The concept of Blockchain has penetrated a wide range of scientific areas, and its use is considered to rise exponentially in the near future. Executing short scripts of predefined code called smart contracts on Blockchain can eliminate the need of intermediaries and can also raise the multitude of execution of contracts. In this paper, we discuss the concept of Blockchain along with smart contracts and discuss their applicability in the Internet of Medical Things (IoMT) in the e-healthcare domain. The paper analyses the dimensions that decentralization and the use of smart contracts will take the IoMT in e-healthcare, proposes a novel architecture, and also outlines the advantages, challenges, and future trends related to the integration of all three. The proposed architecture shows its effectiveness with average packet delivery ratio, average latency, and average energy efficiency performance parameters when compared with traditional approaches.

Diabetic Retinopathy is human eye disease which causes damage to retina of eye and it may eventually lead to complete blindness. Detection of diabetic retinopathy in early stage is essential to avoid complete blindness. Many physical tests like visual acuity test, pupil dilation, optical coherence tomography can be used to detect diabetic retinopathy but are time consuming and affects patients as well. This review paper focuses on decision about the presence of disease by applying ensemble of machine learning classifying algorithms on features extracted from output of different retinal image processing algorithms, like diameter of optic disk, lesion specific (microaneurysms, exudates), image level (pre-screening, AM/FM, quality assessment). Decision making for predicting the presence of diabetic retinopathy was performed using alternating decision tree, adaBoost, Naive Bayes, Random Forest and SVM.

There are more than 962 million people aged 60 and up globally. Physical activity declines as people get older, as does their capacity to undertake everyday tasks, effecting both physical and mental health. Many researchers use machine learning and deep learning methods to recognize human activities, but very few studies have been focused on human activity recognition of elderly people. This paper focuses on providing assistance to elderly people by monitoring their activities in different indoor and outdoor environments using gyroscope and accelerometer data collected from a smart phone. Smart phones have been routinely used to monitor the activities of persons with impairments; routine activities such as sitting, walking, going upstairs, going downstairs, standing, and lying are included in the dataset. Conventional Machine Learning and Deep Learning algorithms such as k-Nearest Neighbors, Random Forest, Support Vector Machine, Artificial Neural Network, and Long Short-Term Memory Network are used for human activity recognition. Long Short-Term Memory is a recurrent neural network variation that is best suited to handling temporal sequences. Two-fold and ten-fold cross-validation methods were performed to show the effect of changing the data in the training and testing dataset. Among all the classification techniques, the proposed Long Short-Term Memory Network gave the best accuracy of 95.04%. However, Support Vector Machine gave 89.07% accuracy with a very low computational time of 0.42 min using 10-fold cross-validation.

Background: Medical image segmentation is more complicated and demanding than ordinary image segmentation due to the density of medical pictures. A brain tumour is the most common cause of high mortality. Objectives: Extraction of tumorous cells is particularly difficult due to the differences between tumorous and non-tumorous cells. In ordinary convolutional neural networks, local background information is restricted. As a result, previous deep learning algorithms in medical imaging have struggled to detect anomalies in diverse cells. Methods: As a solution to this challenge, a deep convolutional generative adversarial network for tumour segmentation from brain Magnetic resonance Imaging (MRI) images is proposed. A generator and a discriminator are the two networks that make up the proposed model. This network focuses on tumour localisation, noise-related issues, and social class disparities. Results: Dice Score Coefficient (DSC), Peak Signal to Noise Ratio (PSNR), and Structural Index Similarity (SSIM) are all generally 0.894, 62.084 dB, and 0.88912, respectively. The model’s accuracy has improved to 97 percent, and its loss has reduced to 0.012. Conclusions: Experiments reveal that the proposed approach may successfully segment tumorous and benign tissues. As a result, a novel brain tumour segmentation approach has been created.

Farmers’ ability to accurately anticipate crop type is critical to global food production and sustainable smart cities since timely decisions on imports and exports, based on precise forecasts, are crucial to the country’s food security. In India, agriculture and allied sectors constitute the country’s primary source of revenue. Seventy percent of the country’s rural residents are small or marginal agriculture producers. Cereal crops such as rice, wheat, and other pulses make up the bulk of India’s food supply. Regarding cultivation, climate and soil conditions play a vital role. Information is of utmost need in predicting which crop is best suited given the soil and climate. This paper provides a statistical look at the features and indicates the best crop type on the given features in an Indian smart city context. Machine learning algorithms like k-NN, SVM, RF, and GB trees are examined for crop-type prediction. Building an accurate crop forecast system required high accuracy, and the GB tree technique provided that. It outperforms all the classification algorithms with an accuracy of 99.11% and an F1-score of 99.20%.

Urban agriculture is the practice of growing food inside the city limits. Due to the exponential amount of data generated by information and technology-based farm management systems, we need proper methods to represent the data. The branch of artificial intelligence known as “knowledge representation and reasoning” is devoted to the representation of information about the environment in a way where a computer system can utilise it to accomplish difficult problems. This research is an extensive survey of the knowledge representation techniques used in smart agriculture, and specifically in the urban agricultural domain. Relevant articles on the knowledge base are extracted from the retrieved set to study the fulfillment of the criteria of the system. Various interesting findings were observed after the review. Spatial–temporal characteristics were rarely approached. A generalised representation technique to include all domains in agriculture is another issue. Finally, proper validation technique is found to be missing in such an ontology.