Connected and autonomous vehicles (CAVs) promise next-gen transportation systems with enhanced safety, energy efficiency, and sustainability. One typical control strategy for CAVs is the so-called cooperative adaptive...
详细信息
Connected and autonomous vehicles (CAVs) promise next-gen transportation systems with enhanced safety, energy efficiency, and sustainability. One typical control strategy for CAVs is the so-called cooperative adaptive cruise control (CACC) where vehicles drive in platoons and cooperate to achieve safe and efficient transportation. In this study, we formulate CACC as a multi-agent reinforcement learning (MARL) problem. Diverging from existing MARL methods that use centralized training and decentralized execution which require not only a centralized communication mechanism but also dense inter-agent communication during training and online adaptation, we propose a fully decentralized MARL framework for enhanced efficiency and scalability. In addition, a quantization-based communication scheme is proposed to reduce the communication overhead without significantly degrading the control performance. This is achieved by employing randomized rounding numbers to quantize each piece of communicated information and only communicating non-zero components after quantization. Extensive experimentation in two distinct CACC settings reveals that the proposed MARL framework consistently achieves superior performance over several contemporary benchmarks in terms of both communication efficiency and control efficacy. In the appendix, we show that our proposed framework's applicability extends beyond CACC, showing promise for broader intelligent transportation systems with intricate action and state spaces. IEEE
Identifying fruit disease manually is time-consuming, expertrequired,and expensive;thus, a computer-based automated system is widelyrequired. Fruit diseases affect not only the quality but also the *** a result, it is...
详细信息
Identifying fruit disease manually is time-consuming, expertrequired,and expensive;thus, a computer-based automated system is widelyrequired. Fruit diseases affect not only the quality but also the *** a result, it is possible to detect the disease early on and cure the fruitsusing computer-based techniques. However, computer-based methods faceseveral challenges, including low contrast, a lack of dataset for training amodel, and inappropriate feature extraction for final classification. In thispaper, we proposed an automated framework for detecting apple fruit leafdiseases usingCNNand a hybrid optimization algorithm. Data augmentationis performed initially to balance the selected apple dataset. After that, twopre-trained deep models are fine-tuning and trained using transfer ***, a fusion technique is proposed named Parallel Correlation Threshold(PCT). The fused feature vector is optimized in the next step using a hybridoptimization algorithm. The selected features are finally classified usingmachine learning algorithms. Four different experiments have been carriedout on the augmented Plant Village dataset and yielded the best accuracy of99.8%. The accuracy of the proposed framework is also compared to that ofseveral neural nets, and it outperforms them all.
Efficiently serving large language models (LLMs) requires batching many requests together to reduce the cost per request. Yet, the key-value (KV) cache, which stores attention keys and values to avoid re-computations,...
详细信息
Efficiently serving large language models (LLMs) requires batching many requests together to reduce the cost per request. Yet, the key-value (KV) cache, which stores attention keys and values to avoid re-computations, significantly increases memory demands and becomes the new bottleneck in speed and memory usage. This memory demand increases with larger batch sizes and longer context lengths. Additionally, the inference speed is limited by the size of KV cache, as the GPU's SRAM must load the entire KV cache from the main GPU memory for each token generated, causing the computational core to be idle during this process. A straightforward and effective solution to reduce KV cache size is quantization, which decreases the total bytes taken by KV cache. However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization. To fill the gap, we conducted a comprehensive study on the element distribution in KV cache of popular LLMs. Our findings indicate that the key cache should be quantized per-channel, i.e., group elements along the channel dimension and quantize them together. In contrast, the value cache should be quantized per-token. From this analysis, we developed a tuning-free 2bit KV cache quantization algorithm, named KIVI. With the hardware-friendly implementation, KIVI can enable Llama (Llama-2), Falcon, and Mistral models to maintain almost the same quality while using 2.6× less peak memory usage (including the model weight). This reduction in memory usage enables up to 4× larger batch size, bringing 2.35× ∼ 3.47× throughput on real LLM inference workload. The source code is available at https://***/jy-yuan/KIVI. Copyright 2024 by the author(s)
This paper deals with the simulation calculation of transmission (S21) and reflection (S22) parameters in a material parametrically based on clay (brick). The electromagnetic parameters of the clay that are the subjec...
详细信息
Respiratory diseases pose significant health challenges worldwide, necessitating accurate and timely diagnosis for effective management. This paper proposes an approach for automated respiratory condition detection us...
详细信息
The dynamic growth of the digital ecosystem presents evolving cybersecurity considerations, highlighting the constant change and emergence of new security concerns. While cloud providers offer robust security for the ...
详细信息
Human behavior research is becoming more and more important in human-centered software. Today, many public spaces utilize video monitoring because of improvements in technology and decreased costs. However, the majori...
详细信息
Wireless sensor node and DDoS (Distributed Denial of Service) is a major attack way that can exhaust the energy of a sensor, disrupt the communication traffic of an IoT network. We must be on the lookout for these att...
详细信息
Quantum Computing (QC) works based on the principle of quantum mechanics, which is different from traditional computers. Heart disease remains the leading cause of mortality worldwide and the development of advanced p...
详细信息
Accurate and effective fruit classification is essential for separating and analyzing in the field of agriculture. This article design a proposed model for classifying date fruit using Sobel Filtered UNet (SFU-Net). T...
详细信息
暂无评论