Most of the existing research focuses on a single MEC server scenario, and there are few studies on computing offloading and resource allocation in multi-MEC server scenarios. Therefore, this paper proposes a dynamic ...
详细信息
The deployment and inference of Deep learning models are investigated in this article on seven different Edge computing (EC) devices. This study addresses the features, performance and limitations of the NVIDIA Jetson...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
The deployment and inference of Deep learning models are investigated in this article on seven different Edge computing (EC) devices. This study addresses the features, performance and limitations of the NVIDIA Jetson Orin NX and Nano, Google Coral DevBoard and USB, Intel Neural Compute Stick 2, NXP ***8 Plus and Xilinx Zynq UltraScale+ MPSoC ZCU104 on Deep learning inference. Fully Connected, Convolutional and Long Short-Term Memory (LSTM) neural networks are implemented to test these EC devices. The benchmarking focuses on the performance metrics: inference latency, increase in error metric, and power consumption. The results show considerable variability among devices, with the ZCU104 and Jetson Orin achieving the lowest latencies across most models without any increase in the error metric. At the same time, Coral devices exhibit increased latency and error for complex convolutional models. NVIDIA Jetson devices, ZCU104 and Neural Compute Stick 2 are the only devices that support LSTM inference. The study also highlights differences in power consumption, with USB accelerators being the most energy-efficient.
Load balancing has arisen as an important challenge in case of Software Defined Network because of the dynamic patterns in the traffic and expanding demands of network. The centralized framework of SDN delivers unique...
详细信息
As a key component of next-generation information technology, blockchain technology has been widely applied in fields such as finance, healthcare, and the Internet of Things, leading to a high demand for specialized t...
详细信息
Federated learning has rapidly become a research hotspot in the field of distributed deep learning because raw data does not need to be shared. However, it is still characterized by problems in terms of privacy securi...
详细信息
Tuberculosis (TB) continues to be a health hazard globally, especially in the developing world, thus requiring effective diagnostic techniques. This research focuses on the utilization of the transfer learning Incepti...
详细信息
Use-inspired artificial intelligence (AI) tailors deep-learning models for image processing tasks in targeted scientific domains. These use-inspired models meet domain requirements for accuracy while parsimoniously us...
详细信息
ISBN:
(纸本)9798331528690;9798331528706
Use-inspired artificial intelligence (AI) tailors deep-learning models for image processing tasks in targeted scientific domains. These use-inspired models meet domain requirements for accuracy while parsimoniously using compact and efficient model architectures needed for inference in the field. However, before settling upon a model, domain experts repeatedly train and test models over a wide range of hyperparameters, contextual settings, and data configurations, making model training bespoke, time-consuming, and costly. Model-training-as-a-Service (MTaaS), i.e., cloud services designed for generic training workloads, can reduce training costs, but domain-aware designs and runtime adaptations could yield further reductions. This paper characterizes the potential for domain-aware design and runtime adaptation for MTaaS in digital agriculture. First, we studied the time to train models for 10 use-inspired agricultural datasets using pre-trained model weights derived from other agricultural datasets versus pre-trained weights derived from ImageNet, a widely used benchmark. Using agricultural datasets sped training time by up to 2X for some datasets, but provided modest speedups (< 1.07) in the common case;Choosing the right dataset is critical. Next, we present an approach to predict training time given domain-aware pre-trained weights. Our predictions are strongly correlated with training time (r = 0.93). Finally, we studied the use of domain-aware pre-trained weights in a MTaaS under Poisson and bursty arrival patterns for training tasks. Under bursty arrivals and tight memory constraints, domain-aware MTaaS reduced training time by 2.8X and 12.2X compared to model training using pre-trained ImageNet weights and from scratch, respectively.
Classification of crops is vital for improving yields and provision of food items through agriculture. In India particularly, the identification of bottle gourds, with more emphasis on varieties like Pusa Samridhi, Pu...
详细信息
This paper proposes a deep learning-based optimization framework for Electic Vehicle that leverages LSTM, CNN, and DRL to enhance battery management, autonomous navigation, and energy efficiency. The LSTM model predic...
详细信息
In contemporary agriculture, optimizing crop yield necessitates efficient weed management and precise irrigation. This review amalgamates insights from ten studies, centering on the integration of machine learning, de...
详细信息
暂无评论