Plant diseases can cause a considerable reduction in the quality and number of agricultural products. Guava, well known to be the tropics’ apple, is one significant fruit cultivated in tropical regions. It is attacked by 177 pathogens, including 167 fungal and others such as bacterial, algal, and nematodes. In addition, postharvest diseases may cause crucial production loss. Due to minor variations in various guava disease symptoms, an expert opinion is required for disease analysis. Improper diagnosis may cause economic losses to farmers’ improper use of pesticides. Automatic detection of diseases in plants once they emerge on the plants’ leaves and fruit is required to maintain high crop fields. In this paper, an artificial intelligence (AI) driven framework is presented to detect and classify the most common guava plant diseases. The proposed framework employs the ΔE color difference image segmentation to segregate the areas infected by the disease. Furthermore, color (RGB, HSV) histogram and textural (LBP) features are applied to extract rich, informative feature vectors. The combination of color and textural features are used to identify and attain similar outcomes compared to individual channels, while disease recognition is performed by employing advanced machine-learning classifiers (Fine KNN, Complex Tree, Boosted Tree, Bagged Tree, Cubic SVM). The proposed framework is evaluated on a high-resolution (18 MP) image dataset of guava leaves and fruit. The best recognition results were obtained by Bagged Tree classifier on a set of RGB, HSV, and LBP features (99% accuracy in recognizing four guava fruit diseases (Canker, Mummification, Dot, and Rust) against healthy fruit). The proposed framework may help the farmers to avoid possible production loss by taking early precautions.
Wearable technology has played an essential role in the Mobile Health (mHealth) sector for diagnosis, treatment, and rehabilitation of numerous diseases and disorders. One such neuro-degenerative disorder is Parkinson's Disease (PD). It is categorized by motor symptoms that affect a patient's motor skills and non-motor symptoms that affect the general health of a PD patient. The quality of life of a patient with PD is highly compromised. To date, there is no cure for the disease, but early intervention and assistive care can help a PD patient to perform daily activities with considerable ease. Many research works in PD management discuss the challenges that healthcare professionals face in the early detection and management of this disease. Sensor devices have been promising to overcome these challenges to a certain degree because of the low cost and accuracy in measurement, yielding precise conclusive results to detect, monitor, and manage PD. This paper presents a Systematic Literature Review (SLR) that provides an in-depth analysis of the PD symptoms, Motor and Non-Motor Symptoms (NMS), the current diagnosis and management techniques used and their efficacy. The paper also highlights the work of various researchers in wearable sensors and their proposals to improve the quality of life of a PD patient by diagnosing, monitoring, and managing PD symptoms remotely via wearable sensors. Another area of focus is commercially available wearables for PD management and a few promising works in progress. This paper will be beneficial for future researchers to identify existing gaps and provide the clinicians better insight into the disease progression, and avoid complications. This paper analyzes around 50+ articles from 2016 to 2021 and concludes that there is still much room for improvement in wearables for PD management during the research process. While much work has been attributed to PD Motor Symptom management, there is little focus on the management of PD NMS via wearable sensors. Furthermore, this paper also presents future work for PD management.
The highly infectious COVID-19 critically affected the world that has stuck millions of citizens in their homes to avoid possible spreading of the disease. Researchers in different fields are continually working to develop vaccines and prevention strategies. However, an accurate forecast of the outbreak can help control the pandemic until a vaccine is available. Several machine learning and deep learning-based approaches are available to forecast the confirmed cases, but they lack the optimized temporal component and nonlinearity. To enhance the current forecasting frameworks’ capability, we proposed optimized long short-term memory networks (LSTM) to forecast COVID-19 cases and reduce mean absolute error. For the optimization of LSTM, we applied bat algorithm. Furthermore, to tackle the premature convergence and local minima problem of BA, we proposed an enhanced variant of BA. The proposed version utilized Gaussian adaptive inertia weight to control the individual velocity in the entire swarm. In addition, we substitute random walk with the Gaussian walk to observe the local search mechanism. The proposed LSTM examines the personal best solution with the swarm’s local best and preserves the optimal solution by combining the Gaussian walk. To evaluate the optimized LSTM, we compared it with the non-optimal version of LSTM, recurrent neural network, gated recurrent units, and other recent state-of-the-art algorithms. The experimental results prove the superiority of the optimized LSTM over other recent algorithms by obtaining 99.52 % accuracy.
The mobile nodes are infrequent movement in nature; therefore, its packet transmission is also infrequent. Packet overload occurred for routing process, and data are lossed by receiver node, since hackers hide the normal routing node. Basically, the hidden node problem is created based on the malicious nodes that are planned to hide the vital relay node in the specific routing path. The packet transmission loss occurred for routing; so, it minimizes the packet delivery ratio and network lifetime. Then, proposed enhanced self-organization of data packet (EAOD) mechanism is planned to aggregate the data packet sequencially from network structure. The hacker node present in routing path is easy to separate from network with trusty nodes. In order to secure the regular characteristics of organizer node from being confirmed as misbehaving node, the hidden node detection technique is designed for abnormal routing node identification. This algorithm checks the neighboring nodes that are hacker node, which hide the trust node in the routing path. And that trust nodes are initially found based on strength value of every node and assign path immediately. It increases network lifetime and minimizes the packet loss rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.