Search

The NIST selection process for standardizing Post-Quantum Cryptography Mechanisms is currently running. Many papers already studied their theoretical security, but the resistance in deployed device has not been much investigated so far. In particular, fault attack is a serious threat for algorithms implemented in embedded devices. One particularly powerful technique is to use safe-error attacks. Such attacks exploit the fact that a specific fault may or may not lead to a faulty output depending on a secret value. In this paper, we investigate the resistance of various Post-Quantum candidates algorithms against such attacks.

Researchers from academia and the corporate-sector rely on scholarly digital libraries to access articles. Attackers take advantage of innocent users who consider the articles' files safe and thus open PDF-files with little concern. In addition, researchers consider scholarly libraries a reliable, trusted, and untainted corpus of papers. For these reasons, scholarly digital libraries are an attractive-target and inadvertently support the proliferation of cyber-attacks launched via malicious PDF-files. In this study, we present related vulnerabilities and malware distribution approaches that exploit the vulnerabilities of scholarly digital libraries. We evaluated over two-million scholarly papers in the CiteSeerX library and found the library to be contaminated with a surprisingly large number (0.3-2%) of malicious PDF documents (over 55% were crawled from the IPs of US-universities). We developed a two layered detection framework aimed at enhancing the detection of malicious PDF documents, Sec-Lib, which offers a security solution for large digital libraries. Sec-Lib includes a deterministic layer for detecting known malware, and a machine learning based layer for detecting unknown malware. Our evaluation showed that scholarly digital libraries can detect 96.9% of malware with Sec-Lib, while minimizing the number of PDF-files requiring labeling, and thus reducing the manual inspection efforts of security-experts by 98%.

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

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

© 2013 IEEE. With the rapid growth of scientific publications, it is hard for researchers to acquire appropriate papers that meet their expectations. Recommendation system for scientific articles is an essential technology to overcome this problem. In this paper, we propose a novel low-rank and sparse matrix factorization-based paper recommendation (LSMFPRec) method for authors. The proposed method seamlessly combines low-rank and sparse matrix factorization method with fine-grained paper and author affinity matrixes that are extracted from heterogeneous scientific network. Thus, it can effectively alleviate the sparsity and cold start problems that exist in traditional matrix factorization based collaborative filtering methods. Moreover, LSMFPRec can significantly reduce the error propagated from intermediate outputs. In addition, the proposed method essentially captures the low-rank and sparse characteristics that exist in scientific rating activities; therefore, it can generate more reasonable predicted ratings for influential and uninfluential papers. The effectiveness of the proposed LSMFPRec is demonstrated by the recommendation evaluation conducted on the AAN and CiteULike data sets.

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.

The pervasive use of software systems and current threat environment demand that software systems not only survive cyberattacks, but also bounce back better, stronger, and faster. However, what constitutes a modern software system? Where should the security and resilience mechanisms be-in the application software or in the cloud environment where it runs? In this concept paper, we set up a context to pose these questions and present a roadmap to answer them. We describe challenges to achieving resilience and beyond, and outline potential research directions to stimulate discussion in the workshop.

Cloud computing is a new paradigm. In recent years, cloud computing has been a popular model for hosting and providing services, as it has gained great popularity in providing multiple services such as storage and cloud hosting. Moreover, the cloud provides a powerful computing platform that enables many individuals and organizations to perform many tasks such as: use of online storage space, approval on business applications, developing custom computer software, and creating a virtual network environment. In previous years, the number of people using cloud services increased dramatically and a lot of data was stored in cloud computing environments. Meanwhile, data breaches of cloud services are also increasing every year due to hackers who are always trying to exploit security holes in the cloud architecture, so the security problems in these systems are horrific because they store a lot of private and confidential data. In this paper, the authors review security and privacy issues, bottlenecks associated with cloud computing, and the specific security issues in cloud computing layers and vulnerabilities, and how to avoid and control them. This paper helps the reader understand the problems related to cloud computing.

Critical flaws continue to exist at the level of domain, requirement, and/or design specification, and specification verification (i.e. to check whether a specification has desirable properties) is still one of the most important challenges in software/system engineering. CafeOBJ is an executable algebraic specification language system and domain/requirement/design engineers can write proof scores in CafeOBJ for improving quality of specifications by the specification verification. This paper describes advances of the proof scores for the specification verification in CafeOBJ from the author’s point of view.

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.

The emerging of information technology (IT)and operational technology (OT) convergence has driven the smart grid technology adoption in the European (EU) energy system for better visibility and automated controllability. On the other hand, the energy system infrastructures can be threaten by the cyber attacks due to the increasing of information and communication technology integration. The cyber vulnerabilities are caused by the increasing of internet connection and the application complexities. It is crucial to identify essential skills in the field of cyber security protection and defense for the students. This paper presents the outcome of a literature review and a workshop with stakeholders from industry and academia about the state of the art and trends in the education of cyber security in smart grids.

Coarse-grained reconfigurable arrays (CGRAs) are programmable hardware platforms that can be used to realize application-specific accelerators for higher performance and energy efficiency. A CGRA is a 2D array of configurable logic blocks & interconnect, where the logic blocks are typically large & ALU-like, and the interconnect is word-wide. CGRA-ME is a software framework that enables the modelling and exploration of CGRA architectures, as well as research on CGRA CAD algorithms. With CGRA-ME, an architect can specify a CGRA architecture at a high level of abstraction. A set of applications can be mapped onto the architecture to assess the mappability, power, performance and cost. CGRA-ME also allows one to generate synthesizable Verilog RTL for the modelled CGRA, permitting its implementation as an ASIC or FPGA overlay. In this paper, we describe the CGRA-ME framework [5] and overview its capabilities and current limitations. We discuss ongoing and prior research conducted with the framework, as well as outline future plans. We believe CGRA-ME will be a valuable contribution to the community, enabling new research on CGRA CAD & architectures.

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.

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.

Conventional research trend detection methods require a large number of papers to perform analysis, while the trends detected are usually retrospective and cannot represent the emerging topic which is in embryonic stage, because detection method based on word features or citation relationships have to wait for the trend to come into form and become popular to detect it. Besides, the acquisition of paper full text is usually costly. We employ the paper metadata, which is relatively easy to acquire and process, to detect potentially valuable papers in specific field once the papers are published or their metadata become accessible and extract emerging cutting-edge trend from them. By comparing the result with conventional methods, we prove the effectiveness of the method.

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 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.

As the connectivity of autonomous vehicles keeps growing, it is an accepted fact that they are even more vulnerable to malicious cyber-attacks. Recently, sensor spoofing has become an emerging attack that can compromise vehicle safety as vehicles are equipped with more sensors. Thus, it is critical to validate the sensor readings before utilizing them for future actions. In this paper, we develop HDAD, a hyperdimensional computing-based anomaly detection method. Hyperdimensional computing (HDC) is an emerging brain-inspired computing paradigm that mimics the brain cognition and leverages hyperdimensional vectors with fully distributed holographic representation and (pseudo)randomness. The key idea of HDAD is to use HDC to build encoder and decoder to reconstruct the sensor readings. The anomalous data typically have comparatively higher reconstruction errors than normal sensor readings. We explore three different metrics to measure the reconstruction error including mean squared error, mean absolute error, and cosine similarity. Using a real-world vehicle sensor reading dataset, we demonstrate the feasibility and efficacy of HDAD, opening the door for a new set of anomaly detection algorithm design.

Improper Input Validation (IIV) is a software vulnerability that occurs when a system does not safely handle input data. Even though IIV is easy to detect and fix, it still commonly happens in practice. In this paper, we study to what extent developers can detect IIV and investigate underlying reasons. This knowledge is essential to better understand how to support developers in creating secure software systems. We conduct an online experiment with 146 participants, of which 105 report at least three years of professional software development experience. Our results show that the existence of a visible attack scenario facilitates the detection of IIV vulnerabilities and that a significant portion of developers who did not find the vulnerability initially could identify it when warned about its existence. Yet, a total of 60 participants could not detect the vulnerability even after the warning. Other factors, such as the frequency with which the participants perform code reviews, influence the detection of IIV. Preprint: https://arxiv.org/abs/2102.06251. Data and materials: https://doi.org/10.5281/zenodo.3996696.

Wireless communication base stations have strong requirements in flexibility, performance and real-time responsiveness. Building an application-specific lightweight LibOS on a general OS is a good technique to make a balance among real-time responsiveness, performance and flexibility. Compared to traditional ext-kernel systems, the fast progress of virtualization technology brings a more efficient implementation of LibOS. In this paper, we propose a virtualization assisted real-time LibOS system named Tenma for wireless Baseband Unit (BBU). In Tenma, lightweight process virtualization, enhanced isolation between host OS and guest OS, interrupt direct-pass and application specific lightweight scheduling are used to guarantee the requirements of performance and real-time responsiveness while keeping system flexibility. The Tenma system is already in commercial deployment. Experiments in practice prove that it can meet the requirements of wireless base station applications.

Constantly increasing botnets powered by vulnerable IoT devices perform record-breaking DDoS attacks to critical infrastructures. Therefore, it is imperative to find vulnerabilities in IoT devices ahead of attackers. In this paper, we first present a systematic analysis on various kinds of IoT malware to further explore the challenges of IoT Honeypot design. We then propose HoneyIoT, a scalable IoT Honeypot framework, which aims at attracting IoT attacks and recording malicious behaviors with configurable vulnerabilities and firmware support. During a 7day real-world industrial experiment, HoneyIoT observed over 12,500 malicious connections and 3,423 distinct login attempts.

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.

The security of software systems relies so heavily on the use of secrets, ranging from credentials, API keys, and tokens to secret keys for cryptographic security. This paper examines approaches for managing and handling secrets in software development life cycle, focusing on mobile applications where software must be distributed to devices and operate in an untrusted environment. This paper points out the shortcomings in activities related to secrets management and handling in mobile application development life cycle and outlines future directions in this area of research.

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.

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.

With the rapid development of virtual reality technology and new media technology, virtual reality panoramic news has become an emerging form in news communication. In this paper, by studying the feasibility of virtual reality panoramic news, designing the implementation scheme of virtual reality panoramic news for sports events through Unity3D, establishing a news dissemination effect evaluation system and quantitatively evaluating the sports news in this paper, the results show that the virtual reality panoramic news dissemination technology has a better dissemination impact.

With the huge amount of published research papers, retrieving relevant information is a difficult task for any researcher. Effective clustering algorithms can help improve and simplify the retrieval process. Here, we propose an approach for automatic clustering for text document using a Self-Organizing Map (SOM). It is one of unsupervised artificial neural network that widely used for data analysis, data compression, clustering, and data mining. The quality and accuracy of a SOM algorithm depends on the selection of values for some of its parameters which are its initial learning rate, SOM matrix dimensions, and the number of iterations. Best values are typically selected using trial and error; however, in the current paper we suggest a more systematic approach to parameters optimization using the genetic algorithm. The proposed method is applied to cluster 3 scientific papers datasets using their keywords. Similar research papers were mapped closer to each other. Clustering results were validated using the Dunn index.

In today's scenario cloud computing in growing concept in the computer and information technology field for storing the data. Because on the physical storage device whatever the huge amount of data which is sensitive or confidential that cannot be stored. So the cloud computing comes into the picture for storing the data as per their requirement. But if we store the data on cloud it will be easily accessible to all and the confidentiality of that data is not maintained. So for that purpose we are going make the data on the cloud to be secure with the help of cryptography. In this Paper we talk about earlier work in this field of encryption algorithm and the key issues for encrypting the data and decoding the data in cloud environment and proposed the objectives for improving the encryption algorithm and key issues which would help to store the data in cloud environment securely and efficiently. The paper proposed the defined objectives for the secrecy of the data in the storage of cloud computing environment which is the main aspect of our paper.

Cryptography is wide domain with many subs. The objective of this review paper is to give light review for readers and students of the three common used algorithm two in symmetric cryptography DES, AES and one in asymmetric cryptography RSA. Allowing the reader to have simple understanding of the background history of the algorithm in review and the key functional cipher operation of the algorithm. Accordingly summary of strength and weakness of each algorithm under the review will be highlighted. And how the security goals is such confidentiality and integrity are achieve using the mentioned algorithms. The paper will sequentially list and review the said algorithms and clarify the relational between them. Such as the relation between the symmetric and asymmetric algorithm the one with secret key and the ones with key pairs. The paper may insight some of the research window for upcoming scholar research in the field of cryptography.

Under the background of information society, it is a necessary means to protect and inherit Intangible Cultural Heritage to promote the artistic value and economic value of paper engraving art by introducing digital display technology such as virtual reality. This thesis starts with the common features extraction of paper-engraving art in the Han nationality area of China, and puts forward the basic principles of systematization, integrity and extensibility for the design of digital interactive display platform for Intangible Cultural Heritage paper-engraving, and expounds the design strategy of digital interactive display platform from five aspects: user requirement analysis, data classification, two-dimensional and three-dimensional elements reconstruction, platform building and interactive design and user feedback. The Digital Interactive Platform of paper engraving based on virtual reality technology gives the viewer the best immersion and interactive experience, which is helpful to better understand its cultural essence and has very important application value for the inheritance of paper engraving art.

Several applications can benefit from recording information about the places a mobile entity visits and the length of time it spends there (e.g., shoppers, employees, buses, movable equipment, autonomous robots, etc.). In this paper, we present our approach to recording spatio-temporal information in a secure and inviolable way using a Distributed Ledger Technology. So far in this work, we observe that, although sending data to the blockchain is a heavy process, there are ways that this transaction time does not disrupt the flow of new data such as adding these data to a queue. However, this makes the sending process overall longer. We intend to continue this study by testing different blockchain services and comparing their performances.

Facing the difficulty and inefficiency of creating and maintaining High-Definition (HD) maps in our commercial deployments, we have developed an edge-based crowdsourcing task distribution framework for HD Map in autonomous driving. Our key observation is that: HD map data crowdsourcing exhibits the diminishing marginal utility thus there exists an inflection point for maximum utility, meanwhile its premature convergence of utility will leave some map updates not notified in time. Based on this observation, we develop a periodic crowdsourcing task distribution framework. It discretizes the demands for collecting source data into different periods and uses an optimal stopping rule to terminate the data collection for the maximum crowdsourcing utility. The experimental results verify that our crowdsourcing framework can achieve high time coverage and high efficiency with lower cost.

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.

As a fundamental component in the autonomous driving technology stack, High Definition Maps (HD map) provide high-precision descriptions of the environment. It enables extremely accurate perception and localization while improving the efficiency of path planning. However, the HD map’s extremely large data volume poses great challenges for the real-time and safety requirements of autonomous driving. Based on our real-world deployment experiences, we first demonstrate how the existing data transmission mechanism is weak in supporting HD map services. To address this problem, we propose an HD map data service mechanism on top of Vehicle-to-Infrastructure (V2I) data transmission under a tight time and energy budget. By this mechanism, the selected road side unit (RSU) nodes cooperate on map provisioning tasks and transmit HD map data proportionately. Furthermore, we model the real-time map data service into a partial knapsack problem and develop a greedy data transmission algorithm. Experimental results confirm that the proposed mechanism can ensure the real-time HD map data service meanwhile meeting the energy limits.

Virtual Reality (VR) and 360 film have caught the attention of audiences and content creators and emerged as a new media, however, the market penetration of VR and head mounted hardware has remained slow despite the availability of more affordable mobile options. This has resulted in some audiences turning to VR cinemas, festivals and out-of-home exhibitions. Creating affordable, scalable VR cinemas presents a number of challenges and many of the decisions taken in both developing and facilitating these curated exhibitions directly impact audience's reception of spatial audio soundtracks. This workshop position paper looks to discuss the potential issues and future solutions in the use of current synchronous exhibition applications, the competing formats, standardised Head Related Transfer Functions, headphone build/colourisation, and the on-boarding process.

We develop and commercialize autonomous machines, such as logistic robots and self-driving cars, around the globe. A critical challenge to our—and any—autonomous machine is accurate and efficient localization under resource constraints, which has fueled specialized localization accelerators recently. Prior acceleration efforts are point solutions in that they each specialize for a specific localization algorithm. In real-world commercial deployments, however, autonomous machines routinely operate under different environments and no single localization algorithm fits all the environments. Simply stacking together point solutions not only leads to cost and power budget overrun, but also results in an overly complicated software stack.This paper demonstrates our new software-hardware co-designed framework for autonomous machine localization, which adapts to different operating scenarios by fusing fundamental algorithmic primitives. Through characterizing the software framework, we identify ideal acceleration candidates that contribute significantly to the end-to-end latency and/or latency variation. We show how to co-design a hardware accelerator to systematically exploit the parallelisms, locality, and common building blocks inherent in the localization framework. We build, deploy, and evaluate an FPGA prototype on our next-generation self-driving cars. To demonstrate the flexibility of our framework, we also instantiate another FPGA prototype targeting drones, which represent mobile autonomous machines. We achieve about $2 \times$ speedup and $4 \times$ energy reduction compared to widely-deployed, optimized implementations on general-purpose platforms.

Now a days due to the development in color printing technology the rate of counterfeit notes production and distribution is increasing. This is a massive problem, faced by almost all the countries. It affects the economy, sine it compromises the security of the real economy. Such counterfeit currencies are used to fuel nefarious motives, usually involving terrorist activities. According to the research, developing countries like India have been impacted by this very negatively. Even after the steps taken in 2016 to remove the counterfeits, by executing the demonetization of 500 and 1000 rupees bank notes in India the counterfeits of the new notes have begun circulating. This is due to the highly advanced technology adopted by the counterfeiters which makes the tracking of these counterfeit notes hard. This has become a very critical issue and the negative impact due to the counterfeit currency keeps rising. The only one solution for this problem for a common man is to detect the fake currency, by using the fake currency detector machine. These machines are used in banks and large scale business, but for a small business or for a common man these machines are not affordable. This paper gives the complete methodology of fake note detector machine, which is affordable even for a common man. By implementing the applications of image processing techniques we can find out whether the currency notes are fake or not. Image processing technique consists of a number of operations that can be performed on an image, some of which include image segmentation, edge detection, gray scale conversion etc. The proposed system will have advantages like simplicity, reliability and costs less.

Computing machines, it seems, have been becoming more deeply embedded in our lives. Today, this alliance with computers is taking shape as competition with robots for jobs that are becoming increasingly mechanized, be it on the smart factory floor, or next to hospital beds, or humanoid robots making elderly Japanese laugh, or even cognitive cooking. Should we be concerned at this development or just think of this as another agricultural revolution or Gutenberg’s printing press revolution with a bonanza of benefits in retrospect? What about human-robot cooperation, could that be a happy medium? Or, are machines destined to take over more facets of our lives at work and at play, like the sensors monitoring our sleep patterns and helping to improve sleep quality. Would you consider scenarios like some of the ones mentioned above to be a threat or an entry ramp to utopia? Some questions to think of: What are the jobs where robots can or should have only a marginal role? Where can man and machine work together? How do we guarantee that the machine stays tamed? Does AI pose an existential threat?

In the present work, the 48 input-output data points of the paper mill process have been considered with the desired machine speed as the input and required total head as the output. The data has been taken from the literature. Two clustering techniques are applied on this data using MATLAB. One is the FCM (fuzzy C-means clustering), another is the subtractive clustering. In present work, initial FIS (fuzzy inference system) developed by subtractive clustering is further optimized to improve its performance, and finally their responses are compared.

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.

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