytics Pipeline (namely iProcess) to enable analysts ingest data from IoT devices, extract knowledge from this data and link them to process (execution) data. We introduce the notion of process Knowledge Lake and present novel techniques to summarize the linked IoT and process data to construct process narratives. This enables us to put the first step towards enabling storytelling with process data.

Process and data are equally important for business process management. Data-driven approaches in process analytics aims to value decisions that can be backed up with verifiable private and open data. Over the last few years, data-driven analysis of how knowledge workers and customers interact in social contexts, often with data obtained from social networking services such as Twitter and Facebook, have become a vital asset for organizations. For example, governments started to extract knowledge and derive insights from vastly growing open data to improve their services. A key challenge in analyzing social data is to understand the raw data generated by social actors and prepare it for analytic tasks. In this context, it is important to transform the raw data into a contextualized data and knowledge. This task, known as data curation, involves identifying relevant data sources, extracting data and knowledge, cleansing, maintaining, merging, enriching and linking data and knowledge. In this paper we present CrowdCorrect, a data curation pipeline to enable analysts cleansing and curating social data and preparing it for reliable business data analytics. The first step offers automatic feature extraction, correction and enrichment. Next, we design micro-tasks and use the knowledge of the crowd to identify and correct information items that could not be corrected in the first step. Finally, we offer a domain-model mediated method to use the knowledge of domain experts to identify and correct items that could not be corrected in previous steps. We adopt a typical scenario for analyzing Urban Social Issues from Twitter as it relates to the Government Budget, to highlight how CrowdCorrect significantly improves the quality of extracted knowledge compared to the classical curation pipeline and in the absence of knowledge of the crowd and domain experts.

The Internet of Things (IoT) changes many sectors of our lives. In the healthcare domain, IoT presents as mobile medical applications over various sensors that update healthcare professionals on patients' health information. However, IoT-based healthcare systems also face major challenges in protecting patients' privacy via an effective access control system. This paper presents an ambient home solution framework for privacy-preserving monitoring of patients' health status. We focus on two major points: 1) how to use the data collected from ambient and biometric sensors, to perform the high-level task of activity recognition, and 2) how to secure the collected healthcare data via effective access control. We achieve multi-level access control by using Public Key Infrastructure (PKI) for authentication and Attribute-Based Access Control (ABAC) for authorisation. Our access control system regulates access to healthcare data by classification over healthcare professionals and data. Our system provides guidelines to define data classes and healthcare professional groups and specifies security policies to control access to the data classes. The system is flexible and can incorporate more policy rules, professionals, and data classes.

International audience; Protecting Information Systems (IS) relies traditionally on security risk anal-ysis methods. Designed for well-perimetrised environments, these methods rely on a systematic identification of threats and vulnarabilities to identify efficient control-centered protection countermeasures. Unfortunately, this does not fit security challenges carried out by the opened and agile organiza-tions provided by the Social, Mobile, big data Analytics, Cloud and Internet of Things (SMACIT) environment. Due to their inherently collaborative and distributed organization, such multi-tenancy systems require the integration of contextual vulnerabilities, depending on the a priori unknown way of us-ing, storing and exchanging data in opened cloud environment. Moreover, as data can be associated to multiple copies, different protection requirements can be set for each of these copies, which may lead the initial data owner lose control on the data protection. This involves (1) turning the traditional control-centered security vision to a dynamic data-centered protection and even (2) considering that the way a data is used can be a potential threat that may corrupt data protection efficiency. To fit these challenges, we propose a Data-centric Usage-based Protection service (DUP). This service is based on an information system meta-model, used to identify formally data assets and store the processes using copies of these assets. To define a usage-entered protection, we extend the Usage Based Access Control model, which is mostly focused on managing CRUD operations, to more complex operation fitting the SMACIT context. These usage rules are used to generate smart contracts, storing usage consents and managing usage control for cloud ser-vices.