Biblio

Fashion is the way we present ourselves which mainly focuses on vision, has attracted great interest from computer vision researchers. It is generally used to search fashion products in online shopping malls to know the descriptive information of the product. The main objectives of our paper is to use deep learning (DL) and machine learning (ML) methods to correctly identify and categorize clothing images. In this work, we used ML algorithms (support vector machines (SVM), K-Nearest Neirghbors (KNN), Decision tree (DT), Random Forest (RF)), DL algorithms (Convolutionnal Neurals Network (CNN), AlexNet, GoogleNet, LeNet, LeNet5) and the transfer learning using a pretrained models (VGG16, MobileNet and RestNet50). We trained and tested our models online using google colaboratory with Tensorflow/Keras and Scikit-Learn libraries that support deep learning and machine learning in Python. The main metric used in our study to evaluate the performance of ML and DL algorithms is the accuracy and matrix confusion. The best result for the ML models is obtained with the use of ANN (88.71%) and for the DL models is obtained for the GoogleNet architecture (93.75%). The results obtained showed that the number of epochs and the depth of the network have an effect in obtaining the best results.

This study develops a framework for personalized care to tackle heart disease risk using an at-home system. The machine learning models used to predict heart disease are Logistic Regression, K - Nearest Neighbor, Support Vector Machine, Naive Bayes, Decision Tree, Random Forest and XG Boost. Timely and efficient detection of heart disease plays an important role in health care. It is essential to detect cardiovascular disease (CVD) at the earliest, consult a specialist doctor before the severity of the disease and start medication. The performance of the proposed model was assessed using the Cleveland Heart Disease dataset from the UCI Machine Learning Repository. Compared to all machine learning algorithms, the Random Forest algorithm shows a better performance accuracy score of 90.16%. The best model may evaluate patient fitness rather than routine hospital visits. The proposed work will reduce the burden on hospitals and help hospitals reach only critical patients.

Cloud computing forms the backbone of the era of automation and the Internet of Things (IoT). It offers computing and storage-based services on consumption-based pricing. Large-scale datacenters are used to provide these service and consumes enormous electricity. Datacenters contribute a large portion of the carbon footprint in the environment. Through virtual machine (VM) consolidation, datacenter energy consumption can be reduced via efficient resource management. VM selection policy is used to choose the VM that needs migration. In this research, we have proposed PbV mSp: A priority-based VM selection policy for VM consolidation. The PbV mSp is implemented in cloudsim and evaluated compared with well-known VM selection policies like gpa, gpammt, mimt, mums, and mxu. The results show that the proposed PbV mSp selection policy has outperformed the exisitng policies in terms of energy consumption and other metrics.

The Internet of Vehicles (IoV) has a tremendous prospect for numerous vehicular applications. IoV enables vehicles to transmit data to improve roadway safety and efficiency. Data security is essential for increasing the security and privacy of vehicle and roadway infrastructures in IoV systems. Several researchers proposed numerous solutions to address security and privacy issues in IoV systems. However, these issues are not proper solutions that lack data authentication and verification protocols. In this paper, a blockchain-enabled automated data management system for vehicles has been proposed and demonstrated. This work enables automated data verification and authentication using smart contracts. Certified organizations can only access vehicle data uploaded by the vehicle user to the Interplanetary File System (IPFS) server through that vehicle user’s consent. The proposed system increases the security of vehicles and data. Vehicle privacy is also maintained here by increasing data privacy.

Building occupancy data helps increase energy management systems’ performance, enabling lower energy use while preserving occupant comfort. The focus of this study is employing environmental data (e.g., including but not limited to temperature, humidity, carbon dioxide (CO2), etc.) to infer occupancy information. This will be achieved by exploring the application of information theory metrics with machine learning (ML) approaches to classify occupancy levels for a given dataset. Three datasets and six distinct ML algorithms were used in a comparative study to determine the best strategy for identifying occupancy patterns. It was determined that both k-nearest neighbors (kNN) and random forest (RF) identify occupancy labels with the highest overall level of accuracy, reaching 97.99% and 98.56%, respectively.

Existing anomaly detection models show success in detecting abnormal images with generative adversarial networks on the insufficient annotation of anomalous samples. However, existing models cannot accurately identify the anomaly samples which are close to the normal samples. We assume that the main reason is that these methods ignore the diversity of patterns in normal samples. To alleviate the above issue, this paper proposes a novel anomaly detection framework based on generative adversarial network, called ADe-GAN. More concretely, we construct a self-supervised learning task to fully explore the pattern information and latent representations of input images. In model inferring stage, we design a new abnormality score approach by jointly considering the pattern information and reconstruction errors to improve the performance of anomaly detection. Extensive experiments show that the ADe-GAN outperforms the state-of-the-art methods over several real-world datasets.

In recent years, generative adversarial networks (GAN) have become a research hotspot in the field of deep learning. Researchers apply them to the field of anomaly detection and are committed to effectively and accurately identifying abnormal images in practical applications. In anomaly detection, traditional supervised learning algorithms have limitations in training with a large number of known labeled samples. Therefore, the anomaly detection model of unsupervised learning GAN is the research object for discussion and research. Firstly, the basic principles of GAN are introduced. Secondly, several typical GAN-based anomaly detection models are sorted out in detail. Then by comparing the similarities and differences of each derivative model, discuss and summarize their respective advantages, limitations and application scenarios. Finally, the problems and challenges faced by GAN in anomaly detection are discussed, and future research directions are prospected.

The paper introduces and develops the new concept of current-mode multifunctional circuit, a computational structure that is able to implement, using the same functional core, a multitude of circuit functions: amplifying, squaring, square-rooting, multiplying, exponentiation or generation of any continuous mathematical function. As a single core computes a large number of circuit functions, the original approach of analog signal processing from the perspective of multifunctional structures presents the important advantages of a much smaller power consumption and design costs per implemented function comparing with classical designs. The current-mode operation, associated with the original concrete implementation of the proposed structure increase the accuracy of computed functions and the frequency behaviour of the designed circuit. Additionally, the temperature-caused errors are almost removed by specific design techniques. It will be also shown a new method for third-order approximating the exponential function using an original approximation function. A generalization of this method will represent the functional basis for realizing an improved accuracy function synthesizer circuit with a simple implementation in CMOS technology. The proposed circuits are compatible with low-power low voltage operations.

The concept of a connected vehicle refers to the linking of vehicles to each other and to other things. Today, developments in the Internet of Things (IoT) and 5G have made a significant contribution to connected vehicle technology. In addition to many positive contributions, connected vehicle technology also brings with it many security-related problems. In this study, a digital signature algorithm based on elliptic curve cryptography is proposed to verify the message and identity sent to the vehicles. In the proposed model, with the anonymous identification given to the vehicle by the central unit, the vehicle is prevented from being detected by other vehicles and third parties. Thus, even if the personal data produced in the vehicles is shared, it cannot be found which vehicle it belongs to.

Network attacks become more complicated with the improvement of technology. Traditional statistical methods may be insufficient in detecting constantly evolving network attack. For this reason, the usage of payload-based deep packet inspection methods is very significant in detecting attack flows before they damage the system. In the proposed method, features are extracted from the byte distributions in the payload and these features are provided to characterize the flows more deeply by using N-Gram analysis methods. The proposed procedure has been tested on IDS 2012 and 2017 datasets, which are widely used in the literature.

Real-time data transmissions from a vehicle enhance road safety and traffic efficiency by aggregating data in a central server for data analytics. When drivers share their instantaneous vehicular information for a service provider to perform a legitimate task, a curious service provider may also infer private information it has not been authorized for. In this paper, we propose a privacy preservation framework based on the Hilbert Schmidt Independence Criterion (HSIC) to sanitize driving data to protect the vehicle’s trajectory from adversarial inference while ensuring the data is still useful for driver behavior detection. We develop a deep learning model to learn the HSIC sanitizer and demonstrate through two datasets that our approach achieves better utility-privacy trade-offs when compared to three other benchmarks.

Unsupervised cross-domain NER task aims to solve the issues when data in a new domain are fully-unlabeled. It leverages labeled data from source domain to predict entities in unlabeled target domain. Since training models on large domain corpus is time-consuming, in this paper, we consider an alternative way by introducing syntactic dependency structure. Such information is more accessible and can be shared between sentences from different domains. We propose a novel framework with dependency-aware GNN (DGNN) to learn these common structures from source domain and adapt them to target domain, alleviating the data scarcity issue and bridging the domain gap. Experimental results show that our method outperforms state-of-the-art methods.

Scanning Transmission Electron Microscopy (STEM) offers high-resolution images that are used to quantify the nanoscale atomic structure and composition of materials and biological specimens. In many cases, however, the resolution is limited by the electron beam damage, since in traditional STEM, a focused electron beam scans every location of the sample in a raster fashion. In this paper, we propose a scanning method based on the theory of Compressive Sensing (CS) and subsampling the electron probe locations using a line hop sampling scheme that significantly reduces the electron beam damage. We experimentally validate the feasibility of the proposed method by acquiring real CS-STEM data, and recovering images using a Bayesian dictionary learning approach. We support the proposed method by applying a series of masks to fully-sampled STEM data to simulate the expectation of real CS-STEM. Finally, we perform the real data experimental series using a constrained-dose budget to limit the impact of electron dose upon the results, by ensuring that the total electron count remains constant for each image.

Signals get sampled using Nyquist rate in conventional sampling method, but in compressive sensing the signals sampled below Nyquist rate by randomly taking the signal projections and reconstructing it out of very few estimations. But in case of recovering the image by utilizing compressive measurements with the help of multi-resolution grid where the image has certain region of interest (RoI) that is more important than the rest, it is not efficient. The conventional Cartesian sampling cannot give good result in motion image sensing recovery and is limited to stationary image sensing process. The proposed work gives improved results by using Radial sampling (a type of compression sensing). This paper discusses the approach of Radial sampling along with the application of Sparse Fourier Transform algorithms that helps in reducing acquisition cost and input/output overhead.

Dielectric capacitors have attracted attention as energy storage devices that can achieve rapid charge and discharge. But the key to restricting its development is the low energy storage density of dielectric materials. Polyvinylidene fluoride (PVDF), as a polymer with high dielectric properties, is expected to improve the energy storage density of dielectric materials. In this work, the multilayer structure of PVDF ferroelectric polymer is designed, and the influence of the number of layers on the maximum polarization, remanent polarization, applied electric field and energy storage density of the dielectric material is studied. The final obtained double-layer PVDF obtained a discharge energy storage density of 10.6 J/cm3 and an efficiency of 49.1% at an electric field of 410 kV/mm; the three-layer PVDF obtained a discharge energy storage density of 11.0 J/cm3 and an efficiency of 37.2% at an electric field of 440 kV/mm.

With the development of social networks, traditional covert communication requires more consideration of lossy processes of Social Network Platforms (SNPs), which is called robust steganography. Since JPEG compression is a universal processing of SNPs, a method using repeated JPEG compression to fit transport channel matching is recently proposed and shows strong compression-resist performance. However, the repeated JPEG compression will inevitably introduce other artifacts into the stego image. Using only traditional steganalysis methods does not work well towards such robust steganography under low payload. In this paper, we propose a simple and effective method to detect the mentioned steganography by chasing both steganographic perturbations as well as continuous compression artifacts. We introduce compression-forensic features as a complement to steganalysis features, and then use the ensemble classifier for detection. Experiments demonstrate that this method owns a similar and better performance with respect to both traditional and neural-network-based steganalysis.

Security in the communication systems rely mainly on a trusted Public Key Infrastructure (PKI) and Certificate Authorities (CAs). Besides the lack of automation, the complexity and the cost of assigning a signed certificate to a device, several allegations against CAs have been discovered, which has created trust issues in adopting this standard model for secure systems. The automation of the servers certificate assignment was achieved by the Automated Certificate Management Environment (ACME) method, but without confirming the trust of assigned certificate. This paper presents a complete tested and implemented solution to solve the trust of the Certificates provided to the servers by using the blockchain platform for certificate validation. The Blockchain network provides an immutable data store, holding the public keys of all domain names, while resolving the trust concerns by applying an automated Blockchain-based Domain Control Validation (B-DCV) for the server and client server verification. The evaluation was performed on the Ethereum Rinkeby testnet adopting the Proof of Authority (PoA) consensus algorithm which is an improved version of Proof of Stake (Po \$S\$) applied on Ethereum 2.0 providing superior performance compared to Ethereum 1.0.

Recent studies have demonstrated the lack of robustness of image reconstruction networks to test-time evasion attacks, posing security risks and potential for misdiagnoses. In this paper, we evaluate how vulnerable such networks are to training-time poisoning attacks for the first time. In contrast to image classification, we find that trigger-embedded basic backdoor attacks on these models executed using heuristics lead to poor attack performance. Thus, it is non-trivial to generate backdoor attacks for image reconstruction. To tackle the problem, we propose a bi-level optimization (BLO)-based attack generation method and investigate its effectiveness on image reconstruction. We show that BLO-generated back-door attacks can yield a significant improvement over the heuristics-based attack strategy.

Nowadays, in this COVID era, work from home is quietly more preferred than work from the office. Due to this, the need for a firewall has been increased day by day. Every organization uses the firewall to secure their network and create VPN servers to allow their employees to work from home. Due to this, the security of the firewall plays a crucial role. In this paper, we have compared the two most popular open-source firewalls named pfSense and OPNSense. We have examined the security they provide by default without any other attachment. To do this, we performed four different attacks on the firewalls and compared the results. As a result, we have observed that both provide the same security still pfSense has a slight edge when an attacker tries to perform a Brute force attack over OPNSense.

Today, many internet-based applications, especially e-commerce and banking applications, require the transfer of personal data and sensitive data such as credit card information, and in this process, all operations are carried out over the Internet. Users frequently perform these transactions, which require high security, on web sites they access via web browsers. This makes the browser one of the most basic software on the Internet. The security of the communication between the user and the website is provided with SSL certificates, which is used for server authentication. Certificates issued by Certificate Authorities (CA) that have passed international audits must meet certain conditions. The criteria for the issuance of certificates are defined in the Baseline Requirements (BR) document published by the Certificate Authority/Browser (CA/B) Forum, which is accepted as the authority in the WEB Public Key Infrastructure (WEB PKI) ecosystem. Issuing the certificates in accordance with the defined criteria is not sufficient on its own to establish a secure SSL connection. In order to ensure a secure connection and confirm the identity of the website, the certificate validation task falls to the web browsers with which users interact the most. In this study, a comprehensive SSL certificate public key infrastructure (SSL Test Suite) was established to test the behavior of web browsers against certificates that do not comply with BR requirements. With the designed test suite, it is aimed to analyze the certificate validation behaviors of web browsers effectively.

The wide application of deep learning techniques is boosting the regulation of deep learning models, especially deep neural networks (DNN), as commercial products. A necessary prerequisite for such regulations is identifying the owner of deep neural networks, which is usually done through the watermark. Current DNN watermarking schemes, particularly white-box ones, are uniformly fragile against a family of functionality equivalence attacks, especially the neuron permutation. This operation can effortlessly invalidate the ownership proof and escape copyright regulations. To enhance the robustness of white-box DNN watermarking schemes, this paper presents a procedure that aligns neurons into the same order as when the watermark is embedded, so the watermark can be correctly recognized. This neuron alignment process significantly facilitates the functionality of established deep neural network watermarking schemes.

Visible light communication (VLC) is a short-range wireless optical communication that can transmit data by switching lighting elements at high speeds in indoor areas. In common areas, VLC can provide data security at every layer of communication by using physical layer security (PLS) techniques as well as existing cryptography-based techniques. In the literature, PLS techniques have generally been studied for monochrome VLC systems, and multicolor VLC studies are quite limited. In this study, to the best of authors’ knowledge, null steering (NS) and artificial noise (AN), which are widely used PLS methods, have been applied to multi-colored LED-based VLC systems for the first time in the literature and the achievable secrecy rate has been calculated.

Vehicular Ad-hoc Networks (VANET) are capable of offering inter and intra-vehicle wireless communication among mobility aware computing systems. Nodes are linked by applying concepts of mobile ad hoc networks. VANET uses cases empower vehicles to link to the network to aggregate and process messages in real-time. The proposed paper addresses a security vulnerability known as Sybil attack, in which numerous fake nodes broadcast false data to the neighboring nodes. In VANET, mobile nodes continuously change their network topology and exchange location sensor-generated data in real time. The basis of the presented technique is source testing that permits the scalable identification of Sybil nodes, without necessitating any pre-configuration, which was conceptualized from a comparative analysis of preceding research in the literature.

The Inertial Navigation System(INS) and Doppler Velocity Logs(DVL) which are used frequently on autonomous underwater vehicles can be fused under different types of integration architectures. These architectures differ in terms of algorithm requirements and complexity. DVL may experience acoustic beam losses during operation due to environmental factors and abilities of the sensor. In these situations, radial velocity information cannot be received from lost acoustic beam. In this paper, the performances of INS and DVL integration under tightly and loosely coupled architectures are comparatively presented with simulations. In the tightly coupled approach, navigation filter is updated with solely available beam measurements by using sequential measurement update method, and the sensitivity of this method is investigated for acoustic beam losses.

The security proposed for Vehicle-to-Everything (V2X) systems in the European Union is specified in the ETSI Cooperative Intelligent Transport System (C-ITS) standards, and related documents are based on the trusted PKI/CAs. The C-ITS trust model platform comprises an EU Root CA and additional Root CAs run in Europe by member state authorities or private organizations offering certificates to individual users. A new method is described in this paper where the security in V2X is based on the Distributed Public Keystore (DPK) platform developed for Ethereum blockchain. The V2X security is considered as one application of the DPK platform. The DPK stores and distributes the vehicles, RSUs, or other C-ITS role-players’ public keys. It establishes a generic key exchange/ agreement scheme that provides mutual key, entity authentication, and distributing a session key between two peers. V2X communication based on this scheme can establish an end-to-end (e2e) secure session and enables vehicle authentication without the need for a vehicle certificate signed by a trusted Certificate Authority.