Search

In education quality assurance, the accuracy of test data is crucial. However, there is still a problem regarding to the possibility of incorrect data filled by test taker during paper-based test. On the contrary, this problem does not appear in computer-based test. In this study, a method was proposed in order to analyze the accuracy of answer sheet filling out in paper-based test using data mining technique. A single layer of data comprehension was added within the method instead of raw data. The results of the study were a web-based program for data pre-processing and decision tree models. There were 374 instances which were analyzed. The accuracy of answer sheet filling out attained 95.19% while the accuracy of classification varied from 99.47% to 100% depend on evaluation method chosen. This study could motivate the administrators for test improvement since it preferred computer-based test to paper-based.

With the increasing advance of computer and information technologies, numerous research papers have been published online as well as offline, and as new research fields have been continuingly created, users have a lot of trouble in finding and categorizing their interesting research papers. In order to overcome the limitations, this paper proposes a research paper classification system that can cluster research papers into the meaningful class in which papers are very likely to have similar subjects. The proposed system extracts representative keywords from the abstracts of each paper and topics by Latent Dirichlet allocation (LDA) scheme. Then, the K-means clustering algorithm is applied to classify the whole papers into research papers with similar subjects, based on the Term frequency-inverse document frequency (TF-IDF) values of each paper.

For a suspected forgery that involves the falsification of a document or its contents, the investigator will primarily analyze the document&rsquo, s paper and ink in order to establish the authenticity of the subject under investigation. As a non-destructive and contactless technique, Hyperspectral Imaging (HSI) is gaining popularity in the field of forensic document analysis. HSI returns more information compared to conventional three channel imaging systems due to the vast number of narrowband images recorded across the electromagnetic spectrum. As a result, HSI can provide better classification results. In this publication, we present results of an approach known as the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm, which we have applied to HSI paper data analysis. Even though t-SNE has been widely accepted as a method for dimensionality reduction and visualization of high dimensional data, its usefulness has not yet been evaluated for the classification of paper data. In this research, we present a hyperspectral dataset of paper samples, and evaluate the clustering quality of the proposed method both visually and quantitatively. The t-SNE algorithm shows exceptional discrimination power when compared to traditional PCA with k-means clustering, in both visual and quantitative evaluations.

Coinduction occurs in two guises in Horn clause logic: in proofs of self-referencing properties and relations, and in proofs involving construction of (possibly irregular) infinite data. Both instances of coinductive reasoning appeared in the literature before, but a systematic analysis of these two kinds of proofs and of their relation was lacking. We propose a general proof-theoretic framework for handling both kinds of coinduction arising in Horn clause logic. To this aim, we propose a coinductive extension of Miller et al's framework of uniform proofs and prove its soundness relative to coinductive models of Horn clause logic., Comment: In Proceedings HCVS 2018, arXiv:1809.04554

In this article, we put forward the substantial challenges in cyber resilience in the domain of autonomous systems and outline foundational solutions to address these challenges. These solutions fall into two broad themes: resilience-by-design and resilience-by-reaction . We use several application drivers from autonomous systems to motivate the challenges in cyber resilience and to demonstrate the benefit of the solutions. We focus on some autonomous systems in the near horizon (autonomous ground and aerial vehicles) and also a little more distant (autonomous rescue and relief). For resilience-by-design , we focus on design methods in software that are needed for our cyber systems to be resilient. In contrast, for resilience-by-reaction , we discuss how to make systems resilient by responding, reconfiguring, or recovering at runtime when failures happen. We also discuss the notion of adaptive execution to improve resilience, execution transparently and adaptively among available execution platforms (mobile/embedded, edge, and cloud). For each of the two themes, we survey the current state, and the desired state and ways to get there. We conclude the paper by looking at the research challenges we will have to solve in the short and the mid-term to make the vision of resilient autonomous systems a reality. This article came out of discussions that started at the NSF-sponsored Grand Challenges in Resilience Workshop held at Purdue in 2019 with the co-authors contributing to going into the depth of the issues and then this article.

Purpose To develop a structured, rich media digital paper authoring tool with an object-based model that enables interactive, playable, and convertible functions. Design/methodology/approach We propose Dpaper to organize the content (text, data, rich media, etc.) of dissertation papers as XML and HTML5 files by means of digital objects and digital templates. Findings Dpaper provides a structured-paper editorial platform for the authors of PhDs to organize research materials and to generate various digital paper objects that are playable and reusable. The PhD papers are represented as Web pages and structured XML files, which are marked with semantic tags. Research limitations The proposed tool only provides access to a limited number of digital objects. For instance, the tool cannot create equations and graphs, and typesetting is not yet flexible compared to MS Word. Practical implications The Dpaper tool is designed to break through the patterns of unstructured content organization of traditional papers, and makes the paper accessible for not only reading but for exploitation as data, where the document can be extractable and reusable. As a result, Dpaper can make the digital publishing of dissertation texts more flexible and efficient, and their data more assessable. Originality/value The Dpaper tool solves the challenge of making a paper structured and object-based in the stage of authoring, and has practical values for semantic publishing.

© 2018, the Authors. Fast-growing scientific papers bring the problem of rapidly and accurately finding a list of reference papers for a given manuscript. Reference paper recommendation is an essential technology to overcome this obstacle. In this paper, we study the problem of personalized query-focused astronomy reference paper recommendation and propose a heterogeneous information network embedding based recommendation approach. In particular, we deem query researchers, query text, papers and authors of the papers as vertices and construct a heterogeneous information network based on these vertices. Then we propose a heterogeneous information network embedding (HINE) approach, which simultaneously captures intra-relationships among homogeneous vertices, inter-relationships among heterogeneous vertices and correlations between vertices and text contents, to model different types of vertices as vector formats in a unified vector space. The relevance of the query, the papers and the authors of the papers are then measured by the distributed representations. Finally, the papers which have high relevance scores are presented to the researcher as recommendation list. The effectiveness of the proposed HINE based recommendation approach is demonstrated by the recommendation evaluation conducted on the IOP astronomy journal database.

This paper proposes the use of notebooks for the design documentation and tool interaction in the rigorous design of embedded systems. Conventionally, a notebook is a sequence of cells alternating between (textual) code and prose to form a document that is meant to be read from top to bottom, in the spirit of literate programming. We extend the use of notebooks to embedded systems specified by pCharts. The charts are visually edited in cells inline. Other cells can contain statements that generate code and analyze the charts qualitatively and quantitatively; in addition, notebook cells can contain other instructions to build the product from the generated code. This allows a notebook to be replayed to re-analyze the design and re-build the product, like a script, but also allows the notebook to be used for presentations, as for this paper, and for the inspection of the design. The interaction with the notebook is done through a web browser that connects to a local or remote server, thus allowing a computationally intensive analysis to run remotely if needed. The pState notebooks are implemented as an extension to Jupyter. The underlying software architecture is described and the issue of proper placement of transition labels in charts embedded in notebooks is discussed., Comment: In Proceedings F-IDE 2018, arXiv:1811.09014

In a paper manufacturing system, it is substantially important to detect machine failure before it occurs and take necessary maintenance actions to prevent an unexpected breakdown of the system. Multiple sensor data collected from a machine provides useful information on the system's health condition. However, it is hard to predict the system condition ahead of time due to the lack of clear ominous signs for future failures, a rare occurrence of failure events, and a wide range of sensor signals which might be correlated with each other. We present two versions of feature extraction techniques based on the nearest neighbor combined with machine learning algorithms to detect a failure of the paper manufacturing machinery earlier than its occurrence from the multistream system monitoring data. First, for each sensor stream, the time series data is transformed into the binary form by extracting the class label of the nearest neighbor. We feed these transformed features into the decision tree classifier for the failure classification. Second, expanding the idea, the relative distance to the local nearest neighbor has been measured, results in the real‐valued feature, and the support vector machine is used as a classifier. Our proposed algorithms are applied to the dataset provided by Institute of Industrial and Systems Engineers 2019 data competition, and the results show better performance than other state‐of‐the‐art machine learning techniques.

In recent years, a large body of literature has accumulated around the topic of research paper recommender systems. However, since most studies have focused on the variable of accuracy, they have overlooked the serendipity of recommendations, which is an important determinant of user satisfaction. Serendipity is concerned with the relevance and unexpectedness of recommendations, and so serendipitous items are considered those which positively surprise users. The purpose of this article was to examine two key research questions: firstly, whether a user’s Tweets can assist in generating more serendipitous recommendations; and secondly, whether the diversification of a list of recommended items further improves serendipity. To investigate these issues, an online experiment was conducted in the domain of computer science with 22 subjects. As an evaluation metric, we use the serendipity score (SRDP), in which the unexpectedness of recommendations is inferred by using a primitive recommendation strategy. The results indicate that a user’s Tweets do not improve serendipity, but they can reflect recent research interests and are typically heterogeneous. Contrastingly, diversification was found to lead to a greater number of serendipitous research paper recommendations., The records of the review process are available at: https://peerj.com/articles/cs-273/reviews/, reviews.pdf includes the reviewers' contributions as follows, * Anonymous Reviewer (2020) Peer Review #1 of "Influence of tweets and diversification on serendipitous research paper recommender systems (v0.1)". PeerJ Computer Science https://doi.org/10.7287/peerj-cs.273v0.1/reviews/1, * Achakulvisut T (2020) Peer Review #2 of "Influence of tweets and diversification on serendipitous research paper recommender systems (v0.1)". PeerJ Computer Science https://doi.org/10.7287/peerj-cs.273v0.1/reviews/2, * Anonymous Reviewer (2020) Peer Review #1 of "Influence of tweets and diversification on serendipitous research paper recommender systems (v0.2)". PeerJ Computer Science https://doi.org/10.7287/peerj-cs.273v0.2/reviews/1

Computer vision has been studied from many persective. It expands from raw data recording into techniques and ideas combining digital image processing, pattern recognition, machine learning and computer graphics. The wide usage has attracted many scholars to integrate with many disciplines and fields. This paper provide a survey of the recent technologies and theoretical concept explaining the development of computer vision especially related to image processing using different areas of their field application. Computer vision helps scholars to analyze images and video to obtain necessary information, understand information on events or descriptions, and scenic pattern. It used method of multi-range application domain with massive data analysis. This paper provides contribution of recent development on reviews related to computer vision, image processing, and their related studies. We categorized the computer vision mainstream into four group e.g., image processing, object recognition, and machine learning. We also provide brief explanation on the up-to-date information about the techniques and their performance.

Cloud computing delivers computing resources like software and hardware as a service to the users through a network. Due to the scale of the modern datacentres and their dynamic resources provisioning nature, we need efficient scheduling techniques to manage these resources. The main objective of scheduling is to assign tasks to adequate resources in order to achieve one or more optimization criteria. Scheduling is a challenging issue in the cloud environment, therefore many researchers have attempted to explore an optimal solution for task scheduling in the cloud environment. They have shown that traditional scheduling is not efficient in solving this problem and produce an optimal solution with polynomial time in the cloud environment. However, they introduced sub-optimal solutions within a short period of time. Meta-heuristic techniques have provided near-optimal or optimal solutions within an acceptable time for such problems. In this work, we have introduced the major concepts of resource scheduling and provided a comparative analysis of many task scheduling techniques based on different optimization criteria.

In the digital era like today the growth of data in the database is very rapid, all things related to technology have a large contribution to data growth as well as social media, financial technology and scientific data. Therefore, topics such as big data and data mining are topics that are often discussed. Data mining is a method of extracting information through from big data to produce an information pattern or data anomaly

This Special Issue of Algorithms is of a different nature than other Special Issue in the journal, which are usually dedicated to a particular subjects in the area of algorithms [...]

The current paper presents a soft-sensor method based on belief-rule-base (BRB) system for solving the problem of tipping paper permeability measurement in the tobacco industry. Firstly, BRB is utilized to establish a model between the feature variables in the tipping paper image and the corresponding paper permeability obtained by the traditional measuring device. Unlike the traditional case of BRB, this paper adds the output attribute as the optimization parameters. In this way, the feasible solution space can be enlarged to obtain an effective BRB model. Second, in order to find the reasonable parameters of BRB in a complex nonconvex solution space, an enhanced differential evolutionary (DE) algorithm is developed to train BRB, which not only embeds a simplex method to stress the balance between the global and local search but also designs a perturbation operation and an adaptively selected mutation strategy to maintain the diversity of search direction. The test results and comparisons based on the data collected from a cigarette factory in China show that the presented method is effective and robust.

With the development of network technology, the design for the automatic generative system of examination papers that is based on web has become a trend. In order to reduce the burden on teachers and avoid duplication of work, we design the system to automatically generate test papers. It is based on a constantly updated examination question bank system, according to the teachers' demands, which can automatically generate the test paper with a certain degree of difficulty, the number and value. The client configuration is simple and it can be free from geographic constraint. Users only need to go through their own identity authentication to enter the automatically generated system of test papers, and to manage and maintain examination questions, exam and user information and so on. The exam contents can be constantly enriched and improved and the data sharing among teachers can be easily performed. It will have important practical significance to improve work efficiency.

Image classification becomes a very challenging task when it involves classes that have shared characteristics and few data are available for training the classifier. Considering this problem, in this work we adopt a case study based on images from geoscience papers and investigate how different features can be combined in order to improve image classification results. In our investigation, we present a tool for evaluating class separability based on the position of the samples in a two-dimensional map according to different features. Moreover, we investigate the usefulness of classifiers’ membership probabilities for our scenario, validating if they can be used as reliable measures of the confidence in the predicted labels. Our experimental results show that it is possible to take advantage of deep learning models’ ability to learn discriminating features from data and combine them with hand-crafted features to improve classification. With this feature combination, we trained a Support Vector Machine (SVM) classifier whose results are better than the ones achieved using only deep learning.

Radio frequency Identification (RFID) is an automatic identification technology that enables tracking of people and objects. Recently, RFID technology has been deployed in hospital environment for patient and equipment tracking, surgical equipment monitoring, medication monitoring and improving health record access in emergency cases. The main advantages RFID technology are to provide resource optimization, quality customers’ care, enhanced accuracy, efficient and effective business processes and healthcare processes. The pharmacy department undergoes challenges such as complex manual work of record keeping and inventory management. The RFID technology can be deployed in pharmacy hospital unit to automate pharmacy process. In this work we present a review on current pharmacy management practices in the case study of public hospital in Tanzania, review on different research work to address the pharmacy challenges and finally proposed a system to overcome the limitation identified in the current systems.

RedPRL is an experimental proof assistant based on Cartesian cubical computational type theory, a new type theory for higher-dimensional constructions inspired by homotopy type theory. In the style of Nuprl, RedPRL users employ tactics to establish behavioral properties of cubical functional programs embodying the constructive content of proofs. Notably, RedPRL implements a two-level type theory, allowing an extensional, proof-irrelevant notion of exact equality to coexist with a higher-dimensional proof-relevant notion of paths., Comment: In Proceedings LFMTP 2018, arXiv:1807.01352

This guest editorial outlines the way papers from the SAICSIT 2016 conference were selected, extended and reviewed and summarizes the key content of each paper.

Recently, wireless sensor networks have employed the concept of mobile agent to reduce energy consumption and obtain effective data gathering. Typically, in data gathering based on mobile agent, it is an important and essential step to find out the optimal itinerary planning for the mobile agent. However, single-agent itinerary planning suffers from two primary disadvantages: task delay and large size of mobile agent as the scale of the network is expanded. Thus, using multi-agent itinerary planning overcomes the drawbacks of single-agent itinerary planning. Despite the advantages of multi-agent itinerary planning, finding the optimal number of distributed mobile agents, source nodes grouping, and optimal itinerary of each mobile agent for simultaneous data gathering are still regarded as critical issues in wireless sensor network. Therefore, in this article, the existing algorithms that have been identified in the literature to address the above issues are reviewed. The review shows that most of the algorithms used one parameter to find the optimal number of mobile agents in multi-agent itinerary planning without utilizing other parameters. More importantly, the review showed that theses algorithms did not take into account the security of the data gathered by the mobile agent. Accordingly, we indicated the limitations of each proposed algorithm and new directions are provided for future research.

Issue 2 of volume 18 of the CLEI Electronic Journal presents a selection of the best papers from the XL Latin American Computing Conference (CLEI 2014).

This special issue of the CLEI Electronic Journal consists of extended and revised versions of a selection of the best papers presented at the XXXIX Latin American Computing Conference (CLEI 2013), which took place in October 2013 in Naiguatá, Venezuela. The editors for this special issue were the chairs of the symposia from CLEI 2013 where these papers have been selected, plus the general chair of the program committee, which have participated in the selection and revision process

Smartphones have become indispensable computational tools. However, some tasks can be difficult to perform on a smartphone because these devices have small displays. Here, we explore methods for augmenting the display of a smartphone, or other PDA, using interactive paper. Specifically, we present a prototype interface that enables a user to interactively interrogate technical drawings using an Anoto-based smartpen and a PDA. Our software system, called PaperCAD, enables users to query geometric information from CAD drawings printed on Anoto dot-patterned paper. For example, the user can measure a distance by drawing a dimension arrow. The system provides output to the user via a smartpen’s audio speaker and the dynamic video display of a PDA. The user can select either verbose or concise audio feedback, and the PDA displays a video image of the portion of the drawing near the pen tip. The project entails advances in the interpretation of pen input, such as a method that uses contextual information to interpret ambiguous dimensions and a technique that uses a hidden Markov model to correct interpretation errors in handwritten equations. Results of a user study suggest that our user interface design and interpretation techniques are effective and that users are highly satisfied with the system.

Space Robots

PROLOG project aims to provide a complementary ICT tool for the assessment of cognitive skills of mentally disabled working people. The project is developed by Centre d’Accessibilitat i Intel·ligència Ambiental de Catalunya (CAiAC), Indra, Fundación Adecco and PRODIS, and is part of Cátedra INDRA de Tecnologías Accesibles. The project provides a platform to evaluate, in a quick and personalized way, the attentional performance of users through specific tasks grounded in existing psychological tests. Interaction with the tests is done by Kinect technology. Also a platform execution logs users in different tests over time in order to detect possible cognitive impairments. The platform records the worker’s performance on various tasks and presents the evolution over time in order to detect possible cognitive impairment. This paper details the first phase of the project corresponding to the design of the tests.

We propose a Drawing-Frequency based Layered (DFL) Canvas approach to reduce a synchronization delay in collaborative web applications. The synchronization delay consists of a network delay and a drawing delay. The network delay is well-argued topic by various researches. We focus on the drawing delay, which is a primary bottleneck of Canvas objects synchronizations. We introduce the DFL Canvas approach in order to solve the drawing problem. The DFL Canvas divides Canvas objects by drawingfrequency. We implemented a collaborative paper editing support system with the DFL Canvas. Users can edit the same document and share Canvas objects on papers in real-time on web browsers. We present an evaluation result that indicates the approach is suited for collaborative paper editing support systems.

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

Self-adaptation and self-organization (SASO) have been introduced to the management of technical systems as an attempt to improve robustness and administrability. In particular, both mechanisms adapt the system&rsquo, s structure and behavior in response to dynamics of the environment and internal or external disturbances. By now, adaptivity has been considered to be fully desirable. This position paper argues that too much adaptation conflicts with goals such as stability and user acceptance. Consequently, a kind of situation-dependent degree of adaptation is desired, which defines the amount and severity of tolerated adaptations in certain situations. As a first step into this direction, this position paper presents a quantification approach for measuring the current adaptation behavior based on generative, probabilistic models. The behavior of this method is analyzed in terms of three application scenarios: urban traffic control, the swidden farming model, and data communication protocols. Furthermore, we define a research roadmap in terms of six challenges for an overall measurement framework for SASO systems.

Digital technology in Indonesia, especially in Manado, begin to grow very rapidly followed by the availability of adequate technology market, better financial economy, and high enthusiasm from the local people, mostly academic educators. Supported by the existence of network based technology, it is mostly expected that the process of transferring information and learning in classroom will be easier and no longer become great problem in the future. People will acceptdigital technology not as a threat, but cultivate and utilize them for the improvement of human civilization, while keep maintaining respect to traditional learning and manual opinions and analysis because after all those concepts are merely the best. This paper based on author experience, observations, and reviews, offers solutions to utilize digital technology for developing aneffective learning process. The research methods are literature study, analysis taken from personal experience, system design, and future implementation. The results of this research givesperspective to design a learning system in a proper way, using digital technology individually or integrated, which will also support research activities and improve good digital technology products designed and produced by people of Indonesia and other Nations.

Designing games for learning in the workplace is challenging in many ways. Within the process industry, the aluminium production cells are harsh environments that are difficult to instrument and pose domain related challenges, which make effective training difficult to achieve. In particular, cognitive challenges arise due to the slow nature of the physical process that disconnects the operators' actions and causality. The complex chemical process demands a high level of understanding of the parameters and their complex interdependencies. Additional challenges are related to representing an appropriate level of detail and precision of the workplace, including integration with existing tools. This paper describes the digital simulation game designed and developed for the operators in aluminium plants to master the cognitive skills required for Heat Balance in the aluminium production cells. A co-design process was adopted from the initial inception of the idea, development and evaluation. The paper will discuss and present the co-creation artefacts used, namely a paper prototype, hybrid prototype of the game along with the output from iterative development cycles. This work is conducted within the research and innovation project, Accelerated Learning for Technology Transfer, with the Norwegian company Hydro.

Collaborative Mixed-Reality (CMR) applications are gaining interest in a wide range of areas including games, social interaction, design and health-care. To date, the vast majority of published work has focused on display technology advancements, software, collaboration architectures and applications. However, the potential security concerns that affect collaborative platforms have received limited research attention. In this position paper, we investigate the challenges posed by cyber-security threats to CMR systems. We focus on how typical network architectures facilitating CMR and how their vulnerabilities can be exploited by attackers, and discuss the degree of potential social, monetary impacts, psychological and other harms that may result from such exploits. The main purpose of this paper is to provoke a discussion on CMR security concerns. We highlight insights from a cyber-security threat modelling perspective and also propose potential directions for research and development toward better mitigation strategies. We present a simple, systematic approach to understanding a CMR attack surface through an abstraction-based reasoning framework to identify potential attack vectors. Using this framework, security analysts, engineers, designers and users alike (stakeholders) can identify potential Indicators of Exposures (IoE) and Indicators of Compromise (IoC). Our framework allows stakeholders to reduce their CMR attack surface as well understand how Intrusion Detection System (IDS) approaches can be adopted for CMR systems. To demonstrate the validity to our framework, we illustrate several CMR attack surfaces through a set of use-cases. Finally, we also present a discussion on future directions this line of research should take.

Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task. When the acquired images are highly imbalanced and not adequate, the desired task may not be achievable. Unfortunately, the occurrence of imbalance problems in acquired image datasets in certain complex real-world problems such as anomaly detection, emotion recognition, medical image analysis, fraud detection, metallic surface defect detection, disaster prediction, etc., are inevitable. The performance of computer vision algorithms can significantly deteriorate when the training dataset is imbalanced. In recent years, Generative Adversarial Neural Networks (GANs) have gained immense attention by researchers across a variety of application domains due to their capability to model complex real-world image data. It is particularly important that GANs can not only be used to generate synthetic images, but also its fascinating adversarial learning idea showed good potential in restoring balance in imbalanced datasets.In this paper, we examine the most recent developments of GANs based techniques for addressing imbalance problems in image data. The real-world challenges and implementations of synthetic image generation based on GANs are extensively covered in this survey. Our survey first introduces various imbalance problems in computer vision tasks and its existing solutions, and then examines key concepts such as deep generative image models and GANs. After that, we propose a taxonomy to summarize GANs based techniques for addressing imbalance problems in computer vision tasks into three major categories: 1. Image level imbalances in classification, 2. object level imbalances in object detection and 3. pixel level imbalances in segmentation tasks. We elaborate the imbalance problems of each group, and provide GANs based solutions in each group. Readers will understand how GANs based techniques can handle the problem of imbalances and boost performance of the computer vision algorithms.

Annually, lots of research papers are published in scientific journals around the world. The knowledge of the status of research is a prerequisite for research planning and policy making. This type of knowledge could be gained through a scientometrics study on the published literature that analyzes research products in a scientific field. Always healthcare was a permanent concern of researchers and also rapidly expanding field of Big Data analytics has started to play a pivotal role in the evolution of healthcare practices and research. It leads attracting attention from academia, industry and even governments around the world to “Big data in Healthcare”. Therefore, this paper has done a meta-analysis on published researches methodology in this field in the period of 2008–2018. Statistical finding shows the “Meta-analysis and evidence” is the most used methodology in published papers. We applied data mining techniques for predicting using methodologies in the various databases to achieving knowledge discovery in the field. Naïve Bayes classifier in RapidMiner has been applied and results show eight main categories for words used in papers while “Developing methods to evaluate of care” averagely is the most intended using methodology for publishing papers and “Agent-based modeling” in nature is most using methodology and could be better predicted.

The value of graph-based big data can be unlocked by exploring the topology and metrics of the networks they represent, and the computational approaches to this exploration take on many forms. The use-case of performing global computations over a graph, it is first ingested into a graph processing system from one of many digital representations. Extracting information from graphs involves processing all their elements globally, and can be done with single-machine systems (with varying approaches to hardware usage), distributed systems (either homogeneous or heterogeneous groups of machines) and systems dedicated to high-performance computing (HPC). We provide an overview of different aspects of the graph processing landscape and describe classes of systems based on a set of dimensions we detail. The dimensions we detail encompass paradigms to express graph processing, different types of systems to use, coordination and communication models in distributed graph processing, partitioning techniques and different definitions related to the potential for a graph to be updated. This survey is aimed at both the experienced software engineer or researcher as well as the newcomer looking for an understanding of the landscape of solutions (and their limitations) for graph processing., Comment: 42 pages, 5 figures, 2 tables

This survey explores how Deep Learning has battled the COVID-19 pandemic and provides directions for future research on COVID-19. We cover Deep Learning applications in Natural Language Processing, Computer Vision, Life Sciences, and Epidemiology. We describe how each of these applications vary with the availability of big data and how learning tasks are constructed. We begin by evaluating the current state of Deep Learning and conclude with key limitations of Deep Learning for COVID-19 applications. These limitations include Interpretability, Generalization Metrics, Learning from Limited Labeled Data, and Data Privacy. Natural Language Processing applications include mining COVID-19 research for Information Retrieval and Question Answering, as well as Misinformation Detection, and Public Sentiment Analysis. Computer Vision applications cover Medical Image Analysis, Ambient Intelligence, and Vision-based Robotics. Within Life Sciences, our survey looks at how Deep Learning can be applied to Precision Diagnostics, Protein Structure Prediction, and Drug Repurposing. Deep Learning has additionally been utilized in Spread Forecasting for Epidemiology. Our literature review has found many examples of Deep Learning systems to fight COVID-19. We hope that this survey will help accelerate the use of Deep Learning for COVID-19 research.

Gradient Boosted Decision Trees (GBDT’s) are a powerful tool for classification and regression tasks in Big Data. Researchers should be familiar with the strengths and weaknesses of current implementations of GBDT’s in order to use them effectively and make successful contributions. CatBoost is a member of the family of GBDT machine learning ensemble techniques. Since its debut in late 2018, researchers have successfully used CatBoost for machine learning studies involving Big Data. We take this opportunity to review recent research on CatBoost as it relates to Big Data, and learn best practices from studies that cast CatBoost in a positive light, as well as studies where CatBoost does not outshine other techniques, since we can learn lessons from both types of scenarios. Furthermore, as a Decision Tree based algorithm, CatBoost is well-suited to machine learning tasks involving categorical, heterogeneous data. Recent work across multiple disciplines illustrates CatBoost’s effectiveness and shortcomings in classification and regression tasks. Another important issue we expose in literature on CatBoost is its sensitivity to hyper-parameters and the importance of hyper-parameter tuning. One contribution we make is to take an interdisciplinary approach to cover studies related to CatBoost in a single work. This provides researchers an in-depth understanding to help clarify proper application of CatBoost in solving problems. To the best of our knowledge, this is the first survey that studies all works related to CatBoost in a single publication.

The collective of autonomous cars is expected to generate almost optimal traffic. In this position paper we discuss the multi-agent models and the verification results of the collective behaviour of autonomous cars. We argue that non-cooperative autonomous adaptation cannot guarantee optimal behaviour. The conjecture is that intention aware adaptation with a constraint on simultaneous decision making has the potential to avoid unwanted behaviour. The online routing game model is expected to be the basis to formally prove this conjecture., Comment: In Proceedings FVAV 2017, arXiv:1709.02126

The CBS framework supports component-based specification of programming languages. It aims to significantly reduce the effort of formal language specification, and thereby encourage language developers to exploit formal semantics more widely. CBS provides an extensive library of reusable language specification components, facilitating co-evolution of languages and their specifications. After introducing CBS and its formal definition, this short paper reports work in progress on generating an IDE for CBS from the definition. It also considers the possibility of supporting component-based language specification in other formal language workbenches., Comment: In Proceedings F-IDE 2019, arXiv:1912.09611

In copper mining, there are two main separation processes: leaching for oxidized minerals and flotation for sulfide minerals. In Chile, the increase of sulfide minerals in the deposits and the decrease of oxidized minerals have led to an increase in the investigation of flotation processes and the optimization of their associated operations. One of the concentration processes is the use of thickeners, whose main objective is to treat the tailings that leave the plants in pulp form with approximately 30% solids and obtain a pulp with a concentration greater than 50% with clear water flow. The recovery of water is the main goal, so knowing the concentration profiles of solids and sedimentation is crucial. However, the characteristics of the pulp and the operation of the thickeners are complex because a great variety of forms can be found in the concentration profile of said pulp. This limits conventional measurement techniques and makes it difficult to apply deterministic models to the solids profile, given the high nonlinearities and variability of the system. In this article, a solution is proposed by developing a sensor that allows the online estimation of sludge level and concentration of solids, based on a model of neural networks (with the model of Maxwell for dispersions), allowing to measure the solids profile regardless of the operating conditions. The structure selected has nine inputs with a hidden layer, two neurons, and two outputs being trained with tailings from Chuquicamata, obtaining the information from a 50 L pilot with 10-electrode bar of 60 cm of length, resulting in an estimation error of 0.8 cm with a network of 26 parameters.

An agent who lacks preferences and instead makes decisions using criteria that are costly to create should select efficient sets of criteria, where the cost of making a given number of choice distinctions is minimized. Under mild conditions, efficiency requires that binary criteria with only two categories per criterion are chosen. When applied to the problem of determining the optimal number of digits in an information storage device, this result implies that binary digits (bits) are the efficient solution, even when the marginal cost of using additional digits declines rapidly to 0. This short paper pays particular attention to the symmetry conditions entailed when sets of criteria are efficient., Comment: In Proceedings TARK 2015, arXiv:1606.07295

The explosive growing number of data from mobile devices, social media, Internet of Things and other applications has highlighted the emergence of big data. This paper aims to determine the worldwide research trends on the field of big data and its most relevant research areas. A bibliometric approach was performed to analyse a total of 6572 papers including 28 highly cited papers and only papers that were published in the Web of ScienceTM Core Collection database from 1980 to 19 March 2015 were selected. The results were refined by all relevant Web of Science categories to computer science, and then the bibliometric information for all the papers was obtained. Microsoft Excel version 2013 was used for analyzing the general concentration, dispersion and movement of the pool of data from the papers. The t test and ANOVA were used to prove the hypothesis statistically and characterize the relationship among the variables. A comprehensive analysis of the publication trends is provided by document type and language, year of publication, contribution of countries, analysis of journals, analysis of research areas, analysis of web of science categories, analysis of authors, analysis of author keyword and keyword plus. In addition, the novelty of this study is that it provides a formula from multi-regression analysis for citation analysis based on the number of authors, number of pages and number of references.

Over the last decade we have witnessed an increasing use of data processing in embedded systems. Where in the past the data processing was limited (if present at all) to the handling of a small number of "on-off control signals", more recently much more complex sensory data is being captured, processed and used to improve system performance and dependability. The advent of systems-of-systems aggravates the use of more and more data, for instance, by bringing together data from several independent sources, allowing, in principle, for even better performing systems. However, this ever stronger data-orientation brings along several challenges in system design, both technically and organisationally, and also forces manufacturers to think beyond their traditional field of expertise. In this short paper, I will address these new design challenges, through a number of examples. The paper finishes with concrete challenges for supporting tools and techniques for system design in this new context., In Proceedings AiSoS 2013, arXiv:1311.3195

Cloud computing is currently the prevailing mode of designing, creating, and deploying complex applications, and it has implied a paradigm shift in all three areas; even if it taps and extends previous concepts such as service oriented, concurrent, and distributed computing, this shift has to be eventually translated to the algorithmic and conceptual aspects of sciences such as artificial life. In this short paper, we will review how the world of cloud computing has intersected the artificial life field, and how it has been used as an inspiration for new models or the design and implementation of new and powerful algorithms; in the other direction, we will also examine how artificial life concepts such as self-organization have been applied to the field of cloud computing.

A fault detection, isolation, and estimation approach is proposed in this paper based on Interactive Multimodel (IMM) fusion filtering and Strong Tracking Filtering (STF) for asynchronous multisensors dynamic systems. Time-varying fault is considered and a candidate fault model is built by augmenting the unknown fault amplitude directly into the system state for each kind of possible fault mode. By doing this, the dilemma of predetermining the fault extent as model design parameters in traditional IMM-based approaches is avoided. After that, the time-varying fault amplitude is estimated based on STF using its strong ability to track abrupt changes and robustness against model uncertainties. Through fusing information from multiple sensors, the performance of fault detection, isolation, and estimation is approved. Finally, a numerical simulation is performed to demonstrate the feasibility and effectiveness of the proposed method.

In this position paper we discuss three main shortcomings of existing approaches to counterfactual causality from the computer science perspective, and sketch lines of work to try and overcome these issues: (1) causality definitions should be driven by a set of precisely specified requirements rather than specific examples; (2) causality frameworks should support system dynamics; (3) causality analysis should have a well-understood behavior in presence of abstraction., In Proceedings CREST 2017, arXiv:1710.02770

In this position paper (1) we discuss two particular aspects of Systems of Systems, i.e., variability and evolution. (2) We argue that concepts from Product Line Engineering and Software Evolution are relevant to Systems of Systems Engineering. (3) Conversely, concepts from Systems of Systems Engineering can be helpful in Product Line Engineering and Software Evolution. Hence, we argue that an exchange of concepts between the disciplines would be beneficial., In Proceedings AiSoS 2013, arXiv:1311.3195