One of the In our technology, we successfully decode gene sequences and transplant seeds from various sources to produce greater productivity within crop yields in a shorter period of time. In a non-progressive way, its technology can have an impact on health issues and also go a long way towards preventing hunger. One of the world's more pressing issues is hunger. Considering important assessments of yields of crops, it is projected that worldwide populations could reach 10 billion and 11.5 billion by 2100, as reported by UNICEF, the Global Hunger Index (GHI), the Global Report on Food Crises (GRFC), and the UN Department of Economic and Social Affairs. It is expected that food production will improve accordingly. Technology advancements must be incorporated into the cultivation area to meet these needs. A major area of agricultural development innovation is the Internet of Things. By using this system, we can enhance the productivity of crops at a lower cost than smart farming. In order to analyze crop data, a variety of sensors are used, such as soil sensors, pest sensors, and environmental sensors. An increase in crop yield can be achieved through either automated or manual controls. Urban agriculture products can be organic and secure because less pesticides, chemicals, and manpower are used. In addition to reducing global warming, the system also produces automatic afforestation.

Keywords : IoT, Smart Agriculture, Global Warming, Synthetic Aperture Radar.

Authors : Gudla Sateesh

Title : Energy-Efficient IoT based Precision Smart Agriculture Monitoring System for Enhanced Crop Fruitage

Volume/Issue : 2026;8(1 (January - February))

Page No : 51 - 57

One of the most common cancers in the world, thyroid cancer is becoming more common. Improving patient outcomes requires precise thyroid cancer prediction and early identification. The creation of prediction models based on a variety of patient data is now possible thanks to machine learning techniques, which have become highly effective instruments for medical diagnostics. This study uses machine learning algorithms to propose a novel method of predicting thyroid cancer. We gathered a large dataset from a cohort of patients with thyroid cancer that included clinical, demographic, and imaging data. We developed prediction models for thyroid cancer risk assessment by utilizing this data and a variety of machine learning algorithms, such as decision trees, support vector machines, random forests, and logistic regression. The findings of our investigation show how well these machine learning algorithms predict thyroid cancer. Our models show promise for accurate risk assessment and early diagnosis due to their high sensitivity and specificity. In order to determine the most important variables influencing the risk of thyroid cancer, we also carried out feature selection and engineering. This helped us uncover prospective biomarkers and risk factors. This study can help medical practitioners make well-informed decisions about patient care and has great promise for the diagnosis of thyroid cancer. By identifying high-risk patients and assisting physicians in offering prompt therapies, machine learning can be integrated into the prediction of thyroid cancer, ultimately improving patient outcomes and lessening the burden of this common malignancy.

Keywords : Decision Trees, Thyroid Cancer, Machine Learning, Support Vector Machine, Malignancy.

Authors : MOLLI SRINIVASA RAO, P J V G PRAKASA RAO

Title : Unveiling Hidden Insights for Early Detection using Machine Learning-Driven Thyroid Cancer Prognosis

Volume/Issue : 2026;8(1 (January - February))

Page No : 40 - 50

Nowadays, many people have pets, but because of busy daily schedules, they are not always able to feed their pets on time. Irregular feeding can create health problems for pets such as obesity, poor nutrition, and shortage of water. To solve this problem, we developed an IoT-based automatic pet feeding system that helps pet owners manage feeding in an easy way. This system ensures that pets receive food at the correct time and in the required quantity without manual effort. In our project, we used an ESP32 microcontroller with a Wi-Fi connection to control the entire feeding system. A motor and servo mechanism is used to dispense food automatically, while sensors are used to monitor the food and water levels. These sensors help the user know when refilling is required. A mobile application connected through the cloud allows pet owners to check the feeding status and control the system from anywhere. During testing, we observed that the system worked smoothly and delivered food accurately at scheduled times. The system also provided real-time updates through the mobile application. Overall, the system can be easily used at home and does not require high cost.

Keywords : Internet of Things (IoT), Automatic Pet Feeder, ESP32, Sensors, Smart Pet Care.

Authors : Dr D Aruna Kumari

Title : Automatic Pet Feeder With Smart Monitoring using IoT

Volume/Issue : 2026;8(1 (January - February))

Page No : 35 - 39

Schizophrenia (SZ) is a severe neuropsychiatric illness that interferes with cognitive and emotional functioning, making early diagnosis essential. Traditional clinical assessments are often subjective, while EEG signals offer valuable insights but are challenged by high dimensionality, noise, and non-linear patterns. To address these issues, a Novel Heterogeneous Dual-Channel Edge-Enhanced Temporal Graph Convolutional Networks with Quantum-Based Avian Navigation Optimizer (NHDETGCNets+QBANO) is proposed for accurate schizophrenia prediction. The proposed framework begins with the preprocessing of raw EEG signals obtained from the Moscow and Warsaw schizophrenia datasets, employing the Adaptive Self-Guided Loop Filter (AS-GLF) to efficiently suppress noise, artifacts, and other signal distortions while enhancing overall signal quality. Subsequently, informative features are extracted using the Quaternion Quadratic-Phase Fourier Transform Domain (QQ-PFTD), capturing both the temporal and spectral characteristics of the EEG signals. For predictive modeling, the NHDETGCNets architecture is utilized, which seamlessly integrates A Novel Dual-Channel Temporal Convolutional Network (AND-CTCN) with a Heterogeneous Edge-Enhanced Graph Attention Network (HE-EGAN), enabling robust relational modeling across EEG channels. To further optimize performance, the Quantum-Based Avian Navigation Optimizer (QBANO) is employed for dynamic hyperparameter tuning, ensuring faster convergence, minimized error rates, reduced computational overhead, and enhanced scalability. Extensive experimental evaluations demonstrate that the NHDETGCNets+QBANO framework consistently achieves an outstanding prediction accuracy of 99.9%, outperforming existing state-of-the-art approaches and establishing itself as a highly reliable and efficient tool for the early and precise prediction of schizophrenia. The outcomes of the suggested framework provide reliable and precise schizophrenia prediction, accurately distinguishing affected individuals, reducing errors, maintaining consistent performance, and demonstrating robustness and efficiency for early detection.

Keywords : Adaptive Self-Guided Loop Filter, Heterogeneous Edge-Enhanced Graph Attention Network, QQPFTTD

Authors : Ramya T

Title : Heterogeneous Dual-Channel Edge-Enhanced Temporal Graph Networks with Quantum Optimization for Accurate Schizophrenia Detection

Volume/Issue : 2026;8(1 (January - February))

Page No : 14 - 34

Gridlock in metropolitan areas is the severe problem regarded within the gift lifestyles. The motors are extended at a excessive rate prompts gridlock at both pinnacle and non-pinnacle hours. This reasons much less powerful site visitors signal administration of streets. Traffic sign control frameworks depend upon a decent time span visitors lighting fixtures. These time touchy signs and symptoms will burn through the proper opportunity for the side of few vehicles out and approximately which surpasses one more avenue of vehicles at a high price to grasp tight for quite some time. The development framework facilities around time squandered for motors of a street at a low fee. It dispenses signal to tune down the thickness of the vehicles. Utilizing photograph dealing with ml python code with ML to compute the thickness of traffic on each path. Constantly A camera is about in every path to be able to seize pics of road. In out model we want to transfer every direction photographs of street. Our framework will song down items in every picture and count the quantity of cars, man or woman walking and emergency car. In view of variety of cars, character on foot and rescue car popularity our framework will accord manipulate traffic signals of separate course. In this venture we've utilized the model like the green and red signs are addressed making use of LEDs.

Keywords : Adaptive Traffic Signal Control, Pedestrian Detection , Emergency Vehicle Preemption, Computer Vision.

Authors : Kodeboina Suresh

Title : Real-Time Traffic Signal Optimization with Pedestrian Detection and Emergency Vehicle Priority

Volume/Issue : 2026;8(1 (January - February))

Page No : 9 - 13

Detection and analysis of brain tumours from Magnetic Resonance Imaging (MRI) scans are essential for the early detection and treatment of brain cancers. Manual analysis of the MRI images is a time-consuming process for radiologists, as there are possibilities of human errors, especially while handling large volumes of medical images. An automatic brain tumor image classification method utilizing Deep Learning algorithms is proposed to counter this problem. For this project, three different models of deep learning are applied. First, a personal solution of the Convolutional Neural Network (CNN) architecture is developed as a basic model to identify the spatial features of the MRI images. Second, VGG16, a transfer learning model developed earlier for other large-scale image databases, is utilized to tap into the experience gained from handling large-scale image databases. Third, ResNet50, a more complex model of the residual network architecture, is applied to overcome the problem of a disappearing gradient during the backward propagation process to achieve better results for the classification process of the brain tumor dataset. The proposed system can also provide real-time prediction, and any new MRI image can be uploaded by the user, showing the predicted tumor type with the confidence score. The experimental findings prove that the transfer learning models achieve higher performance compared to the basic CNN, among which ResNet50 obtained the top result. This work verifies deep learning and transfer learning in medical image analysis and delivers a trustworthy way of automatic brain tumor classification.

Keywords : Brain MRI, Tumor Classification, CNN, VGG16, ResNet50, Deep Learning, Transfer Learning.

Authors : C Lokeshwari

Title : MRI Image Analysis for Early Brain Tumor Detection using Deep Learning

Volume/Issue : 2026;8(1 (January - February))

Page No : 1 - 8