Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Department of Software and Systems Engineering

Purpose: The power of the Internet has impacted various industries, especially the healthcare industry. With the rapid population growth and advancement of various sensor technologies and smart devices, the demand for quality healthcare services has increased in the past few years. At the same time, Internet of Things (IoT) technology makes intelligent objects communicate with each other by connecting all the objects without human intervention. IoT facilitated services and technologies in healthcare to provide low-cost and efficient service delivery to patients and consumers. It reduces the patient’s hospital stay time and efficient information exchange by providing cost-effective healthcare services. This systematic review analyzes different technologies, core applications, datasets, algorithms, challenges, and limitations of IoT in the healthcare sector. Methods: Database search is performed to review IoT healthcare-enabling technologies, algorithms, applications, and IoT- centric architectures. Search has been conducted over popular databases like Springer, Elsevier, and IEEE Xplore. We have downloaded around 544 research papers, out of which we have selected only 116 based on our interests. Results: We identified different challenges in healthcare IoT applications as security and privacy, scalability, high cost, energy efficiency, quality of service, network architecture, mobility, and interoperability. However, data security and privacy issues are significant challenges in the healthcare sector as they deal with patients’ confidential information. Also, we proposed a novel architecture that covers most IoT healthcare requirements. IoT healthcare applications are also detailed. In addition, it reviews most of the healthcare datasets and the utilized algorithms. Conclusions: Based on the reviewed articles in this paper, it is has been concluded that IoT devices are beneficial in the healthcare applications, regardless of their limitations in terms of energy, processing, and storage. It is a promising technology that can save time and effort to the practitioners and doctors. Several architectures and technologies are discussed as well as the limitations, which enables researchers to tackle those limitations. However, the future of IoT healthcare holds immense potential for high-security enabled and pervasive applications. Analyzing vast healthcare data using deep learning techniques can play a vital role in extracting valuable insights. To leverage the power of deep learning, it is crucial to design a well-structured cloud architecture capable of implementing these techniques and predicting future trends. While researchers have proposed various frameworks for IoT healthcare, there remains a need to assess the feasibility and effectiveness of these proposed frameworks. Furthermore, it is essential to address the specific requirements and intricacies when designing detailed architectural patterns for healthcare applications. Overall, the future of IoT healthcare is expansive and offers exciting research opportunities for scholars and experts in the field. By embracing innovative technologies and addressing the specific needs of the healthcare industry, we can unlock the full potential of IoT in revolutionizing healthcare delivery and improving patient outcomes.

School of Information Technology and Engineering

Vellore Campus

World University root node

Health and Technology

Internet of things in Healthcare: a conventional literature review

The Internet of Things (IoT) paradigm is changing how people do business by interacting and connecting with things around them. IoT in industrial applications enables the connections between various architectures to provide better efficiency and flexibility. The Industrial Internet of Things brings potential innovation in multiple industries such as manufacturing, energy, transportation, agriculture, and healthcare. Industrial IoT is enabled by various technologies like sensors, big data, cloud, fog, machine learning, and deep learning. The emergence of all these technologies leads industries to enhance productivity, automate the manufacturing process, improve connectivity, scalability, cost-effectiveness, and decision-making tasks. Recently, privacy and security seem to be significant challenges in industrial IoT applications. Therefore, an in-depth review is needed to identify the various challenges in bringing IoT into industries. Hence, this book chapter gives an overview of various Industrial IoT applications in different sectors. It is also focused on significant technologies and architectural frameworks in Industrial IoT applications. Finally, this chapter presents the current technological challenges in developing Industrial IoT applications, which helps researchers pave the way and solve these challenges in the future.

Industrial Internet of Things: Applications and Challenges

Journal of Electronic Imaging

Polygonal approximation for digital image boundary using firefly algorithm

The Face Mask Detection model is used to make sure a person is wearing Mask or not. This model results from the grappling situation presented by COVID-19, resulting in the mandatory use of Masks at public places. Security agencies need to plant actual personnel to make sure all the people in public are wearing 'Masks', this model will lessen the risk of people being contacted by COVID-19. This research helps us understand a broader perspective about the Face Detection models by comparing different state of the art models. The model uses MobileNetV2 architecture, that has inverted bottlenecks and depth-wise convolutions, to filter features. The complete model is built in 2 phases, the first one consisting of making a Face mask detection model trained to detect the Face and mask, and then placing it in the Real Time environment by using the OpenCV for actually predicting the usage of Face Mask.

ECS Transactions

Face Mask Detection for Real Time Video Streams

Hyperspectral imaging (HSI), measuring the reflectance over visible (VIS), near-infrared (NIR), and shortwave infrared wavelengths (SWIR), has empowered the task of classification and can be useful in a variety of application areas like agriculture, even at a minor level. Band selection (BS) refers to the process of selecting the most relevant bands from a hyperspectral image, which is a necessary and important step for classification in HSI. Though numerous successful methods are available for selecting informative bands, reflectance properties are not taken into account, which is crucial for application-specific BS. The present paper aims at crop mapping for agriculture, where physical properties of light and biological conditions of plants are considered for BS. Initially, bands were partitioned according to their wavelength boundaries in visible, near-infrared, and shortwave infrared regions. Then, bands were quantized and selected via metrics like entropy, Normalized Difference Vegetation Index (NDVI), and Modified Normalized Difference Water Index (MNDWI) from each region, respectively. A Convolutional Neural Network was designed with the finer generated sub-cube to map the selective crops. Experiments were conducted on two standard HSI datasets, Indian Pines and Salinas, to classify different types of crops from Corn, Soya, Fallow, and Romaine Lettuce classes. Quantitatively, overall accuracy between 95.97% and 99.35% was achieved for Corn and Soya classes from Indian Pines; between 94.53% and 100% was achieved for Fallow and Romaine Lettuce classes from Salinas. The effectiveness of the proposed band selection with Convolutional Neural Network (CNN) can be seen from the resulted classification maps and ablation study.

Fulltext

Applied Sciences

Crop Classification for Agricultural Applications in Hyperspectral Remote Sensing Images

Abstract The problem of data skewness, class imbalance, data scarcity and noise limits the application of machine learning and deep learning models in applications like anomaly detection, fraud detection, intrusion detection, fault diagnosis, machine-tomachine communication, etc. Performance of supervised learning leans towards majority class and fails to generalize testing data in class imbalance and noisy data problems. Using neural-based data augmentation techniques for data generation and deep convolutional models for classification would enhance the performance of the applications mentioned above. Recently, GANs (generative adversarial networks) showed significant improvements in generating images. In this paper, a model that uses a conditioned deep convolutional GAN and an auxiliary classifier are proposed to tackle the aforementioned issues. The conditioned GAN is used for data generation of minority classes images and noisy images. Another auxiliary deep convolutional model is employed for the classification of images on data augmented dataset. Also, a multi-hinge loss is employed in both the data augmentation and classification tasks. The effectiveness of the proposed model is investigated on the quality of generated images and classification metrics using four publicly available popular datasets: MNIST, EMNIST, CIFAR10, and SVHN. The proposed model has shown significant improvements over the other often used models of data augmentation and multi-class imbalance image classification in terms of generated samples and classification accuracy. Keywords Imbalanced data · Convolutional neural network · Data augmentation · Generative model · Adversarial network&nbsp; &nbsp;

International Journal of Multimedia Information Retrieval

Multi-class imbalanced image classification using conditioned GANs

Purpose – Artificial Intelligence (AI) has surpassed expectations in opening up different possibilities for machines from different walks of life. Cloud service providers are pushing. Edge computing reduces latency, improving availability and saving bandwidth. Design/methodology/approach – The exponential growth in tensor processing unit (TPU) and graphics processing unit (GPU) combined with different types of sensors has enabled the pairing of medical technology with deep learning in providing the best patient care. A significant role of pushing and pulling data from the cloud, big data comes into play as velocity, veracity and volume of data with IoT assisting doctors in predicting the abnormalities and providing customized treatment based on the patient electronic health record (EHR). Findings – The primary focus of edge computing is decentralizing and bringing intelligent IoT devices to provide real-time computing at the point of presence (PoP). The impact of the PoP in healthcare gains importance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of patients. The impact edge computing of the PoP in healthcare gains significance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of patients. Originality/value – The utility value of sensors data improves through the Laplacian mechanism of preserved PII response to each query from the ODL. The scalability is at 50% with respect to the sensitivity and preservation of the PII values in the local ODL. Keywords Edge computing, Deep learning, Cloud computing, Fog computing, Electronic health record, Tensor processing unit, Graphics processing unit, Point of presence&nbsp; &nbsp;

International Journal of Intelligent Computing and Cybernetics

Emphasizing privacy and security of edge intelligence with machine learning for healthcare

Smart education derived from information communication technologies (ICT) has attracted various academicians towards it. The growth of multiple sensor devices and wireless networks has brought drastic changes in IoT in the education sector. Applications of IoT in the education sector can improve academicians' and learners' considerable skills. Therefore, this chapter analyses various applications, advantages, and challenges of IoT in the education sector. The multiple applications of IoT in the education sector are identified in terms of smart classroom management, student tracking and monitoring, campus energy management, and intelligent learning. IoT in education's significant advantages are an innovative teaching and learning process, cost reduction, and smart infrastructure development. Various challenges in developing IoT-based applications identify as designing a secure learning environment, efficient resource tracking, efficient access to information, and intellectual plan development.&nbsp;

IoT in the Education Sector Applications and Challenges

The primordial way of communication is through vocal signals, which pave the way for support between individuals in a social structure. Computer applications provide a way to create Automatic Speech Recognition (ASR) with a combination of Speech Emotion Recognition (SER) to detect and identify emotions in the speech signals. The semantic relatedness of words with abstract concepts proves to be complicated than concrete ideas. An ensemble of different clustering techniques is utilized to automatically segregate sense distinctions in the various dialects of sentences spoken to tackle this issue. The interpretation of word sense of a word may change with time and group of people. The proposed model maps characters to word sense with weights provided by Senticnet with trial-and-error methods and tuning. The proposed model utilizes stop words to distinguish word senses with 72.78% accuracy for regional dialects.

International Journal of Speech Technology

Language dialect based speech emotion recognition through deep learning techniques

As the hyperspectral image consists of hundreds of highly correlated spectral bands, the selection of informative and highly discriminative bands is necessary for hyperspectral image classification. The recent growth of machine learning and artificial intelligence techniques play a major role in various domains of hyperspectral image processing. In this paper, a comprehensive survey of machine learning and artificial intelligence technique-based band selection strategies for hyperspectral image classification is given. As per the outcome of this study, we have identified the research challenges and research for future directions in band selection strategies for hyperspectral image classification.