There are millions of individuals who cannot access important environmental sounds like alarm clocks, sirens etc., due to their auditory impairments [1]. The Visual Sound Alert System is designed specifically for these individuals and is an economical IoT-based Embedded System containing a MAX4466 Microphone and ESP8266 (NodeMCU) Microcontroller which performs 64-Point FFT Frequency Analysis of the Ambient Sound to classify its severity level (Low intensity which is (<300 Hz), Medium intensity which is between (300–1000 Hz) and High intensity which is (>1000 Hz). Notifications will be sent/received via an RGB LED lamp, a 16×2 I2C LCD Display, and Push Notifications on the Blynk IoT Mobile App for High Intensity (Severe) Events. The accuracy of our experimentalresults indicates that the latency of our classification model (less than 500ms) for discriminating between sounds was below 3 seconds for delivery of push notifications to an end-user mobile device as such our Embedded System represents an economically viable assistive technology solution designed to improve the individual’s situational awareness.

Agricultural systems are multifaceted adaptive systems that are constructed through dynamic processes of interaction between climate, soil, vegetation, and management activities, and which are progressively evidently, climate variability and extreme events. Conventional methods of monitoring have constraints of low spatial coverage, expensive nature and low sensitivity to the spatiotemporal heterogeneity. Current developments in satellite remote sensing have made available large amounts of multisensory data including optical, SAR, and thermal data, that when combined with the meteorological and edaphic data, can be used to fully monitor the agriculture. This chapter reviews the methods of artificial intelligence (AI) and machine learning, deep learning, and spatiotemporal models to monitor crops, predict yields and assess food security. The focus is put on the time-series analysis, multi-source data fusion, and early-warning applications, including the drought detection and yield-gap analysis.

The purpose of this project is to design an AI-Based Secure Software Defined Networking (SDN) Framework for Smart City IoT Networks to provide intelligent traffic management, real-time threat detection, and improved security for IoT devices that can communicate with each other. This project suggests a methodology that utilizes AI methods into SDN to improve the network's dynamic ability for identifying and mitigating cyberattacks. A hybrid security solution is utilized that uses both Rule-Based Detection mechanisms and Machine Learning (ML) Based Detection techniques. The Rule-Based Detection mechanisms make use of predefined rules and thresholds to recognize malicious activity, and a ML algorithm employs trained models to recognize sophisticated and unknown threats with high precision. The framework itself is realized in an SDN setup and also emulated through MATLAB software to analyze performance in various network attack situations. The outcomes show that the Rule-Based Detection registered an accuracy of 98.285% for well-known attack patterns, and the ML Based Detection was realized at a perfect degree of accuracy (100%) with the aim of efficient identification and classification of malicious network behavior. Overall, the AI based SDN framework integrates.

Corrosion can be described as a gradual degradation of the steel and concrete structures that generates less strength of the structure and decreases the service life when the process is not detected in time. The conventional inspection techniques like visual inspection and destructive testing are slow and subjective, and in many cases, they cannot be used to detect corrosion at an early stage. In the framework of this paper, a multimodal deep-learning framework will be offered, which combines both corrosion surface images and numerical structural information to facilitate automated evaluation of bridge condition and Remaining Useful Life (RUL) prediction. The extraction of corrosion features from high-resolution images is performed using a Convolutional Neural Network (ResNet-based), which can be 98.1 percent accurate in classifying corrosion. Parallel to this, age, stress, temperature, and humidity are solved with an XGBoost regression model, and an $R^{2}$ score of 0.99 is obtained to estimate RUL. The two-branch outputs are combined with a latefusion mechanism promoting the predictive reliability yielding a multimodal prediction $R^{2}$ of 0.995 that is better than singlemodal models. The system facilitates real-time tracking and helps with proactive maintenance scheduling to have safer and longerlasting bridge infrastructure.

IoT-Enabled Smart Mobility in Logistics offers a novel approach to enhance logistics and supply chain management in urban transport by integrating embedded systems, sensor network system, and fog computing. The system employs the ESP32 SoC as the central processing unit, facilitating local data processing at the edge rather than in the cloud center, thereby significantly reducing latency, minimizing data transmission costs, and improving operational efficiency, particularly in settings with restricted or sporadic internet connectivity. The system also employs RFID tags for efficient product identification, facilitating automated tracking and inventory control management. A consortium of sensors, including tilt, temperature, humidity, and poisonous gas sensors, perpetually monitors shipment conditions and product status in live time, thereby insuring product integrity and safety throughout storage and transportation. The data gathered from these sensors is processed locally by the ESP32 SoC and forwarded to Node-RED fog computing platform facilitating prompt decision-making and immediate response to any identified anomalies. The Node-RED platform offers an intuitive dashboard that delivers real-time updates, system notifications, detailed analytics and telegram notification. This web dashboard is available on mobile devices and personal computers, enabling logistics managers to remotely oversee inventory, track shipments, and swiftly address possible concerns. By integrating the advantages of fog computing, such as diminished latency, improved security, and optimized data management. It is versatile across multiple sectors, such as retail, healthcare, food storage, and manufacturing, offering increased safety, superior decision-making, and optimized operations throughout the logistics and supply chain network.

There are numerous in number of visually impaired individuals present i.e., more than 2.2 billion of the world population. For them, Traditional aid methods like walking canes have limited reach and can only partially identify the obstacles in front of the people having vision impairment. Therefore, primary goal of this project is to provide assistance in both indoors and outdoors for visually impaired peoples by addressing all the problems facing by them in single solution. The Proposed system can be used to find route and provide direction to the users through google API embedded in the system. Light Detection and Ranging sensor can be used to detect obstacle around 360-degree of the impaired people and intimate distance of the in-front object from user. The defined system can detect the required product around them indoors with the help of Open-Source computer vision library (OpenCV) and inbuilt trained Ollama AI. The head mount device will assist the visually impaired by providing real time feedbacks through Bluetooth earphones that can be connected with the microprocessor. In addition to the object detection, the system can detect the Indian currency denominations with the help of OpenCV and Ollama AI. Also, the defined system can provide emergency alerts to the saved contacts in the emergency situations through GSM module.

Rapid growth of medical data in both hospitals and healthcare industries has made data handling increasingly challenging. Fast access to relevant medical information in an emergency is essential, but the huge data in databases makes this difficult. The management of data in the public domain is made more difficult by privacy and security concerns, which calls for the creation of a safe data handling system. The primary objective of this research is to propose and implement an intelligent framework, Smart MedDB, for real-time tracking of medical records. The framework highlights privacy and security considerations while addressing the difficulties of managing massive medical databases effectively and providing prompt access to individual patient information. The platform also aims to make e-Token booking with healthcare providers easier and simplify the process of filing health insurance claims. The proposed methodology involves the development and implementation of Smart MedDB, an intelligent framework that employs advanced data handling techniques to ensure quick and secure access to medical records. Patient databases can only be handled or shared by authorized personnel thanks to the integration of authentication measures. Smart MedDB makes use of state-of-the-art protocols and technology to automate the health insurance claim procedure. User experience and system responsiveness are taken into consideration while evaluating the framework’s qualitative capacity to offer rapid and secure access to medical records. The quantity of medical records increased five times, and then the responsiveness and bandwidth of the present medical data handling system increased to 60 seconds and 1,200[Formula: see text]KB. However, the proposed system maintains almost the same level throughout the entire operation since it is stream-based. Metrics including data processing speed, security precautions, and retrieval time are quantified and contrasted with current systems. This framework presents an effective way to expedite medical data access by resolving privacy, security, and efficiency concerns. It ensures prompt and safe retrieval during emergencies and automates associated activities for improved healthcare services.

In today's transportation environment, identifying driver fatigue is essential to improving road safety. A camera is used to scan video frames, a real-time monitoring system analyzes facial expressions to identify signs of tiredness including head movement and eyelid closure. When fatigue is detected, a signal is sent to a microcontroller (Node MCU ESP8266) to initiate safety procedures, and an auditory alarm is triggered. To bring the car to a stop, the system communicates with a motor control unit (L298N). In an effort to increase safety, an autonomous steering system uses an ultrasonic sensor to ensure obstacle-free lane shifting and tries to reroute the car to the left. In addition to in-car safety, Twilio's SMS service enables remote monitoring, notifying the relevant authorities for timely action. A 9V Li-ion battery powers each component, ensuring This technology improves driver safety by combining automated vehicle control, remote alarms, and real-time fatigue detection. Future developments might concentrate on improving response speed, enhancing detection accuracy, and increasing adaptability to various driving conditions.

The rapid growth of urbanization and industrial development has resulted in a substantial rise in solid waste production, leading to serious environmental and public health concerns. Conventional waste segregation techniques are largely manual, labor-intensive, and inefficient, often causing improper disposal and increased pollution. To overcome these challenges, this project introduces an intelligent waste management system that utilizes Machine Learning and embedded technologies to automate the sorting and classification of waste.A webcam captures live images of waste materials, which are then processed using OpenCV methods including noise filtering and feature detection. These processed images are classified by a Convolutional Neural Network (CNN) into categories such as biodegradable, non-biodegradable, and recyclable. The ESP8266 microcontroller acts as the core component of the system, handling communication between various sensors, actuators, and cloud-based services.Based on the classification results from the CNN model, the controller activates stepper and servo motors to channel the waste into appropriate bins. Additionally, the system supports remote monitoring through IoT connectivity, enabling real-time data access and control. With its compact structure, energy efficiency, and potential for scalability, this solution is well-suited for implementation in smart cities and modern infrastructures. By automating waste segregation, the system reduces human effort and promotes environmentally responsible waste handling practices.

Coconut farming is an essential agricultural practice that contributes significantly to the global economy by providing valuable products such as coconut water, oil, and meat. However, the management of coconut plantations faces numerous challenges, including labor shortages, pest control, and the demand for precise irrigation and fertilization. This paper proposes an integrated smart farming system that leverages advanced sensor technologies and automation to address these challenges. The system employs precision irrigation and fertigation methods, facilitated by a centralized motor controller and solenoid valves, to deliver water and nutrients efficiently to the base of each coconut tree. A pH sensor monitors soil acidity or alkalinity, ensuring optimal nutrient availability and promoting sustainable farming practices by reducing chemical inputs. Additional features include a tree motion sensor and a tilt sensor for monitoring tree stability under adverse weather conditions. Soil moisture sensors, temperature, humidity, and light intensity sensors provide real-time data to enhance decision-making. Farmers can remotely monitor and control the system via a Node-RED dashboard, receiving alerts through platforms like Telegram. By integrating these technologies, the proposed system aims to optimize resource utilization, enhance crop yield, and reduce the environmental impact of coconut farming.

Underground mining operations face increased dangers from unidentified medical emergencies together with delayed rescue times due to the lack of real time integrated systems that monitor body health and location. Current safety protocols experience restrictions due to limited visibility together with dangerous environmental factors and weak communication systems. This research fills the essential knowledge gap by building a glove-wearable smart monitoring device which permanently monitors worker vital signs and their real-time movements. A monitoring system composed of an LM75 sensor for temperature checking and a MAX30102 sensor for pulse rate reading along with an MPU6050 module for both movement tracking and fall detection capabilities. Real-time monitoring data passes through NodeMCU ESP8266 microcontrollers to Wi-Fi repeaters and reaches both Flutter-based mobile applications using a Node.js and MongoDB backend system. The system successfully passed tests within simulated underground mining conditions because it exhibited operational stability while acquiring accurate data effectively alerting users in real-time. The analyzed system proves its ability to decrease emergency response delays while improving miner safety because it tracks location and health information in real-time within dangerous environments.

Cloud computing and cloud services have revolutionized the way organizations access and utilize computing resources. This chapter provides an overview of cloud computing, its evolution, and the advantages it offers. It discusses the different types of cloud services and the importance of service-level agreements. The chapter also explores cloud deployment models and their considerations. It highlights the impact of cloud computing on various industries and the challenges of migration. Cloud computing and cloud services have revolutionized the IT landscape. They provide organizations with scalable, flexible, and cost-effective solutions that drive innovation and enable businesses to focus on their core competencies. By carefully evaluating their needs and requirements, considering factors such as security, compliance, and customization, organizations can select the most suitable cloud service type and deployment model. Embracing cloud technologies empowers businesses to unlock new opportunities, increase efficiency, and stay competitive in the rapidly evolving digital world.

Parkinson disease (PD), which is more prevalent in persons over 50, has affected millions of people worldwide. The two most common neurodegenerative illnesses are Alzheimer's and Parkinson's, in which majority of people with PD are elderly, since it is a common central nervous system condition. The Clinical diagnosis of the ailment is difficult due to the difficult signs of the sickness. Additionally, it is anticipated to rise over the next ten years, driving up treatment costs. The significance of medical outcomes on patients' financial investments leads to bias, errors, and high clinical expenditures. Precise planning of a treatment is necessary to lower the possibility of a consequence that cannot be retrieved. In this work, the ensemble classifiers are utilized to back up the specialists' diagnosis of PD. Using boosting and bagging algorithm, a collection of classifiers is created, and the classifiers' predictions are then used to categorize new data. The dataset for this study comprises of a variety of biological speech signals from 31 people, including 8 healthy subjects and 23 people with Parkinson's disease. The UCI machine learning (ML) database was used to compile a set of data about Parkinson's disease. The performance metrics used to evaluate the effectiveness of the device include accuracy (ACC), true positive rate (TPR), true negative rate (TNR), positive prediction value (PPV), negative prediction value (NPV), false positive rate (FPR), and false negative rate (FNR). A very high accuracy rate of about 94.4% is indicated by the Parkinson's data.

Combining Linear Discriminant Analysis (LDA) and Primary Component Analysis (PCA) feature extraction techniques to improve the efficacy of the face-centered real-time review approach. The measurement functions used to extract PCA and LDA values must be combined to get scores expressing the degree of similarity. When the total of the values generated from both functions is used, the scores are identical. The combination extractor has the capacity to enhance specific qualities in scanned facial photographs. The Euclidean distance between a subset of the test shots and the templates must be computed in order to determine the template image that most closely resembles the test shots. A comparative study of the user’s facial traits in relation to a database-stored reference image can be used to authenticate an individual’s identity. Based on the assessment of the eleven-user image, it appears that the combination extractor outperforms the single extraction feature. On average, the performance of the proposed methodology outperforms that of using a single extractor. If the performance of a system is proven to be insufficient, one alternative course of action is to implement a facial identification instrument. To achieve better results, it is critical to increase the adaptability and applicability of the time allotted for problem-solving activities.