Search

In the tourism industry, the sales of local specialties is an important part, and the package design and integrity of the specialties are very important. This paper first introduced the support vector machine (SVM) algorithm that was used for detecting defects on the surface of paper packages. Then, the design of red wind packages was briefly described, and the simulation experiment was carried out on SVM algorithm using red wine packages with different degrees of surface defects. Proper parameters were tested using the k-fold cross-validation method. The results demonstrated that the properties of paper improved the value of packages and the SVM algorithm had better accuracy than artificial recognition in recognizing different degrees of defects on the surface of packages. In conclusion, this paper describes the application of paper in packages and provides an effective method for the defection of defects on the surface of packages. This study provides an effective references to the improvement of package values and the enhancement of package integrity.

International audience; This paper focuses on the problem of the hierarchical multi‐label classification of research papers, which is the task of assigning the set of relevant labels for a paper from a hierarchy, using reduced amounts of labelled training data. Specifically, we study leveraging unlabelled data, which are usually plentiful and easy to collect, in addition to the few available labelled ones in a semi‐supervised learning framework for achieving better performance results. Thus, in this paper, we propose a semi‐supervised approach for the hierarchical multi‐label classification task of research papers based on the well‐known Co‐training algorithm, which exploit content and bibliographic coupling information as two distinct papers' views. In our approach, two hierarchical multi‐label classifiers, are learnt on different views of the labelled data, and iteratively select their most confident unlabelled samples, which are further added to the labelled set. The success of our suggested Co‐training‐based approach lies in two main components. The first is the use of two suggested selection criteria (i.e., Maximum Agreement and Labels Cardinality Consistency) that enforce selecting confident unlabelled samples. The second is the appliance of an oversampling method that rebalances the labels distribution of the initial labelled set, which reduces the reinforcement of the label imbalance issue during the Co‐training learning. The proposed approach is evaluated using a collection of scientific papers extracted from the ACM digital library. Performed experiments show the effectiveness of our approach with regards to several baseline methods.

Proportional–Integral–Derivative controller technique continues to provide the easiest and effective solutions to most of the industrial applications in recent years. However PID controller is poorly tuned in practice compared to most other tuning methods and is complicated with poor performance. This research presents a multi objective optimization approach involving Genetic Algorithm, Evolutionary Programming, Particle Swarm Optimization and Bacterial foraging optimization. The proposed multi objective optimization algorithm is used to tune the PID controller parameters and their performances have been compared with the conventional methodologies like Ziegler Nichols method. The results proved that the use of multi objective optimization approach based controller tuning improves the performance of process in terms of time domain specifications and performance index, set point tracking and regulatory changes and also provides stability. This paper describes the various multi objective optimization algorithms and its implementation to tune the PID Controller used in paper machine DCS as real time processing of a Pulp and paper industry processes.

In this paper, we analyze the intelligent subdesign of the simulated marking system through an in-depth study of it. This paper proposes a correlation analysis-based quantification of N-element sense values and a rationality enhancement-based scoring fitting algorithm for English essays. This paper also extracts word features, sentence features, and chapter structure features in essays to fit English composition scores. Since not all students can complete the essays according to the topic requirements, a triage scoring model is used to separate the normal essays from the low-scoring essays. Statistically, it was found that the essay scores also showed a certain normal distribution. The standard support vector regression algorithm is prone to data skewing problems, so this paper addresses this problem by using a rationality enhancement method that gives a corresponding penalty factor according to the distribution of the dataset. The results show that the English essay scoring fitting algorithm proposed in this paper can well improve the prediction accuracy of some data and solve the problem of skewed data where the scores show a normal distribution. This paper designs and implements an online mock examination system that incorporates an intelligent scoring system for essays, enabling it to meet the needs of teachers and students for online examinations and intelligent scoring.

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.

Educational evaluation helps to improve the learning and teaching process. The learning process can be assessed by the examination system. In the examination system, the learners have to answer a set of questions. The learning assessment ensures improved performance in the educational system. The success of the learning assessment is highly dependent on the listening and understanding ability of each student. The assessment of the question paper can be at two levels—cognitive level assessment and difficulty level. The cognitive level assessment is purely based on Bloom’s Taxonomy and the difficulty level assessment is purely based on the examination marks of each student. This article presents a technical method called Question Paper’s Difficulty Level (QPDL) that helps to identify the difficulty level of each question in the question paper. The QPDL method is incorporate in the implementation of ‘QAUDIT’ web application to assess the difficulty level of the question paper systematically. The systematic analysis to identify the difficulty level of the question paper is made for 239 question papers. Each question paper can be recognized based on three difficulty levels such as High, Moderate and Low.

With the arrival of the Internet and social media, at the same time as masses of humans have benefitted from the full-size reassets of records available, there was an full-size boom with inside the upward push of cyber-crimes, mainly targeted closer to women. According to a 2019 file with inside the Economics Times, India has witnessed a 457% upward push in cybercrime with inside the 5 years span among 2011 and 2016. Most speculate that that is because of effect of social media inclusive of Facebook, Instagram and Twitter on our day by day lives. While those simply assist in growing a legitimate social network, advent of consumer debts in those websites normally desires simply an email-id. A actual lifestyles man or woman can create more than one fake IDs and for this reason impostors can effortlessly be made. Unlike the actual international state of affairs in which more than one policies and guidelines are imposed to become aware of oneself in a completely unique manner (as an instance at the same time as issuing one’s passport or driver’s license), with inside the digital international of social media, admission does now no longer require this kind of checks. In this paper, we study the one-of-a-kind debts of Instagram, specifically and try and verify an account as fake or actual the use of Machine Learning strategies specifically Logistic Regression and Random Forest Algorithm.

Paper-based digital microfluidic biochips (or P-DMFBs) are becoming highly impelling due to its low-cost and in-place fabrication of electrodes and control wiring on a single piece of paper having an inkjet printer and conductive ink. Despite enormous advantages, several complex design rules also subsist, such as avoidance of induced control interference, minimum separation among the control lines, and congestion-free wiring on a single layer, which is to be correlated leading toward overall feasibility of the design. Several cost raising issues, such as schedule length, control pin count, and wire length, must be considered for attaining a successful fluid-control codesign. Moreover, design gaps exist among the subtasks of the fluid level, control level, and fluid-control design as a whole, which undeniably impose expensive design cycles increasing overall cost. This article builds a machine learning-based model for the pin-constrained P-DMFBs to predict violation in control design beforehand and accordingly guides the fluid-control codesign to tackle important cost-driving issues while attaining congestion- and conflict-free wiring. This model effectively eliminates the design cycles producing a low-cost platform. The predictive model has been evaluated over a balanced data set. Several benchmarks for assessing the performance are studied.

Flying insect detection, identification, and counting are the key components of agricultural pest management. Insect identification is also one of the most challenging tasks in agricultural image processing. With the aid of machine vision and machine learning, traditional (manual) identification and counting can be automated. To achieve this goal, a particular data acquisition device and an accurate insect recognition algorithm (model) is necessary. In this work, we propose a new embedded system-based insect trap with an OpenMV Cam H7 microcontroller board, which can be used anywhere in the field without any restrictions (AC power supply, WIFI coverage, human interaction, etc.). In addition, we also propose a deep learning-based insect-counting method where we offer solutions for problems such as the “lack of data” and “false insect detection”. By means of the proposed trap and insect-counting method, spraying (pest swarming) could then be accurately scheduled.

Exam paper generation is an indispensable part of teaching. Existing methods focus on the use of question extraction algorithms with labels for each question provided. Obviously, manual labeling is inefficient and cannot avoid label bias. Furthermore, the quality of the exam papers generated by the existing methods is not guaranteed. To address these problems, we propose a novel approach to generating exam papers based on prediction of exam performance. As such, we update the quality of the initially generated questions one by using dynamic programming, as well as in batches by using genetic algorithms. We performed the prediction task by using Deep Knowledge Tracing. Our approach considered the skill weight, difficulty, and distribution of exam scores. By comparisons, experimental results indicate that our approach performed better than the two baselines. Furthermore, it can generate exam papers with adaptive difficulties closely to the expected levels, and the related student exam scores will be guaranteed to be relatively reasonable distribution. In addition, our approach was evaluated in a real learning scenarios and shows advantages.

Photographs are taken as valid evidences in various scenarios of our day to day life. Because of the developments in the field of Image Processing, altering images according to ones need is not a difficult task. Techniques of Image Forensics play its crucial role at this juncture. One of the mostly found types of image tampering is Copy-Move forgery. A copy-move forgery is performed by copying a region in an image and pasting it on another region in the same image, mostly after some form of post-processing like rotation, scaling, blurring, noise addition, JPEG compression etc. Two types of copy-move forgery detection techniques exist in literature. They are the Block based methods and Key-point based methods. Both the methods have their own advantages and limitations. This paper presents a survey on the recent developments in block based methods. As forgeries have become popular, the importance of forgery detection is much increased. Copy-move forgery, one of the most commonly used methods, copies a part of the image and pastes it into another part of the image. In this paper, we propose a detection method of copy-move forgery that localizes duplicated regions using Zernike moments. Since the magnitude of Zernike moments is algebraically invariant against rotation, the proposed method can detect a forged region even though it is rotated. Our scheme is also resilient to the intentional distortions such as additive white Gaussian noise, JPEG compression, and blurring. Experimental results demonstrate that the proposed scheme is appropriate to identify the forged region by copy-rotate-move forgery.

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.

Back within the 1950s, Minsky and McCarthy described AI as any task performed by a program or a machine that, if a person administered an equivalent activity, we can say that he had to use his intelligence to accomplish the task. Neural networks help us to train and process Machines. These are brain-inspired networks of interconnected layers, called neurons, that feed data into one another. During the training of those neural networks, the weights attached to different inputs will still be varied until the output from the neural network is extremely on the brink of what is desired, at which point the network will have 'learned' the way to perform a specific task. A subset of machine learning is deep learning, where neural networks are expanded into sprawling networks with an enormous number of layers that are trained using massive amounts of knowledge. It is these deep neural networks that have fuelled the present breakthrough within the ability of computers to hold out tasks like speech recognition and computer vision.

In this paper, we propose an end-to-end approach to addressing QRS complex detection and measurement of Electrocardiograph (ECG) paper using convolutional neural networks (CNNs). Unlike conventional detection solutions that convert images to digital data, our method can directly detect QRS complex in images using Faster-RCNN, then the R-peak can be located and measured through a CNN. Validated by clinical ECG data in the St.-Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database and real ECG paper from Peking University People’s Hospital, the proposed method can achieve the recall of 98.32%, the precision of 99.01% in detecting and 0.012 mv of mean absolute error in measuring. Experimental results demonstrate the superior performance of our method over conventional solutions, which would pave the way to detect and measure ECG paper using CNNs.

Laser-induced breakdown spectroscopy (LIBS) is an important analysis technique with applications in many industrial branches and fields of scientific research. Nowadays, the advantages of LIBS are impaired by the main drawback in the interpretation of obtained spectra and identification of observed spectral lines. This procedure is highly time-consuming since it is essentially based on the comparison of lines present in the spectrum with the literature database. This paper proposes the use of various computational intelligence methods to develop a reliable and fast classification of quasi-destructively acquired LIBS spectra into a set of predefined classes. We focus on a specific problem of classification of paper-ink samples into 30 separate, predefined classes. For each of 30 classes (10 pens of each of 5 ink types combined with 10 sheets of 5 paper types plus empty pages), 100 LIBS spectra are collected. Four variants of preprocessing, seven classifiers (decision trees, random forest, k-nearest neighbor, support vector machine, probabilistic neural network, multi-layer perceptron, and generalized regression neural network), 5-fold stratified cross-validation, and a test on an independent set (for methods evaluation) scenarios are employed. Our developed system yielded an accuracy of 99.08%, obtained using the random forest classifier. Our results clearly demonstrates that machine learning methods can be used to identify the paper-ink samples based on LIBS reliably at a faster rate.

Due to the increasing size of s (s), their design and optimization phases (i.e., ) grow increasingly complex. At design time, a large design space needs to be explored to find an implementation that fulfills all specifications and then optimizes metrics like energy, area, delay, reliability, etc. At run time, a large configuration space needs to be searched to find the best set of parameters (e.g., voltage/frequency) to further optimize the system. Both spaces are infeasible for exhaustive search typically leading to heuristic optimization algorithms that find some trade-off between design quality and computational overhead. ML can build powerful models that have successfully been employed in related domains. In this survey, we categorize how () may be used and is used for design-time and run-time optimization and exploration strategies of s. A meta-study of published techniques unveils areas in that are well-explored and underexplored with, as well as trends in the employed algorithms. We present a comprehensive categorization and summary of the state of the art on for. Finally, we summarize remaining challenges and promising open research directions.

The confluence of significant computational power and inexpensive sensors provides the opportunity to reliably collect large volumes of information from the world and extract humanly useful information resources. This paper reviews a coherent body of work over the last 20+ years focused on development of advanced bio-inspired computing techniques, and their applications primarily for human related data in behaviour and human centered computing. We close with a synthesis proposing an experiment analysis methodology combining these tools.

Paper recommendation is a research topic to provide users with personalized papers of interest. However, most existing approaches equally treat title and abstract as the input to learn the representation of a paper, ignoring their semantic relationship. In this paper, we regard the abstract as a sequence of sentences, and propose a two-level attentive neural network to capture: (1) the ability of each word within a sentence to reflect if it is semantically close to the words within the title. (2) the extent of each sentence in the abstract relative to the title, which is often a good summarization of the abstract document. Specifically, we propose a Long-Short Term Memory (LSTM) network with attention to learn the representation of sentences, and integrate a Gated Recurrent Unit (GRU) network with a memory network to learn the long-term sequential sentence patterns of interacted papers for both user and item (paper) modeling. We conduct extensive experiments on two real datasets, and show that our approach outperforms other state-of-the-art approaches in terms of accuracy.

Because of the cost and complexity of implementing an optical paper sorting system, the demand for an intelligent system for waste paper sorting has increased. This research focused on the development of a smart intelligent system (SIS) for recyclable waste paper sorting. The basis for selecting the regions of interests (ROIs) is the margin area of a paper object image because almost all printed documents keep the margin area intact. The paper grade is identified using a proximity search. The SIS with the HSI colour space offered maximum success rates of 99 %, 82 % and 89 %, while with the RGB model, the classification success rates were 94 %, 93 % and 98 % for white paper, old newsprint paper and old corrugated cardboard, respectively. The SIS is clearly superior to other prevailing techniques because of the faster decision making and lower cost of implementation.

In this paper, we propose a novel paper currency defect detection algorithm using quaternion uniform strength. We first build paper currency image preprocessing integration framework which includes intensity balancing, paper currency location, and geometric correction. We then propose a global–local paper currency image registration algorithm by moving key areas within certain range which can eliminate the false difference effectively. Finally, the quaternion uniform strength is calculated by using quaternion convolution edge detector. The defect degree of paper currency is determined by using the quaternion uniform color difference. The proposed algorithm is tested using different datasets from five countries: CNY, USD, EUR, VND, and RUB. The experimental results demonstrate that the proposed algorithm yields better results than the existing state-of-the-art paper currency defect detection techniques. The demo of the proposed paper currency defect detection algorithm will be publicly available.

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.

Function-as-a-Service (FaaS) has raised a growing interest in how to "tame" serverless to enable domain-specific use cases such as data-intensive applications and machine learning (ML), to name a few. Recently, several systems have been implemented for training ML models. Certainly, these research articles are significant steps in the correct direction. However, they do not completely answer the nagging question of when serverless ML training can be more cost-effective compared to traditional "serverful" computing. To help in this task, we propose MLLess, a FaaS-based ML training prototype built atop IBM Cloud Functions. To boost cost-efficiency, MLLess implements two key optimizations: a significance filter and a scale-in auto-tuner, and leverages them to specialize model training to the FaaS model. Our results certify that MLLess can be 15X faster than serverful ML systems [24] at a lower cost for ML models (such as sparse logistic regression and matrix factorization) that exhibit fast convergence.

Number plate recognition brings a drastic improvement for the city traffic enhancement. It provides the direction in which the steps should be taken for working of an effective intelligent transportation system. ANPR have become necessity for traffic control management due to rapid increment of vehicles. The main aim of ANPR is to monitor traffic and for security purpose. Recognition of number plate uses image processing techniques and latest technology in detecting characters on vehicle license plates automatically. In recent years, there are many technological developments in recognizing license plate area of research. Image processing protocols like OCR technology allow the traffic surveillance to deal with several problems that occurs in criminal investigation, toll collection, monitoring traffic, controlling speed, parking management etc. For efficient management of traffic and mass surveillance in transportation system, an ANPR system is essential. With the aid of image processing algorithms and vehicle images dataset, it becomes possible to monitor traffic at a large scale. Vehicle images are helpful for recognizing characters on license plates by performing image segmentation, feature extraction and character recognition. Data collected through captured images are utilized in the commercial applications, law enforcement, traffic applications etc. The software examines the vehicle picture as an input image that results in displaying the plate numbers. The system with image processing used reliably for traffic detection where modification of the technologies enables an accurate acknowledgement of vehicle number plates. There are several ANPR systems developed, working on character recognition of LP by the help of image processing technique. This paper reviews the performance by researchers in this particular area towards meeting goals of transportation system. It also provides major issues and challenges in this field.

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.

Automatic data processing represents the future for the development of any system, especially in scientific research. In this paper, we describe one of the automatic classification methods applied to scientific research as a supervised learning task. Throughout the process, we identify the main features that are used as keys to play a significant role in terms of predicting the new rank under the supervised learning setup. First, we propose an overview of the work that has been realized in ranking scientific research papers. Second, we evaluate and compare some of state-of-the-art for the classification by supervised learning, semi-supervised learning and non-supervised learning. During the preliminary tests, we have obtained good results for performance on realistic corpus then we have compared performance metrics, such as NDCG, MAP, GMAP, F-Measure, Precision and Recall in order to define the influential features in our work. Keywords: Scientific research, Ranking scientific research papers, Data mining, Supervised learning, Multilayer perceptron algorithm

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows easy integration, configuration, and combination of different methods and heuristics. This is demonstrated by embedding dozens of popular algorithms and evaluating them, from seminal works to the cutting edge of machine learning research. We show that with proper settings, classical solutions may still outperform the perceived state of the art. Besides establishing the actual state of the art, the conducted experiments reveal unexpected properties of Structure from Motion (SfM) pipelines that can help improve their performance, for both algorithmic and learned methods. Data and code are online https://github.com/vcg-uvic/image-matching-benchmark, providing an easy-to-use and flexible framework for the benchmarking of local features and robust estimation methods, both alongside and against top-performing methods. This work provides a basis for the Image Matching Challenge https://vision.uvic.ca/image-matching-challenge., Comment: Added: KeyNet-SOSNet, AffNet-HardNet, TFeat, MKD from kornia

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.

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.

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.

Automatically detecting the positions of key-points (e.g., facial key-points or finger key-points) in an image is an essential problem in many applications, such as driver's gaze detection and drowsiness detection in automated driving systems. With the recent advances of Deep Neural Networks (DNNs), Key-Points detection DNNs (KP-DNNs) have been increasingly employed for that purpose. Nevertheless, KP-DNN testing and validation have remained a challenging problem because KP-DNNs predict many independent key-points at the same time -- where each individual key-point may be critical in the targeted application -- and images can vary a great deal according to many factors. In this paper, we present an approach to automatically generate test data for KP-DNNs using many-objective search. In our experiments, focused on facial key-points detection DNNs developed for an industrial automotive application, we show that our approach can generate test suites to severely mispredict, on average, more than 93% of all key-points. In comparison, random search-based test data generation can only severely mispredict 41% of them. Many of these mispredictions, however, are not avoidable and should not therefore be considered failures. We also empirically compare state-of-the-art, many-objective search algorithms and their variants, tailored for test suite generation. Furthermore, we investigate and demonstrate how to learn specific conditions, based on image characteristics (e.g., head posture and skin color), that lead to severe mispredictions. Such conditions serve as a basis for risk analysis or DNN retraining., to appear in ISSTA 2021

The aim of this study was to examine the effects that reading on screens (using digital devices with different screen sizes) and on paper have on reading time and comprehension. The study group was...

Stream reasoning systems are designed for complex decision-making from possibly infinite, dynamic streams of data. Modern approaches to stream reasoning are usually performing their computations using stand-alone solvers, which incrementally update their internal state and return results as the new portions of data streams are pushed. However, the performance of such approaches degrades quickly as the rates of the input data and the complexity of decision problems are growing. This problem was already recognized in the area of stream processing, where systems became distributed in order to allocate vast computing resources provided by clouds. In this paper we propose a distributed approach to stream reasoning that can efficiently split computations among different solvers communicating their results over data streams. Moreover, in order to increase the throughput of the distributed system, we suggest an interval-based semantics for the LARS language, which enables significant reductions of network traffic. Performed evaluations indicate that the distributed stream reasoning significantly outperforms existing stand-alone LARS solvers when the complexity of decision problems and the rate of incoming data are increasing. Under consideration for acceptance in Theory and Practice of Logic Programming., Comment: 16 pages. Under consideration for acceptance in TPLP

We explored the paper augmentation technique where a tablet computer is placed under the paper to modify its content appearance and create the illusion of a static object appearing perceptually dynamic. Our approach is based on the Deformation Lamps (DL) technique commonly used with front projection. However, we applied it to rear projection, which removes the need for a fixed hardware setup or handling and wearing dedicated hardware. The key challenge was to ensure the appropriate mixing of light reflecting from the paper (to see what is printed on the paper) and the light passing though the paper (to see what the tablet screen is projecting) since (i) a tablet screen is a relatively weak light source when being used in rear projection and (ii) commonly, paper has high opacity so the content from one side is not visible on the other side. In order to achieve the appropriate mixing of light, we reduced the opacity of the paper by perforating it (thus allowing more light to pass through), and modified the algorithm for generating dynamic luminance animation by adding gamma and brightness correction. The outcomes provide a guide on how to modify the paper and the algorithm in order to achieve the DL effect with rear projection using a tablet computer.

Color 3D printing allows for 3D-printed parts to represent 3D objects more realistically, but its surface color quality evaluation lacks comprehensive objective verification considering printing materials. In this study, a unique test model was designed and printed using eco-friendly and vivid paper-based full-color 3D printing as an example. By measuring the chromaticity, roughness, glossiness, and whiteness properties of 3D-printed surfaces and by acquiring images of their main viewing surfaces, this work skillfully explores the correlation between the color representation of a paper-based 3D-printed coloring layer and its attached underneath blank layer. Quantitative analysis was performed using ΔE*ab, feature similarity index measure of color image (FSIMc), and improved color-image-difference (iCID) values. The experimental results show that a color difference on color-printed surfaces exhibits a high linear correlation trend with its FSIMc metric and iCID metric. The qualitative analysis of microscopic imaging and the quantitative analysis of the above three surface properties corroborate the prediction of the linear correlation between color difference and image-based metrics. This study can provide inspiration for the development of computational coloring materials for additive manufacturing.

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.

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).

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.

Using machine learning (ML) services, both service customers and providers need to monitor complex contractual constraints of ML service that are strongly related to ML models and data. Therefore, establishing and monitoring comprehensive ML contracts are crucial in ML serving. This paper demonstrates a set of features and utilities of the QoA4ML framework for ML contracts.

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

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

Industrial archived process data represent a convenient source of information for data-driven models, such as artificial neural network (ANN), that can be used for safety and efficiency improvement like early or even predictive fault detection and diagnosis (FDD). Nonetheless, most of the data used for model generation are representative of the process nominal states and therefore are not enough for classification problems intended to determine abnormal process conditions. This work proposes the use of techniques to augment the original real data standards, dismissing the need for experiments that could jeopardize process safety. It uses the Monte Carlo technique to artificially increase the number of model inputs coupled to the nearest neighbor search (NNS) by geometric distances to consistently classify the generated patterns in normal or faulty statuses. Finally, a radial basis function neural network is trained with the augmented data. The methodology was validated by a study case in which 3381 pulp and paper industrial data points were expanded to monitor the formation of particles in a recovery boiler. Only 5.8% of the original process data were examples of faulty conditions, but the new expanded and balanced data collection leveraged the classification performance of the neural network, allowing its future use for monitoring purpose.

Successful problem solving relies on the availability of suitable mental representations of the task domain. Especially for more complex problems, there might be a wide variety of possible problem representations, and it might even be beneficial to change them during problem solving. In a first part, we argue that investigating the dynamics of understanding in terms of dynamically changing problem representations is an underexplored aspect of problem solving research, and that most classic tasks even preclude the opportunity of such dynamics to occur. Continuing this theoretical discussion, as an illustrative example of a task designed for the exploration of such representational dynamics, the second part of the paper discusses a novel, complex spatial transformation and problem solving task. In this task, one is asked to repeatedly mentally cross-fold a sheet of paper, and to predict the resulting sheet geometry without the use of external aids. Through its deliberate openness and difficulty, this task requires finding new and more efficient representations – ranging from kinaesthetic and visuospatial imagery to symbolic notions. We present an overview of the task domain and discuss various ways of representing the domain as well as potential dynamics between them.

Literature reviews are essential for any researcher trying to keep up to date with the burgeoning software engineering literature. FAST$^2$ is a novel tool for reducing the effort required for conducting literature reviews by assisting the researchers to find the next promising paper to read (among a set of unread papers). This paper describes FAST$^2$ and tests it on four large software engineering literature reviews conducted by Wahono (2015), Hall (2012), Radjenovi\'c (2013) and Kitchenham (2017). We find that FAST$^2$ is a faster and robust tool to assist researcher finding relevant SE papers which can compensate for the errors made by humans during the review process. The effectiveness of FAST$^2$ can be attributed to three key innovations: (1) a novel way of applying external domain knowledge (a simple two or three keyword search) to guide the initial selection of papers---which helps to find relevant research papers faster with less variances; (2) an estimator of the number of remaining relevant papers yet to be found---which in practical settings can be used to decide if the reviewing process needs to be terminated; (3) a novel self-correcting classification algorithm---automatically corrects itself, in cases where the researcher wrongly classifies a paper., Comment: 20+3 pages, 6 figures, 5 tables, and 4 algorithms. Accepted by Journal of Expert Systems with Applications

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.

The quality of the final prints in electronic-shaft paper-folding machinesseriously influenced by the mechanical periodic disturbance. This paper takes the periodic shock-disturbance and sinusoidal disturbance in the electronic-shaft paper-folding machineas as the research objects. Disturbance observer is designed based on Propotional Integral Diffrential (PID) control algorithm. Firstly this paper establishes a model of the system with MTALAB system identification tools in the process of establishing the control system. Secondly,the paper inverses this established model. In order to approximate the mode and guarantee the stability of the inversed model, zero-phase error-tracking controller (ZPETC) has been designed to remove the instable zero-point of the original model. Finally, the paper constructs the disturbance observer of the established reversed model based on PID control algorithm. The simulation on experimental platform shows that the resistivity of paper-folding machine to the external disturbance has been improved impressively and the proposed PID algorithm disturbance observer has been proved can be used in periodic disturbance suppression in the electronic-shaft paper-folding machine.

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.

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.

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