Search

For the detection of product color uniformity and seam texture defects in the production process of test paper, detection methods are proposed respectively. For the detection of the color uniformity, a uniformity detection method based on dynamic light correction is proposed. The illumination correction image is used for color dynamic compensation of the test paper image to solve the influence of uneven illumination on the test paper. For the detection of texture defects such as seams, a texture defect detection method based on gray gradient aggregation intensity is proposed. This method uses one-way Gaussian convolution to strengthen features, and then calculates the gradient, divides the region and calculates the gradient extremum aggregation strength to judge texture defects, which can quickly and efficiently find seam defects. The experimental results show that the above methods have obvious effects on the color uniformity and seam detection of the test paper. The color uniformity accuracy rate is 96%, the seam detection accuracy rate is 97%. The total detection time of a single test paper is about 90ms. The algorithm is real-time and accurate, and can be used in actual production detection.

In this paper, we obtain samples of thermal aging transformer insulation paper at 6 time points through an accelerated thermal aging test that simulates the actual operating state of the transformer. The Raman spectroscopy diagnosis model of transformer insulating paper aging is proposed. The model combines an autoencoder and a linear discriminant analysis algorithm to extract the characteristics of the Raman spectrum, and uses a Naive Bayes classification method to divide the aging stage of the insulating paper. Through the Raman spectroscopy diagnosis model of transformer insulation paper aging designed in this paper, the Raman spectroscopy characteristic quantity extracted by the AE-LDA method can effectively reflect the aging characteristic information of the insulating paper, and the Naive Bayes classification algorithm is used to predict. Research shows that the model has a high predictive accuracy for the assessment of the aging state of insulating paper, and can effectively diagnose the aging state of transformer oil-paper insulation. The Raman spectroscopy used in the diagnosis of the aging of insulating paper has good aging discrimination ability and good application prospects, and provides a new idea for the diagnosis of the aging state of transformer oil-paper insulation.

Because the traditional insulation paper state detection method has some shortcomings, this paper proposes a non-destructive detection method, which uses the texture feature value of insulation paper image to establish a relationship with the degree of polymerization (DP) of insulation paper state, and then indirectly estimates the aging state of insulation paper. Firstly, the insulation paper images in different aging states are collected, and the texture feature values of the images are extracted by gray histogram, gray level co-occurrence matrix and gray level run-length matrix; then, the texture feature values are selected by correlation; then, the validity of the selected texture feature values to represent the insulation paper state is verified by support vector machine (SVM); finally, the multiple linear regression method is used. The relationship between the degree of polymerization and the texture feature value is established and verified by the actual results. The results show that the texture feature value has a good fitting relationship with the degree of polymerization, which verifies the effectiveness of this method in evaluating the state of insulating paper.

The ageing status of the oil-paper insulation is closely related to the operation of the transformers. Recently, near infrared spectroscopy (NIRS) is used to identify the ageing condition of oil-paper insulation for it is a more rapid and nondestructive detection than the traditional viscometry method. However, the identification accuracy of existing quantitative analysis method of NIRS are still insufficient. This paper proposed an improved Linear discriminant analysis (LDA) method to classify the spectra and to identify the ageing condition of the insulating paper. Based on DP measurement, the insulating paper specimens prepared in laboratory are divided into varying ageing groups. The principle of LDA method is introduced. The classic LDA method has been applied to identify the ageing status of specimens respectively from 4 ageing groups and 3 ageing groups. The results show that LDA has a better performance in classifying four groups than three groups. To achieve an accurate ageing condition identification with balanced accuracy of the model and enough categories of ageing status, the improved LDA method is proposed. The identification results show that the improved method has satisfactory performance and indicates great application potentials in the ageing assessment of the oil-paper impregnated insulation.

In this work, we describe the application of the ‘steerable pyramid’ (Portilla and Simoncelli, 2000), a high-dimensional texture descriptor, to the discrimination and classification of a large collection of photographic paper textures. This work is part of a broader effort to bring precise physical measurements to the characterization of photographic papers, and our intended audience includes photograph conservators, curators, and collectors. For our purposes, it is important both to enable fine-grained local comparisons of very similar textures and to identify salient groupings across the entire landscape of photographic papers. The steerable pyramid was developed with the explicit goal of synthesizing textures; as such, it is an overcomplete representation. Its high native dimensionality is an advantage for highly precise local comparisons of texture, as in nearest neighbor search; it is, however, a disadvantage for grouping tasks, which require a well-structured global topology. For grouping tasks, we describe a number of compression and grouping approaches designed to meet a variety of analytical needs. Finally, we validate the steerable pyramid descriptor numerically using ‘one versus all’ classification on an augmented data set that includes multiple samples per paper type.

The purpose of this work is to explore the applicability and effectiveness of deep learning methods for the task------moves recognition in abstract of research paper. We firstly build a large corpus for moves recognition. Then we choose the traditional machine learning method SVM as a benchmark, and develop four moves recognition methods based on DNN, LSTM, Attention-BiLSTM and BERT. Finally, we design two groups of experiments with sample size 10,000 and 50,000 and then compare experimental results. The results show that most of the deep learning methods outperform the traditional machine learning method SVM especially in large-scale sample experiments, in which the BERT with a re-pre-trained model achieves the best results in both groups of experiments. Deep learning methods are proved applicable and effective for moves recognition in research paper abstracts.

Machine learning (ML) has increasingly been adopted in safety-critical systems such as autonomous vehicles (AVs) and industrial robotics. In these domains, reliability and safety are important considerations, and hence it is critical to ensure the resilience of ML systems to faults and errors. On the other hand, soft errors are becoming more frequent in commodity computer systems due to the effects of technology scaling and reduced supply voltages. Further, traditional solutions for masking hardware faults such as Triple-Modular Redundancy (TMR) are prohibitively expensive in terms of their energy and performance overheads. Therefore, there is a compelling need to ensure the resilience of ML applications to soft errors on commodity hardware platforms.We first experimentally assess the resilience of safety-critical ML applications to soft errors. We demonstrate through fault injection experiments that even a single bit flip due to a soft error can lead to misclassification in Deep Neural Network (DNN) applications deployed in AVs, leading to safety violations. However, not all the errors in an DNN will result in serve consequences such as safety violations, and hence it is sufficient to protect the DNN from the ones that do. Unfortunately, finding all possible errors that result in safety violations is a very compute intensive task. We propose BinFI, a fault injection approach that efficiently injects critical faults that are highly likely to result in safety violations, based on the unique properties of DNNs. Finally, we propose Ranger, an approach to protect DNNs from critical faults with minimal performance overheads and no accuracy loss. We will conclude by presenting some of our ongoing work, and the future challenges in this area.

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.

In this article we are presenting a state of the art in the Artificial Intelligence (AI) and Robotics fields, so as to address the problem of autonomy and integration of autonomous heterogeneous systems for decision making autonomy. This state of the art is followed by the presentation of some avenues addressing the issue in order to lead the autonomy of heterogeneous robotic systems in the naval defence environment possible.

Paper dating analysis is an important research direction of document inspection, which is widely used in the inspection and identification of cultural relics and ancient books. This article focuses on the analysis of paper dating in ancient books, and proposes a non-destructive inspection and analysis method based on paper fiber texture images. Aiming at the global stacking morphology of paper fibers and the local features of specific types of fiber morphology, we propose a neural network-based hybrid texture feature extraction and representation method: On the one hand, we use convolutional networks to obtain global features of fiber texture; at the same time, we designed a method of extracting and representing local fiber morphological features based on the attention mechanism. By mixing the above two types of features, we realize the extraction and representation of paper fiber features. Furthermore, we use the GRU(Gate Recurrent Unit) model to establish a paper dating time series model and design a new loss function. In order to verify the method, this paper selects 36 domestic books published from 1950 to 2000, and uses the document checker VSC 6000 to collect paper texture images as a dataset, and verifies the effectiveness of the proposed method on this dataset. Experiments prove that the method proposed in this paper has achieved ideal results in paper dating analysis.

Currently, racial oil blotting papers are counted by hand. However, it takes a long time and this is hard work. Hence, an automatic counting system is necessary. In order to achieve this, we developed a cheap system using a webcam. This system firstly captures one image of arranged papers by shifting. Secondly, the paper boundaries are obtained as straight lines by utilizing the proposed image processing. By counting the acquired lines, the system outputs the number of papers. However, the captured image has noises such as the change of illumination and shadows. They make the extraction of the accurate boundaries difficult. For the accurate extraction, optimal parameters of the image processing must be set. Since the prediction of the optimal parameters in advance is difficult, the proposed method adopts genetic algorithm (GA). Also, Hough transformation for the straight line detection is improved. By applying the proposed method, the accurate paper counting is possible. For the experiment, 14 images were captured in various environments using a general webcam. Then, the proposed method was compared to a latest related work. As a result, F-measure of each method was 0.995 and 0.945.

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.

In the last several years, we published several papers to address the problem of Face Identification. The techniques employed in those articles were implemented in transform domains. The Discrete Cosine (DCT) and the Discrete Wavelet (DWT) Transforms were utilized, either combined or individually, to extract features which form the final model for each participant in a given dataset. In this paper, we highlight significant parts of our previous works in order to give a fair comparison among all approaches. The results included here are for the following datasets: ORL, YALE, FERET, FEI, Georgia Tech, and Cropped AR. Features are DWT, DCT, energy-based selected DCT-DWT, and combined DCT-DWT coefficients while the classifier is Euclidean distance, either squared or with power of one.

Visions have an important role in guiding and legitimizing technical research, as well as contributing to expectations of the general public towards technologies. In this paper we analyze technical robotics papers published between 1998 and 2019 to identify themes, trends and issues with the visions and values promoted by robotics research. In particular, we identify the themes of robotics visions and implicitly normative visions; and we quantify the relative presence of a variety of values and applications within technical papers. We conclude with a discussion of the language of robotics visions, marginalized visions and values, and possible paths forward for the robotics community to better align practice with societal interest. We also discuss implications and future work suggestions for Responsible Robotics and HRI research.

Even current OCR technology has made significant progress with the help of deep learning, rapid identification algorithms for specific information in documents still need elaborate design. In this paper, a lightweight operating framework based on deep neural network is established to deal with the extraction of date and time information from paper worksheets used in transformer station. In the framework, YOLOv4-Tiny is employed to detect the locations of the dates and the time in document images which are mixed with printing and handwritten fonts. Since the handwritten dates in pictures are difficult to segment, a novel lightweight CNN named MobileDateNet is proposed that can recognize the date serially without segmentation. The experimental results show that the identification accuracy of the whole framework reaches 92.1% at the average running speed of 36.5 FPS on an NVIDIA 3090 GPU, ensuring the recognition accuracy and the operating efficiency.

Forgery of paper invoices and certificates negatively causes huge economic loss every year. In the molding process of paper, plant fibres inside will distribute randomly and form the unique microscopic surface. Accordingly, forensic researchers have presented many techniques to build its feature descriptor for paper anti-counterfeiting. Among those methods, normal vector field and reconstructed surface based on multi-view photos captured by mobile camera have indicated incredibly effectiveness and practicality. However, the inefficiency of existing models using mobile camera is the neck in real time detection scenarios. In this paper, we focus on the efficient microstructure orientation estimation of paper surface for authentication. To address this problem, we investigate the reflection characteristics of rough surface and quantify the light attenuation accurately. Then, we model the entire propagation path of light emitted by flash, and exploit single photo captured by mobile camera to reconstruct microscopic inclination based on beam energy loss. Reduction of required pictures significantly enhances forensics efficiency. Through comparison experiments, we demonstrate that our proposed method can be used for paper discrimination effectively with speedy feature extraction.

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.

The experiment of quality assurance of polymeric outdoor insulators service life is necessary to be checked the class of wettability by using the digital image processing tools. The image processing can improve its pictorial information for human interpretation, render it more suitable for autonomous machine perception. This paper provides a survey of the recent technology and theoretical concept to explain the development of the Hydrophobicity Class (HC) of porcelain insulator. The hydrophobic properties of the housing material were found degraded to a different extent between field-aged insulators due to differences in material structure and pollution conditions. This paper contributes to the latest development of reviews relating to image processing for the implementation of porcelain insulator hydrophobic systems testing., and their related studies. We categorized the computer vision mainstream into 2 group such as Machine Learning Methods Applied to Digital Image Processing and Deep Learning Methods Applied to Digital Image Processing. Then compare pros/cons in each type of technique. We also provide brief explanation on the up-to-date information about the techniques and their performance.

In modern academic social network, it is very difficult for scholars to find academic papers consistent with their research direction. Time is a critical factor in paper recommendation. As time goes on, the impact of an academic paper would gradually fade. Likewise, the research interests of users may also change. Therefore, we propose a temporal perceptual neural collaborative filtering model that integrates the multi-dimensional features of papers. We conducted our experiments on the dataset from CiteULike, comparing the recommended results by using four time-decay functions and evaluating our model with multiple evaluation indicators. The satisfactory results show that our model is effective in filtering out the expired papers by considering the characteristics of papers and the changes of scholars' interests.

Summary models, whether extractive or abstractive, have achieved great success recently. For long academic papers, the abstractive model with the encoder-decoder architecture mainly only relies on the attentional context vector for generation, unlike humans who have already mastered the salient information of the source text to have full control over what to write. While the extracted sentences always contain the correct and salient information which can be used to control the abstraction process. Therefore, based on a hierarchical encoder-decoder architecture specifically for academic papers, we proposed a summary model with an Instructor, an encoder in essence by taking the guiding sentences as the input to further control the generating process. In the encoder part, the final hidden state from Instructor is directly added to the basic hierarchical hidden state from the encoder. Experimental results on arXiv/PubMed show that the only encoder-improved model can generate better abstract. In the decoder part, the context vector from Instructor is integrated with the original discourse-aware context vector for the generation. The results show that Instructor is effective for control and our model can generate a more accurate and fluent abstract with significantly higher ROUGE values.

In this paper, we propose a data augmentation framework for Optical Character Recognition (OCR). The proposed framework is able to synthesize new viewing angles and illumination scenarios, effectively enriching any available OCR dataset. Its modular structure allows to be modified to match individual user requirements. The framework enables to comfortably scale the enlargement factor of the available dataset. Furthermore, the proposed method is not restricted to single frame OCR but can also be applied to video OCR. We demonstrate the performance of our framework by augmenting a 15% subset of the common Brno Mobile OCR dataset. Our proposed framework is capable of leveraging the performance of OCR applications especially for small datasets. Applying the proposed method, improvements of up to 2.79 percentage points in terms of Character Error Rate (CER), and up to 7.88 percentage points in terms of Word Error Rate (WER) are achieved on the subset. Especially the recognition of challenging text lines can be improved. The CER may be decreased by up to 14.92 percentage points and the WER by up to 18.19 percentage points for this class. Moreover, we are able to achieve smaller error rates when training on the 15% subset augmented with the proposed method than on the original nonaugmented full dataset.

Lately, Deep Learning has indicated its capacity by adequately tackling complex learning issues which were not possible previously. Specifically, Convolutional Neural Networks are most generally utilized and have indicated their viability in image detection and recognition problems. Convolutional Neural Networks(CNN) can be used to perform different kinds of tasks. However, to recognize even a single image, billions of calculations are required. For example, ResNet 50 takes 8 billion calculations just to figure out what's in a single image. So we need to find out ways to be able to run that superfast and that's why we need hardware accelerators. In this paper the basic information about Convolutional Neural Networks is provided along with the key operations involved and the brief idea about Field Programmable Gate Arrays(FPGA) is given which enable them to be used for accelerating the inference process of Convolutional Neural Networks. Various techniques which were employed previously for accelerating the Convolutional Neural Networks are discussed. We are focussing on designing a energy efficient Field Programmable Gate Arrays accelerator for accelerating the inference process of Convolutional Neural Networks with reduced latency and increased throughput.

People re-identification is a fundamental stage in video surveillance systems. This stage is used for determining the labels of the people’s images usually based on their visual similarities. The appearance salience caused by wearing the clothes and carrying objects, with specific colors can be used for improving the performance of re-identification systems. To address the mentioned point, in this paper, we propose a color-based re-ranking process. In the proposed approach first, the input images are semantically segmented as: person’s body, possible carried objects, and background. Then the most frequent colors of person’s body and possible carried objects are used to re-order the ranked results obtained from two commonly used re-identification approaches i.e., Gaussian of Gaussian (GOG) and Hierarchical Gaussian Descriptors (HGDs). Experimental results on various people re-identification datasets show that our proposed re-ranking approach can improve the performance of re-identification systems.

Due to the increasingly growing demand for user identification on cell phones, PCs, laptops, and so on, face anti-spoofing has risen to significance and is an active research area in academia and industry. The detection of the real face then recognize it present an important challenge regarding the techniques that can be used to spoof any recognition system like masks, printed photos. This paper we present an anti-spoofing face method to solve the real-world scenario that learns the target domain classifier based on samples used for training in a particular source domain. Specifically, with the conventional regression CNN, the Spatial/Channel-wise Attention Modules were introduced. Two modules, namely the Spatial-wise Attention Module and the Channel-wise Attention Module, were used at spatial and channel levels to improve local features and ignore the irrelevant features. Extensive experiments on current collections with benchmarks datasets verifies that the recommended solution will significantly benefit from the two modules and better generalization capability by providing significantly improved results in anti-spoofing.

Drowsiness can be dangerous when performing tasks that require constant attention, such as driving a vehicle. Sleepiness is correlated with a variety of physiological variables, such as eye closing, head movements, pulse rate, eye twitch rate, etc. Also, the yawn can be considered as an accurate indicator of drowsiness and fatigue. Yawning detection is very important for the safety purpose of drivers as it will let the driver know if he/she is getting drowsy. Driving at that moment may not be safe. Several automatic yawning detection techniques have been developed for driver's drowsiness monitoring system. Nevertheless, correctly detecting the yawning of the driver and predicting exhaustion in real-time situations is still a crucial challenge. In this paper, we will be reviewing various existing machine learning approaches for driver's yawning detection. In previous approaches, various classical machine learning algorithms such as viola-Jones, contour activation algorithm and SVM have been used for yawning detection, but these approaches failed to predict yawning in realtime situations. Using Deep learning techniques, we can make a real-time yawn detection system with high accuracy. We find that some precious Deep learning algorithms like CNN, RNN, LSTM, Bi-LSTM can detect the patterns with high accuracy. After the comparison of various algorithms and techniques, we find that with the help of Deep learning algorithms the yawning can be detected in real time with high accuracy.

Human recogntion technologies are gaining significant research attention, where the model can be trained to be more precise to recognize the poses performed by objects. Activity identification is a kind of problem, which needs more research consideration and improvement. There is also an increasing need to detect different poses of objects. To tackle the issue, different sensors like Gyroscope and Accelerometer are required to classify the data in the form of images using machine learning algorithms like SVM and CNN. These approaches help us in implementing real-time applicaions such as health monitoring, tracking sports activity and security. The paper also discusses about its benefits, limitations and prominent approach for human activity recognition.

The written exam is a universal tool for evaluating student performance in the field of education. The written exam provides a mechanism by which instructors and organizations ensure the consistency of the assessment process. Human effort required for the assessment is very high and it depends on several factors such as knowledge of the teacher, application level understanding of the teacher, criteria of the marking and time allotted. However, traditional evaluation processes consume very costly efforts and take huge time for the completion of the complete evaluation, verification and publishing of the result process. This research introduces the design and implementation of Handwritten Answer Evaluation (HAES) system for student exam papers. The HAES is an automatic response assessment system that enables the identification of text in answer sheets and can evaluate the grade of each answer based on the previous knowledge of the model. In this study, Optical Character Recognition (OCR) tool is used to extract the text from human written scanned answer script and machine learning/natural language processing (NLP) techniques are used for grading the answer sheets. The scores are based on cosine set similarity measures, where each sentence in the evaluated answer paper carries their corresponding mark. The developed model can be used to evaluate the marks of the unscored descriptive answers.

In this paper, a method has been proposed for user profiling based on tweeter data. The sentiments of the tweets are retrieved programmatically with the help of WordNet and News Paper Archive. In this experiment, the English WordNet 2.1 has been used as an online semantic dictionary and machine readable version of the "Times of India" news paper has been used to generate a news paper archive. The algorithm is tested on a data set of 1000 tweets from four different categories which are initially tagged by their innate senses for validation of the derived result.First of all, the data set is evaluated with the help of newspaper archive by using lexical overlap and the accuracy in sense retrieval task is 48.7%. The reason behind this scenario is the varieties of representations of a single statement in natural language which creates a mare similarity between the lexical entities of the statements. To overcome this problem, the contexts of the tweets are expanded with the help of WordNet by considering the synonyms of every meaningful word of the tweets and after that the senses of these tweets are evaluated. As the contexts of the statements are expanded in this approach, semantic relatedness between the statements is resolved in an efficient way which leads the system towards a better performance.

As Machine Learning (ML) becomes pervasive in the era of artificial intelligence, ML specific tools and frameworks are required for architectural research. This paper introduces NeuroMeter, an integrated power, area, and timing modeling framework for ML accelerators. NeuroMeter models the detailed architecture of ML accelerators and generates a fast and accurate estimation on power, area, and chip timing. Meanwhile, it also enables the runtime analysis of system-level performance and efficiency when the runtime activity factors are provided. NeuroMeter’s micro-architecture model includes fundamental components of ML accelerators, including systolic array based tensor units (TU), reduction trees (RT), and 1D vector units (VU). NeuroMeter has accurate modeling results, with the average power and area estimation errors below 10% and 17% respectively when validated against TPU-v1, TPU-v2, and Eyeriss.Leveraging the NeuroMeter’s new capabilities on architecting manycore ML accelerators, this paper presents the first in-depth study on the design space and tradeoffs of “Brawny and Wimpy” inference accelerators in datacenter scenarios with the insights that are otherwise difficult to discover without NeuroMeter. Our study shows that brawny designs with 64x64 systolic arrays are the most performant and efficient for inference tasks in the 28nm datacenter architectural space with a 500mm2 die area budget. Our study also reveals important tradeoffs between performance and efficiency. For datacenter accelerators with low batch inference, a small $(\sim 16$%) sacrifice of system performance (in achieved Tera OPerations per Second, aka TOPS) can lead to more than a 2x efficiency improvement (in achieved TOPS/TCO). To showcase NeuroMeter’s capability to model a wide range of diverse ML accelerator architectures, we also conduct a followon mini-case study on implications of sparsity on different ML accelerators, demonstrating wimpier accelerator architectures benefit more readily from sparsity processing despite their lower achievable raw energy efficiency.

In this paper, the problem of intelligent test paper generation is discussed, and the advantages and disadvantages of current commonly used intelligent test paper generation algorithms are analyzed. By comparing genetic algorithm with ant colony algorithm, it is found that the two algorithms have complementary advantages and they can be integrated organically. On this basis, an intelligent test paper generating strategy based on hybrid genetic algorithm and ant colony algorithm is proposed. The experiments show that the convergence speed of hybrid test paper generating strategy is faster than that of single genetic algorithm and ant colony algorithm. Compared with single genetic algorithm and ant colony algorithm, the efficiency and success of hybrid test paper generating strategy are greatly improved, which has better practicability.

This paper is review on image fusion for different technique i.e. Non-subsampled Contourlet Transform (NSCT) and Neural Network (NN). NSCT is the pyramid structure and gives the multiscale feature of the image. NSCT used to directional filtering structure and used to filter bank. Neural network is a progression of calculations that tries to perceive fundamental connections in a bunch of information through an interaction that impersonates the manner in which the human mind works. The implemented algorithm will applied to MRI image and with the help of NN to calculated accuracy. The previous algorithm was work of different technique i.e. principal component analysis, discrete wavelet transorm and curvelet transform. The implemented algorithm will implement MATLAB software and calculate mean square error and peak signal to noise ratio.

This paper proposes an intelligent cockpit based on artificial intelligence technologies such as voice recognition ASR, TTS, NLP, and multi-round dialogue. The cockpit monitors the progress of the distribution network virtual dispatcher and analyzes the decision engine, and replays the virtual dispatcher online. The implementation process and thinking progress of the virtual dispatcher are overall monitored, and the online monitoring and safety monitoring of the operating personnel are supported.

In this invited paper, applications for Machine Learning (ML) in several areas of semiconductor manufacturing and test are reviewed and potential opportunities are discussed.

The rapid growth of Internet technologies and further dependence on online services, increase the demand for keeping these networks and data secure. The protection of online information is becoming even more vital to the national security and economic stability. Recently, network security has become one of the most concerning subjects in the current research and industry fields. Intrusion Detection Systems (IDSs) are considered as the backbone for network and data protection. Throughout time, different IDS approaches have been implemented to attain maximum detection accuracy. Machine learning IDS is one of the promising IDS techniques that have been created to detect known as well as unknown attacks. This paper investigates various machine learning techniques used to deploy Network-based Intrusion Detection System (NIDS). This survey could provide a more robust understanding of the existing techniques and assists intrigued researchers to identify research opportunities and investigate more in this direction.

In order to automate the task of correcting handwritten subjective answers, we envision a system that reads such answers and grades them. In this project, we have created a mobile application to achieve this task. We have used the RAKE algorithm to extract key-phrases, which are then embedded using Word2vec model and compared using Word Mover's Distance. Our created model achieved almost human like evaluation accuracy. We have also provided accessibility features to the users with the aim of making this application a one-stop solution to automatic evaluation of handwritten subjective answers.

Sentiment analysis and opinion mining have developed significantly throughout the last decades. This study aims to assess, amongst many other aspects, people's feelings, opinions, and emotions of someone or something. This review's principal objective is to automatically assess the direction of the review and contrast this with the evaluation made by the reviewers. This will allow scientists to categorize and evaluate reviews cross-sectionally and encourage a scientific article's overall evaluation more critically. An EM-VC ensemble approach has been proposed for analyzing the reviews. This approach uses POS to achieve a syntactic sentence structure. With dictionaries, this syntactic structure enables the semantic orientation of the analysis via the scoring algorithm to be determined. To test the proposed approach's efficiency and performance about the baseline method, some tests have been performed using typical performance metrics like precision, accuracy, F1-score, and recall. The findings reveal that improvements are achieved in binary classification, ternary classification, & five-point classification compared to the existing HS-SVM method. Still, it provides a slight improvement in accuracy in the context of multiclass classification compared to others.

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.

In my talk I will discuss the AI and brain-computer interface (BCI) technologies overview in the context of integration with robotic and biological systems starting from classical Rosenblatt perceptron till current breaking through technologies of BCI that could change the scientific outlook of the field. This is what we currently broadly call now AI and neurotechnology. Two bright examples are ResNet inspired by the projections of a mammalian cortical column and U-Net with close to ResNet ideas and topology. The other interesting cortical column inspired NN architecture is hierarchical temporal memory introduced by the Numenta company. These brain or neuro inspired approaches are widely used in machine learning, computer vision, natural language processing, path planning and broader in robotics.In the neurotechnology field I want to reference a lot of interesting and projects dedicated to BCI. Starting from works of Miguel Nicolelis where researchers connected the robotic hand via a computer system with a motor cortex of a monkey and later Lebedev group demonstrated the adaptation of a mammalian brain to create the representation of robotic limb extending biological limbs. I want to pay the special attention to works of Kevin Warwick that implemented invasive nervous system to nervous system interface and the robot managed by neurons of a rat brain developed and trained during the experiment.The commercial company Neuralink recently demonstrated the most advanced 1536-channel BCI exploiting wireless Blue-tooth interface to record and process a brain activity. Elon Musk in his Neuralink presentation last year demanded that one of the nearest goals of the company is spinal cord injury and the recovery of the lost motor control of limbs. Several projects in neurorehabilitation targeted to the motor control demonstrated recently important success using medical programmed neurostimulators.The perspective but currently in early state of the development is the direction of neurosimulation based models that could be used for the robotic system control (exoskeleton) or as neuroprosthesis as the part of closed loop system for example projects simulating the spinal cord, where I can see interesting future opportunities both in medicine and robotics.

The aim of this work is to classify the dementia stage using microstructural white matter (WM) diffusion kurtosis indices. We develop various class imbalance machine learning methods in classifying the cognitive normals (CN), Alzheimer's disease (AD) and mild cognitive impairment (MCI) individuals. Diffusion-weighted images of 155 subjects were collected with 44 CN, 88 MCI and 23 AD individuals aged between 60 to 96 years. We first perform skull striping using FSL tool along with head motion and artifact correction. We calculate the mean diffusivity, fractional anisotropy from various brain regions of WM indices from diffusion kurtosis imaging (DKI) using tract based spatial statistics. Then we estimate the kurtosis fractional anisotropy of various WM regions. After estimation of all the regional KFA indices, we trained these indices using various class imbalance machine learning classification algorithms, as the sample size is different in all the three groups. We found that balanced random forest classifier was the best classifier with an accuracy of 74% when compared to other methods for 5-fold cross-validation. We conclude that class imbalance machine learning methods are potential in classifying cognitive normals, AD and cognitive impairment individuals.

In autonomous driving, 3D object detection is es-sential as it provides basic knowledge about the environment. However, as deep learning based 3D detection methods are usually computation intensive, it is challenging to support realtime 3D object detection on edge-computing devices in selfdriving cars with limited computation and memory resources. To facilitate this, we propose a compiler-aware pruning search framework, to achieve real-time inference of 3D object detection on the resource-limited mobile devices. Specifically, a generator is applied to sample better pruning proposals in the search space based on current proposals with their performance, and an evaluator is adopted to evaluate the sampled pruning proposal performance. To accelerate the search, the evaluator employs Bayesian optimization with an ensemble of neural predictors. We demonstrate in experiments that for the first time, the pruning search framework can achieve real-time 3D object detection on mobile (Samsung Galaxy S20 phone) with state-of-the-art detection performance.

Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-of-Memory (OOM) problem limit the successful application of GNN on edge computing platforms. To tackle these problems, a feature decomposition approach is proposed for memory efficiency optimization of GNN inference. The proposed approach could achieve outstanding optimization on various GNN models, covering a wide range of datasets, which speeds up the inference by up to 3×. Furthermore, the proposed feature decomposition could significantly reduce the peak memory usage (up to 5× in memory efficiency improvement) and mitigate OOM problems during GNN inference.

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.

With the advances in information technologies, different research areas are emerging day by day and thousands of research papers are published in these fields. Papers are not presented to users grouped according to their topics. Therefore, it is getting harder and harder for people to access research papers in their field of interest. To facilitate this search process, a paper classification system is proposed in this study to categorize papers on similar topics. A different approach from the studies presented for classification so far has been proposed. This system is a complex system created by combining Word2vec, network modeling and community discovery. With the Word2vec method, which has attracted great attention recently, paper similarities have been found, a network based on similarity rates has been created and papers have been clustered with the community discovery algorithm. As a result of the application with the proposed system, a success of 89% has been achieved. As can be seen from the results, this approach presented for an important classification problem will provide great convenience to people. It will enable fast and efficient access to papers.

In this paper, we present a plug and play Rock-Paper-Scissors game set that utilizes CNN-based static hand gesture recognition and a Markov chain-based bot. Each game round, the camera output is fed to the neural network and the hand gesture result is compared to the current Markov chain state. We utilize a CNN trained with a dataset containing rock-paperscissors hand gestures and unwanted inputs, and a multi-state Markov chain. Automated tests confirm the bot prediction capabilities and practical tests verify the precision of static hand gesture recognition. Tests against a verification dataset reveal a recognition accuracy of 97.4%.

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.

In the context of papers used in the graphic arts, including silver gelatin, inkjet, and wove papers, prior work has studied measures of texture similarity for purposes of classifying such papers. The majority of prior work has been based on classical image processing approaches such as Fourier, wavelet, and fractal analysis. In this work, recent advances in deep learning are used to develop a texture similarity approach for measuring paper texture similarity. Since the available datasets generally lack labels, the convolutional neural network is trained using triplet loss to minimize the feature distance of tiles from the same image while simultaneously maximizing the feature distance of tiles drawn from different images. The approach is tested on three paper texture image databases considered in prior works and the results suggest the proposed approach achieves state-of-the-art performance.

Anti-counterfeiting technique is a research hotspot in information security domain. Common techniques are usually based on artificial physical cloneable feature which is forgeable. In this paper, we proposed an anti-counterfeit method based on microscopic translucent texture of paper (MTTP). MTTP is image of internal fiber pattern of paper (IFPP) captured by microscope under translucent light source. The IFPP has property of uniqueness and randomness, and the fiber scale of IFPP is at sub-micron or micron level. Then the IFPP is unable to be forged. Furthermore, fiber texture in IFPP is stable under disturbances (including illumination intensity change and surface damage), which guarantees the stability of the MTTP. Experiment results show that the authentication accuracy achieve 100% in our dataset (totally 13,4550 pairs of MTTPs) and the false reject rate achieves the order of magnitude of 10-136 in ideal condition and 10-59 even in condition of illumination change or surface damage. Above results indicate that our method has rather high security and reliability.