the face identification technology-based attendance system represented in this paper is a novel design. the new system is an alternative to conventional more reliable, secure, and user-friendly. methods the key compon...
详细信息
Machine learning-based methods for detecting malicious Android applications are widely researched, but their security is a concern. Adversarial attacks can easily evade the detection of these methods. this paper desig...
详细信息
Low-power architectures are increasingly significant across a spectrum of applications, ranging from the Internet of things (IoT) and Quantum Computing. the Quantum dot cellular automata (QCA) is regarded as a promisi...
详细信息
ISBN:
(纸本)9798350350661;9798350350654
Low-power architectures are increasingly significant across a spectrum of applications, ranging from the Internet of things (IoT) and Quantum Computing. the Quantum dot cellular automata (QCA) is regarded as a promising platform for implementing digital circuits at the nanoscale owing to its less power consumption (PC) and great performance. the proposed design is a 4x1 multiplexer (MUX) using QCA technology. the MUX serves as a fundamental building block in digital systems, enabling the selection of one out of four input signals based on a control signal. Our proposed design leverages the unique properties of QCA, such as Coulombic interactions among quantum dots, to realize compact and efficient multiplexing functionality. We present a Controlled Operational Gate(COG) with detailed design methodology, layout optimization techniques, and performance analysis of the proposed 4x1 QCA 4x1 MUX using COG. Simulation results demonstrate the feasibility and effectiveness of our design in terms of area efficiency, latency, and quantum cost leading to low PC. the proposed 4x1 QCA MUX holds promise for realizing complex digital systems with improved performance and energy efficiency, paving the way for advanced nanoscale computing applications.
Convolutional neural networks play an important role in deep learning, which includes three processes: forward propagation, backpropagation, and weight update. On domestic heterogeneous accelerators, the performance o...
详细信息
ISBN:
(纸本)9798350386783;9798350386776
Convolutional neural networks play an important role in deep learning, which includes three processes: forward propagation, backpropagation, and weight update. On domestic heterogeneous accelerators, the performance of the weight update operator is somewhat weak. In this paper, we handwritten and optimized the weight update operator on domestic heterogeneous accelerators, including both ordinary convolution and grouped convolution. Among them, ordinary convolution uses the implicit gemm algorithm, Grouped convolution uses a parallelized direct convolution algorithm, which reduces memory usage and has strong universality. Parallel direct convolution algorithms make better use of it.
this article examines the utility of image processing and machine learning in analyzing the shape and structure of cell pictures obtained from peripheral blood smears, particularly on automatic identification. the fun...
详细信息
Mud leakage poses a persistent challenge in drilling operations, necessitating innovative solutions for improved sealing and circulation efficiency. this paper leverages data from the Mullen Field to categorize mud lo...
详细信息
Last decades have seen a lot of research on Analog Design Automation. the most recent approaches are based on Reinforcement learning (RL). this paper describes a new learning strategy enhancing the most recent Proxima...
详细信息
Artificial Intelligence (AI) is becoming popular in the field of histopathological imaging. there isn’t a lot of annotated medical image data, and it is time consuming task to get this data annotated. the self-superv...
详细信息
Visually sorted grid layouts provide an efficient method for organizing high-dimensional vectors in two-dimensional space by aligning spatial proximity with similarity relationships. this approach facilitates the effe...
详细信息
ISBN:
(纸本)9798400706028
Visually sorted grid layouts provide an efficient method for organizing high-dimensional vectors in two-dimensional space by aligning spatial proximity with similarity relationships. this approach facilitates the effective sorting of diverse elements ranging from data points to images, and enables the simultaneous visualization of a significant number of elements. However, sorting data on two-dimensional grids is a challenge due to its high complexity. Even for a small 8-by-8 grid with 64 elements, the number of possible arrangements exceeds 1.3.10(89) - more than the number of atoms in the universe - making brute-force solutions impractical. Although various methods have been proposed to address the challenge of determining sorted grid layouts, none have investigated the potential of gradient-based optimization. In this paper, we present a novel method for grid-based sorting that exploits gradient optimization for the first time. We introduce a novel loss function that balances two opposing goals: ensuring the generation of a "valid" permutation matrix, and optimizing the arrangement on the grid to reflect the similarity between vectors, inspired by metrics that assess the quality of sorted grids. While learning-based approaches are inherently computationally complex, our method shows promising results in generating sorted grid layouts with superior sorting quality compared to existing techniques.
Research shows that heuristic optimizationalgorithms can find solutions for complex problems in the physical world. Pairing these algorithms with machine learning models for predictive building control applications h...
详细信息
Research shows that heuristic optimizationalgorithms can find solutions for complex problems in the physical world. Pairing these algorithms with machine learning models for predictive building control applications has been widely explored. this study investigates the efficacy of determining optimal ventilation rates using a particle swarm optimization (PSO) algorithm, a genetic algorithm (GA), and a hybridized genetic particle swarm optimization (GPSO) algorithm developed using MATLAB within an EnergyPlus building energy simulation model. Weather data from Vancouver is used to exemplify a marine climate, where free-cooling opportunities are relatively abundant. the algorithm performance results are collected for boththe heating and cooling seasons and are compared against each other for run times, energy savings, and indoor air quality performance. the results are compared against simulation results using a conventional demand control ventilation (DCV) system. Results indicate that when compared to the DCV controller with an economizer mode, heuristic optimization control methods are capable of reducing HVAC energy consumption during a cooling season with free-cooling opportunities by up to 14.1%. Additionally, all three optimizationalgorithms are capable of minimizing HVAC energy consumption with zero unmet hours for the indoor carbon dioxide concentration setpoint.
暂无评论