Genetic algorithm based approach to compress and accelerate the trained Convolution Neural Network model

Agarwal, Mohit; Gupta, Suneet; Biswas, K. K.

doi:10.1007/s13042-022-01768-4

Cited by 8 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further enhance our model and minimize communication overhead, we have implemented a state-of-the-art compression technique, as exemplified by the genetic algorithmbased approach [27], to reduce the dimensions of terminal models at the edge. In the case of the Convolutional Neural Network (CNN) model, this reduction entails selecting a subset of convolutional filters and nodes within the dense layers while ensuring that the original models' accuracy levels remain intact.…”

Section: B Key Contributionmentioning

confidence: 99%

Decentralized Federated Learning on the Edge Over Wireless Mesh Networks

Salama,

Stergioulis,

Zaidi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The rapid growth of Internet of Things (IoT) devices has generated vast amounts of data, leading to the emergence of federated learning as a novel distributed machine learning paradigm. Federated learning enables model training at the edge, leveraging the processing capacity of edge devices while preserving privacy and mitigating data transfer bottlenecks. However, the conventional centralized federated learning architecture suffers from a single point of failure and susceptibility to malicious attacks. In this study, we delve into an alternative approach called decentralized federated learning (DFL) conducted over a wireless mesh network as the communication backbone. We perform a comprehensive network performance analysis using stochastic geometry theory and physical interference models, offering fresh insights into the convergence analysis of DFL. Additionally, we conduct system simulations to assess the proposed decentralized architecture under various network parameters and different aggregator methods such as FedAvg, Krum and Median methods. Our model is trained on the widely recognized EMNIST dataset for benchmarking handwritten digit classification. To minimize the model's size at the edge and reduce communication overhead, we employ a cutting-edge compression technique based on genetic algorithms. Our simulation results reveal that the compressed decentralized architecture achieves performance comparable to the baseline centralized architecture and traditional DFL in terms of accuracy and average loss for our classification task. Moreover, it significantly reduces the size of shared models over the wireless channel by compressing participants' local model sizes to nearly half of their original size compared to the baselines, effectively reducing complexity and communication overhead.INDEX TERMS Internet of Things (IoT), Federated Learning, Decentralized Federated Learning, Edge Computing and Data Privacy.

show abstract

Section: B Key Contributionmentioning

confidence: 99%

Decentralized Federated Learning on the Edge Over Wireless Mesh Networks

Salama,

Stergioulis,

Zaidi

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Although the above study improves the detection accuracy of the model, it increases the parameters and the detection time of the model. Researchers have conducted various studies in order to compress and accelerate the model from various aspects [16] For example, lightweight network design, pruning, and knowledge distillation. The lightweight network design method is used to design small models and quickly recognize networks by adjusting the internal structure of the network, such as MobileNet [17], GhostNet [18], shuffleNet [19] etc.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight and High-Precision Passion Fruit YOLO Detection Model for Deployment in Embedded Devices

Sun,

Li,

et al. 2024

Preprint

View full text Add to dashboard Cite

In order to shorten the detection time and improve the average precision on embedded devices, A lightweight and high accuracy model is proposed for passion fruit in complex environments (backlight, occlusion, overlap, sunny, cloudy, rainy). Firstly, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computation while improving detection speed. Secondly, a new feature branch is added to the GhostNet network, and the feature fusion layer in the neck network is reconstructed to effectively combine the lower-level and higher-level features, which not only improves the accuracy of the model but also maintains its lightweight. Finally, the knowledge distillation methods are used to transfer the knowledge from the more capable teacher model to the less capable student model, which significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than the original YOLOv5s model. Furthermore, the improved model size is 7.14MB, reduced to half of the original model, and the real-time detection frame rate is 11.25 FPS on the Jetson Nano. Compared to the state-of-the-art model, the proposed model outperforms them in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruits in complex orchard scenes, which can provide valuable technical support for the development of orchard picking robots and greatly improve the intelligence level of orchards.

show abstract

“…The GA is used in many applications, such as game theory [29], polymer design [30], multi-objective problems [31], lung cancer prognosis [32], wind power prediction [33], social networks [34], combustion engine [35], photovoltaic systems [36], task scheduling [37], traffic flow model [38], automotives [39], heat transfer [40], Complex networks [41], traffic management [42], Plasticity Echo State Network [43], prostate cancer [44], pruning for neural network [45], wireless sensor networks [46], Virtual machine [47], electric vehicles [48], IOT network topologies [49], stock market forecasting model [50], and task assignments to agents [51]. Motivated by the above perspectives, this work presents the optimization of piezocomposite transducers by varying the volume fraction of active material and layer thicknesses for highly sensitive configurations.…”

Section: Introductionmentioning

confidence: 99%

Neuro-Evolutionary Framework for Design Optimization of Two-Phase Transducer with Genetic Algorithms

Zameer,

Naz,

Raja

et al. 2023

Micromachines

View full text Add to dashboard Cite

Multilayer piezocomposite transducers are widely used in many applications where broad bandwidth is required for tracking and detection purposes. However, it is difficult to operate these multilayer transducers efficiently under frequencies of 100 kHz. Therefore, this work presents the modeling and optimization of a five-layer piezocomposite transducer with ten variables of nonuniform layer thicknesses and different volume fractions by exploiting the strength of the genetic algorithm (GA) with a one-dimensional model (ODM). The ODM executes matrix manipulation by resolving wave equations and produces mechanical output in the form of pressure and electrical impedance. The product of gain and bandwidth is the required function to be maximized in this multi-objective and multivariate optimization problem, which is a challenging task having ten variables. Converting it into the minimization problem, the reciprocal of the gain-bandwidth product is considered. The total thickness is adjusted to keep the central frequency at approximately 50–60 kHz. Piezocomposite transducers with three active materials, PZT5h, PZT4d, PMN-PT, and CY1301 polymer, as passive materials were designed, simulated, and statistically evaluated. The results show significant improvement in gain bandwidth compared to previous existing techniques.

show abstract

Genetic algorithm based approach to compress and accelerate the trained Convolution Neural Network model

Cited by 8 publications

References 22 publications

Decentralized Federated Learning on the Edge Over Wireless Mesh Networks

Decentralized Federated Learning on the Edge Over Wireless Mesh Networks

A Lightweight and High-Precision Passion Fruit YOLO Detection Model for Deployment in Embedded Devices

Neuro-Evolutionary Framework for Design Optimization of Two-Phase Transducer with Genetic Algorithms

Contact Info

Product

Resources

About