Search

With the acceleration of education informatization, the social demand for online examination papers is increasing. However, there are some problems in the generation of online examination papers. Firstly, it is impossible to randomly generate examination papers quickly. Besides, it is impossible to dynamically adjust examination papers according to test results. Thirdly, it is impossible to generate examination papers based on individual characteristics of students. In order to solve these problems, this paper proposes a new auto-generation examination paper model based on genetic algorithm. The model dynamically adjusts the difficulty factor of individual test questions by analyzing the online learning data and historical user test result data, and then guarantees the difficulty of generating examination papers in line with the changes in the current educational environment. The simulation results show that the algorithm improves the efficiency and accuracy of the generation examination paper, and effectively controls the difficulty coefficient of the examination paper.

A possible practical engineering approach to creation of the general artificial intelligence is considered. The choice of approach is based on modular hierarchical representation of knowledge, where each module uses its own methods of representation and knowledge processing. Work with knowledge is done by a hierarchical multi-agent system. The description of system’s individual elements and information about the current development state are given.

Technology is shaping our lives in a multitude of ways. This is fuelled by a technology infrastructure, both legacy and state of the art, composed of a heterogeneous group of hardware, software, services, and organisations. Such infrastructure faces a diverse range of challenges to its operations that include security, privacy, resilience, and quality of services. Among these, cybersecurity and privacy are taking the centre-stage, especially since the General Data Protection Regulation (GDPR) came into effect. Traditional security and privacy techniques are overstretched and adversarial actors have evolved to design exploitation techniques that circumvent protection. With the ever-increasing complexity of technology infrastructure, security and privacy-preservation specialists have started to look for adaptable and flexible protection methods that can evolve (potentially autonomously) as the adversarial actor changes its techniques. For this, Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) were put forward as saviours. In this paper, we look at the promises of AI, ML, and DL stated in academic and industrial literature and evaluate how realistic they are. We also put forward potential challenges a DL based security and privacy protection system has to overcome. Finally, we conclude the paper with a discussion on what steps the DL and the security and privacy-preservation community have to take to ensure that DL is not just going to be hype, but an opportunity to build a secure, reliable, and trusted technology infrastructure on which we can rely on for so much in our lives.

The data hiding techniques have attracted a lot of attention in recent years and mainly with the intensive growth of multimedia and its possibility for covert communication. Steganography is one of the information hiding methods to confirm the ability of a multimedia carrier to exchange secret information between two end-points so that it is imperceptible, thus avoiding the detection of hidden information. The secret information can be embedded in several multimedia carriers, such as image or audio or video files. It works by embedding the message in a source cover which may make the observer feel it is the source cover itself. The type of multimedia carrier here is an image. However, this technique suffers from the problem of the carrier distortion. In this paper, we investigate the impact of some distortion types on the carrier images and discuss the possibility of using distraction images in steganography to protect the stego-image. Furthermore, we highlight the current challenges of image steganography. The experimentations show very interesting results.

The clustering coefficient has been widely used for identifying the local structure of networks. In this paper, the weighted spectral distribution with 3-cycle (WSD3) that is similar (but not equal) to the clustering coefficient is studied on evolving social networks. It is demonstrated that the ratio of the WSD3 to the network size (i.e., the node number) provides a more sensitive discrimination for the size-independent local structure of social networks in contrast to the clustering coefficient. Moreover, the difference of the WSD3’s performances on social networks and communication networks is investigated, and it is found that the difference is induced by the different symmetrical features of the normalized Laplacian spectral densities on these networks.

Patent terminology relation extraction is of great significance to the construction of patent Knowledge graph. In order to solve the problem of long-distance dependency in traditional depth learning, a new method of patent terminology relation extraction is proposed, which combines attention mechanism and bi-directional LSTM model and with keyword strategy. Category keyword features in each sentence obtained by the improved TextRank with the patent text information vectorization added. BiLSTM neural work and attention mechanism are employed to extract the temporal information and sentence-level global feature information. Moreover, pooling layer is added to obtain the local features of the text. Finally, we fuse the global features and local features, and output the final classification results through the softmax classifier. The addition of category keywords improves the distinction of categories. Substantial experimental results demonstrate that the proposed model outperform the state-of-art neural model in patent terminology relation extraction.

Traditionally, the way one evaluates the performance of an Artificial Intelligence (AI) system is via a comparison to human performance in specific tasks, treating humans as a reference for high-level cognition. However, these comparisons leave out important features of human intelligence: the capability to transfer knowledge and make complex decisions based on emotional and rational reasoning. These decisions are influenced by current inferences as well as prior experiences, making the decision process strongly subjective and apparently biased. In this context, a definition of compositional intelligence is necessary to incorporate these features in future AI tests. Here, a concrete implementation of this will be suggested, using recent developments in quantum cognition, natural language and compositional meaning of sentences, thanks to categorical compositional models of meaning.

At present, under the current quality education, the examination is still one of the main measure of teachers’ teaching ability and student achievement. At the same time, different levels of examination are different to the test paper. Aiming at the multi-combination of constraints in the test paper, an improved genetic algorithm is proposed, which combines the constraints of the papers effectively, so that the test papers can be maximized to meet the needs of the users.

We tested four methods of making document representations cross-lingual for the task of semantic search for the similar papers based on the corpus of papers from three Russian conferences on NLP: Dialogue, AIST and AINL. The pipeline consisted of three stages: preprocessing, word-by-word vectorisation using models obtained with various methods to map vectors from two independent vector spaces to a common one, and search for the most similar papers based on the cosine similarity of text vectors. The four methods used can be grouped into two approaches: 1) aligning two pretrained monolingual word embedding models with a bilingual dictionary on our own (for example, with the VecMap algorithm) and 2) using pre-aligned cross-lingual word embedding models (MUSE). To find out, which approach brings more benefit to the task, we conducted a manual evaluation of the results and calculated the average precision of recommendations for all the methods mentioned above. MUSE turned out to have the highest search relevance, but the other methods produced more recommendations in a language other than the one of the target paper.

In this paper we show how the age of scientific papers can be predicted given a diachronic corpus of papers from a particular domain published over a certain time period. We first train ordinal regression models for the task of predicting the age of individual sentences by fine-tuning series of BERT models for binary classification. We then aggregate the prediction results on individual sentences into a final result for entire papers. Using two corpora of publications from the International World Wide Web Conference and the Journal of Artificial Societies and Social Simulation, we compare various result aggregation methods, and show that the sentence-based approach produces better results than the direct document-level method.

In this paper, we focus on the hierarchical multi-label classification task of scientific papers, which consists in assigning to a paper the set of relevant classes, which are organized in a hierarchy. The difficulty of manually constructing sufficient labeled datasets renders challenging the automatic classification task of research papers according to hierarchical labels. Multi-view active learning is a widely adopted method to address this issue, by iteratively selecting the most useful unlabeled samples for the multi-view classifiers exploiting disjoint data’ views, and querying an oracle on their real labels. However, none of the state of the art studies in this field is proposed for the hierarchical multi-label classification task. In this paper, we propose an effective multi-view active learning framework for the hierarchical multi-label classification task, applied on scientific papers. Our approach adopts a novel selection strategy that relies on both uncertainty and representativeness criteria when selecting the most informative unlabeled samples in each iteration. Experimental results on a real world dataset of ACM research papers show the efficiency of our approach over several baseline methods.

This paper shows the automatic classification of research papers published in Scopus. Our classification is based on the research lines of the university. We apply the K-nearest neighbor classifier and linear discriminant analysis (LDA). Various stages were used from information gathering, creating the vocabulary, pre-processing and data training, and supervised classification in this work. The experiment involved 596 research articles published in SCOPUS from 2003–2017. The results show an overall accuracy of 88.44%.

Coreference resolution is essential for automatic text understanding to facilitate high-level information retrieval tasks such as text summarisation or question answering. Previous work indicates that the performance of state-of-the-art approaches (e.g. based on BERT) noticeably declines when applied to scientific papers. In this paper, we investigate the task of coreference resolution in research papers and subsequent knowledge graph population. We present the following contributions: (1) We annotate a corpus for coreference resolution that comprises 10 different scientific disciplines from Science, Technology, and Medicine (STM); (2) We propose transfer learning for automatic coreference resolution in research papers; (3) We analyse the impact of coreference resolution on knowledge graph (KG) population; (4) We release a research KG that is automatically populated from 55,485 papers in 10 STM domains. Comprehensive experiments show the usefulness of the proposed approach. Our transfer learning approach considerably outperforms state-of-the-art baselines on our corpus with an F1 score of 61.4 (+11.0), while the evaluation against a gold standard KG shows that coreference resolution improves the quality of the populated KG significantly with an F1 score of 63.5 (+21.8).

The rapid growth of scientific literature is presenting several challenges for the search and discovery of research artifacts. Datasets are the backbone of scientific experiments. It is crucial to locate the datasets used or generated by previous research as building suitable datasets is costly in terms of time, money, and human labor. Hence automated mechanisms to aid the search and discovery of datasets from scientific publications can aid reproducibility and reusability of these valuable scientific artifacts. Here in this work, utilizing the next sentence prediction capability of language models, we show that a BERT-based entity recognition model with POS aware embedding can be effectively used to address this problem. Our investigation shows that identifying sentences containing dataset mentions in the first place proves critical to the task. Our method outperforms earlier ones and achieves an F1 score of 56.2 in extracting dataset mentions from research papers on a popular corpus of social science publications. We make our codes available at https://github.com/sandeep82945/data_discovery.

Peer review is an important means of academic evaluation. The evaluation words in peer review texts reflect the important viewpoints of reviewers. In this paper, An evaluation words recognition method for peer review texts (TransPeerBCC) is proposed based on transfer learning method and BiLSTM-CNN-CRF framework. TransPeerBCC first classifies direct evaluation word and indirect evaluation word, and then uses BiLSTM-CNN-CRF framework to identify these words. At the same time, in order to improve the recognition accuracy, the model parameters of public domain data are transferred to the peer review texts’ using the transfer learning method. The effectiveness of the method is verified by the experimental dataset, and the identified evaluation words are quantitatively analyzed.

Artificial intelligence is a buzz word and even more when its accomplishments have challenged our intelligence. However, what is intelligence? Is there a consensus in its meaning for researchers and professionals? Is it just a sales word? What does it mean in practical terms? To answer these questions, we followed a systemic review of literature in most cited papers about intelligent systems in the Internet of Things (IoT) and discovered that only 58% were intelligent as we defined: “Intelligent Systems are systems conformed by algorithms that are programmed using some machine learning techniques and that can learn from data and perform tasks with a superior performance”. The rest 42% were just traditional systems with hardware or software enhancements.

This paper summarizes an empirical study of mining semantic information from the title/abstract of scientific papers’ dataset using the wordnet API. This summary includes description of the background, ideas, and research conducted using a program we wrote which uses Wordnet API and some other libraries. Semantic information from the abstract was obtained using wordnet (after stemming the words and selecting words belonging to certain tags), then these words were expanded, and then evaluated against the textual content of the same paper of which titles/abstracts were used as input. The semantic information is the hypernym (is-a relationship) of the stemmed words found in the title of each selected paper applied recursively (mined) using wordnet. That includes finding the hypernym of words and hypernyms of hypernyms recursively (until level 2). Every title and abstract, when written well, should contain a summary of the paper. By mining their semantic, one can get an insight of how much information can be obtained about the semantic of the paper using wordnet. Then the evaluation of that mining can be conducted by finding the percentage of matches between the semantic information found in the title/abstract and the content (body) of the same paper. It was found that the words/hypernyms: point, head, process are the most frequent matching in all papers. On the other hand, the word “value” is one of the least frequent but matching. It was also found that a paper about Grammars has the highest total number of matches (807 matches), and that the highest percentage of matches is 50%. That and other interesting results.

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.

This article aims to lay a foundation for learning and practicing music online. Massive Open Online Courses (MOOCs) are growing as we are moving to online classes. Current music courses through MOOCs mostly focus on peer evaluation for assessing the students’ performance. However, this technique may not be practical when it is applied to larger class sizes. Therefore, in this research, the main goal is to reduce the instructor’s load and provide online real-time performance feedback. As a contribution to music education, we propose a new technological framework to automate music lessons for learning how to play any favorite songs via existing machine learning (ML) techniques for adaptability to various learning styles.

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.

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.

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.

Body balance is an essential capability for an individual to perform functional activities. There are various performance-based balance measures available to occupational therapists. However, conventional balance measures are limited due to subjectivity. There is a prominent need for a more objective and accurate assessment. NIMBLE, using motion sensing and tracking system was developed for a more objective and accurate measure of body movement with high-resolution recording. A pilot study was conducted in 20 participants for functional sitting balance measures by using both paper-based assessment and the NIMBLE. Results showed substantial discrepancies when the NIMBLE was able to detect balance deficits when the paper-based measures failed. The NIMBLE system can accurately capture the extraction of joint centers and segment orientation, providing the ability to calculate joint kinematics and spatiotemporal aspects of the movement. With this low cost and friendly interface, it has great potential to be widely used in healthcare practices.

Under many circumstances, scholars need to identify new research directions by going through many different databases to identify the research gap and identify areas which have not yet been studied thus far. Checking all the electronic databases is tiresome, and one often misses the important pieces. In this paper, we propose to shorten the time required for identifying the research gap by using web scraping and natural language processing. We tested this approach by reviewing three distinct areas: (i) safety awareness, (ii) housing price, (iii) sentiment and artificial intelligence from 1988 to 2019. Tokenisation was used to parse the titles of the publications indexed on Google Scholar. We then ranked the collocations from the highest to the lowest frequency. Thus, we determined the sets of keywords that had not been stated in the title and identified the initial idea as a research void.

This paper presents the development of a test paper checker that will recognize a handwritten text using Intelligent Character Recognition (ICR) for Alphanumeric Characters. An examination can be conducted in two ways—digital and manual—and each way has a different approach in checking. In this study, the main objective is to recognize alphanumeric handwritten characters accurately using intelligent character recognition. OpenCV is used in the Python programming language and Support Vector Machine as a tool in machine learning for ICR. Answer sheet was designed with 120 items for MCQ and problem-solving questions. Item analysis and printing of results are included in the device. Experiments were conducted by giving an actual examination from the 131 participants in Technological University of the Philippines for testing the accuracy of the device. The results obtained from comparing manual and machine checking had an accuracy of 93.0769%. Thus, the proposed method is applicable for the development of handwritten character recognition.

Paper manufacturing is energy demanding and improved modelling of the pulp bleach process is the main non-invasive means of reducing energy costs. In this paper, time it takes to bleach paper pulp to desired brightness is examined. The model currently used is analysed and benchmarked against two machine learning models Random Forest and TreeBoost. Results suggests that the current model can be superseded by the machine learning models and it does not use the optimal compact subset of features. Despite the differences between the machine learning models, a feature ranking correlation has been observed for the new models. One novel, yet unused, feature that both machine learning models found to be important is the concentration of bleach agent.

In this paper an automated multiple choice grader for paper-based exams is implemented. The system consists of two main parts, a software program and a document feeder scanner. The exam papers are fed to the scanner which scans them one by one and send them as an input to the software. The software program recognizes the student Identification Number (ID) and the answers for each exam paper and reports the final results in an Excel sheet. The system starts by applying an aligning procedure and segmenting the scanned image in order to extract form number, student ID, and answers boxes, then a pre-processing step that handles all irregular cases of input is implemented; where in this step a best possible shape that results in the highest recognition accuracy is gained. After getting a proper separated characters and numbers, a feature extraction process is applied on each character/number to calculate its feature vector. The feature vector is then compared with templates of feature vectors for each of the answers choices and numbers with their variations, where both characters and numbers are in English language. After recognizing all the answers and all ID number digits; the system starts grading the student paper and comparing student answer with the pre-entered key answers. A recognition rate of 95.58 % is attained.

In this paper, we report a study of an innovative mobile application to support grading paper-based programming exams. We call the app – Programming Grading Assistant (PGA). It scans pre-generated QR-codes of paper-based question-and-concepts associations and uses OCR to recognize handwritten answers. PGA provides interfaces for teachers to calibrate recognition results, as well as to adjust partial credit assignment according to conceptual incorrectness of the answers. We evaluate the mobile grading process and the quality of grading results based on the assessed semantic information. The results demonstrate that the mobile grading approach keeps persistent traces of students’ performance, including semantic feedback and ultimately enhances grading consistency.

Clinical neuropsychologists develop comprehensive behavioral profiles on their patients primarily by using paper-and-pencil test stimuli. Despite these tests being significantly cheaper and faster than complex procedures such as MRI scans, multiple drawbacks remain. Constructing these behavioral profiles can take upwards of six hours to fully complete, and the analysis of the sketches from these pencil-and-paper tests is still largely subjective and qualitative. We developed SmartStrokes, a testing suite that implements digital versions of common clinical neuropsychology pencil-and-paper tests, with the purpose of helping to automate and analyze patient sketches using the principles of sketch recognition.

While medical image analysis has seen extensive use of deep neural networks, learning over multiple tasks is a challenge for connectionist networks due to tendencies of degradation in performance over old tasks while adapting to novel tasks. It is pertinent that adaptations to new data distributions over time are tractable with automated analysis methods as medical imaging data acquisition is typically not a static problem. So, one needs to ensure that a continual learning paradigm be ensured in machine learning methods deployed for medical imaging. To explore interpretable lifelong learning for deep neural networks in medical imaging, we introduce a perspective of understanding forgetting in neural networks used in ultrasound image analysis through the notions of attention and saliency. Concretely, we propose quantification of forgetting as a decline in the quality of class specific saliency maps after each subsequent task schedule. We also introduce a knowledge transfer from past tasks to present by a saliency guided retention of past exemplars which improve the ability to retain past knowledge while optimizing parameters for current tasks. Experiments on a clinical fetal echocardiography dataset demonstrate a state-of-the-art performance for our protocols.

Gesture recognition is one of the most popular tasks in computer vision, where convolutional neural networks (CNNs) based method has obtained the state-of-the-art performance. However, it is generally acknowledged that CNNs need a large amount of data to achieve such performance. Event Camera is a kind of biologically inspired event-based camera, which can keep the information of moving objects and remove the redundant background data. In this paper, we set up a rock-paper-scissor hand gesture recognition system based on FlowNet and Event Camera. Event camera is used to acquire event data. Then we propose an algorithm for the proposed gesture recognition. Specifically, FlowNet2.0 is employed to extract the motion representation of the pre-processed visual data, and a CNN classification network is applied to recognize the symbols extracted according to the motion representation. As a comparison, we also apply the rock-paper-scissor gesture recognition algorithm on traditional camera. The experimental results show that the proposed system based on Event Camera gets better performance, and to some extent, weaken the dependence on the training data. The whole system achieves 94.0\(\%\) out-of-sample accuracy and allows computation at up to 30 fps.

Scientific papers are important for scholars to track trends in specific research areas. With the increase in the number of scientific papers, it is difficult for scholars to read all the papers to extract emerging or noteworthy knowledge. Paper modeling can help scholars master the key information in scientific papers, and relation classification (RC) between entity pairs is a major approach to paper modeling. To the best of our knowledge, most of the state-of-the-art RC methods are using entire sentence’s context information as input. However, long sentences have too much noise information, which is useless for classification. In this paper, a flexible context is selected as the input information for convolution neural network (CNN), which greatly reduces the noise. Moreover, we find that entity type is another important feature for RC. Based on these findings, we construct a typical CNN architecture to learn features from raw texts automatically, and use a softmax function to classify the entity pairs. Our experiment on SemEval-2018 task 7 dataset yields a macro-F1 value of 83.91%, ranking first among all participants.

Although there are a numerous of studies in the facilitative effects of dictionary consultation in promoting word learning, no research has ever been conducted to investigate the effectiveness of a hybrid use of paper-based and electronic dictionaries. The present research, therefore, responds to this call and compares the effectiveness of the pure use of either paper-based or electronic dictionary and the hybrid use of both. The empirical results demonstrate the superiority of the paper-based dictionary over the electronic dictionary, the usefulness of repetition and the greater effectiveness of the hybrid use of both paper-based and electronic dictionary than the pure use of either. We further conclude that the significance of processing for constructing memory, repetition for consolidating memory and diversity for reinforcing memory should be emphasized.

E-commerce customers and general Web users should not believe that the products suggested by Recommender systems or results displayed by Web search engines are either complete or relevant to their search aspirations. The economic priority of Web related businesses requires a higher rank on Web snippets or product suggestions in order to receive additional customers; furthermore, Web search engines and recommender systems revenue is obtained from advertisements and pay-per-click. This survey paper presents a review of Web Search Engines, Ranking Algorithms, Citation Analysis and Recommender Systems. In addition, Neural networks and Deep Learning are also analyzed including their use in learning relevance and ranking. Finally, this survey paper also introduces the Random Neural Network with its practical applications.

Near infrared (NIR) spectroscopy is used in many applications to gather information about chemical composition of materials. For paper waste sorting, a small number of scores computed from NIR-spectra and assuming more or less unimodal clustered data, a pixel classifier can still be crafted by hand using knowledge about chemical properties and a reasonable amount of intuition. Additional information can be gained by visual data (VIS). However, it is not obvious what features, e.g. based on color, saturation, textured areas, are finally important for successfully separating the paper classes in feature space. Hence, a rigorous feature analysis becomes inevitable. We have chosen a generic machine-learning approach to successfully fuse NIR and VIS information. By exploiting a classification tree and a variety of additional visual features, we could increase the recognition rate to 78% for 11 classes, compared to 63% only using NIR scores. A modified feature ranking measure, which takes redundancies of features into account, allows us to analyze the importance of features and reduce them effectively. While some visual features like color saturation and hue showed to be important, some NIR scores could even be dropped. Finally, we generalize this approach to analyze raw NIR-spectra instead of score values and apply it to plastic waste sorting.

The paper aims at the development of fuzzy rough set-based dimensionality reduction for discrimination of electrocardiogram into six classes. ECG acquired by the offline method is in the form of coloured strips. Morphological features are estimated using eigenvalues of Hessian matrix in order to enhance the characteristic points, which are seen as peaks in ECG images. Binarization of the image is carried out using a threshold that maximizes entropy for appropriate extraction of the fiducial features from the background. Various image processing algorithms enhance the image which is utilized for feature extraction. The dataset produced comprises the feature vector consisting of 79 features and 1 decision class for 6 classes of ECG. Extensive analysis of dimensionality reduction has been done to have relevant and nonredundant attributes. Fuzzy rough domain has been explored to take into account the extreme variability and vagueness in the ECG. Optimal feature set is subjected to fuzzification using Gaussian membership function. Further, fuzzy rough set concepts help in defining a consistent rule set to obtain the appropriate decision class. Classification accuracy of unfuzzified dataset is compared with the fuzzified dataset. Semantics of the data are well preserved using fuzzy rough sets and are seen from the performance metrics like accuracy, sensitivity and specificity. The proposed model is named as Fuzzy Rough ECG Image Classifier (FREIC) which can be deployed easily for clinical use as well as experimental use.

Unsupervised random-walk keyphrase extraction models mainly rely on global structural information of the word graph, with nodes representing candidate words and edges capturing the co-occurrence information between candidate words. However, integrating different types of useful information into the representation learning process to help better extract keyphrases is relatively unexplored. In this paper, we propose a random-walk method to extract keyphrases using word embeddings. Specifically, we first design a new word embedding learning model to integrate local context information of the word graph (i.e., the local word collocation patterns) with some crucial features of candidate words and edges. Then, a novel random-walk ranking model is designed to extract keyphrases by leveraging such word embeddings. Experimental results show that our approach outperforms 8 state-of-the-art unsupervised methods on two real datasets consistently for keyphrase extraction.

RoboCup uses soccer competitions as a research area to promote robotics and artificial intelligence. The ultimate goal of the RoboCup is to develop a team of humanoid robots that can win against the human world champion soccer team in 2050. This paper presents the approach of the MRL TeenSize humanoid team to improve its hardware and software which leads to achieving first place in soccer competition and Drop-In games, second place in the technical challenge and third-best humanoid award.

In simple-decision-making scenarios such as in repeated two-person games human behavior is to some extend predictable. To investigate this research question, we focused on developing a system for the Rock-Paper-Scissor (RPS) game. Our approach included three steps: (i) To generate a large data-base of experimental data, (ii) to analyze the data to detect systematic patterns and deviations from rational behavior within the test persons, and (iii) to employ methods from machine learning to identify patterns and predict the next throw of the opponent. We identified as the best current approach a Gated-Reccurent-Unit using User Statistics, which is able to predict the next throw and hence win in about 50% of the cases, beating state-of-the-art approaches. Potentials and limitations of our approach are discussed.

Multi-view data that contains the data represented in many types of features has received much attention recently. The class of method utilising non-negative matrix factorization (NMF) and manifold learning to seek the meaningful latent structure of data has been popularly used for both traditional data and multi-view data. The NMF and manifold based multi-view clustering methods focus on dealing with the challenges of manifold learning and applying manifold learning on the NMF framework. This paper provides a comprehensive review of this important class of methods on multi-view data. We conduct an extensive experiments on several datasets and raise many open problems that can be dealt with in the future so a higher clustering performance can be achieved.

We present RusNLP, a web service implementing semantic search engine and recommendation system over proceedings of three major Russian NLP conferences (Dialogue, AIST and AINL). The collected corpus spans across 12 years and contains about 400 academic papers in English. The presented web service allows searching for publications semantically similar to arbitrary user queries or to any given paper. Search results can be filtered by authors and their affiliations, conferences or years. They are also interlinked with the NLPub.ru service, making it easier to quickly capture the general focus of each paper. The search engine source code and the publications metadata are freely available for all interested researchers.

Recent neural network-based models have proven successful in summarization tasks. However, previous studies mostly focus on comparatively short texts and it is still challenging for neural models to summarize long documents such as academic papers. Because of their large size, summarization for academic papers has two obstacles: it is hard for a recurrent neural network (RNN) to squash all the information on the source document into a latent vector, and it is simply difficult to pinpoint a few correct sentences among a large number of sentences. In this paper, we present an extractive summarizer for academic papers. The idea is converting a paper into a tree structure composed of nodes corresponding to sections, paragraphs, and sentences. First, we build a hierarchical encoder-decoder model based on the tree. This design eases the load on the RNNs and enables us to effectively obtain vectors that represent paragraphs and sections. Second, we propose a tree structure-based scoring method to steer our model toward correct sentences, which also helps the model to avoid selecting irrelevant sentences. We collect academic papers available from PubMed Central, and build the training data suited for supervised machine learning-based extractive summarization. Our experimental results show that the proposed model outperforms several baselines and reduces high-impact errors.

Thousands of academic papers are submitted at top venues each year. Manual audits are time-consuming and laborious. And the result may be influenced by human factors. This paper investigates a modularized and attention-based recurrent convolutional network model to represent academic paper and predict aspect scores. This model treats input text as module-document hierarchies, uses attention pooling CNN and LSTM to represent text, and outputs prediction with a linear layer. Empirical results on PeerRead data show that this model give the best performance among the baseline models.

Calculation of text similarity is an essential task for the text analysis and classification. It be can based, e.g., on Jaccard, cosine or other similar measures. Such measures consider the text as a bag-of-words and, therefore, lose some syntactic and semantic features of its sentences. This article presents a different measure based on the so-called artificial sentence pattern (ASP) method. This method has been developed to analyze texts in the Polish language which has very rich inflection. Therefore, ASP has utilized syntactic and semantic rules of the Polish language. Nevertheless, we argue that it admits extensions to other languages. As a result of the analysis, we have obtained several hypernodes which contain the most important words. Each hypernode corresponds to one of the examined documents, the latter being published papers from agriculture domain written in Polish. Experimental results obtained from that set of papers have been described and discussed. Those results have been visually illustrated using graphs of hypernodes and compared with Jaccard and cosine measures.

The paper presents a novel methodology intended to distinguish between real and artificially generated manuscripts. The approach employs inherent differences between the human and artificially generated wring styles. Taking into account the nature of the generation process, we suggest that the human style is essentially more “diverse” and “rich” in comparison with an artificial one. In order to assess dissimilarities between fake and real papers, a distance between writing styles is evaluated via the dynamic dissimilarity methodology. From this standpoint, the generated papers are much similar in their own style and significantly differ from the human written documents. A set of fake documents is captured as the training data so that a real document is expected to appear as an outlier in relation to this collection. Thus, we analyze the proposed task in the context of the one-class classification using a one-class SVM approach compared with a clustering base procedure. The provided numerical experiments demonstrate very high ability of the proposed methodology to recognize artificially generated papers.

The automatic analysis of water-sensitive papers (WSP) is of great relevance in agriculture. SprayImageMobile is a software tool developed for mobile devices (iOS) that provides full processing of WSP, from image acquisition to the final reporting. One of the initial processing tasks on SprayImageMobile is the detection (or segmentation) of the WSP on the image acquired by the device. This paper presents the method developed for the detection of the WSP that was implemented in SprayImageMobile. The method is based on the identification of reference points along the WSP margins, and the modeling of a quadrilateral that takes into account possible false positive and negative identifications. The method was tested on a set of 360 images, failing to detect the WSP in only 1 case (detection accuracy of 99.7%). The segmentation accuracy was evaluated using references obtained by a semi-automatic method. The average values obtained for the 359 images tested were: 0.9980 (precision), 0.9940 (recall) and 0.9921 (Hammoude metric).

The citation similarity measurement task is defined as determining how similar the meanings of two citations are. This task play an significant role in Natural Language Processing applications, especially in academic plagiarism detection. Yet, computing citation similarity is not a trivial task, due to the incomplete and ambiguous information presented in academic papers, which makes necessity to leverage extra knowledge to understand it, as well as most similarity measures based on the syntactic features, and other based on the semantic part still has many drawbacks. In this paper, we propose a corpus-based approach using deep learning word embeddings to compute more effective citation similarity. Our study explores the previous works on text similarity, namely, string-based, knowledge-based and corpus-based. Then we define our new basis and experiment on a large dataset of scientific papers. The final results demonstrate that deep learning based approach can enhance the effectiveness of citation similarity.

Paper fragments reassembly has been playing an important role in many places such as public security and even archaeology. Combined with the travelling salesman problem, a novel approach based on the matching of greyscale difference matrix is adopted. Experimental results demonstrate its potential in speed, accuracy and less human intervention for double-sided paper fragments reassembly. The study may provide a new direction for the automatic stitching or image mosaic technique.

The paper addresses the task of information extraction from scientific literature with machine learning methods. In particular, the tasks of definition and result extraction from scientific publications in Russian are considered. We note that annotation of scientific texts for creation of training dataset is very labor insensitive and expensive process. To tackle this problem, we propose methods and tools based on active learning. We describe and evaluate a novel adaptive density-weighted sampling (ADWeS) meta-strategy for active learning. The experiments demonstrate that active learning can be a very efficient technique for scientific text mining, and the proposed meta-strategy can be beneficial for corpus annotation with strongly skewed class distribution. We also investigate informative task-independent features for information extraction from scientific texts and present an openly available tool for corpus annotation, which is equipped with ADWeS and compatible with well-known sampling strategies.

Electrocardiogram (ECG) is one of the most practiced methods to detect any abnormalities in human heart function. ECG waveforms are usually recorded as paper form. However, ECG paper records are inconvenient for storage and retrieval of the patient records. In this paper, an improved ECG waveform extraction algorithm from paper records is proposed. It is used to get accurate ECG trajectory information with a serious of adaptive image processing techniques, including skew correction, waveform segmentation, and tracking. The presented algorithm is tested with a number of ECG records printed from different equipment. Furthermore, three metrics are adopted for quantitative measurement between reconstructed signals and original waveforms. The comparison result shows an average accuracy of 95.5%, which proves the effectiveness of the method.