Suggested Topics within your search.
Suggested Topics within your search.
-
21
POQ: Is There a Pareto-Optimal Quantization Strategy for Deep Neural Networks?
Published 2025-01-01Subjects: Get full text
Article -
22
Efficient Detection of Microplastics on Edge Devices With Tailored Compiler for TinyML Applications
Published 2025-01-01Get full text
Article -
23
AI for Sustainable Recycling: Efficient Model Optimization for Waste Classification Systems
Published 2025-06-01“…In this work, we extend our previous research by improving both dataset diversity and model efficiency. We introduce an expanded dataset that includes an organic waste class and more heterogeneous images, and evaluate a range of quantized CNN models to reduce inference time and resource usage. …”
Get full text
Article -
24
Effect of coarsely quantization on next generation systems with low-density parity check codes
Published 2025-09-01Subjects: Get full text
Article -
25
Performance and Efficiency Comparison of U-Net and Ghost U-Net in Road Crack Segmentation with Floating Point and Quantization Optimization
Published 2024-12-01Subjects: Get full text
Article -
26
Efficient secure federated learning aggregation framework based on homomorphic encryption
Published 2023-01-01“…In order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved urgently.However, the computational cost and communication overhead caused by the encryption scheme would affect the training efficiency.Firstly, in the case of protecting data security and ensuring training efficiency, the Top-K gradient selection method was used to screen model gradients, reducing the number of gradients that need to be uploaded.A candidate quantization protocol suitable for multi-edge terminals and a secure candidate index merging algorithm were proposed to further reduce communication overhead and accelerate homomorphic encryption calculations.Secondly, since model parameters of each layer of neural networks had characteristics of the Gaussian distribution, the selected model gradients were clipped and quantized, and the gradient unsigned quantization protocol was adopted to speed up the homomorphic encryption calculation.Finally, the experimental results show that in the federated learning scenario, the proposed framework can protect data privacy, and has high accuracy and efficient performance.…”
Get full text
Article -
27
-
28
-
29
SparseBatch: Communication-efficient Federated Learning with Partially Homomorphic Encryption
Published 2025-01-01Get full text
Article -
30
CRITERIA OF THE ESTIMATION OF EFFICIENCY OF INNOVATIONS IN TRANSPORT BRANCH
Published 2016-12-01“…Efficiency of innovations in any economy branch, transportation included, may be assessed on the basis of qualitative and quantitative indices. …”
Get full text
Article -
31
Toward resource-efficient UAV systems: Deep learning model compression for onboard-ready weed detection in UAV imagery
Published 2025-12-01“…We fine-tuned the pruned model on the UAV dataset to mitigate any performance loss resulting from pruning. We then applied quantization to reduce the precision of numerical parameters and improve computational efficiency. …”
Get full text
Article -
32
-
33
-
34
Quantitative Criteria for Solvent Selection in Liquid-Phase Exfoliation: Balancing Exfoliation and Stabilization Efficiency
Published 2025-02-01“…These results establish a quantitative framework for solvent selection, enhancing the efficiency of the LPE processes.…”
Get full text
Article -
35
EFFICIENCY OF QUANTITATIVE ANALYSIS OF LUNG COMPUTED TOMOGRAPHY FINDINGS IN PATIENTS WITH CHRONIC OBSTRUCTIVE PULMONARY DISEASE
Published 2017-03-01“…Objective: to evaluate the efficiency of detection of emphysema in the analysis of lung computed tomography (CT) images using the “Autoplan” program and to compare the data of quantitative analysis and clinical indicators. …”
Get full text
Article -
36
Quantitative analysis of the efficiency dynamics of global liquefied natural gas shipping under COVID-19
Published 2024-06-01“…This paper proposes a quantitative method to model the impact of COVID-19 on global LNG shipping efficiency based on the spatiotemporal characteristics of behavior mining for LNG ships. …”
Get full text
Article -
37
Modeling the construction of an efficient customer club for the quantitative and qualitative development of increasing customers in the banking system
Published 2024-09-01“…Abstract The purpose of the current research is to find a model to build an efficient customer club for the quantitative and qualitative development of increasing customers in the banking system. …”
Get full text
Article -
38
Statistical Analysis of Unique Web Application Vulnerabilities: A Quantitative Assessment of Scanning Tool Efficiency
Published 2025-06-01“…Web application security is a critical aspect of modern cybersecurity, necessitating efficient and reliable vulnerability detection mechanisms. …”
Get full text
Article -
39
-
40
Quantitative design and production methods for sustainably increasing maize grain yield and resource use efficiency
Published 2025-09-01“…Then the maize population was optimized on the basis of quantitative design principles. By this approach, crop planting density was matched with solar radiation levels, the population structure was matched with appropriate cultivars, and the plow layer-root system-canopy functions were matched with grain yield to ensure increases in grain yield and resource use efficiency in maize production. …”
Get full text
Article