Search

Prediction and detection of skin diseases have always been a challenging and critical task for health care professionals. There are many clinics and skin practitioners who are offering their services at exorbitant costs. At the same time, skin condition prevails in our country in every part. In the current scenario majority of the skincare practitioners are using traditional methods to diagnose the disease which may take a considerable amount of time. Skin Diseases are serious problems in recent times as it is a matter of environmental factors, socioeconomic factors, lack of full diet, etc. This paper is a comparative study about understanding various skin diseases related to normal skin issues as well as cosmetology. A comparison between oily, dry, and normal skin is also projected in this study. A survey of different papers is done on basis of technologies used, results with accuracy, ethical conduct, number of diseases diagnosed, datasets, etc are done.

This paper describes approaches to the use of wearables and related monitoring and diagnostic tools to glean and present data to patients and their caregivers in the form of Personal Health Dashboard. Raw data from devices such as fitness watches, blood glucose and blood pressure monitors can be analyzed by machine learning algorithms ensembles over the cloud or at the edge, and the resulting patterns can be presented to allow for actionable responses. The advent of low-cost computational, sensing, monitoring and diagnostic tools allow for cost-effective solutions that can have wide adaptability. The paper draws from prior and ongoing research conducted by the team to present these positions in the advancement of healthcare.

Basic repair and maintenance tasks of industrial machines are usually performed by local service personnel at the location of the component to be maintained. Complex maintenance tasks require an expert who travels to the customer to solve a specific problem. This process is time and cost intensive. Augmented Reality (AR) Remote Assistance offers means to support newcomers on site by guiding personnel through the maintenance process with novel visualizations. This paper describes an Augmented Reality based remote assistance tool for industrial purposes. We present the technology and our implementation approach, as well as the challenges and limitations we have encountered. The potential of the tool was evaluated and analyzed in an industry oriented use case for repairing an industrial PC. The results were compared with a maintenance procedure that was carried out using standard paper repair instructions. Our approach enabled the users to perform complex tasks faster and with fewer errors. Overall, the error rate decreased significantly due to the AR-based remote support. We also found that paper-based instructions are still more efficient in solving simple tasks.

This paper describes a user identification method conducted across online social networks (OSNs) using information regarding friends’ locations, in contrast to a conventional method based on the similarity of two display names. This latter method encounters the problem of decreased identification accuracy if a user registers different display names across OSNs. Our proposed method aims at addressing this issue by utilizing information on friends’ locations. We convert location information extracted from an OSN to that of such geographic administrative units as country, state and city, and calculate the weighted occurrence frequency of a location pair on the basis of distance between the pair. This is based on the hypothesis that a friend list relatively rarely includes an account pair whose locations are extremely distant from one another. We calculate a similarity score between two accounts’ weighted occurrence frequencies for each geographic administrative unit. Finally, we identify a user on the basis of individual similarity scores or weighted average scores for a given geographic administrative unit. Evaluation experiments show that our proposed method improves performance over that of a conventional method (accuracy: 83.1%$\rightarrow$91.2%).

The exchange of academic marks between HEIs (Higher Education Institutions) is mandatory in every student mobility programs (i.e. the EU Erasmus Program) but that process remains to present date with insufficient technological support and the absence of a comprehensive reference model that allows the integration of potential technological solutions for the exchange of academic data with existing Academic Information Systems seems to limit greatly the possibility of adopting solutions of this type referred to in the existing literature. This work addresses this issue, conducting an initial bibliographic review aimed at the identification of the fundamental requirements of such an architecture as well as explores some of the technologies that are showing potential for usage in the safe exchange of academic results between partner HEIs, with particular interest in blockchain technology applied in an educational context. info:eu-repo/semantics/publishedVersion

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.

Tight assembly of stator windings with no insulation paper damage is a manufacturing challenge. We evaluate different sets of parts according to the following parameters: magnet wire thickness, stator slot smoothness, length of the straight magnet wire after the slot end, and type and amount of insulation cap at the end of the slot. These parameters have discrete values with small differences between them. The damage criterion is the decrease of the insulation paper breakdown voltage after assembly/disassembly of parts, assembled in a small set of designed experiments. Parameter values, i.e., levels at individual experiments are set by an orthogonal experiment matrix. Repetition of each experiment provides statistical significance. Data analysis shows that the additive model alone is not sufficient due to the high correlation of the parameters’ influences. We extend the model to include interparameter influences, which we model by adding a virtual parameter. The extended additive model generates parameter values that do not degrade the insulation paper breakdown voltage within the manufacturing process. These values are verified by repetitions of the control experiment.

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.

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

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

Focusing on the automatic production scheduling of the ratio of waste paper in a paper mill, the research target was minimizing the purchase cost of waste paper under multiple constraints. Having divided, the field data (mixing ratios of waste paper and pulp properties) into the training and validation data sets, the scheduling ratios of waste paper were optimized. Firstly, from the point of view of the average pulp properties and the variances, the predicted results proved that the BP-NN predicted model accuracies of the pulp properties with the mixing ratio of waste paper were better than those of SVM and GA-SVM. Secondly, the minimization of the purchasing costs of waste paper under some constraints were obtained with the BP-NN predicted model and the non-dominated sorting genetic algorithm (NSGAII), Comparing with the general GA in the previous study, the scheduling results improved the pulp brightness by 9.24%, and reduced the purchasing costs of waste paper by 2.16%.

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.

At present, the protection, inheritation, innovation and development of intangible cultural heritage in China are facing more severe opportunities and challenges. In order to overcome the shortcomings of too rigid and conservative expression, and poor interactive of traditional digital means, the virtual reality (VR) technology is applied to the protection and inheritance of the paper-cut art in this paper. Firstly, a variety of paper-cut basic symbols are put into a database, and then the paper-cut symbols are summarized. Now we put them into computer aided design software of CDDataBase, and we can use CorelDRAW for graphic expression and artistic design. Secondly, the virtual digital museum display system is constructed by using the 3D model database. At the same time we can create a digital platform for Mangshi Dai paper-cut art, in order to maximize the utilization of resources and sharing. Finally, using WeChat, weibo, community sites and other mediums of the Web platform to connect digital Dai paper-cut art with social docking platform can make public deeply understand Dai paper-cut arts. So the VR technology can achieve wide protection and inheritance of Dai paper-cut art.

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.

The rapid advance in science and technology is made possible by research conduct and breakthroughs in a wide range of fields, which have resulted in a large number of academic papers. Searching through the enormous literature to find relevant information of one's research interest has become an increasingly important yet challenging problem for many researchers. Most existing methods for academic paper recommendation are based on the analysis of paper contents and only meet with limited success. We propose a novel method based on heterogeneous information networks for academic paper recommendation, referred to as HNPR. This method considers the citation relationship between papers, the collaboration relationship between authors, and the research area information of papers to construct two types of heterogeneous information networks. In such networks, a random walk-based strategy is used to simulate natural sentences for the discovery of relevance between two papers according to a mature natural language processing model. Extensive experimental results using real data in public digital libraries show that HNPR significantly improves the accuracy of academic paper recommendation in comparison with traditional content-based recommendation methods.

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.

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.

Nowadays, in this digital word text is one the vital knowledge carrier. Text can be perceived as structure of symbols which is accustomed to convey, transfer, or inherit civilization and way of life. It is among the major influential novelties of man kind; text performs crucial role in existence of human being. Text can be seen in all places in our day-to-day life. Thus, obtaining data from text which is present in scenarios of our day-to-day life is important. Processing the text that is present in natural scenario has two primary tasks namely Text identification and Text acknowledgment. The method of taking out text body from the natural scene is called as Text detection whereas the procedure of categorizing the characters from scene image which form expressive words is called as Text recognition. There are so many applications of scene text detection in different fields, e.g., intelligent inspection, blind navigation, industrial automation, automotive assistance, robot navigation, instant translation, automatic driving and product search, etc. Thus, street view text detection and recognition have allured rising research consideration in past few years. This paper as first step focuses on Text detection methods for natural scene images.

In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems. Choosing the algorithm and hyperparameter setting correctly can promote the overall performance greatly, but users often fail to do so due to the absence of knowledge. How to help users to effectively and quickly select the suitable algorithm and hyperparameter settings for the given task instance is an important research topic nowadays, which is known as the CASH problem. In this paper, we design the Auto-Model approach, which makes full use of known information in the related research paper and introduces hyperparameter optimization techniques, to solve the CASH problem effectively. Auto-Model tremendously reduces the cost of algorithm implementations and hyperparameter configuration space, and thus capable of dealing with the CASH problem efficiently and easily. To demonstrate the benefit of Auto-Model, we compare it with classical Auto-Weka approach. The experimental results show that our proposed approach can provide superior results and achieves better performance in a short time., 12 pages, 3 figures

In this paper we present a novel method to print paper and cardboard without ink. The method is based on the carbonization of paper by a combination of lasers working on different wavelengths. A prove of concept system is created based on combining existing commercial systems to demonstrate the viability of the method. The results show that no debris is generated and the quality of the mark is superior in terms of contrast and resolution with previously known methods.

Sentiment Analysis is done by gathering the data, analyzing the text and aggregating the words in the text. The main focus of this survey is on the evaluation methods used and their respective core solutions. In this paper we are going to study the aspect based sentiment classification, which is classified into three. Those are Implicit, Explicit and Coreferential aspect based sentiment classification. In this paper we are also going to elaborate the polarity of the reviews into positive and negative sentiments. Aspect Based Classification not only promises to suppress the noisy data but also provides high efficiency in identifying the aspects with an addition of performing classification task with higher accuracy. This accuracy can be achieved by using Neural Network algorithms.

Edge environments are generating an increasingly large amount of data due to the proliferation of edge devices. Accommodating this large influx of data at edge servers is a challenging issue. While some data can be processed as it is generated, others must be stored for later access. This paper proposes the features that a new edge-native storage system must possess including support for user mobility and node fluctuation. To motivate this, we first describe several emerging edge applications and their data needs. We then describe the challenges in meeting these needs. We then evaluate an out-of-the-box cloud storage system, Cassandra, to assess it’s suitability as an edge storage system due to many edge-friendly features. We determined that while a cloud-based storage system can be ported to the edge meeting some of the challenges, other challenges require new solutions. Based on the challenges and the results of Cassandra case study, we propose a set of design principles for a new edge-native storage system.

Deep neural networks (DNNs) have been successfully applied to a great variety of applications, ranging from small IoT devices to large scale services in a data center. In order to improve the efficiency of processing these DNN models, dedicated hardware accelerators are required for all these scenarios. Theoretically, there exists an optimized acceleration architecture for each application. However, considering the cost of chip design and corresponding tool-chain development, researchers need to trade off between efficiency and generality. In this work, we demonstrate that it is practical to use a unified architecture, called Ascend, to support those applications, ranging from IoT devices to data-center services. We provide a lot of design details to explain that the success of Ascend relies on contributions from different levels. First, heterogeneous computing units are employed to support various DNN models. And the datapath is adapted according to the requirement of computing and data access. Second, when scaling the Ascend architecture from a single core to a cluster containing thousands of cores, it involves design efforts, such as memory hierarchy and system level integration. Third, a multi-tier compiler, which provides flexible choices for developers, is the last critical piece. Experimental results show that using accelerators based on the Ascend architecture can achieve comparable or even better performance in different applications. In addition, various chips based on the Ascend architecture have been successfully commercialized. More than 100 million chips have been used in real products.

Communication modules and display devices are required to display and provide dynamic information at bus stops. Conventional bus stops provide bus users delay information and sightseeing information by combining cellular network with bulletin board, a liquid crystal panel, electronic paper (hereinafter referred to as “e-paper”), etc. However, there are many cases in which the visibility of information drops significantly depending on the amount of information of the content displayed on the bus stop and the specification of the display device to be adopted. In this paper, we describe the design of a smart bus stop that can use responsive web design and display optimized content on e-paper with different specifications with one source, and the evaluation results of the smart bus stop implemented with prototype.

The study aimed to realize the automatic production scheduling of waste paper in paper mills. Based on the quantities of the field data (mixing ratios of waste paper and pulp properties) stored in a paper mill, the methods of back propagation neural networks (BP-NN) and support vector machine (SVM), the all data set and the average data set, were firstly applied to develop the prediction models of the pulp properties; and then the genetic algorithm was used to search for the suitable scheduling solutions. The simulation results revealed that: demonstrating its acceptable prediction accuracy and fast training time, the prediction model with SVM method and the average data set was good enough to be used in the genetic algorithm to search for the optimal scheduling ratios of waste paper, the obtained optimal scheduling solution not only had the lowest purchase cost of waste paper, but also met the requirements of the mill: specified types of waste paper, specified ratio of some kind of waste paper and the required pulp brightness.

Pervasive Social Networks of Strangers are available constantly, connecting users directly with no preexisting relationships. Such networks demand a high level of privacy, as users should be anonymous and their behaviour unlinkable. However, the anonymity of users could lead to abusive messages, spam, or fraud. A possible solution is to keep track of users' reputations, based on feedback from other users. However, the need to collate feedback on user behaviour to form reputations is at odds with the need for privacy. Anonymous and unlinkable feedback is also required, whilst multiple feedbacks given on the same item should be detected. To resolve this, we use group signatures and direct anonymous attestation, to give a reputation-based messaging scheme.

International audience; A configuration of antenna using flexible substrate for RF energy harvesting system working at GSM frequency 1800 MHz is presented. The suspended structure is used to surpass the high loss of the substrate. By taking advantage of the flexible properties, the process of miniaturization is achieved through folding the substrate into sections. The antenna prototypes were fabricated and measured. With the compact size of 0.36 λ × 0.33 λ × 0.03 λ, the measured gain is 5.3 dB, about 10 dB gain increase compared to conventional structure.

In order to improve the security of medical data, this paper uses a robust and secure dual watermarking technique in RDWT-SVD domain. Dual watermarking is achieved by embedding text watermark in medical watermark image using DWT, generating the final watermark. Before embedding, turbo code is used to encode the text watermark. Further, trade-off between imperceptibility and robustness is controlled in our scheme through firefly optimization. Experimental results indicate the proposed method offers high imperceptibility and robustness, and have superior overall performance.

The main interest of this paper is concept of Compressive Sensing and its application in 1D biomedical signals. The accent is on analyzing several types of biomedical signals and finding domain in which they are sparse. Therefore, we use gradient-based algorithm to reconstruct these biomedical signals with different number of samples. By working with gradient-based algorithm, we presented reconstruction of Electrocardiogram, Electroencephalogram and Electromyogram biomedical signals and drew a conclusion about differences between them. Several sparsifying basis are tested in order to find the most suitable one, for specific signal type, and we verified the whole theory by experimental results.

This paper introduces the time stamped bijective MAC algorithm (bMAC), which aims at proving firmware integrity in embedded systems. bMAC computes a MAC over a set of memories, in a pseudo random way relying on a permutation. It is based on exponential permutations that induce computing time distributions. Because bMAC performs calculations on SRAM content, it can be bound to physical chips, by means Physical Unclonable Functions (PUF), extracted from SRAM.

Based on the sequential batch reactor (SBR) simulation model of the wastewater treatment process for a secondary fiber paper mill that we have developed, two control strategies, a neural network (BP-PID controller) and a fuzzy logic system (Fuzzy-PID controller), were separately combined with PID to control the dissolved oxygen (DO) concentration in the SBR process of paper mill. Two cases, without and with the presence of noise, have been studied and evaluated using the criteria considered in BSM1. For the case without noise, both two-control strategies demonstrated better control indices than that of the traditional PID control; for the case with noise, the Fuzzy-PID controller possessed the good control indices at almost the same expense of aeration energy. The results under two cases showed that the Fuzzy-PID controller demonstrated better performance than that of BP-PID controller, in the DO control of SBR process in the paper mill, Fuzzy-PID controller improved the control performance without increasing the aeration energy consumption.

The design and engineering of solutions based on sensor data is currently based on legacy low-level sensor communication. The transition to IoT-based sensors has started to provide IP-based sensor communication based on service concepts. This requires radically different solution architectures and the associated engineering process. Here, IoT sensors will provide services instead of a communication interface, as a means of integrating into application solutions. It is further anticipated that the size of the solution will reach well beyond that of the current legacy automation implementations.This paper addresses architectural concepts for very large-scale SoS- and IoT-based solutions. Architecture concepts and their associated engineering concepts are considered. IoT and SoS evolvability, run-time dynamics, scalability and segmentation, run-time engineering, self-engineering, self-mitigation, and machine-to-machine business are some examples of such concepts. These concepts must be coupled with the requirements such as the management of IoT/SoS solution functionality, security, safety, maintenance, and evolution.

The article deals with the problem of organizing student achievement control using an online testing based on the Plickers software. It is established that schools’ teachers in Sumy region (Ukraine) and future mathematics teachers (Makarenko Sumy State Pedagogical University, Ukraine) are mostly unfamiliar with such technology. The usefulness of modernizing the content of educational curricular and master classes for working teachers to integrate the testing technology by using the mobile application Plickers into the educational process is confirmed. The article describes the process of preparation and experience of organizing an online testing of future mathematics teachers by using Plickers based on the study of the discipline "Mathematical logic and theory of algorithms". The advantages and disadvantages of using such a tool in the educational process are noted. The results of the effectiveness of the use of Plickers in the educational process are given.

We discuss the Post Quantum Cryptography algorithms for key establishment under consideration by NIST for standardization. Three of these, Crystals- Kyber, Classic McEliece and Supersingular Isogeny based Key Encapsulation (SIKE), are representatives of the three classes of hard problems underlying the security of almost all 69 candidate algorithms accepted by NIST for consideration in round 1 of evaluation. For each algorithm, we briefly describe the hard problem underlying the algorithm's cryptographic strength, the algebraic structure i.e., the groups or finite fields, underlying the computations, the basic computations performed in these algorithms, the algorithm itself, and the performance considerations for efficient implementation of the basic algorithm on conventional many-core processors. For Crystals- Kyber and SIKE, we will discuss the potential solutions to improve their performance on many-core processors.

A secure medical image watermarking framework using SVD, DE, step space filling curve and IntDCT is proposed. The proposed algorithm starts with partition of the host medical image into 8×8 blocks and then IntDCT is applied in each block. By collecting integer DC coefficients, a feeble resolution medical image is obtained. SVD is applied on this feeble resolution image. For maintaining a strong relationship between imperceptibility and robustness, the popular differential evolution (DE) technique is chosen to examine the most suitable scaling factors. The singular values of the host image are modified with the singular values of the watermark to insert the watermark in the host image. Here, DE is playing a very important role to determine the most suitable scaling factors to the embedded process for maintaining the dilemma between robustness and imperceptibility without degrading the nobility of medical images. To increase the security of the watermark image, first it is scuffled with the help of step space filling curve before the embedding process. The experimental observations and results proved the efficiency of the proposed framework. It maintains the quality of the watermarked images and the watermark can be extracted from the seriously malformed images.

Steganography is the art of hiding a secret message inside a publicly visible carrier message. Ideally, it is done without modifying the carrier, and with minimal loss of information in the secret message. Recently, various deep learning based approaches to steganography have been applied to different message types. We propose a deep learning based technique to hide a source RGB image message inside finite length speech segments without perceptual loss. To achieve this, we train three neural networks; an encoding network to hide the message in the carrier, a decoding network to reconstruct the message from the carrier and an additional image enhancer network to further improve the reconstructed message. We also discuss future improvements to the algorithm proposed.

In recent times, Generative Adversarial Networks (GANs) have created a lot of buzz in the research community. GANs are formulated on the zero-sum game theory, where two neural nets compete against each other. The resultant deep model is capable of generating data similar to any data distribution provided. It utilizes the adversarial learning approach and is far more capable in learning features than the traditional machine learning models. This review focusses on the origin and evolution of GANs. Firstly, the traditional GAN is explored in terms of its structure and loss functions. Then come the common challenges of training GANs. Thirdly, the review dives into numerous GAN variants and explains their improvements. The review then lists the wide variety of applications and ends with the conclusion.

We present a mathematical technique for using Hermite functions to reconstruct various types of images. Even though the functions are not orthogonal, they can be used in image processing. The functions permit us to get good localization of the signals and it is shown that we get better reconstructed image quality for a larger number of Hermite functions used. Finally, we use a Hermit function frame to decompose and reconstruct a few types of images and compare the results for various number of Hermit functions.

The IP is a primary data plane protocol on the Internet, which has several deficiencies when addressing the needs of modern digital society involving machine-to-machine communication and a remarkably enhanced user experience. New IP is an advanced network protocol specification to modernize the network layer without changing the fundamental Internet architecture. New IP envisions a new header format with 3 functional characteristics, i.e., shipping spec, contract spec, and payload spec. Using these fundamental blocks, New IP proposes a new data plane forwarding paradigm with far more advanced capabilities, such as ManyNets addressing, high precision services and qualitative communications.

As designs grow in size and complexity, design verification becomes one of the most difficult and costly tasks facing design teams. Formal verification techniques offer great promise because of their ability to exhaustively explore design behaviors. However, formal techniques also have a reputation for being labor-intensive and limited to small blocks. Is there any hope for successful application of formal techniques at design scale? We answer this question affirmatively by digging deeper to understand what the real technological issues and opportunities are. First, we look at satisfiability solvers, the engines underlying formal techniques such as model checking. Given the recent innovations in satisfiability solving, we argue that there are many reasons to be optimistic that formal techniques will scale to designs of practical interest. We use our CoSA model checker as a demonstration platform to illustrate how advances in solvers can improve scalability. However, even if solvers become blazingly fast, applying them well is still labor-intensive. This is because formal tools are only as useful as the properties they are given to prove, which traditionally have required great effort to develop. Symbolic quick error detection (SQED) addresses this issue by using a single, universal property that checks designs automatically. We demonstrate how SQED can automatically find logic and security bugs in a variety of designs and report on bugs found and efficiency gains realized in academic and industry designs. We also present a generator for an improved SQED module that further reduces the amount of manual effort that has to be spent by the designer.

Previous studies have confirmed that the insulation status of oil-paper transformer can be qualitatively analyzed by its time domain dielectric spectral characteristics. However, it is more important to evaluate the insulation condition of transformers quantitatively in engineering practice. An evaluation system based on characteristics obtained by the return voltage measurements is constructed in this paper for the quantitative evaluation of the insulation state of oil-paper transformers. First, data of characteristics of transformer are normalized and neighborhood radius of each characteristic are calculated. Then, the decision table of oil-paper insulation diagnosis system is generated based on neighborhood rough set theory. Moreover, attribute reduction is carried out to the decision table and the best rules are extracted. Finally, the oil-paper insulation state evaluation system is constructed based on the historical database. Five transformers of known insulation status have verified the accuracy of the evaluation system.

The rapid mainstream adoption of cloud computing and the corresponding spike in the energy usage of big data systems make the efficient management of cloud computing resources a more pressing issue than ever before. To this end, numerous online algorithms such as Receding Horizon Control and Online Balanced Descent have been designed. However it is difficult for cloud service providers to select the best control algorithm dynamically for resource provisioning when confronted with consumer resource demands that are notoriously unpredictable and volatile. Furthermore, it highly possible that it might not be the case for any one algorithm to consistently perform well over the months-long contract period. In this paper, we first exemplify the need to address non-stationarity in cloud computing by showcasing traces from MS Azure. We then develop a novel meta-algorithm that combines change point detection and online optimization. The new algorithm is shown to outperform existing solutions in real-world trace-driven simulations.

Paraphrase extraction is the method of collecting words, phrases or sentences that have same meaning from free text or structured documents. Candidate monolingual pararel corpus was build from scientific papers by clustering techniques. The corpus contain couples of citation sentences that mention same index. The corpus evaluted using weighting techniques and proximity measurements based on the density of each sentence cluster. The results of this reserach are expected to simplify paraphrase labeling by language and computer science experts.

Now a days with the advancement of technology Internet of Things(IOT) has grown up day by day to cater the need of variety of applications in various domains such as consumer applications, smart homes, medical andhealthcare, transportation, home automation, agriculture and many more. IOT may be considered as things or object connected to internet. The name Internet of Things was coined by Kevin Ashton and it was name so as multiple of technologies like sensors embedded systems, wireless sensor network(WSN), control system and machine learning contributed in making the concept of IOT. This paper presents a survey on different architectures of IOT and their challenges like wear ability, security, privacy etc.

Autonomous cyber-physical systems-such as self-driving cars and autonomous drones-often leverage artificial intelligence and machine learning algorithms to act well in open environments. Although testing plays an important role in ensuring safety and robustness, modern autonomous systems have grown so complex that achieving safety via testing alone is intractable. Formal verification reduces this testing burden by ruling out large classes of errant behavior at design time. This paper reviews recent work toward developing formal methods for cyber-physical systems that use AI for planning and control by combining the rigor of formal proofs with the flexibility of reinforcement learning.

Fully convolutional neural networks have shown remarkable success in performing semantic segmentation. The use of convolutional layers for the entire architecture and skip connections to combine different resolution features or predictions have been adopted in successful networks, such as U-Net and DenseNet. However, these models employ several max-pooling layers that cause the network to lose spatial information and require them to mimic an autoencoder architecture to perform semantic segmentation at the original input resolution. In this paper, we propose a network that extracts features automatically with convolutional layers, like the fully convolutional neural network, but retains the spatial information of each of the extracted features. It then utilises the extracted features to make predictions with an efficient upsampling method. We evaluate the network performance on a liver segmentation task where it performs with comparable accuracy to other state-of-the-art networks while being much smaller in terms of the number of parameters as well as faster in computation time.

In this paper, we imaged the retina of wild-type and the triple-transgenic mouse model of Alzheimer’s disease (3xTg- AD) with optical coherence tomography to assess changes in the retinal tissue associated with the Alzheimer’s disease. Texture analysis allowed to identify differences between groups at the age of four months, and to find biomarkers of disease progression. Furthermore, our findings suggest that specific layers of the retina may play a fundamental role in the assessment of early changes associated with the Alzheimer’s disease.

Data storage in the Cloud became a very popular service. However, delegation of data management results in loss of control from user perspective, in particular regarding the real location where data are stored. Thus, data location verification in the Cloud is a challenging issue. Among the huge methods proposed to consider data location verification, this paper focuses on machine learning based methods, which use network Round Trip Times as main metric. In particular, it provides experimental results based on country-wide dataset collected through Grid'5000 platform. Results show the capacities of regression-based methods to support data location verification at specific accuracy depending on user requirements.

Security requirements are the major reasons for secure software developments. Many methods, model and approaches have been designed by many researchers to ensure a correct built of security requirement. The security patterns approach aims to benefit security requirements by allowing requirement engineers who are not security experts to better identifying and understanding security concerns and leads to a correct implementation. In this study, we evaluate various security patterns that existed in Software Requirements Engineering. Based on a literature search conducted traditionally, we report our findings on classifying and structuring this security requirements patterns. Derived from this study, a future direction for our research is clarified.

With today’s eye-tracking technologies, it is possible to analyze cognitive processes such as reading. There are many studies on that topic. We have studied some of these studies that analyze eye movements recording during reading by various machine learning algorithms.