The increasing popularity of applications like the Metaverse has led to the exploration of new, more effective ways of communication. Semantic communication, which focuses on the meaning behind transmitted information...
详细信息
ISBN:
(纸本)9798350339864
The increasing popularity of applications like the Metaverse has led to the exploration of new, more effective ways of communication. Semantic communication, which focuses on the meaning behind transmitted information, represents a departure from traditional communication paradigms. As mobile devices become increasingly prevalent, it is important to explore the potential of edge computing to aid the semantic encoding/decoding process, which requires significant computing power and storage capabilities. However, establishing knowledge bases (KBs) for domain-oriented communication can be time-consuming. To address this challenge, this paper proposes a semantic caching model in edge computing system that caches domain-specialized general models and user-specific individual models. This approach has the potential to reduce the time and resources required to establish individual KBs while accurately capturing the semantics behind users' messages, ultimately leading to more efficient and accessible semantic communication.
Digital twins were introduced to offer digitalized models of real-world systems. These systems can contain systems of systems and processes to perform important tasks in the system. The digital twin technology offers ...
详细信息
Recently, CNN-based networks have exhibited high performance in computer vision. On the other hand, due to the networks becoming deeper and wider, it is hard to implement the model in real-timeembedded environments. ...
详细信息
ISBN:
(纸本)9798350383638;9798350383645
Recently, CNN-based networks have exhibited high performance in computer vision. On the other hand, due to the networks becoming deeper and wider, it is hard to implement the model in real-timeembedded environments. To overcome the drawback, filter pruning has been widely studied for neural network compression. Filter pruning does not need any special hardware or software because it removes filters of CNN and accelerates inference without any special software or hardware. In this paper, we proposed efficient and fast filter pruning (EFFP), which focuses on reducing the training computation resources and searching optimal pruned networks. The success stems from two significant improvements upon other pruning methods. (1) Short training time: In the pruning stage, we make redundant filters to zero to make the output feature map the same as a lightweight model, and (2) adjust the change of redundancy using regrowing: It is difficult to get an optimal pruned model by pruning redundant filters at once. Therefore, we use the pruning/regrowing method to gradually remove unimportant filters to avoid permanently pruning important filters to get an optimal lightweight model. Experimental results indicate that EFFP can reduce the FLOPs and parameters more efficiently and faster than other pruning methods on the object detection model. The inference time is measured on NVIDIA Jetson Xavier NX. As a result, we improve mAP and inference time by a maximum of 45 % compared to other pruning methods.
Edge computing has transformed technology by enabling seamless connections between IoT devices, but it also introduces significant security challenges. EC is crucial for providing minimal latency processing and reduci...
详细信息
Internet of Things (IoT) has lately been expanded across various applications, drawing significant attention to its design, where a loud industrial atmosphere can exist in the mining area. The central essence of this ...
详细信息
Neural Network Inference (NNI) has become a critical element in mobile and autonomous systems, particularly for time-sensitive operations like obstacle detection and avoidance. Alongside execution time, energy consump...
详细信息
ISBN:
(纸本)9798350376975;9798350376968
Neural Network Inference (NNI) has become a critical element in mobile and autonomous systems, particularly for time-sensitive operations like obstacle detection and avoidance. Alongside execution time, energy consumption holds significant importance in such workloads, given that power is a limited resource in these systems. Modern System-on-Chips (SoCs) in mobile and autonomous devices are equipped with a diverse range of accelerators, each characterized by distinct power and performance features. Adapting to dynamically changing physical conditions, the execution flow of these crucial workloads can be optimized to utilize multiple accelerators, allowing for a flexible trade-off between performance and energy consumption. In this study, we leverage multiple accelerators within an SoC to execute NNI using NVIDIA TensorRT. Our primary goal is to enable an energy-performance trade-off by intelligently distributing layers of a neural network between accelerators that prioritize performance and those that emphasize power efficiency. Initially, we analyze the execution time and energy characteristics of neural network layer execution on various accelerators. Subsequently, we examine various factors influencing layer execution. Finally, we propose two algorithms to determine the mapping of layers to accelerators, minimizing energy consumption while adhering to a predetermined target NN inference execution time. We evaluate our approaches on the NVIDIA AGX Orin SoC using the commonly used ResNet50 model. According to the experiment results, we suggest adopting a coarse-grained layer grouping strategy. For applications with stringent realtime requirements, it is recommended to utilize the proposed LTN approach to better achieve the target execution time. Alternatively, in other scenarios, the Knapsack approach may be chosen for potential improvements in energy consumption.
Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises seri...
详细信息
ISBN:
(纸本)9798350369274;9798350369281
Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns for their application in safety-critical domains. Existing defense methods focus on single-frame analysis and are characterized by high computational costs that limit their applicability in multi-frame scenarios, where real-time decisions are crucial. To address this problem, this paper proposes an efficient attention-based defense mechanism that exploits adversarial channel-attention to quickly identify and track malicious objects in shallow network layers and mask their adversarial effects in a multi-frame setting. This work advances the state of the art by enhancing existing over-activation techniques for real-world adversarial attacks to make them usable in real-timeapplications. It also introduces an efficient multi-frame defense framework, validating its efficacy through extensive experiments aimed at evaluating both defense performance and computational cost.
Multicopter drones are becoming a key platform in several application domains, enabling precise on-the-spot sensing and/or actuation. We focus on the case where the drone must process the sensor data in order to decid...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Multicopter drones are becoming a key platform in several application domains, enabling precise on-the-spot sensing and/or actuation. We focus on the case where the drone must process the sensor data in order to decide, depending on the outcome, whether it needs to perform some additional action, e.g., more accurate sensing or some form of actuation. On the one hand, waiting for the computation to complete may waste time, if it turns out that no further action is needed. On the other hand, if the drone starts moving toward the next point of interest before the computation ends, it may need to return back to the previous point, if some action needs to be taken. In this paper, we propose a learning approach that enables the drone to take informed decisions about whether to wait for the result of the computation (or not), based on past experience gathered from previous missions. Through an extensive evaluation, we show that the proposed approach, when properly configured, outperforms several static policies, up to 25.8%, over a wide variety of different scenarios where the probability of some action being required at a given point of interest remains stable as well as for scenarios where this probability varies in time.
The phenomenon of road dust during vehicle operation poses threats to visibility and road safety, while also negatively impacting respiratory health and air quality, becoming an environmental concern. In order to addr...
详细信息
ISBN:
(纸本)9798350386851;9798350386844
The phenomenon of road dust during vehicle operation poses threats to visibility and road safety, while also negatively impacting respiratory health and air quality, becoming an environmental concern. In order to address this issue, this study proposes an AI-based street cleaning vehicle system aimed at reducing dust emissions and providing a clean and safe driving environment, while also preventing driver distraction leading to traffic accidents. The system utilizes two cameras on the street cleaning vehicle to capture images of road conditions and surface pollution, which are then input into an embedded system for real-time image analysis. This technology requires classification of 8 categories, and leveraging deep learning technology like YolactEdge, real-time detection of road pollution is achieved. AI automatically adjusts water pressure for road cleaning and categorizes road pollution into four levels, adjusting water pressure accordingly. This method achieves good results in road pollution identification and adjusting the amount of water for road cleaning. Firstly, in terms of road pollution identification, the average accuracy is 99.85%, and the frame rate on the NVIDIA Jetson Xavier NX embedded system is 13 frames per second. Secondly, in adjusting the amount of water for road cleaning, after measurement, it is found to reduce water consumption by over 40% compared to traditional methods. This system achieves efficient water usage by accurately identifying road surface dirt and debris for application in low-speed street cleaning vehicles traveling at 20 km/hr.
This paper outlines formal methods and design automation techniques for exact checking of control safety and reachability properties of cyber-physical systems (CPS), under timing uncertainties (common deadline miss ha...
详细信息
ISBN:
(纸本)9798350384406
This paper outlines formal methods and design automation techniques for exact checking of control safety and reachability properties of cyber-physical systems (CPS), under timing uncertainties (common deadline miss handling and control update policies). While such checking is often fraught with state-space explosion problems and is hence not scalable. This paper discusses a new joint encoding of control and scheduling behaviors as a satisfiability-modulo-theory (SMT) formulation and a novel abstraction-refinement procedure with incremental solving, to scale the analysis. In addition, we also outline empirical performance results of multiple well-known SMT solvers for this problem. These results can inform practical decision making for large scale control safety verification in the industry.
暂无评论