Deep Learning-Driven Chatbots for Crop Health Monitoring and Agricultural Decision Support | Chapter 1 | Mathematics and Computer Science: Research Updates Vol. 9

 

Numerous problems in agriculture, including unpredictable crop yields, disease susceptibility, and the consequences of weather variability, put nutrition and farmer livelihoods at risk. In order to increase agricultural yields, detect diseases early, and provide valuable insights on the Crop Yield Prediction Dataset and Plant Village Dataset, this research provides an AI-powered solution to these issues by integrating deep learning, sophisticated machine learning algorithms, and instantaneous data analysis. The system employs a sophisticated methodology that forecasts temperature, humidity, and conditions for the next five days using the PyOWM API; detects crop diseases using data augmentation and deep learning models such as CNN (accuracy 99.14%), DenseNet-201 (accuracy 99.04%), and Visual Geometry Group-VGG19 (accuracy 97%); and predicts crop yield using models such as Multi-Layer Perceptron-MLP (R2 Score: 0.8242), MLP + Regressor, and Random Forest Regressor achieves the highest R2 Score (0.1789). An AI chatbot that provides farmers with recommendations, disease control methods, and personalised suggestions is part of the technology's real-time help. In order to provide an AI-driven system for weather forecasting, disease detection, yield prediction, and real-time assistance via a chatbot, this project integrates models with high accuracy rates. The user-friendly Streamlit UI is available in Telugu, Hindi, and English, and SQLite handles the secure login and registration procedure.

 

 

Author(s) Details

 

Anantha Kranthi Suravarapu
Department of CSE (Artificial Intelligence & Machine Learning), Ramachandra College of Engineering, Eluru, Andhra Pradesh, India.

 

Please see the book here :- https://doi.org/10.9734/bpi/mcsru/v9/6825

License Plate Recognition and Extraction of Details from Database | Chapter 20 | Leading the Charge: A Guide to Management, Entrepreneurship and Technology in the Dynamic Business Landscape Edition 1

A sort of technology known as number plate recognition (LPR), primarily software, allows computer systems to automatically read a car's number plate number from digital photos. License Plate Recognition systems use the concept of optical character recognition to read the characters on vehicle license plates. Registration plate detection devices rely on optical character processing to comprehend the written information on the automobile's registration tag. Stated differently, LPR produces the characters that are engraved on an automobile's registration plate after receiving an image of the vehicle as input. It displays the vehicle's details and reads the characters. It can make use of already-installed closed-circuit television, and traffic enforcement cameras. It is used by enforcement agencies across the globe to enforce the law, including Figuring out whether an automobile is licensed or registered. On top of that, this is the case utilized by highway agencies and other pay-per-use roadways for electronic toll collecting and traffic flow cataloging. The main motive is to interpret and show registration plate individuals so that cars may be recognized and categorized.

 

Author (s) Details

 

P. Haarathi
Department of Electronics and Communication Engineering, V R Siddhartha college, Andhra Pradesh, India.

 

G. Venkata Subbaiah
Department of Electronics and Communication Engineering, V R Siddhartha college, Andhra Pradesh, India.

 

P. Hema Nandini
Department of Electronics and Communication Engineering, V R Siddhartha college, Andhra Pradesh, India.

 

P. Bala Naveena
Department of Electronics and Communication Engineering, V R Siddhartha college, Andhra Pradesh, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mono/978-93-48859-98-3/CH20

SIAS: Sensory Impairment Assistive Software | Chapter 16 | Leading the Charge: A Guide to Management, Entrepreneurship and Technology in the Dynamic Business Landscape Edition 1

SIAS – Sensory Impairment Assistive Software, presents an innovative application of YOLO (You Only Look Once), and CNN (Convolutional Neural Network). Through Python-based deep learning techniques, the system leverages YOLO’s speed and accuracy to identify objects within a live camera feed, providing vocal announcements to the user. Furthermore, it offers a few additional features, which include gesture-to-speech conversion to facilitate communication between the physically challenged, Text-to-speech conversion, and Image Processing. This proposes an innovative communication system framework for deaf, dumb and blind people within a single compact device.

 

Author (s) Details

 

Supriya C

Department of Information Science and Engineering, Acharya Institute of Technology, Bengaluru, Karnataka -560107, India.

 

Janavi Mahesh
Department of Information Science and Engineering, Acharya Institute of Technology, Bengaluru, Karnataka -560107, India.

 

Karan
Department of Information Science and Engineering, Acharya Institute of Technology, Bengaluru, Karnataka -560107, India.

 

Keerthana K S
Department of Information Science and Engineering, Acharya Institute of Technology, Bengaluru, Karnataka -560107, India.

 

Navyashree R
Department of Information Science and Engineering, Acharya Institute of Technology, Bengaluru, Karnataka -560107, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mono/978-93-48859-98-3/CH16

Suspicious Activity Detection System Using Machine Learning | Chapter 34 | Innovative Solutions: A Systematic Approach towards Sustainable Future

Monitoring human activities is an important part of ensuring public safety. The aim is to detect suspicious behavior. To achieve this, we use LRCN, a long-term continuous regression algorithm, to identify negative functions. When analyzing suspicious behavior, it is important to consider the temporal data of these videos, using a blend of CNN and RNN to explore the frames and extract relevant features. The main activities in the project include research, collecting and processing preliminary data, creating and training models, and evaluating their performance. The detection result can be accurate and detect suspicious behavior immediately. We use the KTH dataset containing 600 walking and running frames and the Kaggle dataset containing 100 training images to build the model. Our test models show that the system and video can detect suspicious situations with 86% accuracy, and we expect this accuracy to increase as the data grows.

 

Author (s) Details

Sumangala S J
Department of ECE, Acharya Institute of Technology, Bangalore, India.

 

Darshan M Y
Department of ECE, Acharya Institute of Technology, Bangalore, India.

 

Kiran M B
Department of ECE, Acharya Institute of Technology, Bangalore, India.

 

Nandish R
Department of ECE, Acharya Institute of Technology, Bangalore, India.

 

Akarsh D H
Department of ECE, Acharya Institute of Technology, Bangalore, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mono/978-93-49238-47-3/CH34

Sentinel Lymph Node (SLN) Metastases in Breast Carcinoma Whole Slide Image (WSI) through Densenet Deep Learning Network: An Approach towards Clinical Management and Treatment | Chapter 20 | Issues and Developments in Medicine and Medical Research Vol. 5

 This research proposes a novel sentinel lymph metastasis categorization methodology that will aid pathologists in making quick and accurate diagnoses. DenseNet-161, a CNN-based image classification model for classifying breast lymph node metastases from WSI images, was discussed in this study. Breast cancer has the intention of spreading throughout the body. Locally, cancer cells spread by infecting healthy tissue nearby. It can also spread throughout an area by infecting nearby lymph nodes, tissues, or organs. The CNN model learns the features from the training data at first. Following that, after successfully fitting the training data, it attempts to generalise and generate correct predictions for new data that it has not seen before. A model that overfits the training data is referred to as overfitting. Even after applying the thresholding pre-processing technique, the noise persists, necessitating additional pre-processing before training the model. Furthermore, data-augmentation will considerably improve the accuracy by expanding the dataset size.

Author(S) Details

Rajasekaran Subramanian
Keshav Memorial Institute of Technology, Hyderabad, Telangana, India.

R. Devika Rubi
Keshav Memorial Institute of Technology, Hyderabad, Telangana, India.

Abhay Krishna Kasavaraju
Keshav Memorial Institute of Technology, Hyderabad, Telangana, India.

Samayk Jain
Keshav Memorial Institute of Technology, Hyderabad, Telangana, India.

Swathi Guptha
Keshav Memorial Institute of Technology, Hyderabad, Telangana, India.

Suraj Raghavendra Pingali
Keshav Memorial Institute of Technology, Hyderabad, Telangana, India.

View Book:- https://stm.bookpi.org/IDMMR-V5/article/view/5913