Artificial Intelligence System for Effective Detection of Animal Intervention in Croplands (original) (raw)

Implementation of Smart Security System in Agriculture elds Using Embedded Machine Learning

2023 International Conference on Applied Intelligence and Sustainable Computing (ICAISC), 2023

Tiny Machine Learning (TinyML), a branch of machine learning that focuses on the effectiveness of machine learning on extremely constrained edge machines, is flourishing. Deep learning techniques are being used more frequently lately in a variety of data-intensive and time-sensitive Internet of Things (IoT) apps. Because MCUs lack resources like RAM, deploying new methods like Deep Neural Networks (DNN) models on them has proven challenging. However, recent developments in the TinyML space promise to create a completely new class of peripheral apps. By eliminating the need for the cloud's omnipresent computing support, which uses power and presents risks to data security and privacy, TinyML paves the way for the development of original apps and services. Traditional machine learning needs a lot of processing capacity to predict a scenario. This computational capacity will be moved from high-end systems to low-end devices thanks to the TinyML method for machine learning on small devices. To keep the precision of the learning models, enable resource-efficient small edge devices to manage the training and deployment process, maximize computing capacity, and enhance dependability are some of the challenges presented by this change. Here in this paper, we propose a efficient method to detect animals near farmland for security purposes using TinyML and compared with many algorithms and their effectiveness.

Animal Repellent System for Smart Farming Using AI and Deep Learning

Agribusiness robotization has been on the ascent using, among others, Deep Neural Networks (DNN) and IOT for the turn of events and sending of many controlling, endlessly checking applications to a great grained degree. In this quickly developing situation, replicating the association with the components out of ways to the rural environmental factors, comprising vegetation and fauna, is applicable to open trouble. One of the statute issues of current ranchers is cautious plants from wild animals' attacks. There are unmistakable customary cycles to resolve this issue which might be deadly (e.g., shooting, catching) and non-deadly (e.g., scarecrow, synthetic anti-agents, natural substances, cross-section, or electric-fueled walls). In this endeavor, we expand a gadget that joins AI PC innovative and judicious the use of DCNN for identifying and spotting creature species and explicit ultrasound outflow (i.e., outstanding for each species) for repulsing them.

IoT Based Smart Agriculture and Animal Detection System

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

Agriculture, the science and art of cultivating plants, plays a pivotal role in the evolution of a primary agricultural economy. More than 50% of the population in India depends upon farming. Hurdles concerning agriculture have significantly retarded the growth in this sector. The most significant obstacle incurred by the farmers is inefficient crop management and crop raiding by external sources, especially the human-wildlife conflict. A cumulative approach including the application of "Internet of Things" and traditional farming techniques, along with methods to barricade crop destruction has been elaborately highlighted by way of integrated systems. Hence this proposed module targets at making agriculture smart by proposing a device detects the presence of any living being by using either PIR Sensor or Ultrasonic Sensor, especially animals around the land to be cultivated, along with smart irrigation control and real-time data analysis which is also inclusive of smart warehouse management parameters like-temperature, humidity and pressure measured by using (DHT22 Sensor and BMP180 Sensor). This data may either be visualized by using the Blynk Software or received in the form of messages through the GSM Module. To combat the ruckus caused by animals, detection of their presence along with a laser security system has been provided in the proposed system. Efforts have been made to help the farmer in rectifying multiple issues at once.

Animal Intrusion Detection Model based on Temporal Convolutional Network for Smart Farming

Our project revolves around integration of image processing and AI for preventing animals from approaching the crops and ensuring the protection of crops. It incorporates two key features: detecting live animal through a live camera feed and predicting unseen animals image uploads in-off assistance. The system involves advance image processing software techniques like edge detection and object recognition to identify animals and categorize them base on their species, and triggers timely alarms or deterrents that help to minimize the loss. Furthermore, the customers can upload images for artificial intelligence-based analysis so that they can get insights into animal behavioral patterns and extract the best remedial measures The program's integrated approach seeks to improve food security and ensure crop protection methods are not only humane but also technology-driven for sustainable farming.

Security Measures for Crops and Domestic Animals using CNN

IJISRT, 2022

India is mainly an agriculture based country. Security of agricultural farm is of utmost importance for protecting the produce. Not being able to make the grown crops to the market is another side of the problem. Valuable investments and efforts can be ruined in minutes intentionally or unintentionally by persons or by animals. Introducing machine learning to this problem paves a way to smart agriculture. The proposed system employs Raspberry Pi board to detect any malicious activities or motion in the farm land and triggers the thermal camera to take picture of the scene image. The captured image is fed into the trained CNN (Convolutional Neural Network) model of deep learning. And after detecting the class of the animal, a sound file mapped to that class is played at little higher frequency, so as to scare away the animal. The result shows that the system is 80-95% accurate and 100% consistent for detecting any suspicious movement and to act accordingly.

Developing a Prototype of Smart Crop Protection System from Animals

CERN European Organization for Nuclear Research - Zenodo, 2022

India is an agrarian country. Agriculture has perpetually been India's most significant economic sector. However, farmers are facing many issues. One of them is the destruction of the crops by animals. This leads to huge losses for the farmers. Considering this scenario an automatic crop protection system is suggested in this paper. In this, first of all, an animal detection system is developed which gives a warning and diverts the animal from the farm without harming it. Further, it informs the farm owner about the entry of animals on the farm. This is achieved with the help of an Arduino Uno-based system using a microcontroller. The system continuously checks the activity of animals. The passive infrared sensors and ultrasonic sensors are used to detect animals and birds and they send the signal to the controller. In this prototype, the complete safety of crops is ensured from animals without harming animals and with minimum loss to the farm. Also, an attempt is made to cover all kinds of animals and birds. Deployment of the system may result in a significant increase in the yield of crops.

IOT Based Crop Protection System against Birds and Wild Animal Attacks

The main aim of our project is to protect the crops from damage caused by animal as well as divert the animal without any harm. Crops in farms are many times ravaged by local animals like buffaloes, cows, goats, birds etc. This leads to huge losses for the farmers. It is not possible for farmers to barricade entire fields or stay on field 24 hours and guard it. So here we propose automatic crop protection system from animals. Animal detection system is designed to detect the presence of animal and offer a warning. In this project we used PIR and ultrasonic sensors to detect the movement of the animal and send signal to the controller. It diverts the animal by producing sound and signal further, this signal is transmitted to GSM and which gives an alert to farmers and forest department immediately.

IoT solutions for crop protection against wild animal attacks

2018 IEEE International Conference on Environmental Engineering (EE)

Technology plays a central role in our everyday life. There has been a surge in the demand of Internet of Things (IoT) in many sectors, which has drawn significant research attention from both the academia and the industry. In the agriculture sector alone, the deployment of IoT has led to smart farming, precision agriculture, just to mention a few. This paper presents the development of Internet of Things application for crop protection to prevent animal intrusions in the crop field. A repelling and a monitoring system is provided to prevent potential damages in Agriculture, both from wild animal attacks and weather conditions.

AI Crop Predictor and Weed Detector Using Wireless Technologies: A Smart Application for Farmers

Arabian Journal for Science and Engineering, 2020

Agriculture is undoubtedly one of the biggest and most important professions in the world. Optimization of agriculture and aiming gradually and extensively toward smart agriculture are the need of the hour. IOT (Internet of Things) technology has already been successful in easing people's lives with its wide range of applications in almost all arenas. In this paper, our work takes the help of IOT devices, wireless sensor network (WSN) and AI techniques and combines them for faster and effective recommendation of suitable crops to farmers based on a list of factors such as temperature, annual precipitation, total available land size, past crop grown history and other resources. Additionally, detection of unwanted plants on crops, namely weed detection, is implemented with frame-capturing drone and deep learning methods. Naïve Bayes algorithm for crop recommendation based on several factors detected by WSN sensor nodes has been used, resulting in an accuracy of 89.29%, which has proved to be better than several other discussed algorithms in the paper, like regression or support vector machine. Deep learning using neural network successfully identifies weeds present in a specific area of crop growth extending an additional protective measure to farmers. The comprehensive application developed for farmers not only reduces the physical hardship and time spent on different agricultural activities, but also increases the overall land yield, reduces possibility of losses due to failure of crops in a particular soil and lessens the chances of damage caused to crops by weeds.

Agriculture Field Automation and Digitization Using Internet of Things and Machine Learning

Journal of Sensors

The real-time smart monitoring with intelligence highly gained significant attention for enhancing the productivity of the crop. Currently, IoT generates a lot of real-time data from the sensors, actuators, and identification technologies. However, extracting the meaningful insights from the data is necessary for realizing the intelligent ecosystem in agriculture. Based upon the previous studies, it is also identified that the limited studies have merely implemented machine learning (ML) on real-time data obtained through customized hardware with dedicated server. In this study, we have proposed a customized hand-held device that enables to deliver recommendations to the farmer on the basis of real-time data obtained through IoT hardware and ML. A three-layer structure is proposed in the study for realizing custom hardware with 2.4 GHz ZigBee and IoT sensors for the data acquisition, communication, and recommendation. As a part of real-time implementation, the calibration of the sen...