Research is the Jedi's path of science—guided by curiosity, fueled by data, and always pushing the boundaries of the known universe.
Research is the Jedi's path of science—guided by curiosity, fueled by data, and always pushing the boundaries of the known universe.
The integration of Internet of Things (IoT) technologies into healthcare presents a transformative opportunity to enhance the management of Alzheimer's disease, a neurodegenerative disorder that progressively impairs memory and cognitive function. As the global prevalence of Alzheimer's continues to rise, there is an increasing demand for innovative solutions that can support patients, caregivers, and healthcare providers in managing the disease more effectively.
1. Remote Monitoring and Early Detection
IoT-enabled devices such as wearable sensors, smart home systems, and mobile health applications can continuously monitor patients' vital signs, movement patterns, and behavioral changes. These devices can collect and transmit data in real time to healthcare providers, enabling early detection of symptoms such as wandering, agitation, or irregular sleep patterns. By analyzing this data, predictive models can be developed to identify potential triggers and prevent adverse events before they occur.
2. Personalized Care and Cognitive Support
IoT technologies can facilitate personalized care plans tailored to the individual needs of Alzheimer's patients. For instance, smart home environments can be equipped with sensors that adapt to the patient's routine, providing reminders for medication, hydration, and daily activities. Cognitive support systems, integrated with AI, can offer interactive exercises and memory aids, helping to slow cognitive decline and improve the quality of life.
3. Caregiver Assistance and Stress Reduction
Caregivers often face significant challenges in managing Alzheimer's patients, including stress and burnout. IoT solutions can assist caregivers by providing real-time alerts and remote monitoring capabilities, allowing them to supervise the patient's condition from a distance. Additionally, IoT-enabled devices can automate routine tasks, such as medication dispensing or environmental adjustments, reducing the caregiver's workload and stress levels.
4. Data-Driven Insights for Research and Treatment
The vast amount of data generated by IoT devices can contribute to a deeper understanding of Alzheimer's disease. Researchers can analyze this data to identify patterns, evaluate the effectiveness of interventions, and develop new treatment approaches. Furthermore, the integration of IoT with machine learning algorithms can lead to the discovery of novel biomarkers for early diagnosis and personalized treatment strategies.
The exponential growth of network-connected devices is leading to a significant increase in spectrum congestion, resulting in heightened interference and cross-talk issues. As high-bandwidth applications like streaming platforms and the metaverse become more prevalent, the demand for efficient data transmission methods continues to rise. Additionally, there are concerns regarding the potential health implications of prolonged exposure to dense radio frequency (RF) signals. To address these challenges, leveraging the properties of visible light for communication presents a compelling solution. This research is motivated by the need to develop efficient modulation techniques for Visible Light Communication (VLC) that can provide high data rates, minimize error rates, and maintain reliable communication over varying distances, particularly in indoor environments for IoT applications.
This work contributes significantly to the field by designing and developing prototypes for photodiode-based VLC and camera-based Optical Camera Communication (OCC) systems. Several innovative modulation techniques have been proposed and evaluated using these prototypes in real-world settings. The research includes the development of a low-cost VLC testbed, performance analysis of OOK and PWM modulation techniques, and the introduction of advanced modulation schemes such as rolling shutter-based hybrid frequency shift pulse width modulation (HFSPDM), and Binary Hierarchical Image Classification. Additionally, the research explores the integration of VLC in IoT applications, proposing solutions for image transmission, indoor positioning, and real-time sensor data transmission. The performance of each proposed technique has been rigorously compared with existing methods, demonstrating improvements in efficiency and reliability suitable for practical deployment in IoT environments.
Design, Implementation, and Evaluation of a Low-Cost Visible Light Communication Testbed
LiCamIoT: An 8x8 LED Matrix Pattern to Camera Communication for LiFi-IoT Applications
A Novel 2D LED Matrix and Aztec Pattern Inspired Optical Camera Communication for Industrial IoT
A Nested Texture Inspired Novel Image Pattern Based Optical Camera Communication
LiCamPos : An Indoor Positioning System using Light to Camera Communication
An Image Transmission Technique using Low-Cost Li-Fi Testbed
From Light to Li-Fi: Research Challenges in Modulation, MIMO, Deployment Strategies and Handover
The rapid urbanization and population growth have led to a significant decrease in cultivable land, especially in developing and underdeveloped countries. This has created an urgent need for innovative farming techniques that can maximize agricultural output within limited spaces. Traditional farming practices are no longer sufficient to meet the growing demand for food, making it essential to explore advanced methods like multi-level farming and hydroponics. The motivation behind the research is to address this pressing issue of food scarcity by proposing a Multi-Level Hydroponics System that integrates cutting-edge technologies such as IoT, Edge Computing, and Computer Vision. By optimizing space and resources, this system aims to enhance agricultural productivity and sustainability, particularly in urban environments where space is at a premium.
The proposed research makes several significant contributions to the field of modern agriculture and resource management. First, a Multi-Level Hydroponics System is developed, which uses image processing for accurate cultivation estimation, achieving up to 95% accuracy in estimating fodder production for crops like corn. Additionally, the research introduces an automatic ration distribution system utilizing RFID and fingerprint sensors, designed to improve transparency and efficiency in India's public distribution system (PDS). Integrating cloud platforms and chatbot assistance further enhances the system’s functionality. Moreover, the research addresses water management challenges by proposing a Smart Water Grid that detects tank leakages and optimizes water usage through cloud-based monitoring and control. Finally, the study presents a Do-It-Yourself (DIY) approach to building agricultural drones equipped with IoT and cloud computing features, enabling autonomous field monitoring and data analysis for improved crop management. These contributions collectively advance the development of sustainable, technology-driven solutions for agriculture and resource management.
HydroIoT: An IoT and Edge Computing based Multi-Level Hydroponics System
A Smart Biometric-Based Public Distribution System with Chatbot and Cloud Platform Support
An IoT-Based Smart Water Microgrid and Smart Water Tank Management System
AgrOne: An Agricultural Drone using Internet of Things, Data Analytics and Cloud Computing Features
Cloud based data analysis and monitoring of smart multi-level irrigation system using IoT
Contributions
This research contributes significantly to the optimization and scalability of distributed systems, particularly within the realm of IoT applications. The introduction of a blockchain-integrated sharding algorithm specifically designed for IoT frameworks addresses the challenge of limited scalability. By focusing on frequently traded sender-receiver pairs, the proposed algorithm enhances the system's transaction handling capabilities, evidenced by a 10% reduction in execution time and improved transactions per second (TPS) as the task volume increases. This research also introduces an indoor localization system using low-cost microphones, which incorporates machine learning for efficient data processing and integration with smart home devices, further exemplifying the application of IoT in enhancing system efficiency.
Additionally, the research presents several innovative solutions aimed at addressing practical challenges in various domains. The "Rail-Rakshak" solar-powered autonomous vehicle is designed for railway track inspection, utilizing cloud computing and NLP for effective crack detection and reporting. The "Saur Sikka" platform facilitates Peer-to-Peer Solar Energy trading, enabling efficient management and remote tracking of surplus energy through IoT and cloud technologies. Other contributions include a Smart Waste Segregation and Monitoring System, a Sign Language Recognition system using sensor-enabled gloves, and an automated waste collection system employing a line follower robot, all of which leverage IoT and cloud platforms to provide cost-effective, scalable solutions for real-world problems.
A ROOF Computing Architecture-based Indoor Positioning System for IoT Applications
AI-based Solar Powered Railway Track Crack Detection and Notification System with Chatbot Support
SAF-Sutra: A Prototype of Remote Smart Waste Segregation and Garbage Level Monitoring System
Talking hands — An Indian sign language to speech translating gloves
Fully Automated Waste Management System Using Line Follower Robot