Rice Disease Recognition Using Effective Deep Neural Networks

2021 ◽  
Author(s):  
S. Mathulaprangsan ◽  
S. Patarapuwadol ◽  
K. Lanthong ◽  
D. Jetpipattanapong ◽  
S. Sateanpattanakul
Keyword(s):  
High Performance ◽  
Deep Neural Networks ◽  
High Accuracy ◽  
Learning Models ◽  
Early Disease ◽  
Image Dataset ◽  
Rate Adjustment ◽  
Rice Disease ◽  
Critical Problems ◽  
Adjustment Strategies

Rice is the most important grain in Thailand for both consuming and exporting. One of the critical problems in rice cultivation is rice diseases, which affects directly to the yield. Early disease recognition is handled by a human, which is difficult to achieve high accuracy and the performance depends on the farmer’s experience. To overcome this problem, we did three folds of contributions. First, an infield rice diseases image dataset, named K5RD, was created. Second, a number of additional techniques to enhance the classification scores including data augmentations and learning rate adjustment strategies were carefully surveyed. Third, a set of selective deep learning models including ResNets and DenseNets were applied to classify such rice diseases. The experimental results reveal that the proposed framework can achieve high performance, which its F1 score is higher than 98% on average, and has the potential to be implemented as a practical system to provide to Thai farmers in the future.

scholarly journals Zero-Keep Filter Pruning for Energy/Power Efficient Deep Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1238
Author(s):  
Yunhee Woo ◽  
Dongyoung Kim ◽  
Jaemin Jeong ◽  
Young-Woong Ko ◽  
Jeong-Gun Lee
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
High Performance ◽  
Deep Neural Networks ◽  
Learning Models ◽  
Power Efficient ◽  
Number Of Zeros ◽  
Iot Devices ◽  
Deep Learning Model ◽  
Performance Computing

Recent deep learning models succeed in achieving high accuracy and fast inference time, but they require high-performance computing resources because they have a large number of parameters. However, not all systems have high-performance hardware. Sometimes, a deep learning model needs to be run on edge devices such as IoT devices or smartphones. On edge devices, however, limited computing resources are available and the amount of computation must be reduced to launch the deep learning models. Pruning is one of the well-known approaches for deriving light-weight models by eliminating weights, channels or filters. In this work, we propose “zero-keep filter pruning” for energy-efficient deep neural networks. The proposed method maximizes the number of zero elements in filters by replacing small values with zero and pruning the filter that has the lowest number of zeros. In the conventional approach, the filters that have the highest number of zeros are generally pruned. As a result, through this zero-keep filter pruning, we can have the filters that have many zeros in a model. We compared the results of the proposed method with the random filter pruning and proved that our method shows better performance with many fewer non-zero elements with a marginal drop in accuracy. Finally, we discuss a possible multiplier architecture, zero-skip multiplier circuit, which skips the multiplications with zero to accelerate and reduce energy consumption.

scholarly journals Compressing Deep Networks by Neuron Agglomerative Clustering

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6033
Author(s):  
Li-Na Wang ◽  
Wenxue Liu ◽  
Xiang Liu ◽  
Guoqiang Zhong ◽  
Partha Pratim Roy ◽  
...  
Keyword(s):  
High Performance ◽  
Deep Neural Networks ◽  
Clustering Algorithm ◽  
Building Blocks ◽  
Computational Time ◽  
Storage Space ◽  
Learning Models ◽  
Agglomerative Clustering ◽  
Deep Networks ◽  
Fully Connected

In recent years, deep learning models have achieved remarkable successes in various applications, such as pattern recognition, computer vision, and signal processing. However, high-performance deep architectures are often accompanied by a large storage space and long computational time, which make it difficult to fully exploit many deep neural networks (DNNs), especially in scenarios in which computing resources are limited. In this paper, to tackle this problem, we introduce a method for compressing the structure and parameters of DNNs based on neuron agglomerative clustering (NAC). Specifically, we utilize the agglomerative clustering algorithm to find similar neurons, while these similar neurons and the connections linked to them are then agglomerated together. Using NAC, the number of parameters and the storage space of DNNs are greatly reduced, without the support of an extra library or hardware. Extensive experiments demonstrate that NAC is very effective for the neuron agglomeration of both the fully connected and convolutional layers, which are common building blocks of DNNs, delivering similar or even higher network accuracy. Specifically, on the benchmark CIFAR-10 and CIFAR-100 datasets, using NAC to compress the parameters of the original VGGNet by 92.96% and 81.10%, respectively, the compact network obtained still outperforms the original networks.

scholarly journals Statistical and machine learning models for optimizing energy in parallel applications

2019 ◽  
Vol 33 (6) ◽  
pp. 1079-1097 ◽  
Author(s):  
Mark Endrei ◽  
Chao Jin ◽  
Minh Ngoc Dinh ◽  
David Abramson ◽  
Heidi Poxon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
High Performance ◽  
Large Scale ◽  
Energy Use ◽  
Parallel Applications ◽  
Learning Models ◽  
Trade Off ◽  
Time Required ◽  
Machine Learning Models

Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.

414 Deep Neural Networks: A Survey Tool for Obstructive Sleep Apnea Prediction

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A164-A164
Author(s):  
Pahnwat Taweesedt ◽  
JungYoon Kim ◽  
Jaehyun Park ◽  
Jangwoon Park ◽  
Munish Sharma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Deep Neural Networks ◽  
Support Vector ◽  
Learning Models ◽  
Obstructive Sleep ◽  
Screening Questionnaires ◽  
Machine Learning Models

Abstract Introduction Obstructive sleep apnea (OSA) is a common sleep-related breathing disorder with an estimation of one billion people. Full-night polysomnography is considered the gold standard for OSA diagnosis. However, it is time-consuming, expensive and is not readily available in many parts of the world. Many screening questionnaires and scores have been proposed for OSA prediction with high sensitivity and low specificity. The present study is intended to develop models with various machine learning techniques to predict the severity of OSA by incorporating features from multiple questionnaires. Methods Subjects who underwent full-night polysomnography in Torr sleep center, Texas and completed 5 OSA screening questionnaires/scores were included. OSA was diagnosed by using Apnea-Hypopnea Index ≥ 5. We trained five different machine learning models including Deep Neural Networks with the scaled principal component analysis (DNN-PCA), Random Forest (RF), Adaptive Boosting classifier (ABC), and K-Nearest Neighbors classifier (KNC) and Support Vector Machine Classifier (SVMC). Training:Testing subject ratio of 65:35 was used. All features including demographic data, body measurement, snoring and sleepiness history were obtained from 5 OSA screening questionnaires/scores (STOP-BANG questionnaires, Berlin questionnaires, NoSAS score, NAMES score and No-Apnea score). Performance parametrics were used to compare between machine learning models. Results Of 180 subjects, 51.5 % of subjects were male with mean (SD) age of 53.6 (15.1). One hundred and nineteen subjects were diagnosed with OSA. Area Under the Receiver Operating Characteristic Curve (AUROC) of DNN-PCA, RF, ABC, KNC, SVMC, STOP-BANG questionnaire, Berlin questionnaire, NoSAS score, NAMES score, and No-Apnea score were 0.85, 0.68, 0.52, 0.74, 0.75, 0.61, 0.63, 0,61, 0.58 and 0,58 respectively. DNN-PCA showed the highest AUROC with sensitivity of 0.79, specificity of 0.67, positive-predictivity of 0.93, F1 score of 0.86, and accuracy of 0.77. Conclusion Our result showed that DNN-PCA outperforms OSA screening questionnaires, scores and other machine learning models. Support (if any):

scholarly journals High accuracy data-driven heliostat calibration and state prediction with pretrained deep neural networks

Solar Energy ◽  
2021 ◽  
Vol 218 ◽  
pp. 48-56
Author(s):  
Max Pargmann ◽  
Daniel Maldonado Quinto ◽  
Peter Schwarzbözl ◽  
Robert Pitz-Paal
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
High Accuracy ◽  
Data Driven ◽  
State Prediction ◽  
Accuracy Data

Optimal Data-Driven Modeling-Free Differential-Inversion-Based Iterative Control: A Wafer Stage Example

2020 ◽  
Author(s):  
Zezhou Zhang ◽  
Qingze Zou
Keyword(s):  
System Dynamics ◽  
High Performance ◽  
Random Noise ◽  
High Accuracy ◽  
Data Driven ◽  
Modeling Process ◽  
Random Disturbances ◽  
Noise Disturbances ◽  
Data Driven Modeling ◽  
Iterative Control

Abstract In this paper, an optimal data-driven modeling-free differential-inversion-based iterative control (OMFDIIC) method is proposed for both high performance and robustness in the presence of random disturbances. Achieving high accuracy and fast convergence is challenging as the system dynamics behaviors vary due to the external uncertainties and the system bandwidth is limited. The aim of the proposed method is to compensate for the dynamics effect without modeling process and achieve both high accuracy and robust convergence, by extending the existed modeling-free differential-inversion-based iterative control (MFDIIC) method through a frequency- and iteration-dependent gain. The convergence of the OMFDIIC method is analyzed with random noise/disturbances considered. The developed method is applied to a wafer stage, and shows a significant improvement in the performance.

scholarly journals Brain hierarchy score: Which deep neural networks are hierarchically brain-like?

2020 ◽  
Author(s):  
Soma Nonaka ◽  
Kei Majima ◽  
Shuntaro C. Aoki ◽  
Yukiyasu Kamitani
Keyword(s):  
Neural Networks ◽  
Image Recognition ◽  
High Performance ◽  
Deep Neural Networks ◽  
Recognition Performance ◽  
Brain Activity ◽  
Spatial Integration ◽  
Hierarchical Processing ◽  
Visual Areas ◽  
The Brain

SummaryAchievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on the decoding of individual DNN unit activations from human brain activity. We find that BH scores for 29 pretrained DNNs with varying architectures are negatively correlated with image recognition performance, indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that relatively simple feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method provides new ways for designing DNNs and understanding the brain in consideration of their representational homology.

Sign in / Sign up

Export Citation Format

Share Document