Quantization-Aware Pruning Criterion for Industrial Applications

Gil, Yoonhee; Park, Jonghyuk; Baek, Jongchan; Han, Soohee

doi:10.1109/tie.2021.3070517

Cited by 14 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These models aim to strike a balance between accuracy and resource efficiency, enabling effective deployment in industrial environments. Currently, several compression methods for large neural networks are being explored, including parameter compression [163], pruning [164], and distillation [165]. These techniques aim to reduce the model size and computational requirements without significantly sacrificing predictive performance.…”

Section: A Lightweight Model For Industrial Edge Intelligencementioning

confidence: 99%

Deep Learning for Time-Series Prediction in IIoT: Progress, Challenges, and Prospects

Ren

Jia

Laili

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Time-series prediction plays a crucial role in the Industrial Internet of Things (IIoT) to enable intelligent process control, analysis, and management, such as complex equipment maintenance, product quality management, and dynamic process monitoring. Traditional methods face challenges in obtaining latent insights due to the growing complexity of IIoT. Recently, the latest development of deep learning provides innovative solutions for IIoT time-series prediction. In this survey, we analyze the existing deep learning-based time-series prediction methods and present the main challenges of time-series prediction in IIoT. Furthermore, we propose a framework of state-of-the-art solutions to overcome the challenges of time-series prediction in IIoT and summarize its application in practical scenarios, such as predictive maintenance, product quality prediction, and supply chain management. Finally, we conclude with comments on possible future directions for the development of time-series prediction to enable extensible knowledge mining for complex tasks in IIoT.

show abstract

Section: A Lightweight Model For Industrial Edge Intelligencementioning

confidence: 99%

Deep Learning for Time-Series Prediction in IIoT: Progress, Challenges, and Prospects

Ren

Jia

Laili

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…⑤.We process the trained model with optimization, quantization, and pruning, to speed up its operation on intelligent modules [12] . After these optimizations, our algorithm has improved in both recognition speed and accuracy, with better performance.…”

Section: Remote Sensing Image Object Detection Systemmentioning

confidence: 99%

Research and application of YOLOv3-based intelligent module for remote sensing image recognition on satellites

Tang

Shi

et al. 2023

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023)

View full text Add to dashboard Cite

With the continuous development of satellite technology, the acquisition and processing of satellite remote sensing data have become increasingly common. However, at present, satellites still use a mode of transmitting data back to the ground and utilizing ground CPU/GPU platforms for intelligent processing, which is inefficient due to the process of data transmission between the satellite and the ground. This article studies the application method and implementation of real-time remote sensing image recognition by integrating the Yulong810 on-board intelligent module on a satellite based on the YOLOv3 object detection algorithm. In response to the actual needs of satellite remote sensing image recognition, the algorithm is optimized based on the Yulong810 on-board intelligent module, which improves the recognition efficiency and reduces power consumption while ensuring the accuracy of remote sensing image recognition. By comparing with ground CPU/GPU platforms, the results show that the Yulong810 on-board intelligent module has lower power consumption and higher efficiency, and the recognition accuracy is comparable to that of ground platforms, which can completely replace ground remote sensing image detection equipment when integrated into satellites. By integrating the module into the satellite, real-time intelligent processing can be achieved in orbit, improving the efficiency of satellite remote sensing image recognition.

show abstract

“…For example, quantization [14], changing the model parameters from floating-point numbers to low-bit width numbers; Pruning [15], removing the least important parameters that do not affect the decision-making process of the model; Knowledge distillation [16], transferring the knowledge to the student model arXiv:2301.05748v1 [eess.SP] 13 Jan 2023 form a teacher model. Those model compression approaches can be considered individually as well as jointly [17], [18] and have shown their validity in enormous use scenarios [19]- [21]. Besides that, novel hardware architectures were also developed to bring intelligence to the edge.…”

Section: Introductionmentioning

confidence: 99%

Exploring Automatic Gym Workouts Recognition Locally on Wearable Resource-Constrained Devices

Bian¹,

Wang²,

Polonelli³

et al. 2022

2022 IEEE 13th International Green and Sustainable Computing Conference (IGSC)

View full text Add to dashboard Cite

Automatic gym activity recognition on energyand resource-constrained wearable devices removes the humaninteraction requirement during intense gym sessions -like softtouch tapping and swiping. This work presents a tiny and highly accurate residual convolutional neural network that runs in milliwatt microcontrollers for automatic workouts classification. We evaluated the inference performance of the deep model with quantization on three resource-constrained devices: two microcontrollers with ARM-Cortex M4 and M7 core from ST Microelectronics, and a GAP8 system on chip, which is an opensourced, multi-core RISC-V computing platform from Green-Waves Technologies. Experimental results show an accuracy of up to 90.4% for eleven workouts recognition with full precision inference. The paper also presents the trade-off performance of the resource-constrained system. While keeping the recognition accuracy (88.1%) with minimal loss, each inference takes only 3.2 ms on GAP8, benefiting from the 8 RISC-V cluster cores. We measured that it features an execution time that is 18.9x and 6.5x faster than the Cortex-M4 and Cortex-M7 cores, showing the feasibility of real-time on-board workouts recognition based on the described data set with 20 Hz sampling rate. The energy consumed for each inference on GAP8 is 0.41 mJ compared to 5.17 mJ on Cortex-M4 and 8.07 mJ on Cortex-M7 with the maximum clock. It can lead to longer battery life when the system is battery-operated. We also introduced an open data set composed of fifty sessions of eleven gym workouts collected from ten subjects that is publicly available.

show abstract

Quantization-Aware Pruning Criterion for Industrial Applications

Cited by 14 publications

References 13 publications

Deep Learning for Time-Series Prediction in IIoT: Progress, Challenges, and Prospects

Deep Learning for Time-Series Prediction in IIoT: Progress, Challenges, and Prospects

Research and application of YOLOv3-based intelligent module for remote sensing image recognition on satellites

Exploring Automatic Gym Workouts Recognition Locally on Wearable Resource-Constrained Devices

Contact Info

Product

Resources

About