Multi-valued logic (MVL) is a promising solution for high-power consumption and area caused by the limitation of binary systems. Quaternary logic is one of the MVL types more compatible with binary logic. While tradit...
详细信息
Multi-valued logic (MVL) is a promising solution for high-power consumption and area caused by the limitation of binary systems. Quaternary logic is one of the MVL types more compatible with binary logic. While traditional CMOS technology struggles with achieving multiple threshold voltage levels efficiently, leading to greater complexity and energy inefficiency, CNTFETs offer tunable thresholds ideal for MVL applications. Neural networks can retrieve data from inaccurate data, detect trends, and extract patterns that traditional computing methods or humans find difficult to extract. In artificial neural networks (ANNs), the demand for substantial memory to store numerous weights is a critical consideration. Leveraging emerging technologies like magnetic tunnel junctions (MTJ) for non-volatility and CNTFETs for diverse threshold voltage values presents a groundbreaking stride. This convergence of technologies assures non-volatile storage and facilitates the intricate hardware implementation of MVL systems, marking a pioneering leap forward in crafting the next generation of memory for ANN applications. This paper proposes an algorithm for quantizing neural networks using quaternary logic. According to the proposed algorithm, the circuits required to implement quaternary neural networks are designed. The simulation results demonstrate that the proposed algorithm for quantized neural networks significantly reduces the overall memory requirements compared to their full precision counterparts, with minimal accuracy degradation. Specifically, the accuracy drop is less than 1.67% on CIFAR-10 and 1.22% on CIFAR-100 for ResNet-18, while improvements for MNIST on MLP, CIFAR-10 on LeNet-5, and CIFAR-10 and CIFAR-100 on VGG-16, are even observed.
Deep learning network models have achieved inspiring performances in various fields such as computer vision, natural language processing, and biomedicine. However, the high computational and storage costs of the model...
详细信息
Distributed acoustic sensing (DAS) is an emerging technology that has gained significance in various domains, including geophysics and security, due to its unique characteristics of long-distance capability, massive s...
详细信息
Distributed acoustic sensing (DAS) is an emerging technology that has gained significance in various domains, including geophysics and security, due to its unique characteristics of long-distance capability, massive sensing points, and large bandwidth. DAS based on coherent detection has been heavily studied in recent years, due to its unique advantages over direct-detection scheme. However, coherent detection DAS usually generates a significant volume of data, since probe signals with wider bandwidth generally have better performance, which presents substantial challenges in data acquisition, storage, transmission and processing, especially for real-time applications. The study of quantization algorithm could be an effective means of addressing these challenges. It should be noted that, due to the impact of quantization noise, signals after quantization exhibit different levels of distortion depending on the quantization bits, resulting in the deterioration of noise floor. This article introduces, to the best of our knowledge, the theory elucidating how quantization bits affect the performance of coherent detection DAS for the first time. It derives a specific formula suitable for quantitative analysis, and the formula's outcomes align with both simulation and experimental results. In addition, this article shows a 50 km long-distance experiment using nonlinear frequency-modulated pulses as the probing signal, further extending the practical application scope of the theory. This article serves as a comprehensive guide for reducing hardware requirements, accelerating data processing to satisfy versatile and demanding application scenarios, and fostering interdisciplinary research.
This paper concerns the problem of defending against spoofing attacks without a secret key. We address the problem using the Physical-Layer-Authentication (PLA) because of its high security, low overhead, and high com...
详细信息
This paper concerns the problem of defending against spoofing attacks without a secret key. We address the problem using the Physical-Layer-Authentication (PLA) because of its high security, low overhead, and high compatibility. However, many PLA schemes have the following limitations: quantization errors, local optimums, and performance loss due to the change in the communication environment. In this paper, two phase-noise-based PLA schemes are proposed to address the limitations of the prior schemes. We denote the first scheme as the Multiple Phase Noises PLA (MPP) scheme, which realizes the PLA by using multiple phase noise innovations. Note that since the MPP scheme avoids using any quantization algorithm, it outperforms the prior schemes on the authentication performance. We denote the second scheme as the Enhanced Multiple Phase Noises PLA (EMPP) scheme, which introduces an artificial random phase to the transmitted symbols at the transmitter to further improve the authentication performance. The theoretical analyses of the proposed schemes over fading channels are provided, where the closed-form expressions are derived. Theoretical comparisons between the proposed schemes and prior schemes are provided. The theoretical analyses and simulation results demonstrated the superiority of the proposed schemes. In comparison with the prior schemes, the MPP scheme achieves 13% authentication-performance gain without demodulation-performance loss, while the EMPP scheme achieves 42% authentication-performance gain with merely 16% demodulation-performance loss.
作者：
Xie, NingChen, JunjieHuang, LeiShenzhen Univ
Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Univ
Coll Elect & Informat Engn Shenzhen Key Lab Media Secur Shenzhen 518060 Peoples R China Shenzhen Univ
Coll Elect & Informat Engn Guangdong Engn Res Ctr Posit Sensing & Detect Shenzhen 518060 Peoples R China
This paper concerns the problem of authenticating the transmitter without a secret key. In comparison with traditional cryptographic-based authentication mechanisms, the Physical-Layer Authentication (PLA) has the fol...
详细信息
This paper concerns the problem of authenticating the transmitter without a secret key. In comparison with traditional cryptographic-based authentication mechanisms, the Physical-Layer Authentication (PLA) has the following advantages: high security, low complexity, and high compatibility, since it exploits intrinsic and unique features of the physical layer to authenticate the transmitter rather than using a secret key. The prior channel-based PLA schemes use a quantization algorithm to deal with multiple channel-based features for simplicity. However, there are two main limitations in the prior schemes: performance loss due to quantization error and the difficulty of obtaining the optimal thresholds in closed-form. In this paper, we propose two multiple Channel Impulse Response (CIR) based PLA schemes to effectively overcome the aforementioned limitations of the prior schemes. The first scheme uses multiple CIRs to realize the PLA, which is named as the Multiple CIRs PLA (MCP) scheme. The MCP scheme has better authentication performance than the prior schemes, since it avoids to use a quantization algorithm. The second scheme further improves the authentication performance by exploiting the channel correlation coefficient, which is named as the Enhanced Multiple CIRs PLA (EMCP) scheme. We provide rigorous performance analysis of two proposed schemes. We implemented the proposed schemes and conducted extensive performance comparisons through simulations. Our experimental results show that the closed-form expressions of the theoretical results of the proposed schemes perfectly match the corresponding simulation results. The EMCP scheme has the best authentication performance and the MCP scheme is the second one, whereas the prior scheme is the worst one. As the SNR or the channel correlation coefficient declines, the performance gap among various schemes gradually increases.
Designed the weld line quantization algorithm based on the moldflow secondary development of technology, obtained the numerical experimental data of weld line with this. Analyzed of the impact of the relationship betw...
详细信息
ISBN:
(纸本)9783037859063
Designed the weld line quantization algorithm based on the moldflow secondary development of technology, obtained the numerical experimental data of weld line with this. Analyzed of the impact of the relationship between the process parameters and weld line, and optimized the process parameters by orthogonal experimental design. These provided an important basis for the forming process design.
Intelligent mining risk assessment (MIRA) is a vital approach for enhancing safety and operational efficiency in mining. In this study, we introduce MIRA-ChatGLM, which leverages pre-trained large language models (LLM...
详细信息
Intelligent mining risk assessment (MIRA) is a vital approach for enhancing safety and operational efficiency in mining. In this study, we introduce MIRA-ChatGLM, which leverages pre-trained large language models (LLMs) for the domain of gas risk assessment in coal mines. We meticulously constructed a dataset specifically designed for mining risk analysis and performed parameter-efficient fine-tuning on the locally deployed GLM-4-9B-chat base model to develop MIRA-ChatGLM. By utilizing consumer-grade GPUs and employing LoRA and various levels of quantization algorithms such as QLoRA, we investigated the impact of different data scales and instruction settings on model performance. The evaluation results show that MIRA-ChatGLM achieved excellent performance with BLEU-4, ROUGE-1, ROUGE-2, and ROUGE-L scores of 84.47, 90.63, 86.88, and 90.63, respectively, highlighting its outstanding performance in coal mine gas risk assessment. Through comparative experiments with other large language models of similar size and manual evaluation, MIRA-ChatGLM demonstrated superior performance across multiple key metrics, fully demonstrating its tremendous potential in intelligent mine risk assessment and decision support.
暂无评论