Search

With the swift development of deep learning applications, the convolutional neural network (CNN) has brought a tremendous challenge to traditional processors to fulfil computing requirements. It is urgent to embrace new strategies to improve efficiency and diminish energy consumption. Currently, diverse accelerator strategies for CNN computation based on the field-programmable gate array (FPGA) platform have been gradually explored because they have edges of high parallelism, low power consumption, and better programmability. This paper first illustrates state-of-the-art FPGA-based accelerator design by emphasizing the contributions and limitations of existing research works. Subsequently, we demonstrated significant concepts of parallel computing (PC) in the convolution algorithm and discussed how to accomplish parallelism based on the FPGA hardware structure. Eventually, with the proposed CPU+ FPGA framework, we performed experiments and compared the performance against traditional computation strategies in terms of the operation efficiency and energy consumption ratio. The results revealed that the efficiency of the FPGA platform is much higher than that of the central processing unit and graphics processing unit., Competing Interests: The authors declare no conflicts of interest., (Copyright © 2022 Zhi Qi et al.)

In the evolving landscape of portfolio management (PM), the fusion of advanced machine learning techniques with traditional financial methodologies has opened new avenues for innovation. Our study introduces a cutting-edge model combining deep reinforcement learning (DRL) with a non-stationary transformer architecture. This model is designed to decode complex patterns in financial time-series data, enhancing portfolio management strategies with deeper insights and robustness. It effectively tackles the challenges of data heterogeneity and market uncertainty, key obstacles in PM. Our approach integrates key macroeconomic indicators and targeted news sentiment analysis into its framework, capturing a comprehensive picture of market dynamics. This amalgamation of varied data types addresses the multifaceted nature of financial markets, enhancing the model's ability to navigate the complexities of asset management. Rigorous testing demonstrates the model's efficacy, highlighting the benefits of blending diverse data sources and sophisticated algorithmic approaches in mastering the nuances of PM. [ABSTRACT FROM AUTHOR]

Nowadays the storing of sensitive information in cyberspace shows a significant increase and this led to an escalation of cyberattacks. Hence, the protection against the confidentiality of data or programs has been a matter of special concern to many security experts. One of the problematic cyberattacks is the cache side-channel attacks as caches are playing an important rule to ensure the performance of computer. The leakage of information can occur by observing the distinct access time for a cache miss or hit. This paper conducts some background research about the categorization of different cache side-channel attacks. Besides that, several strategies which are used to defend against cache side-channel attacks such as detection method, prevention method and some proposed secure cache design will be reviewed. Also, the difficulties about the defenses in cache side-channel attacks and some recommended strategies will also be discussed in the following content. [ABSTRACT FROM AUTHOR]

Deep Neural Networks have gained popularity due to their superiority in performance in various applications. Hence, domain-specific architectures have been introduced to speed up the model training process. Since the launch of TPUs by Google, there were few literatures that examines the performance of TPUs compared to existing processing units such as the CPU and GPU in deep learning applications. The recent inclusion of the PyTorch framework to use Google Colaboratory's resources also provided an opportunity for us to build a PyTorch-based Colab notebook that can be used for further study in this area. In this study, we evaluated the performance of the Intel Xeon CPU, Nvidia T4 GPU and TPU v2-8 by using the Convolutional Neural Network (CNN) model on the CIFAR-10 and MNIST datasets. Our study also considers the accuracy and convergence of the model while testing, which were implemented by data augmentation and batch normalization techniques in the VGG16 model trained from scratch. We achieved a model accuracy of 86% and 96% for the CIFAR-10 and MNIST datasets respectively. During the experiments, we observed that the GPU performed 25x faster than the CPU; meanwhile the TPU only achieved a 12x speedup compared to the CPU as there were some issues faced. We proposed some issues and possible solutions in this paper for further study. [ABSTRACT FROM AUTHOR]

In deploying the Internet of Things (IoT) and Internet of Medical Things (IoMT)-based applications and infrastructures, the researchers faced many sensors and their output's values, which have transferred between service requesters and servers. Some case studies addressed the different methods and technologies, including machine learning algorithms, deep learning accelerators, Processing-In-Memory (PIM), and neuromorphic computing (NC) approaches to support the data processing complexity and communication between IoMT nodes. With inspiring human brain structure, some researchers tackled the challenges of rising IoT- and IoMT-based applications and neural structures' simulation. A defective device has destructive effects on the performance and cost of the applications, and their detection is challenging for a communication infrastructure with many devices. We inspired astrocyte cells to map the flow (AFM) of the Internet of Medical Things onto mesh network processing elements (PEs), and detect the defective devices based on a phagocytosis model. This study focuses on an astrocyte's cholesterol distribution into neurons and presents an algorithm that utilizes its pattern to distribute IoMT's dataflow and detect the defective devices. We researched Alzheimer's symptoms to understand astrocyte and phagocytosis functions against the disease and employ the vaccination COVID-19 dataset to define a set of task graphs. The study improves total runtime and energy by approximately 60.85% and 52.38% after implementing AFM, compared with before astrocyte-flow mapping, which helps IoMT's infrastructure developers to provide healthcare services to the requesters with minimal cost and high accuracy. [ABSTRACT FROM AUTHOR]

Deepfake is one of the applications that is deemed harmful. Deepfakes are a sort of image or video manipulation in which a person's image is changed or swapped with that of another person's face using artificial neural networks. Deepfake manipulations may be done with a variety of techniques and applications. A quintessential countermeasure against deepfake or face manipulation is deepfake detection method. Most of the existing detection methods perform well under symmetric data distributions, but are still not robust to asymmetric datasets variations and novel deepfake/manipulation types. In this paper, for the identification of fake faces in videos, a new multistream deep learning algorithm is developed, where three streams are merged at the feature level using the fusion layer. After the fusion layer, the fully connected, Softmax, and classification layers are used to classify the data. The pre-trained VGG16 model is adopted for transferred CNN1stream. In transfer learning, the weights of the pre-trained CNN model are further used for training the new classification problem. In the second stream (transferred CNN2), the pre-trained VGG19 model is used. Whereas, in the third stream, the pre-trained ResNet18 model is considered. In this paper, a new large-scale dataset (i.e., World Politicians Deepfake Dataset (WPDD)) is introduced to improve deepfake detection systems. The dataset was created by downloading videos of 20 different politicians from YouTube. Over 320,000 frames were retrieved after dividing the downloaded movie into little sections and extracting the frames. Finally, various manipulations were performed to these frames, resulting in seven separate manipulation classes for men and women. In the experiments, three fake face detection scenarios are investigated. First, fake and real face discrimination is studied. Second, seven face manipulations are performed, including age, beard, face swap, glasses, hair color, hairstyle, smiling, and genuine face discrimination. Third, performance of deepfake detection system under novel type of face manipulation is analyzed. The proposed strategy outperforms the prior existing methods. The calculated performance metrics are over 99%. [ABSTRACT FROM AUTHOR]

To enhance the safety and stability of autonomous vehicles, we present a deep learning platooning-based video information-sharing Internet of Things framework in this study. The proposed Internet of Things framework incorporates concepts and mechanisms from several domains of computer science, such as computer vision, artificial intelligence, sensor technology, and communication technology. The information captured by camera, such as road edges, traffic lights, and zebra lines, is highlighted using computer vision. The semantics of highlighted information is recognized by artificial intelligence. Sensors provide information on the direction and distance of obstacles, as well as their speed and moving direction. The communication technology is applied to share the information among the vehicles. Since vehicles have high probability to encounter accidents in congested locations, the proposed system enables vehicles to perform self-positioning with other vehicles in a certain range to reinforce their safety and stability. The empirical evaluation shows the viability and efficacy of the proposed system in such situations. Moreover, the collision time is decreased considerably compared with that when using traditional systems. [ABSTRACT FROM AUTHOR]