scholarly journals Plant Leaf Disease Recognition Using Depth-Wise Separable Convolution-Based Models

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 511
Author(s):  
Syed Mohammad Minhaz Hossain ◽  
Kaushik Deb ◽  
Pranab Kumar Dhar ◽  
Takeshi Koshiba

Proper plant leaf disease (PLD) detection is challenging in complex backgrounds and under different capture conditions. For this reason, initially, modified adaptive centroid-based segmentation (ACS) is used to trace the proper region of interest (ROI). Automatic initialization of the number of clusters (K) using modified ACS before recognition increases tracing ROI’s scalability even for symmetrical features in various plants. Besides, convolutional neural network (CNN)-based PLD recognition models achieve adequate accuracy to some extent. However, memory requirements (large-scaled parameters) and the high computational cost of CNN-based PLD models are burning issues for the memory restricted mobile and IoT-based devices. Therefore, after tracing ROIs, three proposed depth-wise separable convolutional PLD (DSCPLD) models, such as segmented modified DSCPLD (S-modified MobileNet), segmented reduced DSCPLD (S-reduced MobileNet), and segmented extended DSCPLD (S-extended MobileNet), are utilized to represent the constructive trade-off among accuracy, model size, and computational latency. Moreover, we have compared our proposed DSCPLD recognition models with state-of-the-art models, such as MobileNet, VGG16, VGG19, and AlexNet. Among segmented-based DSCPLD models, S-modified MobileNet achieves the best accuracy of 99.55% and F1-sore of 97.07%. Besides, we have simulated our DSCPLD models using both full plant leaf images and segmented plant leaf images and conclude that, after using modified ACS, all models increase their accuracy and F1-score. Furthermore, a new plant leaf dataset containing 6580 images of eight plants was used to experiment with several depth-wise separable convolution models.

2021 ◽  
Vol 5 (OOPSLA) ◽  
pp. 1-26
Author(s):  
Arjun Pitchanathan ◽  
Christian Ulmann ◽  
Michel Weber ◽  
Torsten Hoefler ◽  
Tobias Grosser

Presburger arithmetic provides the mathematical core for the polyhedral compilation techniques that drive analytical cache models, loop optimization for ML and HPC, formal verification, and even hardware design. Polyhedral compilation is widely regarded as being slow due to the potentially high computational cost of the underlying Presburger libraries. Researchers typically use these libraries as powerful black-box tools, but the perceived internal complexity of these libraries, caused by the use of C as the implementation language and a focus on end-user-facing documentation, holds back broader performance-optimization efforts. With FPL, we introduce a new library for Presburger arithmetic built from the ground up in modern C++. We carefully document its internal algorithmic foundations, use lightweight C++ data structures to minimize memory management costs, and deploy transprecision computing across the entire library to effectively exploit machine integers and vector instructions. On a newly-developed comprehensive benchmark suite for Presburger arithmetic, we show a 5.4x speedup in total runtime over the state-of-the-art library isl in its default configuration and 3.6x over a variant of isl optimized with element-wise transprecision computing. We expect that the availability of a well-documented and fast Presburger library will accelerate the adoption of polyhedral compilation techniques in production compilers.


2022 ◽  
pp. 1-10
Author(s):  
Daniel Trevino-Sanchez ◽  
Vicente Alarcon-Aquino

The need to detect and classify objects correctly is a constant challenge, being able to recognize them at different scales and scenarios, sometimes cropped or badly lit is not an easy task. Convolutional neural networks (CNN) have become a widely applied technique since they are completely trainable and suitable to extract features. However, the growing number of convolutional neural networks applications constantly pushes their accuracy improvement. Initially, those improvements involved the use of large datasets, augmentation techniques, and complex algorithms. These methods may have a high computational cost. Nevertheless, feature extraction is known to be the heart of the problem. As a result, other approaches combine different technologies to extract better features to improve the accuracy without the need of more powerful hardware resources. In this paper, we propose a hybrid pooling method that incorporates multiresolution analysis within the CNN layers to reduce the feature map size without losing details. To prevent relevant information from losing during the downsampling process an existing pooling method is combined with wavelet transform technique, keeping those details "alive" and enriching other stages of the CNN. Achieving better quality characteristics improves CNN accuracy. To validate this study, ten pooling methods, including the proposed model, are tested using four benchmark datasets. The results are compared with four of the evaluated methods, which are also considered as the state-of-the-art.


Author(s):  
Arpan Singh Rajput ◽  
Shailja Shukla ◽  
S. S. Thakur

Purpose: Agricultural productivity is something on which the economy highly depends in India as well in all over the world. India is an agriculture-dependent country; wherein about 70% of the population depends on agriculture. Methodology: This is one of the main reasons that disease detection in agriculture plays an important role, as having the disease in plant leaf is quite natural. If proper observations are not taken in the agriculture field then it causes serious effects on plants due to which respective product quality and productivity are affected. Detection of plant leaf disease through effective and accurate automatic technique is beneficial at the starting stage as it reduces a large work of monitoring in big farms of crops. Result: This paper presents the review on the state of the art disease classification techniques presently used using image processing that can be used for plant leaf disease detection in agriculture.


2021 ◽  
Author(s):  
Changyu Deng ◽  
Yizhou Wang ◽  
Can Qin ◽  
Wei Lu

Abstract Topology optimization by optimally distributing materials in a given domain requires gradient-free optimizers to solve highly complicated problems. However, with hundreds of design variables or more involved, solving such problems would require millions of Finite Element Method (FEM) calculations whose computational cost is huge and impractical. Here we report a Self-directed Online Learning Optimization (SOLO) which integrates Deep Neural Network (DNN) with FEM calculations. A DNN learns and substitutes the objective as a function of design variables. A small number of training data is generated dynamically based on the DNN's prediction of the global optimum. The DNN adapts to the new training data and gives better prediction in the region of interest until convergence. Our algorithm was tested by compliance minimization problems and fluid-structure optimization problems. It reduced the computational time by 2 ~ 5 orders of magnitude compared with directly using heuristic methods, and outperformed all state-of-the-art algorithms tested in our experiments. This approach enables solving large multi-dimensional optimization problems.


Author(s):  
Wonkyung Jung ◽  
Sangpyo Kim ◽  
Jung Ho Ahn ◽  
Jung Hee Cheon ◽  
Younho Lee

Fully Homomorphic encryption (FHE) has been gaining in popularity as an emerging means of enabling an unlimited number of operations in an encrypted message without decryption. A major drawback of FHE is its high computational cost. Specifically, a bootstrapping step that refreshes the noise accumulated through consequent FHE operations on the ciphertext can even take minutes of time. This significantly limits the practical use of FHE in numerous real applications.By exploiting the massive parallelism available in FHE, we demonstrate the first instance of the implementation of a GPU for bootstrapping CKKS, one of the most promising FHE schemes supporting the arithmetic of approximate numbers. Through analyzing CKKS operations, we discover that the major performance bottleneck is their high main-memory bandwidth requirement, which is exacerbated by leveraging existing optimizations targeted to reduce the required computation. These observations motivate us to utilize memory-centric optimizations such as kernel fusion and reordering primary functions extensively.Our GPU implementation shows a 7.02× speedup for a single CKKS multiplication compared to the state-of-the-art GPU implementation and an amortized bootstrapping time of 0.423us per bit, which corresponds to a speedup of 257× over a single-threaded CPU implementation. By applying this to logistic regression model training, we achieved a 40.0× speedup compared to the previous 8-thread CPU implementation with the same data.


2018 ◽  
Author(s):  
Yvens R. Serpa ◽  
Mária Andréia F. Rodrigues

Graphics applications with visual quality and increasing levels of interactivity have been of fundamental interest. Within this context, visibility culling algorithms restrict the processing to the objects actually visible by the observer, speeding up the scene visualization. However, state-of-the-art solutions still require a high computational cost, do not scale in complex scenarios and are limited in generalization. In contrast, this work presents RHView, an innovative generic solution for static and dynamics scenes, which is based on a replicated space-partitioning structure and heuristics. RHView uses novel heuristics for rendering time estimation and balance between processing cost and triangle removal accuracy, while maintaining interactive frame rates, even in scenes with billions of triangles. It is the only solution currently available to reduce draw calls, one of the factors that have the greatest impact on graphics processing. Systematic tests have shown that RHView can be up to 2.8 times faster than the state-of-the-art algorithms.


2012 ◽  
Vol 2 (1) ◽  
pp. 7-9 ◽  
Author(s):  
Satinderjit Singh

Median filtering is a commonly used technique in image processing. The main problem of the median filter is its high computational cost (for sorting N pixels, the temporal complexity is O(N·log N), even with the most efficient sorting algorithms). When the median filter must be carried out in real time, the software implementation in general-purpose processorsdoes not usually give good results. This Paper presents an efficient algorithm for median filtering with a 3x3 filter kernel with only about 9 comparisons per pixel using spatial coherence between neighboring filter computations. The basic algorithm calculates two medians in one step and reuses sorted slices of three vertical neighboring pixels. An extension of this algorithm for 2D spatial coherence is also examined, which calculates four medians per step.


1995 ◽  
Vol 32 (2) ◽  
pp. 95-103
Author(s):  
José A. Revilla ◽  
Kalin N. Koev ◽  
Rafael Díaz ◽  
César Álvarez ◽  
Antonio Roldán

One factor in determining the transport capacity of coastal interceptors in Combined Sewer Systems (CSS) is the reduction of Dissolved Oxygen (DO) in coastal waters originating from the overflows. The study of the evolution of DO in coastal zones is complex. The high computational cost of using mathematical models discriminates against the required probabilistic analysis being undertaken. Alternative methods, based on such mathematical modelling, employed in a limited number of cases, are therefore needed. In this paper two alternative methods are presented for the study of oxygen deficit resulting from overflows of CSS. In the first, statistical analyses focus on the causes of the deficit (the volume discharged). The second concentrates on the effects (the concentrations of oxygen in the sea). Both methods have been applied in a study of the coastal interceptor at Pasajes Estuary (Guipúzcoa, Spain) with similar results.


Sign in / Sign up

Export Citation Format

Share Document