An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN

Plant diseases must be identified at the earliest stage for pursuing appropriate treatment procedures and reducing economic and quality losses. There is an indispensable need for low-cost and highly accurate approaches for diagnosing plant diseases. Deep neural networks have achieved state-of-the-art performance in numerous aspects of human life including the agriculture sector. The current state of the literature indicates that there are a limited number of datasets available for autonomous strawberry disease and pest detection that allow fine-grained instance segmentation. To this end, we introduce a novel dataset comprised of 2500 images of seven kinds of strawberry diseases, which allows developing deep learning-based autonomous detection systems to segment strawberry diseases under complex background conditions. As a baseline for future works, we propose a model based on the Mask R-CNN architecture that effectively performs instance segmentation for these seven diseases. We use a ResNet backbone along with following a systematic approach to data augmentation that allows for segmentation of the target diseases under complex environmental conditions, achieving a final mean average precision of 82.43%.

Download Full-text

An Integrated Deep Learning Framework of Tomato Leaf Disease Detection

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.k1010.09811s19 ◽

2019 ◽

Vol 8 (11S) ◽

pp. 46-50

Keyword(s):

Deep Learning ◽

Plant Disease ◽

Raw Materials ◽

Human Life ◽

High Accuracy ◽

Tomato Leaf ◽

Plant Diseases ◽

Ensemble Model ◽

Agriculture Sector ◽

Learning Framework

Plants are a very important part of human life. They have variety of use as food, medication, raw materials and maintaining a balanced ecosystem. Plant disease is a deterioration of normal state of plant that interrupts and modifies its functionality. Pathogens are the main cause of such diseases. For agricultural purposes, a variety of methods have been proposed to detect plant diseases in the recent technological era. However, detecting plant diseases with high accuracy is still a challenge in computer vision. In this study, we propose an integrated deep learning framework where a pre-trained VGG-19 model is used for feature extraction and stacking ensemble model is used to detect and classify leaf diseases from images so as to reduce production and economic loses in agriculture sector. A dataset consisting of two classes (Infected and Healthy) and a total of 3242 images was used to test the system. Our proposed work has been compared with other contemporary algorithms (kNN, SVM, RF and Tree) and have outperformed by obtaining an accuracy of 98.6%

Download Full-text

Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

Mobile Information Systems ◽

10.1155/2019/4570808 ◽

2019 ◽

Vol 2019 ◽

pp. 1-14 ◽

Cited By ~ 2

Author(s):

Yong He ◽

Hong Zeng ◽

Yangyang Fan ◽

Shuaisheng Ji ◽

Jianjian Wu

Keyword(s):

Deep Learning ◽

Integrated Pest Management ◽

Pest Management ◽

Real Time ◽

Oilseed Rape ◽

Data Augmentation ◽

Low Cost ◽

Response Speed ◽

Original Model ◽

Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

Download Full-text

Methods of Respiratory Virus Detection: Advances towards Point-of-Care for Early Intervention

Micromachines ◽

10.3390/mi12060697 ◽

2021 ◽

Vol 12 (6) ◽

pp. 697

Author(s):

Siming Lu ◽

Sha Lin ◽

Hongrui Zhang ◽

Liguo Liang ◽

Shien Shen

Keyword(s):

Viral Load ◽

Respiratory Virus ◽

Viral Infections ◽

Point Of Care ◽

Human Life ◽

Low Cost ◽

Virus Detection ◽

Frequent Monitoring ◽

User Friendly ◽

New Strategies

Respiratory viral infections threaten human life and inflict an enormous healthcare burden worldwide. Frequent monitoring of viral antibodies and viral load can effectively help to control the spread of the virus and make timely interventions. However, current methods for detecting viral load require dedicated personnel and are time-consuming. Additionally, COVID-19 detection is generally relied on an automated PCR analyzer, which is highly instrument-dependent and expensive. As such, emerging technologies in the development of respiratory viral load assays for point-of-care (POC) testing are urgently needed for viral screening. Recent advances in loop-mediated isothermal amplification (LAMP), biosensors, nanotechnology-based paper strips and microfluidics offer new strategies to develop a rapid, low-cost, and user-friendly respiratory viral monitoring platform. In this review, we summarized the traditional methods in respiratory virus detection and present the state-of-art technologies in the monitoring of respiratory virus at POC.

Download Full-text

Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition

2020 IEEE International Conference on Visual Communications and Image Processing (VCIP) ◽

10.1109/vcip49819.2020.9301763 ◽

2020 ◽

Author(s):

Hao Li ◽

Xiaopeng Zhang ◽

Qi Tian ◽

Hongkai Xiong

Keyword(s):

Data Augmentation ◽

Fine Grained ◽

Semantic Data

Download Full-text

A Machine Vision Approach for Bioreactor Foam Sensing

SLAS TECHNOLOGY Translating Life Sciences Innovation ◽

10.1177/24726303211008861 ◽

2021 ◽

pp. 247263032110088

Author(s):

Jonas Austerjost ◽

Robert Söldner ◽

Christoffer Edlund ◽

Johan Trygg ◽

David Pollard ◽

...

Keyword(s):

Machine Learning ◽

Machine Vision ◽

State Of The Art ◽

Low Cost ◽

High Accuracy ◽

Consumer Electronics ◽

Learning System ◽

Automotive Applications ◽

Fine Grained

Machine vision is a powerful technology that has become increasingly popular and accurate during the last decade due to rapid advances in the field of machine learning. The majority of machine vision applications are currently found in consumer electronics, automotive applications, and quality control, yet the potential for bioprocessing applications is tremendous. For instance, detecting and controlling foam emergence is important for all upstream bioprocesses, but the lack of robust foam sensing often leads to batch failures from foam-outs or overaddition of antifoam agents. Here, we report a new low-cost, flexible, and reliable foam sensor concept for bioreactor applications. The concept applies convolutional neural networks (CNNs), a state-of-the-art machine learning system for image processing. The implemented method shows high accuracy for both binary foam detection (foam/no foam) and fine-grained classification of foam levels.

Download Full-text

A Feasibility Study of the Use of Smartwatches in Wearable Fall Detection Systems

Sensors ◽

10.3390/s21062254 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2254

Author(s):

Francisco Javier González-Cañete ◽

Eduardo Casilari

Keyword(s):

Low Cost ◽

Fall Detection ◽

The Elderly ◽

Point Of View ◽

False Alarms ◽

Battery Life ◽

Area Network ◽

Battery Lifetime ◽

Detection Systems ◽

Operational Aspects

Over the last few years, the use of smartwatches in automatic Fall Detection Systems (FDSs) has aroused great interest in the research of new wearable telemonitoring systems for the elderly. In contrast with other approaches to the problem of fall detection, smartwatch-based FDSs can benefit from the widespread acceptance, ergonomics, low cost, networking interfaces, and sensors that these devices provide. However, the scientific literature has shown that, due to the freedom of movement of the arms, the wrist is usually not the most appropriate position to unambiguously characterize the dynamics of the human body during falls, as many conventional activities of daily living that involve a vigorous motion of the hands may be easily misinterpreted as falls. As also stated by the literature, sensor-fusion and multi-point measurements are required to define a robust and reliable method for a wearable FDS. Thus, to avoid false alarms, it may be necessary to combine the analysis of the signals captured by the smartwatch with those collected by some other low-power sensor placed at a point closer to the body’s center of gravity (e.g., on the waist). Under this architecture of Body Area Network (BAN), these external sensing nodes must be wirelessly connected to the smartwatch to transmit their measurements. Nonetheless, the deployment of this networking solution, in which the smartwatch is in charge of processing the sensed data and generating the alarm in case of detecting a fall, may severely impact on the performance of the wearable. Unlike many other works (which often neglect the operational aspects of real fall detectors), this paper analyzes the actual feasibility of putting into effect a BAN intended for fall detection on present commercial smartwatches. In particular, the study is focused on evaluating the reduction of the battery life may cause in the watch that works as the core of the BAN. To this end, we thoroughly assess the energy drain in a prototype of an FDS consisting of a smartwatch and several external Bluetooth-enabled sensing units. In order to identify those scenarios in which the use of the smartwatch could be viable from a practical point of view, the testbed is studied with diverse commercial devices and under different configurations of those elements that may significantly hamper the battery lifetime.

Download Full-text

A Study on the Improvement of Fine-grained Ship Classification through Data Augmentation Using Generative Adversarial Networks

10.1109/ictc52510.2021.9620888 ◽

2021 ◽

Author(s):

SungWon Moon ◽

Jiwon Lee ◽

Jungsoo Lee ◽

Ah Reum Oh ◽

Dowon Nam ◽

...

Keyword(s):

Data Augmentation ◽

Generative Adversarial Networks ◽

Fine Grained ◽

Adversarial Networks ◽

Ship Classification

Download Full-text

Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

International Journal of Asian Language Processing ◽

10.1142/s2717554520500125 ◽

2021 ◽

pp. 2050012

Author(s):

Peilian Zhao ◽

Cunli Mao ◽

Zhengtao Yu

Keyword(s):

Sentiment Analysis ◽

Domain Knowledge ◽

Opinion Mining ◽

Data Augmentation ◽

Training Data ◽

Knowledge Graph ◽

Fine Grained ◽

Learning Framework ◽

Proposed Model ◽

Real World Applications

Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.

Download Full-text