arXiv subjects

Manoj Kumar Rajagopal

Publications and source records attributed to Manoj Kumar Rajagopal.

5 recordsLinked to original sources

arXiv2023

Cashew dataset generation using augmentation and RaLSGAN and a transfer learning based tinyML approach towards disease detection

Cashew is one of the most extensively consumed nuts in the world, and it is also known as a cash crop. A tree may generate a substantial yield in a few months and has a lifetime of around 70 to 80 years. Yet, in addition to the benefits, there are certain constraints to its cultivation. With the exception of parasites and algae, anthracnose is the most common disease affecting trees. When it comes to cashew, the dense structure of the tree makes it difficult to diagnose the disease with ease compared to short crops. Hence, we present a dataset that exclusively consists of healthy and diseased cashew leaves and fruits. The dataset is authenticated by adding RGB color transformation to highlight diseased regions, photometric and geometric augmentations, and RaLSGAN to enlarge the initial collection of images and boost performance in real-time situations when working with a constrained dataset. Further, transfer learning is used to test the classification efficiency of the dataset using algorithms such as MobileNet and Inception. TensorFlow lite is utilized to develop these algorithms for disease diagnosis utilizing drones in real-time. Several post-training optimization strategies are utilized, and their memory size is compared. They have proven their effectiveness by delivering high accuracy (up to 99%) and a decrease in memory and latency, making them ideal for use in applications with limited resources.

eess.IV↗

arXiv2023

Human activity recognition using deep learning approaches and single frame cnn and convolutional lstm

Human activity recognition is one of the most important tasks in computer vision and has proved useful in different fields such as healthcare, sports training and security. There are a number of approaches that have been explored to solve this task, some of them involving sensor data, and some involving video data. In this paper, we aim to explore two deep learning-based approaches, namely single frame Convolutional Neural Networks (CNNs) and convolutional Long Short-Term Memory to recognise human actions from videos. Using a convolutional neural networks-based method is advantageous as CNNs can extract features automatically and Long Short-Term Memory networks are great when it comes to working on sequence data such as video. The two models were trained and evaluated on a benchmark action recognition dataset, UCF50, and another dataset that was created for the experimentation. Though both models exhibit good accuracies, the single frame CNN model outperforms the Convolutional LSTM model by having an accuracy of 99.8% with the UCF50 dataset.

cs.CV↗

arXiv2023

Amity -- A Hybrid Mental Health Application

Wellness in trivial terms combines physical, social, and mental wellbeing. While mental health is neglected, long-term success in a person life is mostly determined by his psychological health and contentment. For a person in distress, professional mental health services are quite expensive, unpopular, and invite a lot of hesitation. Hence, it would be effective to use an Android application that can offer day to day therapeutic assistance, meditation sessions, and guidance since it can cater to a massive community instantly. In this paper, we propose a mobile and web application AMITY with a chat group and chatbot created using a machine learning approach. We have also built a dataset to train the chatbot model that we propose in this paper. We briefly introduce the dataset and the machine learning model in section 3. In section 4, we include the architecture and the development details of the Hybrid application. Next, we present our results on usability and the efficiency of the idea we propose.

cs.HC↗

arXiv2023

Comparative study on Judgment Text Classification for Transformer Based Models

This work involves the usage of various NLP models to predict the winner of a particular judgment by the means of text extraction and summarization from a judgment document. These documents are useful when it comes to legal proceedings. One such advantage is that these can be used for citations and precedence reference in Lawsuits and cases which makes a strong argument for their case by the ones using it. When it comes to precedence, it is necessary to refer to an ample number of documents in order to collect legal points with respect to the case. However, reviewing these documents takes a long time to analyze due to the complex word structure and the size of the document. This work involves the comparative study of 6 different self-attention-based transformer models and how they perform when they are being tweaked in 4 different activation functions. These models which are trained with 200 judgement contexts and their results are being judged based on different benchmark parameters. These models finally have a confidence level up to 99% while predicting the judgment. This can be used to get a particular judgment document without spending too much time searching relevant cases and reading them completely.

cs.CL↗

arXiv2023

Artificial Intelligence based drone for early disease detection and precision pesticide management in cashew farming

The use of unmanned aerial vehicles (UAV) is revolutionizing the agricultural industry. Cashews are grown by approximately 70% of small and marginal farmers, and the cashew industry plays a critical role in their economic development. To take timely counter measures against plant diseases and infections, it is imperative to monitor and detect diseases as early as possible and take suitable measures. Using UAVs, such as those that are equipped with artificial intelligence, can assist farmers by providing early detection of crop diseases and precision pesticide application. An edge computing paradigm of Artificial Intelligence is employed to process this image in order to make decisions with the least amount of latency possible. As a result of these decisions, the stage of infestation, the crops affected, the method of prevention of spreading the disease, and what type and amount of pesticides need to be applied can be determined. UAVs equipped with sensors detect disease patterns quickly and accurately over large areas. Combined with AI algorithms, these machines can analyse data from a variety of sources such as temperature, humidity, CO2 levels and soil composition. This allows them to recognize disease symptoms before they become visible. Early detection allows for more effective control strategies that can reduce costs caused by lost production due to infestations or crop failure. Using an end-to-end training architecture, mobileNetV2 determines how to classify anthracnose disease in cashew leaves. A standard PlantVillage dataset is used for performance evaluation and for standardization. Additionally, samples captured with a drone present a variety of image samples captured in a variety of conditions, which complicates the analysis. According to our analysis, we were able to identify the anthracnose with 95% accuracy and the healthy leaves with 99% accuracy.

eess.IV↗