For dealing with the electricity theft detection in the smart grids, this article introduces a hybrid deep learning model. The model tackles various issues such as class imbalance problem, curse of dimensionality and low theft detection rate of the existing models. The model integrates the benefits of both GoogLeNet and gated recurrent unit (GRU). The one dimensional electricity consumption (EC) data is fed into GRU to remember the periodic patterns of electricity consumption. Whereas, GoogLeNet model is leveraged to extract the latent features from the two dimensional weekly stacked EC data. Furthermore, the time least square generative adversarial network (TLSGAN) is proposed to solve the class imbalance problem. The TLSGAN uses unsupervised and supervised loss functions to generate fake theft samples, which have high resemblance with real world theft samples. The standard generative adversarial network only updates the weights of those points that are available at the wrong side of the decision boundary. Whereas, TLSGAN even modifies the weights of those points that are available at the correct side of decision boundary that prevent the model from vanishing gradient problem. Moreover, dropout and batch normalization layers are utilized to enhance model's convergence speed and generalization ability. The proposed model is compared with different state-of-the-art classifiers including multilayer perceptron (MLP), support vector machine, naive bayes, logistic regression, MLP-long short term memory network and wide and deep convolutional neural network. It outperforms all classifiers by achieving 96% and 97% precision-recall area under the curve and receiver operating characteristics area under the curve, respectively.INDEX TERMS Electricity theft detection, gated recurrent unit, GoogLeNet, non-technical losses, smart grids, SGCC.

No abstract

BACKGROUND: COVID-19 is an ongoing virus disease also recognized as a coronavirus pandemic that propelled the world to rethink organizational strategies during this unprecedented challenge. Although research on CSR has broadly been done over the past decades; nonetheless, how CSR can contribute a leading role in engaging the stakeholders such as customers during this pandemic period and post-pandemic is an important research gap that ought to be uncovered. OBJECTIVES: This study explores the impact of CSR on external stakeholders like customers and how organizations can dramatically sustain the relationships during the COVID-19 period. First, this study investigates the relationships between CSR and customer satisfaction (CS). Second, this study explores the relationships between CSR and customer retention (CR). Finally, the moderating impact of gender and education were examined among the proposed relationships. METHODS: Using the survey of 500 respondents, this study prospected the linkages among CSR, CS, and CR from China using a convenience sampling approach. The questionnaires were disseminated to 700 Chinese online shoppers between Jan 2020 and March 2020 and explored using SEM model. RESULTS: It found that customers are more attached and satisfied with those organizations that are socially responsible and value their stakeholders, especially during uncertain situations like COVID-19 since presently revealed a positive relationship between CSR and CS. Second, it is found that there is a positive influence of CSR on CR as well. Finally, the study affirmed the positive nexus of gender and education as the moderators among CSR, CR, and CS. CONCLUSION: CSR is always on the front line blending social and environmental goals into business operations, especially during uncertain times and challenges. Undeniably, the COVID-19 pandemic is not only a global health emergency but is also leading to a major global challenge that drives organizations to revisit policies to sustain the relationships with their stakeholders. This study concluded the positive nexus of CSR and affirmed the positive role in sustaining relationships with customers during distinct uncertainties like COVID-19.

Elliptic Curve Cryptography (ECC), provides all public key cryptographic primitives like digital signatures and key agreement algorithms/protocols in a constrained applications such as wireless sensor networks and radio frequency identification networks (RFIDs). In order to achieve digital signatures and key agreements, point/scalar multiplication is necessary to perform. However, we demonstrate the hardware architecture of elliptic curve point multiplication for low area constrained applications over binary (2) field with = 233 bit field size. The lower area is achieved, by using single hybrid karatsuba multiplier for both squarer and multiplication computations. The novel architecture is modeled in Verilog (HDL) using Xilinx (ISE) design tool and synthesized for Virtex 7 fieldprogrammable-gate-array (FPGA). Moreover, it achieves a maximum operational frequency of 157MHz and utilizes only 11849 FPGA slices.

The size of neural networks in deep learning techniques is increasing and varies significantly according to the requirements of real-life applications. The increasing network size, along with the scalability requirements, poses significant challenges for a high performance implementation of deep neural networks (DNN). Conventional implementations, such as graphical processing units and application specific integrated circuits, are either less efficient or less flexible. Consequently, this article presents a system-on-chip (SoC) solution for the acceleration of DNN, where an ARM processor controls the overall execution and off-loads computational intensive operations to a hardware accelerator. The system implementation is performed on a SoC development board. Experimental results show that the proposed system achieves a speed-up of 22.3, with a network architecture size of 64X64, in comparison with the native implementation on a dual core cortex ARM-A9 processor. In order to generalize the performance of complete system, a mathematical formula is presented which allows to compute the total execution time for any architecture size. The validation is performed by taking Epileptic Seizure Recognition as the target case study. Finally, the results of the proposed solution are compared with various state-of-the-art solutions in terms of execution time, scalability, and clock frequency.