Search

Objective: We propose a MATLAB-based tool to convert electrocardiography (ECG) waveforms from paper-based ECG records into digitized ECG signals that is vendor-agnostic. The tool is packaged as an open source standalone graphical user interface (GUI) based application. Methods and procedures: To reach this objective we: (1) preprocess the ECG records, which includes skew correction, background grid removal and linear filtering; (2) segment ECG signals using Connected Components Analysis (CCA); (3) implement Optical Character Recognition (OCR) for removal of overlapping ECG lead characters and for interfacing of patients’ demographic information with their research records or their electronic medical record (EMR). The ECG digitization results are validated through a reader study where clinically salient features, such as intervals of QRST complex, between the paper ECG records and the digitized ECG records are compared. Results: Comparison of clinically important features between the paper-based ECG records and the digitized ECG signals, reveals intra- and inter-observer correlations of 0.86–0.99 and 0.79–0.94, respectively. The kappa statistic was found to average at 0.86 and 0.72 for intra- and inter-observer correlations, respectively. Conclusion: The clinically salient features of the ECG waveforms such as the intervals of QRST complex, are preserved during the digitization procedure. Clinical and Healthcare Impact: This open-source digitization tool can be used as a research resource to digitize paper ECG records thereby enabling development of new prediction algorithms to risk stratify individuals with cardiovascular disease, and/or allow for development of ECG-based cardiovascular diagnoses relying upon automated digital algorithms.

To improve the accuracy of user implicit rating prediction, we combine the traditional latent factor model (LFM) and bidirectional gated recurrent unit neural network (BiGRU) model to propose a hybrid model that deeply mines the latent semantics in the unstructured content of the text and generates a more accurate rating matrix. First, we utilize the user’s historical behavior (favorites records) to build a user rating matrix and decompose the matrix to obtain the latent factor vectors of users and literature. We also apply the BERT model for word embedding of the research papers to obtain the sequence of word vectors. Then, we apply the BiGRU with the user attention mechanism to mine the research paper textual content and to generate the new literature latent feature vectors that are used to replace the original literature latent factor vectors decomposed from the rating matrix. Finally, a new rating matrix is generated to obtain users’ ratings of noninteractive research papers and to generate the recommendation list according to the user latent factor vector. We design experiments on the real datasets and verify that the research paper recommendation model is superior to traditional recommendation models in terms of precision, recall, F1-value, coverage, popularity and diversity.

Machine learning (ML) components are increasingly adopted in many automated systems. Their ability to learn and work with novel input/incomplete knowledge and their generalization capabilities make them highly desirable solutions for complex problems. This has motivated the inclusion of ML techniques/components in products for many industrial domains including automotive systems. Such systems are safety-critical systems since their failure may cause death or injury to humans. Therefore, their safety must be ensured before they are used in their operational environment. However, existing safety standards and Verification and Validation (V&V) techniques do not properly address the special characteristics of ML-based components such as non-determinism, non-transparency, instability. This position paper presents the authors' view on the safety of automotive systems incorporating ML-based components, and it is intended to motivate and sketch a research agenda for extending a safety standard, namely ISO 26262, to address challenges posed by incorporating ML-based components in automotive systems.

Most existing studies and public datasets for handwritten Chinese text recognition are based on the regular documents with clean and blank background, lacking research reports for handwritten text recognition on challenging areas such as educational documents and financial bills. In this paper, we focus on examination paper text recognition and construct a challenging dataset named examination paper text (SCUT-EPT) dataset, which contains 50 000 text line images (40 000 for training and 10 000 for testing) selected from the examination papers of 2 986 volunteers. The proposed SCUT-EPT dataset presents numerous novel challenges, including character erasure, text line supplement, character/phrase switching, noised background, nonuniform word size, and unbalanced text length. In our experiments, the current advanced text recognition methods, such as convolutional recurrent neural network (CRNN) exhibits poor performance on the proposed SCUT-EPT dataset, proving the challenge and significance of the dataset. Nevertheless, through visualizing and error analysis, we observe that humans can avoid vast majority of the error predictions, which reveal the limitations and drawbacks of the current methods for handwritten Chinese text recognition (HCTR). Finally, three popular sequence transcription methods, connectionist temporal classification (CTC), attention mechanism, and cascaded attention-CTC are investigated for HCTR problem. It is interesting to observe that although the attention mechanism has been proved to be very effective in English scene text recognition, its performance is far inferior to the CTC method in the case of HCTR with large-scale character set.

Privacy of the individual data, especially in the Health data, is very sensitive and important. Privacy preserving Machine learning is emerging as one of the solutions for the security of data with the utility to create knowledge. In this paper, we have proposed a differential private artificial neural network (DP-ANN) and shows its application to predict the spread and the peak number of COVID-19 cases. We proposed a differential private artificial neural network (DP-ANN) in which laplacian noise has been introduced at activation function level and it has been compared with existing privacy ideas at error function and weights level of ANN. Results show that DP-ANN model with the private activation function produces the result similar to the base ANN model.

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

We investigate end-to-end optimized optical transmission systems based on feedforward or bidirectional recurrent neural networks (BRNN) and deep learning. In particular, we report the first experimental demonstration of a BRNN auto-encoder, highlighting the performance improvement achieved with recurrent processing for communication over dispersive nonlinear channels.

Fiber nonlinearities from Kerr effect are considered as major constraints for enhancing the transmission capacity in current optical transmission systems. Digital nonlinearity compensation techniques such as digital backpropagation can perform well but require high computing resources. Machine learning can provide a low complexity capability especially for high-dimensional classification problems. Recently several supervised and unsupervised machine learning techniques have been investigated in the field of fiber nonlinearity mitigation. This paper offers a brief review of the principles, performance and complexity of these machine learning approaches in the application of nonlinearity mitigation.

J.A. Moral-Munoz holds a FPU scholarship (AP2012-1789) from the Spanish Ministry of Education., Citation classics offer an outlook on those papers that have attracted great and historical interest by a research community and that could be also considered the basis of the research field. A new approach, which is called H-Classics, has been developed to identify such highly cited papers. It is based on the H-index and is sensitive to both the own characteristics of the corresponding research discipline and its evolution. The present study provides a useful insight into the development of the intelligent transport systems research field, revealing those scientific actors (authors, countries, and institutions) that have made the biggest research contribution to its development., Spanish Government AP2012-1789

International audience; Texture characterization of photographic papers is likely to provide scholars with valuable information regarding artistic practices. Currently, texture assessment remains mostly based on visual and manual inspections, implying long repetitive tasks prone to inter- and even intra-observer variability. Automated texture characterization and classification procedures are thus important tasks in historical studies of large databases of photographic papers, likely to provide quantitative and reproducible assessments of texture matches. Such procedures may, for instance, produce vital information on photographic prints of uncertain origins. The hyperbolic wavelet transform, because it relies on the use of different dilation factor along the horizontal and vertical axes, permits to construct robust and meaningful multiscale and anisotropic representation of textures. In the present contribution, we explore how unsupervised clustering strategies can be complemented both to assess the significance of extracted clusters and the strength of the contribution of each texture to its associated cluster. Graph based filterbank strategies are notably investigated with the aim to produce small size significant clusters. These tools are illustrated at work on a large database of about 2500 exposed and non exposed photographic papers carefully assembled and documented by the MoMA and P. Messier's foundation. Results are commented and interpreted.

Recycled paper is extensively used worldwide. In the last decades its market has expanded considerably. The increasing use of recycled paper in papermaking has led to the production of paper containing several types of impurities. Consequently, wastepaper mills are forced to implement quality control schemes for evaluating the incoming wastepaper stock, thus guarantying the specifications of the final product. The main objective of this work is to present a fast and reliable system for identifying different paper types. Therefore, undesirable paper types can be refused, improving the performance of the paper machine and the final quality of the paper manufactured. For this purpose two fast techniques, i.e., Fourier transform mid-infrared (FTIR) and reflectance near-infrared (*IR) were applied to acquire the infrared spectra of the paper samples. *ext, four processing multivariate methods, i.e., principal component analysis (PCA), canonical variate analysis (CVA), extended canonical variate analysis (ECVA) and support vector machines (SVM) were employed in the feature extraction –or dimension reduction– stage. Afterwards, the k nearest neighbors algorithm (k**) was used in the classification phase. Experimental results show the usefulness of the proposed methodology and the potential of both FTIR and *IR spectroscopic methods. Using the FTIR spectrum in association with SVM and k** the system achieved maximum classification accuracy of 100%, whereas using the *IR spectrum in association with ECVA or SVM and k** the system achieved maximum classification accuracy of 96.4%

International audience; In this paper, we investigate the retrieval of paper watermark by visual similarity. We propose to perform the visual similarity by encoding small regions of the watermark using a non-negative dictionary optimized on a large collection of watermarks. The local codes are then aggregated into a single vector representing the whole watermark. Experiments are carried out on a test of tracings (manual binarization of watermarks).

Falsification of medicines is a big problem in many developing countries, where technological infrastructure is inadequate to detect these harmful products. We have developed a set of inexpensive paper cards, called Paper Analytical Devices (PADs), which can efficiently classify drugs based on their chemical composition, as a potential solution to the problem. These cards have different reagents embedded in them which produce a set of distinctive color descriptors upon reacting with the chemical compounds that constitute pharmaceutical dosage forms. If a falsified version of the medicine lacks the active ingredient or includes substitute fillers, the difference in color is perceivable by humans. However, reading the cards with accuracy takes training and practice, which may hamper their scaling and implementation in low resource settings. To deal with this, we have developed an automatic visual recognition system to read the results from the PAD images. At first, the optimal set of reagents was found by running singular value decomposition on the intensity values of the color tones in the card images. A dataset of cards embedded with these reagents is produced to generate the most distinctive results for a set of 26 different active pharmaceutical ingredients (APIs) and excipients. Then, we train two popular convolutional neural network (CNN) models, with the card images. We also extract some "hand-crafted" features from the images and train a nearest neighbor classifier and a non-linear support vector machine with them. On testing, higher-level features performed much better in accurately classifying the PAD images, with the CNN models reaching the highest average accuracy of over 94\%., Comment: in Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), 2016

This paper presents a novel method for automated manipulation of individual paper fiber bonds using a microrobotic platform, a computer vision algorithm and a robotic software framework. This is a challenging task due to the three-dimensional, heterogeneous and complex morphology of the fiber bonds. The goal is to automatically grasp the fiber bond, and break it by pulling apart the fibers it consists of. We present the components of the microrobotic platform, and the different rules utilized in detecting suitable grasp points from a 3D reconstruction of the bond generated from an image pair. We demonstrate the functionality of the approach with bond breaking experiments of seven fiber bonds. The time required for grasping and breaking of a bond is 10 – 15 seconds making the approach much faster than the current state-of-the-art testing, which is based on manual manipulation. The success rate of the tests is as high as 80 %. acceptedVersion

This paper proposes a method for exploring technical phrase frames by extracting word n-grams that match our information needs and interests from research paper titles. Technical phrase frames, the outcome of our method, are phrases with wildcards that may be substituted for any technical term. Our method, first of all, extracts word trigrams from research paper titles and constructs a co-occurrence graph of the trigrams. Even by simply applying Page Rank algorithm to the co-occurrence graph, we obtain the trigrams that can be regarded as technical key phrases at the higher ranks in terms of Page Rank score. In contrast, our method assigns weights to the edges of the co-occurrence graph based on Jaccard similarity between trigrams and then apply weighted Page Rank algorithm. Consequently, we obtain widely different but more interesting results. While the top-ranked trigrams obtained by unweighted Page Rank have just a self-contained meaning, those obtained by our method are technical phrase frames, i.e., A word sequence that forms a complete technical phrase only after putting a technical word (or words) before or/and after it. We claim that our method is a useful tool for discovering important phrase logical patterns, which can expand query keywords for improving information retrieval performance and can also work as candidate phrasings in technical writing to make our research papers attractive., 29th IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2015; Gwangju; South Korea; 25 March 2015 through 27 March 2015, 2015 IEEE 29th International Conference on Advanced Information Networking and Applications Workshops (WAINA), 7096236; 2015

Peer review has become the most common practice for judging papers submitted to a conference for decades. An extremely important task involved in peer review is to assign submitted papers to reviewers with appropriate expertise which is referred to as paper-reviewer assignment. In this paper, we study the paper-reviewer assignment problem from both the goodness aspect and the fairness aspect. For the goodness aspect, we propose to maximize the topic coverage of the paper-reviewer assignment. This objective is new and the problem based on this objective is shown to be NP-hard. To solve this problem efficiently, we design an approximate algorithm which gives a 1/3-approximation. For the fairness aspect, we perform a detailed study on conflict-of-interest (COI) types and discuss several issues related to using COI, which, we hope, can raise some open discussions among researchers on the COI study. Finally, we conducted experiments on real datasets which verified the effectiveness of our algorithm and also revealed some interesting results of COI.

Previously, robots were mainly used by big companies in high volume manufacturing (i.e.: car industry). Industrial robots were perfect to execute procedures simplified to tiny (angular) movements. Today robots have appeared in small and medium enterprises, and they will appear rapidly in non-engineering fields as well, like offices, hospitals, and even in our homes. Robotics grains ground in newer and newer fields and it is too wide to overview it in one paper. This paper tries to summarize the nowadays robotics trends from the point of view of industrial electronics and industrial informatics.

The ability to manipulate deformable objects, such as textiles or paper, is a major prerequisite to bringing the capabilities of articulated robot hands closer to the level of manual intelligence exhibited by humans. We concentrate on the manipulation of paper, which affords us a rich interaction domain that has not yet been solved for anthropomorphic robot hands. Robust tracking and physically plausible modeling of the paper as well as feedback based robot control are crucial components for this task. This paper makes two novel contributions to this area. The first concerns real-time modeling and visual tracking. Our technique not only models the bending of a sheet of paper, but also paper crease lines which allows us to monitor deformations. The second contribution concerns enabling an anthropomorphic robot to fold paper, and is accomplished by introducing a set of tactile- and vision-based closed loop controllers.

The domain of Digital Libraries presents specific challenges for unsupervised information extraction to support both the automatic classification of documents and the enhancement of userspsila navigation in the digital content. In this paper, we propose a combined use of machine learning techniques (i.e. Support Vector Machines) and Natural Language Processing techniques (i.e. Stanford NLP parser) to tackle the problem of unsupervised key-phrases extraction from scientific papers. The proposed method strongly depends on the robust structural properties of a scientific paper as well as on the lexical knowledge that we are able to mine from its text. For the experimental assessment we have use a subset of ACM papers in the Computer Science domain containing 400 documents. Preliminary evaluation of the approach shows promising result that improves - on the same data-set - on state-of-the-art Bayesian learning system KEA from a minimum 27% to a maximum 77% depending on KEA parameters tuning and specific evaluation set. Our assessment is performed by comparison with key-phrases assigned by human experts in the specific domain and freely available through ACM portal.

Video halftoning is a key technology for use in the new display device, electronic paper (e-paper). One challenging issue is how to save the limited power of mobile e-paper device when a halftone video is displayed with various frame rates. In this paper, we propose a power-scalable multi-layer halftone video display scheme, which is composed of layer coding, non-uniform sampling, and flicker rate reduction. Our method not only efficiently save power over the state of the art video halftoning technology but also keep the quality of halftone video nearly unchanged when power saving is additionally considered. Experimental results demonstrate the effectiveness of the proposed method.

Researchers have largely focused on analyzing citation links from one scholarly work to another. Such citing sentences are an important part of the narrative in a research article. If we can automatically identify such sentences, we can devise an editor that helps suggest when a particular piece of text needs to be backed up with a citation or not. In this paper, we propose a method for identifying citing sentences by constructing a classifier using supervised learning. Our experiments show that simple language features such as proper nouns and the labels of previous and next sentences are effective features to identifying citing sentences.

In this paper the selection of suitable content-based features for the reconstruction of shredded notebook paper is examined. An algorithm for the detection of squared paper is proposed, based on the Hough transform. Experimental results show a good performance of the algorithm.

This paper presents a scheme for generating paper texture of historical documents. A new entropy based segmentation algorithm is used to decompose the image of documents into the image of the paper background and the printing of the document. Statistical analysis allows filling in the gaps from the printing, yielding a blank sheet of paper with similar texture to the original document.

Good registration (alignment to a reference) is essential for accurate face recognition. The effects of the number of landmarks on the mean localization error and the recognition performance are studied. Two landmarking methods are explored and compared for that purpose: (1) the most likely-landmark locator (MLLL), based on maximizing the likelihood ratio, and (2) Viola-Jones detection. Both use the locations of facial features (eyes, nose, mouth, etc) as landmarks. Further, a landmark-correction method (BILBO) based on projection into a subspace is introduced. The MLLL has been trained for locating 17 landmarks and the Viola-Jones method for 5. The mean localization errors and effects on the verification performance have been measured. It was found that on the eyes, the Viola-Jones detector is about 1% of the interocular distance more accurate than the MLLL-BILBO combination. On the nose and mouth, the MLLL-BILBO combination is about 0.5% of the inter-ocular distance more accurate than the Viola-Jones detector. Using more landmarks will result in lower equal-error rates, even when the landmarking is not so accurate. If the same landmarks are used, the most accurate landmarking method gives the best verification performance.