Search

Nowadays, there is a rapidly increasing number of conferences and journals in computer science that make a lot of challenges for researchers to find an appropriate venue to submit their scientific work. There is a need for a recommendation system that can support researchers for a better process of paper submission. In this paper, we present an efficient approach for building such a recommendation model by using embedding methods, Global Vector (GloVe) 1 created by Pennington et al. [1] and FastText 2 proposed by Facebook [2], Convolutional Neural Network (CNN) [3], and LSTM. The experimental results show that the combination of CNNs and FastText, CNN + FastText, can achieve the best performance in terms of the Top 1 Accuracy compared with other techniques, including the S2RSCS model, as presented in [4]. Moreover, the performance by using GloVe or FastText is much better, faster, and more stable than S2RSCS in most cases.

The rapid advance in science and technology is made possible by research conduct and breakthroughs in a wide range of fields, which have resulted in a large number of academic papers. Searching through the enormous literature to find relevant information of one's research interest has become an increasingly important yet challenging problem for many researchers. Most existing methods for academic paper recommendation are based on the analysis of paper contents and only meet with limited success. We propose a novel method based on heterogeneous information networks for academic paper recommendation, referred to as HNPR. This method considers the citation relationship between papers, the collaboration relationship between authors, and the research area information of papers to construct two types of heterogeneous information networks. In such networks, a random walk-based strategy is used to simulate natural sentences for the discovery of relevance between two papers according to a mature natural language processing model. Extensive experimental results using real data in public digital libraries show that HNPR significantly improves the accuracy of academic paper recommendation in comparison with traditional content-based recommendation methods.

1 The aim of the present work is to assess similarities between papers used in a collection of 215 lithographs by Henri Matisse. It combines the use of an anisotropic multiscale analysis built upon the hyperbolic wavelet transform to compute distances between textures, with the fact that four textures of the same print were digitized, corresponding to four different (recto/verso and top/side) views. A permutation algorithm is devised showing the importance of reordering the four views to achieve a meaningful comparison across the papers, thus suggesting possibly different artistic intentions in some prints.

To support the replication of "Instance of Interest Detection", which was presented at MM'19, this companion paper provides the details of the artifacts. Instance of Interest Detection (IOID) aims to provide instance-level user interest modeling for image semantic description. In this paper, we explain the file structure of the source code and publish the details of our IOID dataset, which can be used to retrain the model with custom parameters. We also provide a program for component analysis to help other researchers to do experiments with alternative models that are not included in our experiments. Moreover, we provide a demo program for using our model easily.

This companion paper supports the experimental replication of paper "Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network", which is presented at ACM Multimedia 2019. We provide the software package for replicating the implementation of Multi-Layered Comparison Network (MCN), as well as the Polyvore-T dataset and baseline methods compared in the original paper. This paper contains the guides to reproduce the experiment results including outfit compatibility prediction, outfit diagnosis and automatic outfit revision.

Which are the segmentation algorithms proposed during 2018-2019 in CVPR that have CNN architecture?’ Answering this question involves identifying and analyzing the deep learning architecture diagrams from several research papers. Retrieving such information poses significant challenge as most of the existing academic search engines are primarily based on only the text content. In this paper, we introduce Diag2Graph, an end-to-end framework for parsing deep learning diagram-figures, that enables powerful search and retrieval of architectural details in research papers. Our proposed approach automatically localizes figures from research papers, classifies them, and analyses the content of the diagram-figures. The key steps in analyzing the Figure content is the extraction of the different components data and finding their structural relation. Finally, the extracted components and their relations are represented in the form of a deep knowledge graph. A thorough evaluation on a real-word annotated dataset has been done to demonstrate the efficacy of our approach.

The field of natural language processing is experiencing a period of unprecedented growth, and with it a surge of published papers. This represents an opportunity for us to take stock of how we cite the work of other researchers, and whether this growth comes at the expense of “forgetting” about older literature. In this paper, we address this question through bibliographic analysis. By looking at the age of outgoing citations in papers published at selected ACL venues between 2010 and 2019, we find that there is indeed a tendency for recent papers to cite more recent work, but the rate at which papers older than 15 years are cited has remained relatively stable.

Nowadays, in this digital word text is one the vital knowledge carrier. Text can be perceived as structure of symbols which is accustomed to convey, transfer, or inherit civilization and way of life. It is among the major influential novelties of man kind; text performs crucial role in existence of human being. Text can be seen in all places in our day-to-day life. Thus, obtaining data from text which is present in scenarios of our day-to-day life is important. Processing the text that is present in natural scenario has two primary tasks namely Text identification and Text acknowledgment. The method of taking out text body from the natural scene is called as Text detection whereas the procedure of categorizing the characters from scene image which form expressive words is called as Text recognition. There are so many applications of scene text detection in different fields, e.g., intelligent inspection, blind navigation, industrial automation, automotive assistance, robot navigation, instant translation, automatic driving and product search, etc. Thus, street view text detection and recognition have allured rising research consideration in past few years. This paper as first step focuses on Text detection methods for natural scene images.

One very important component of the paper making process is the headbox. The inflow of the stock is accumulated up to an appropriate height in the headbox. The regulation of this height is to be strictly regulated to sustain an optimum pressure so that the stock jet is released with the preferred speed. The present work addresses the control system design of headbox consistency. The controllers using ZN and LQG techniques have been developed for it and their performance is compared. Further, the undesired effects of deadtime are compensated by designing Smith predictor. The output response, after deadtime compensation, is compared with the previous responses. All the results have been obtained by MATLAB simulations.

In this paper we position Linear Time Temporal Logic (LTL), structural operational semantics (SOS), and a graphical generalization of BNF as central DSLs for program analysis and verification tasks in order to illustrate the impact of language to the mindset: (1) Specifying program analyses in LTL changes the classical algorithmic ‘HOW’ thinking into a property-oriented ‘WHAT’ thinking that allows one to logically combine analysis goals and eases proofs. (2) Playing with the original store component in SOS configurations allows one to elegantly realize variants of abstract program interpretations, and to align different aspects, like e.g., the symbolic values of variables and path conditions. (3) Specializing languages by refining their BNF-like meta models has the power to lift certain verification tasks from the program to the programming language level. We will illustrate the advantages of the change of mindset imposed by these three DSLs, as well as the fact that these advantages come at low price due to available adequate generator technology.

Hyperproperties generalize trace properties by expressing relations between multiple computations. Hyperpropertes include policies from information-flow security, like observational determinism or non-interference, and many other system properties including promptness and knowledge. In this paper, we give an overview on the model checking problem for temporal hyperlogics. Our starting point is the model checking algorithm for HyperLTL, a reduction to Buchi automata emptiness. This basic construction can be extended with propositional quantification, resulting in an algorithm for HyperQPTL. It can also be extended with branching time, resulting in an algorithm for HyperCTL*. However, it is not possible to have both extensions at the same time: the model checking problem of HyperQCTL* is undecidable. An attractive compromise is offered by MPL[E], i.e., monadic path logic extended with the equal-level predicate. The expressiveness of MPL[E] falls strictly between that of HyperCTL* and HyperQCTL*. MPL[E] subsumes both HyperCTL* and HyperKCTL*, the extension of HyperCTL* with the knowledge operator. We show that the model checking problem for MPL[E] is still decidable.

International audience; The task of tagging papers with semantic metadata in order to analyze their relatedness represents a good foundation for a paper recommender system. The analysis from this paper extends from previous research in order to create a graph of papers from a specific domain with the purpose of determining each article's importance within the considered corpus of papers. Moreover, as non-latent representations are powerful when used in conjunction with latent ones, our system retrieves semantically close words, not present in the paper, in order to improve the retrieval of papers. Our previous analyses used the semantic representation of papers in different semantic models with the purpose of creating visual graphs based on the semantic relatedness links between the abstracts. The current analysis takes a step forward by proposing a model that can suggest which papers are of the highest relevance, share similar concepts, and are semantically related with the initial query. Our study is performed using paper abstracts in the field of information technology extracted from the Web of Science citation index. The research includes a use case and its corresponding results by using interactive and exploratory network graph representations.

Emerging smart services, such as indoor smart parking or patient monitoring and tracking in hospitals, incur a significant technical roadblock stemming primarily from a lack of cost-effective and easily deployable localization framework that impedes their widespread deployment. To address this concern, in this paper we present a low-cost, indoor localization and navigation system, which performs continuous and real-time processing of Bluetooth Low Energy (BLE) and IEEE 802.15.4a compliant Ultra-wideband (UWB) sensor data to localize and navigate the concerned entity to its desired location. Our approach depends upon fusing the two feature sets, using the UWB to calibrate the BLE localization mechanism.

We discuss a new approach to interactive exploration of high-dimensional data sets which is aimed at building human’s understanding of the data by iterative additions of recommended attributes and objects that can together represent a context in which it may be useful to analyze the data. We identify challenges and expected benefits that our methodology can bring to the users. We also show how our ideas got inspired by Formal Concept Analysis (FCA) and Rough Set Theory (RST). It is though worth emphasizing that this particular paper is not aimed at investigating relationships between FCA and RST. Instead, the goal is to discuss which algorithmic methods developed within FCA and RST could be reused for the purpose of our approach.

Machine learning is widely used in malware detection systems as a core component. However, machine learning algorithm is based on the assumption that the underlying malware concept is stable for training and testing. The assumption is vulnerable to well-crafted concept drift attacks, such as mimicry attacks, gradient descent attacks, poisoning attacks and so on. This paper proposes an ensemble learning system which combines vertical and horizontal correlation learning models. The significant diversity among vertical and horizontal correlation models increases the difficulty of concept drift attacks. And average p-value assessment is applied to fortify the system to be sensitive to hidden concept drift. The experiment results show that the hybrid system could actively recognize the concept drift among different Miuref variants.

The goal of anti-phishing techniques is to reduce the delivery rate of phishemails, and anti-phishing training aims to decrease the phishing click-through rates. This paper presents the X-Platform Phishing Attack, a deceptive phishing attack with an alarmingly high delivery and click-through rates, and highlights a subclass of phishing attacks that existing anti-phishing methods do not seem to be able to address. The main characteristic of this attack is that an attacker is able to embed a malicious link within a legitimate message generated by service providers (e.g., Github, Google, Amazon) and sends it using their infrastructure to his targets. This technique results in the bypassing of existing anti-phishing filters because it utilizes reputable service providers to generate seemingly legitimate emails. This also makes it highly likely for the targets of the attack to click on the phishing link as the email id of a legitimate provider is being used. An X-Platform Phishing attack can use email-based messaging and notification mechanisms such as friend requests, membership invitations, status updates, and customizable gift cards to embed and deliver phishing links to their targets. We have tested the delivery and click-through rates of this attack experimentally, based on a customized phishing email tunneled through GitHub’s pull-request mechanism. We observed that 100% of X-Platform Phishing emails passed the anti-phishing systems and were delivered to the inbox of the target subjects. All of the participants clicked on phishing messages, and in some cases, forwarded the message to other project collaborators who also clicked on the phishing links.

Intrusion Detection System (IDS) has been an effective way to achieve higher security in detecting malicious activities for the past couple of years. Anomaly detection is an intrusion detection system. Current anomaly detection is often associated with high false alarm rates and only moderate accuracy and detection rates because it’s unable to detect all types of attacks correctly. An experiment is carried out to evaluate the performance of the different machine learning algorithms using KDD-99 Cup and NSL-KDD datasets. Results show which approach has performed better in term of accuracy, detection rate with reasonable false alarm rate.

In this expository work, we sketch some applications of annotated logics. Such logics were discovered in the late 1980s and nowadays have become one of the most fertile logics for applications. They constitute a two-sorted logic, and they are paraconsistent and in general paracomplete and non-alethic logics.

A number of measures for quantifying information leakage of a program have been proposed. Most of these measures evaluate a program as a whole by quantifying how much information can be leaked on average by different program outputs. While these measures perfectly fit for static program analyses, they cannot be used by dynamic analyses since they do not specify what information an attacker learns through observing one concrete program output. In this paper we study the existing definitions of quantitative information flow. Our goal is to find the definition of dynamic leakage -- it should evaluate how much information an attacker learns when she observes one program output.Surprisingly, we find out that none of the existing definitions provide a suitable measure for dynamic leakage. We hence open a new research question in quantitative information flow area: which definition of dynamic leakage is suitable?

This paper describes a work on transfer learning in neural networks carried out in 1970s and early 1980s, which produced its first publication in 1976. In the contemporary research on transfer learning there is a belief that pioneering work on transfer learning took place in early 1990s, and this paper updates that knowledge, pointing out that the transfer learning research started more than a decade earlier. This paper reviews that 1970s research and addresses important issues relevant for the current transfer learning research. It gives a mathematical model and geometric interpretation of transfer learning, and a measure of transfer learning indicating positive, negative, and no transfer learning. It presents experimental investigation in the mentioned types of transfer learning. And it gives an application of transfer learning in pattern recognition using datasets of images.

Co-citation analysis can be exploited as a bibliometric technique used for mining information on the relationships between scientific papers. Proposed methods rely, however, on co-citation counting techniques that slightly take the semantic aspect into consideration. The present study proposes a new technique based on the measure of Semantic Similarity (SS) between the titles of co-cited papers. Several computational measures rely on knowledge resources to quantify the semantic similarity, such as the WordNet «is a» taxonomy. Our proposal analyzes the SS between the titles of co-cited papers using word-based SS measures. Two major analytical experiments are performed: the first includes the benchmarks designed for testing word-based SS measures; the second exploits the dataset DBLP (DBLP: Digital Bibliography & Library Project.) citation network. As a result, we found the SS measures behave the same as human judgement for the lexical similarity and can be consequently used for the automatic assessment of similarity between co-cited papers. The analysis of highly repeated co-citations demonstrates that the different SS measures display almost similar behaviours, with slight differences due to the distribution of the provided SS values. Furthermore, we note a low percentage of similar referred papers into the co-citations.

Biological systems exhibit extraordinary levels of diversity. Embodied behaviours are the emergent property of many loosely-coupled parallel processes, from the microscopic level, e.g. materials, to more abstracted levels, e.g. organs and limbs. We summarise our investigations into using a synthetic methodology, i.e. an understanding-by-building approach, for designing the complex interactions of falling paper shapes. By studying how simple systems such as a falling paper shape behave, we can analyse the specific characteristics of the interaction between morphology and the environment, and how this leads to programmable non-trivial behaviours. We present current results and discuss the implications on the future of design in robotics.

Part 3: Recommendation System; International audience; Vector representations learning (also known as embeddings) for users (items) are at the core of modern recommendation systems. Existing works usually map users and items to low-dimensional space to predict user preferences for items and describe pre-existing features (such as ID) of users (or items) to obtain the embedding of the user (or item). However, we argue that such methods neglect the dual role of users, side information of users and items (e.g., dual citation relationship of authors, authoritativeness of authors and papers) when recommendation is performed for scientific paper. As such, the resulting representations may be insufficient to predict optimal author citations.In this paper, we contribute a new model named scientific paper recommendation using Author’s Dual Role Citation Relationship (ADRCR) to capture authors’ citation relationship. Our model incorporates the reference relation between author and author, the citation relationship between author and paper, and the authoritativeness of authors and papers into a unified framework. In particular, our model predicts author citation relationship in each specific class. Experiments on the DBLP dataset demonstrate that ADRCR outperforms state-of-the-art recommendation methods. Further analysis shows that modeling the author’s dual role is particularly helpful for providing recommendation for sparse users that have very few interactions.

The amount of academic articles in digital libraries is increasing exponentially. This growth of scientific papers’ growth made it difficult for researchers to obtain related papers from their queries. Recommendation systems can help them resolve the problem of information overload. However, existing paper recommender methods generally rely on the simple citation network, which ignores the semantic of papers and has the problem of cold start. In this paper, a hybrid paper recommendation approach AMHG is proposed which is based on a multi-level citation heterogeneous graph. Unlike existing works which only use the reference relationship, we consider the same or similar authors’ papers to alleviate the cold start problem of zero-citation and newly published papers. Besides, the metadata information of papers is also incorporated into a representation model to generate better recommender results to alleviate the cold start problem. We use the authors’ influence factors to reorder the candidate list outputting by MLP to obtain high-quality articles. Through experiments, we compare our model with several methods on the DBLP-REC dataset to demonstrate that AMHG outperforms state-of-the-art performance and the effectiveness of recommender.

Nowadays, recommendation systems play an indispensable role in many fields, including e-commerce, finance, economy, and gaming. There is emerging research on publication venue recommendation systems to support researchers when submitting their scientific work. Several publishers such as IEEE, Springer, and Elsevier have implemented their submission recommendation systems only to help researchers choose appropriate conferences or journals for submission. In this work, we present a demo framework to construct an effective recommendation system for paper submission. With the input data (the title, the abstract, and the list of possible keywords) of a given manuscript, the system recommends the list of top relevant journals or conferences to authors. By using state-of-the-art techniques in natural language understanding, we combine the features extracted with other useful handcrafted features. We utilize deep learning models to build an efficient recommendation engine for the proposed system. Finally, we present the User Interface (UI) and the architecture of our paper submission recommendation system for later usage by researchers.

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

In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems. Choosing the algorithm and hyperparameter setting correctly can promote the overall performance greatly, but users often fail to do so due to the absence of knowledge. How to help users to effectively and quickly select the suitable algorithm and hyperparameter settings for the given task instance is an important research topic nowadays, which is known as the CASH problem. In this paper, we design the Auto-Model approach, which makes full use of known information in the related research paper and introduces hyperparameter optimization techniques, to solve the CASH problem effectively. Auto-Model tremendously reduces the cost of algorithm implementations and hyperparameter configuration space, and thus capable of dealing with the CASH problem efficiently and easily. To demonstrate the benefit of Auto-Model, we compare it with classical Auto-Weka approach. The experimental results show that our proposed approach can provide superior results and achieves better performance in a short time., 12 pages, 3 figures

In this paper we present a novel method to print paper and cardboard without ink. The method is based on the carbonization of paper by a combination of lasers working on different wavelengths. A prove of concept system is created based on combining existing commercial systems to demonstrate the viability of the method. The results show that no debris is generated and the quality of the mark is superior in terms of contrast and resolution with previously known methods.

Tracking progress in machine learning has become increasingly difficult with the recent explosion in the number of papers. In this paper, we present AxCell, an automatic machine learning pipeline for extracting results from papers. AxCell uses several novel components, including a table segmentation subtask, to learn relevant structural knowledge that aids extraction. When compared with existing methods, our approach significantly improves the state of the art for results extraction. We also release a structured, annotated dataset for training models for results extraction, and a dataset for evaluating the performance of models on this task. Lastly, we show the viability of our approach enables it to be used for semi-automated results extraction in production, suggesting our improvements make this task practically viable for the first time. Code is available on GitHub.

Sentiment Analysis is done by gathering the data, analyzing the text and aggregating the words in the text. The main focus of this survey is on the evaluation methods used and their respective core solutions. In this paper we are going to study the aspect based sentiment classification, which is classified into three. Those are Implicit, Explicit and Coreferential aspect based sentiment classification. In this paper we are also going to elaborate the polarity of the reviews into positive and negative sentiments. Aspect Based Classification not only promises to suppress the noisy data but also provides high efficiency in identifying the aspects with an addition of performing classification task with higher accuracy. This accuracy can be achieved by using Neural Network algorithms.

The explosive growth of the number of papers leads to the over-expansion of the paper information, resulting in the problem of information overload, causing a lot of trouble for researchers to find the papers they need. This paper implements a paper recommendation system based on LDA and PageRank. In this system, we recommend papers in the same field to researchers by modeling and analyzing paper data. Therefore, we can provide researchers with a quick and effective reference for related papers in the research field. In this paper, the probability distribution calculation and keywords extraction of paper topics and words are carried out according to the LDA of papers in the paper pool. At the same time, word2dec is used to represent the topic vector, doc2vec is used to represent the paper vector, and by calculating the system similarity between documents and topics, we get the top N papers that are most similar to the topic input by users. We use the PageRank algorithm to reorder the options in the reference network to get the final recommendation results. Under the experimental data set, the accuracy of system recommendation is more than 60%, which has high reliability and achieves the corresponding recommendation effect.

Understanding the current research trends, problems, and their innovative solutions remains a bottleneck due to the ever-increasing volume of scientific articles. In this paper, we propose NLPExplorer, a completely automatic portal for indexing, searching, and visualizing Natural Language Processing (NLP) research volume. NLPExplorer presents interesting insights from papers, authors, venues, and topics. In contrast to previous topic modelling based approaches, we manually curate five course-grained non-exclusive topical categories namely Linguistic Target (Syntax, Discourse, etc.), Tasks (Tagging, Summarization, etc.), Approaches (unsupervised, supervised, etc.), Languages (English, Chinese, etc.) and Dataset types (news, clinical notes, etc.). Some of the novel features include a list of young popular authors, popular URLs and datasets, list of topically diverse papers and recent popular papers. Also, it provides temporal statistics such as yearwise popularity of topics, datasets, and seminal papers. To facilitate future research and system development, we make all the processed dataset accessible through API calls. The current system is available at http://nlpexplorer.org.

Acknowledgements are ubiquitous in scholarly papers. Existing acknowledgement entity recognition methods assume all named entities are acknowledged. Here, we examine the nuances between acknowledged and named entities by analyzing sentence structure. We develop an acknowledgement extraction system, AckExtract based on open-source text mining software and evaluate our method using manually labeled data. AckExtract uses the PDF of a scholarly paper as input and outputs acknowledgement entities. Results show an overall performance of F_1=0.92. We built a supplementary database by linking CORD-19 papers with acknowledgement entities extracted by AckExtract including persons and organizations and find that only up to 50–60% of named entities are actually acknowledged. We further analyze chronological trends of acknowledgement entities in CORD-19 papers. All codes and labeled data are publicly available at https://github.com/lamps-lab/ackextract.

We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search. It’s designed to enable researchers to use natural language queries to find precise answers and extract insights from a massive amount of academic papers. We present a large improvement over classic search engine baseline on several standard QA datasets and provide the community a collaborative data collection tool to curate the first natural language processing research QA dataset via a community effort.

Review rating prediction of text reviews is a rapidly growing technology with a wide range of applications in natural language processing. However, most existing methods either use hand-crafted features or learn features using deep learning with simple text corpus as input for review rating prediction, ignoring the hierarchies among data. In this paper, we propose a Hierarchical bi-directional self-attention Network framework (HabNet) for paper review rating prediction and recommendation, which can serve as an effective decision-making tool for the academic paper review process. Specifically, we leverage the hierarchical structure of the paper reviews with three levels of encoders: sentence encoder (level one), intra-review encoder (level two) and inter-review encoder (level three). Each encoder first derives contextual representation of each level, then generates a higher-level representation, and after the learning process, we are able to identify useful predictors to make the final acceptance decision, as well as to help discover the inconsistency between numerical review ratings and text sentiment conveyed by reviewers. Furthermore, we introduce two new metrics to evaluate models in data imbalance situations. Extensive experiments on a publicly available dataset (PeerRead) and our own collected dataset (OpenReview) demonstrate the superiority of the proposed approach compared with state-of-the-art methods., Accepted by COLING 2020

The overabundance of academic papers makes it difficult for researchers to find relevant or interested papers. To address the problem, existing studies have developed many approaches to recommend academic papers effectively. Most of them mainly utilize content-based filtering or citation analysis to measure similarity or relatedness of two papers and recommend relevant papers to the given query. However, these recommended papers are usually discrete from each other, i.e., the relationship between recommended papers are omitted, which disables researchers from having an sight into the time-oriented development of the topic they are interested in. To overcome the drawbacks of existing work, we propose a novel academic paper recommendation method called PAPR (Path-based Academic Paper Recommendation). Our method aims to recommend an ordered path of relevant papers, which are of great benefit in helping researchers understand the development of a specific topic. During process, we take both content and network structure into account to learn the representation of a paper. Next, the similarity between papers are measured based on the representation. The experimental results based on real data show that the proposed method outperforms the state-of-art methods.

The medical robotics market in the global healthcare industry have spread and extended in these several years. Internet of Medical Robotics Things (IoMRT) is also growing and Internet of Things is extending a new field of healthcare application. Whereas, the previous paper suggested that, in the field of robotics, the cloud platforms for Internet of Robotics Things (IoRT) were gradually developed; therefore, the digital platform and architecture for IoMRT of the healthcare industries should be formulated when necessary. An open healthcare platform for IoMRT is expected to promote and implement the robotics and the IoMRT applications for medical and healthcare communities efficiently. In this paper, we suggest that various medical robotics and the IoMRT-related applications will be designed and verified, while the open platform for medical, healthcare-related Robotics should be proposed and verified by the research initiative named “Open Healthcare Platform 2030–OHP2030.” In addition, the vision for enabling medical robotics and the IoMRT-related applications in the OHP2030 research initiative is explained.

We define and find a most specific generalization of a fuzzy set of topics assigned to leaves of the rooted tree of a taxonomy. This generalization lifts the set to a “head subject” in the higher ranks of the taxonomy, that is supposed to “tightly” cover the query set, possibly bringing in some errors, both “gaps” and “offshoots”. Our hybrid method involves two more automated analysis techniques: a fuzzy clustering method, FADDIS, involving both additive and spectral properties, and a purely structural string-to-text relevance measure based on suffix trees annotated by frequencies. We apply this to extract research tendencies from two collections of research papers: (a) about 18000 research papers published in Springer journals on data science for 20 years, and (b) about 27000 research papers retrieved from Springer and Elsevier journals in response to data science related queries. We consider a taxonomy of Data Science based on the Association for Computing Machinery Classification of Computing System (ACM-CCS 2012). Our findings allow us to make some comments on the tendencies of research that cannot be derived by using more conventional techniques.

GitHub has become a popular social application platform, where a large number of users post their open source projects. In particular, an increasing number of researchers release repositories of source code related to their research papers in order to attract more people to follow their work. Motivated by this trend, we describe a novel item-item cross-platform recommender system, $\textit{paper2repo}$, that recommends relevant repositories on GitHub that match a given paper in an academic search system such as Microsoft Academic. The key challenge is to identify the similarity between an input paper and its related repositories across the two platforms, $\textit{without the benefit of human labeling}$. Towards that end, paper2repo integrates text encoding and constrained graph convolutional networks (GCN) to automatically learn and map the embeddings of papers and repositories into the same space, where proximity offers the basis for recommendation. To make our method more practical in real life systems, labels used for model training are computed automatically from features of user actions on GitHub. In machine learning, such automatic labeling is often called {\em distant supervision\/}. To the authors' knowledge, this is the first distant-supervised cross-platform (paper to repository) matching system. We evaluate the performance of paper2repo on real-world data sets collected from GitHub and Microsoft Academic. Results demonstrate that it outperforms other state of the art recommendation methods.

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, With the continuous growth of scientific literature, discovering relevant academic papers for a researcher has become a challenging task, especially when looking for the latest, most recent papers. In this case, traditional collaborative filtering systems are ineffective, since they are unable to recommend items not previously seen, rated or cited. This is known as the item cold-start problem. In this paper, we explore the potential of exploiting citation knowledge to provide a given user with relevant suggestions about recent scientific publications. A novel hybrid recommendation method that encapsulates such citation knowledge is proposed. Experimental results show improvements over baseline methods, evidencing benefits of using citation knowledge to recommend recently published papers in a personalised way. Moreover, as a result of our work, we also provide a unique dataset that, differently to previous corpora, contains detailed paper citation information

This paper is a plea for developing possibilistic learning methods that would be consistent with if-then rule-based reasoning. The paper first recall the possibility theory-based handling of cascading sets of parallel if-then rules. This is illustrated by an example describing a classification problem. It is shown that the approach is both close to a possibilistic logic handling of the problem and can also be put under the form of a max-min-based matrix calculus describing a function underlying a structure somewhat similar to a max-min neural network. The second part of the paper discusses how possibility distributions can be obtained from precise or imprecise statistical data, and then surveys the few existing works on learning in a possibilistic setting. A final discussion emphasizes the interest of handling learning and reasoning in a consistent way.

The amount of data that produced is increased day after day especially data as a text, so with this massive production it would be difficult to analyze or extract information to discover the patterns from the unstructured text. Text mining is used for availing the massive amount of knowledge that is in the text and deriving high quality information from the text automatically. This Process would save effort and time. Text mining considered as a subset of data mining where data mining is more generic. This paper proposes a methodology of mining a text for a case study related to publication papers. Some of text mining approaches will be introduced for mining the publication papers using machine learning (ML) and natural language processing (NLP) techniques. Describing each phase as following: First phase is keywords extraction using natural language processing techniques, second phase named entity recognition and last phase is document classification. The last two phases are using the ML techniques. Then a case study is built to simulate the system phases, showing what is the input and the output in each phase.

Verification techniques have been applied to the design of secure protocols for decades. However, relatively few efforts have been made to ensure that verified designs are also implemented securely. Static code verification techniques offer one way to bridge the verification gap between design and implementation, but require substantial expertise and manual labor to realize in practice. In this short paper, we propose black-box runtime verification as an alternative approach to extend the security guarantees of protocol designs to their implementations. Instead of instrumenting the complete protocol implementation, our approach only requires instrumenting common cryptographic libraries and network interfaces with a runtime monitor that is automatically synthesized from the protocol specification. This lightweight technique allows the effort for instrumentation to be shared among different protocols and ensures security with presumably minimal performance overhead.

Edge environments are generating an increasingly large amount of data due to the proliferation of edge devices. Accommodating this large influx of data at edge servers is a challenging issue. While some data can be processed as it is generated, others must be stored for later access. This paper proposes the features that a new edge-native storage system must possess including support for user mobility and node fluctuation. To motivate this, we first describe several emerging edge applications and their data needs. We then describe the challenges in meeting these needs. We then evaluate an out-of-the-box cloud storage system, Cassandra, to assess it’s suitability as an edge storage system due to many edge-friendly features. We determined that while a cloud-based storage system can be ported to the edge meeting some of the challenges, other challenges require new solutions. Based on the challenges and the results of Cassandra case study, we propose a set of design principles for a new edge-native storage system.

Distributed smart and connected community applications of the present and future will continuously sense perishable data on which they make decisions. We say the data are perishable when they represent information sensed at a past point in time, possibly at a distant part of the distributed application, and for which the ground truth could have since changed. This paper discusses actions the sensing source, the network, and the controller can take to make the best possible decisions given that we know only a delayed version of the truth. Some of these actions to preserve freshness of data are based on known real-time techniques such as Time Sensitive Networking. To these we add Information Theory applied on a message-by-message basis and cross-layer coordination between content and network handling. Both the unexpectedness (surprisal) and timeliness (freshness) properties of perishable information can be encoded using a Shannon information entropy framework. Examples of smart community systems of the future for which these concepts are relevant are given.

In this companion paper, firstly, we briefly summarize the contributions of our main manuscript: Selective Deep Convolutional Features for Image Retrieval, published in ACM MultiMedia 2017. In addition, we provide detail instructions together with pre-configured MATLAB scripts which allow experiments to be executed and to reproduce the results reported in our main manuscript effortlessly. The source code is available at https://github.com/hnanhtuan/selectiveConvFeatures_ACMMM_reproducibility.

Deep neural networks (DNNs) have been successfully applied to a great variety of applications, ranging from small IoT devices to large scale services in a data center. In order to improve the efficiency of processing these DNN models, dedicated hardware accelerators are required for all these scenarios. Theoretically, there exists an optimized acceleration architecture for each application. However, considering the cost of chip design and corresponding tool-chain development, researchers need to trade off between efficiency and generality. In this work, we demonstrate that it is practical to use a unified architecture, called Ascend, to support those applications, ranging from IoT devices to data-center services. We provide a lot of design details to explain that the success of Ascend relies on contributions from different levels. First, heterogeneous computing units are employed to support various DNN models. And the datapath is adapted according to the requirement of computing and data access. Second, when scaling the Ascend architecture from a single core to a cluster containing thousands of cores, it involves design efforts, such as memory hierarchy and system level integration. Third, a multi-tier compiler, which provides flexible choices for developers, is the last critical piece. Experimental results show that using accelerators based on the Ascend architecture can achieve comparable or even better performance in different applications. In addition, various chips based on the Ascend architecture have been successfully commercialized. More than 100 million chips have been used in real products.

Context and motivation. Collaborative AI systems aim at working together with humans in a shared space. Building these systems, which comply with quality requirements, domain specific standards and regulations is a challenging research direction. This challenge is even more exacerbated for new generation of systems that leverage on machine learning components rather than deductive (top-down programmed) AI.

Traditional polyhedral compilation techniques rely on Integer Linear Programming (ILP) and lexicographic optimization to compute optimal transformations. Although, these techniques excel at exposing and leveraging data and pipeline parallelism as well as exploiting (hidden) available locality, they are not the best suited when tackling problems such as the Manhattan distance in a grid.