Search

In computational photography, high dynamic range (HDR) imaging refers to the family of techniques used to recover a wider range of intensity values compared to the limited range provided by standard sensors. Classical techniques consist of acquiring a scene-varying exposure to compensate for saturated and underexposed regions, followed by a non-linear compression of intensity values called tone mapping. Recently, there has been a growing interest in estimating HDR images from a single exposure. Some methods exploit data-driven models trained to estimate values outside the camera's visible intensity levels. Others make use of polarimetric cameras to reconstruct HDR information without exposure bracketing. In this paper, we present a novel HDR reconstruction method that employs a single PFA (polarimetric filter array) camera with an additional external polarizer to increase the scene's dynamic range across the acquired channels and to mimic different exposures. Our contribution consists of a pipeline that effectively combines standard HDR algorithms based on bracketing and data-driven solutions designed to work with polarimetric images. In this regard, we present a novel CNN (convolutional neural network) model that exploits the underlying mosaiced pattern of the PFA in combination with the external polarizer to estimate the original scene properties, and a second model designed to further improve the final tone mapping step. The combination of such techniques enables us to take advantage of the light attenuation given by the filters while producing an accurate reconstruction. We present an extensive experimental section in which we validate the proposed method on both synthetic and real-world datasets specifically acquired for the task. Quantitative and qualitative results show the effectiveness of the approach when compared to state-of-the-art methods. In particular, our technique exhibits a PSNR (peak signal-to-noise ratio) on the whole test set equal to 23 dB, which is 18 % better with respect to the second-best alternative. [ABSTRACT FROM AUTHOR]

In this paper, a secure energy trading mechanism based on blockchain technology is proposed. The proposed model deals with energy trading problems such as insecure energy trading and inefficient charging mechanisms for electric vehicles (EVs) in a vehicular energy network (VEN). EVs face two major problems: finding an optimal charging station and calculating the exact amount of energy required to reach the selected charging station. Moreover, in traditional trading approaches, centralized parties are involved in energy trading, which leads to various issues such as increased computational cost, increased computational delay, data tempering and a single point of failure. Furthermore, EVs face various energy challenges, such as imbalanced load supply and fluctuations in voltage level. Therefore, a demand-response (DR) pricing strategy enables EV users to flatten load curves and efficiently adjust electricity usage. In this work, communication between EVs and aggregators is efficiently performed through blockchain. Moreover, a branching concept is involved in the proposed system, which divides EV data into two different branches: a Fraud Chain (F-chain) and an Integrity Chain (I-chain). The proposed branching mechanism helps solve the storage problem and reduces computational time. Moreover, an attacker model is designed to check the robustness of the proposed system against double-spending and replay attacks. Security analysis of the proposed smart contract is also given in this paper. Simulation results show that the proposed work efficiently reduces the charging cost and time in a VEN. [ABSTRACT FROM AUTHOR]

In this paper, we address the problems of fraud and anomalies in the Bitcoin network. These are common problems in e-banking and online transactions. However, as the financial sector evolves, so do the methods for fraud and anomalies. Moreover, blockchain technology is being introduced as the most secure method integrated into finance. However, along with these advanced technologies, many frauds are also increasing every year. Therefore, we propose a secure fraud detection model based on machine learning and blockchain. There are two machine learning algorithms—XGboost and random forest (RF)—used for transaction classification. The machine learning techniques train the dataset based on the fraudulent and integrated transaction patterns and predict the new incoming transactions. The blockchain technology is integrated with machine learning algorithms to detect fraudulent transactions in the Bitcoin network. In the proposed model, XGboost and random forest (RF) algorithms are used to classify transactions and predict transaction patterns. We also calculate the precision and AUC of the models to measure the accuracy. A security analysis of the proposed smart contract is also performed to show the robustness of our system. In addition, an attacker model is also proposed to protect the proposed system from attacks and vulnerabilities. [ABSTRACT FROM AUTHOR]

The exponential growth of intelligent vehicles(IVs) development has resulted in a complex network. As the number of IVs in a network increases, so does the number of connections. As a result, a great deal of data is generated. This complexity leads to insecure communication, traffic congestion, security, and privacy issues in vehicular networks (VNs). In addition, detecting malicious IVs, data integration, and data validation are major issues in VNs that affect network performance. A blockchain-based model for secure communication and malicious IV detection is proposed to address the above issues. In addition, this system also addresses data integration and transaction validation using an encryption scheme for secure communication. A multi-chain concept separates the legitimate and malicious data into two chains: the Integrity chain (I-chain) and Fraud chain (F-chain). This multi-chain mechanism solves the storage problem and reduces the computing power. The integration of blockchain in the proposed model provides privacy, network security, transparency, and immutability. To address the storage issue, the InterPlanetary File System (IPFS) is integrated with Certificate Authority (CA). A reputation mechanism is introduced to detect malicious IVs in the network based on ratings. This reputation mechanism is also used to prevent Sybil attack. The evaluation of the proposed work is based on the cost of smart contracts and computation time. Furthermore, two attacker models are presented to prevent the selfish mining attack and the Sybil attack. Finally, a security analysis of the proposed smart contracts with their security vulnerabilities is also presented. [ABSTRACT FROM AUTHOR]

The convolutional neural network (CNN) has become a powerful tool in machine learning (ML) that is used to solve complex problems such as image recognition, natural language processing, and video analysis. Notably, the idea of exploring convolutional neural network architecture has gained substantial attention as well as popularity. This study focuses on the intrinsic various CNN architectures: LeNet, AlexNet, VGG16, ResNet-50, and Inception-V1, which have been scrutinized and compared with each other for the detection of lung cancer using publicly available LUNA16 datasets. Furthermore, multiple performance optimizers: root mean square propagation (RMSProp), adaptive moment estimation (Adam), and stochastic gradient descent (SGD), were applied for this comparative study. The performances of the three CNN architectures were measured for accuracy, specificity, sensitivity, positive predictive value, false omission rate, negative predictive value, and F1 score. The experimental results showed that the CNN AlexNet architecture with the SGD optimizer achieved the highest validation accuracy for CT lung cancer with an accuracy of 97.42%, misclassification rate of 2.58%, 97.58% sensitivity, 97.25% specificity, 97.58% positive predictive value, 97.25% negative predictive value, false omission rate of 2.75%, and F1 score of 97.58%. AlexNet with the SGD optimizer was the best and outperformed compared to the other state-of-the-art CNN architectures. [ABSTRACT FROM AUTHOR]

High energy consumption, rising environmental concerns and depleting fossil fuels demand an increase in clean energy production. The enhanced resiliency, efficiency and reliability offered by microgrids with distributed energy resources (DERs) have shown to be a promising alternative to the conventional grid system. Large-sized commercial customers like institutional complexes have put significant efforts to promote sustainability by establishing renewable energy systems at university campuses. This paper proposes the integration of a photovoltaic (PV) system, energy storage system (ESS) and electric vehicles (EV) at a University campus. An optimal energy management system (EMS) is proposed to optimally dispatch the energy from available energy resources. The problem is mapped in a Linear optimization problem and simulations are carried out in MATLAB. Simulation results showed that the proposed EMS ensures the continuous power supply and decreases the energy consumption cost by nearly 45%. The impact of EV as a storage tool is also observed. EVs acting as a source of energy reduced the energy cost by 45.58% and as a load by 19.33%. The impact on the cost for continuous power supply in case of a power outage is also analyzed. [ABSTRACT FROM AUTHOR]

In recent times, the usage of modern neuromorphic hardware for brain-inspired SNNs has grown exponentially. In the context of sparse input data, they are undertaking low power consumption for event-based neuromorphic hardware, specifically in the deeper layers. However, using deep ANNs for training spiking models is still considered as a tedious task. Until recently, various ANN to SNN conversion methods in the literature have been proposed to train deep SNN models. Nevertheless, these methods require hundreds to thousands of time-steps for training and still cannot attain good SNN performance. This work proposes a customized model (VGG, ResNet) architecture to train deep convolutional spiking neural networks. In this current study, the training is carried out using deep convolutional spiking neural networks with surrogate gradient descent backpropagation in a customized layer architecture similar to deep artificial neural networks. Moreover, this work also proposes fewer time-steps for training SNNs with surrogate gradient descent. During the training with surrogate gradient descent backpropagation, overfitting problems have been encountered. To overcome these problems, this work refines the SNN based dropout technique with surrogate gradient descent. The proposed customized SNN models achieve good classification results on both private and public datasets. In this work, several experiments have been carried out on an embedded platform (NVIDIA JETSON TX2 board), where the deployment of customized SNN models has been extensively conducted. Performance validations have been carried out in terms of processing time and inference accuracy between PC and embedded platforms, showing that the proposed customized models and training techniques are feasible for achieving a better performance on various datasets such as CIFAR-10, MNIST, SVHN, and private KITTI and Korean License plate dataset. [ABSTRACT FROM AUTHOR]