The current era of computing is witnessing a huge amount of data being generated with every passing moment. This massive data if nourished effectively can open new horizons for the computing world. The modern world is slowly but surely moving towards the automation age where every entity and object is being automated to perform desired tasks without the need of human interventions. This has made the lives of people more convenient and comfortable. Automation has taken over every single field of computing and even beyond. Smart mobility is one such example of automation wherein the users get real time information about the traffic conditions as well as alternate route suggestions in case of traffic jams. Transportation is considered as the backbone of every business. The automated intelligent transportation system (ITS) has completely transformed the way how people, goods and services are transported and is quite important for achieving sustainability. This paper provides an overview of the existing ITS system, concept of smart mobility and existing vulnerabilities in these systems. Their security concerns and scenarios are also analyzed. Furthermore, in this paper the importance and need for securing these intelligent systems is highlighted and future trends in ITS is also suggested. Although ITS and smart mobility technology are already providing convenient transportation and navigational facilities, there is still a huge scope to improve these facilities for the end users. The suggested future trends if integrated in an effective manner can provide exemplary means to provide state-of-the-art navigational facilities and smart mobility in a true sense.

With the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulation, etc. At present, most of these systems rely heavily on high-end computing resources. This paper proposes a novel memory and time-efficient automatic license plate recognition (ALPR) system developed using YOLOv5. This approach is ideal for IoT devices that usually have less memory and processing power. Our approach incorporates two stages, i.e., using a custom transfer learned model for license plate detection and an LSTM-based OCR engine for recognition. The dataset that we used for this research was our dataset consisting of images from the Google open images dataset and the Indian License plate dataset. Along with training YOLOv5 models, we also trained YOLOv4 models on the same dataset to illustrate the size and performance-wise comparison. Our proposed ALPR system results in a 14 megabytes model with a mean average precision of 87.2% and 4.8 ms testing time on still images using Nvidia T4 GPU. The complete system with detection and recognition on the other hand takes about 85 milliseconds.

Over the years Vision based real time gesture recognition system has witnessed an exponential growth because of its manifoldness applications, ranging from sign language to virtual reality and its ability to interact with system efficiently through HCI. In this paper, we have proposed a hand gesture recognition system for American Sign Language recognition using important features of hand such as fingertips, palm center etc. The system is capable of recognizing hand gestures even when the fore-arm is involved and it can tolerate a certain rotation of palm and fore-arm. We have implemented principal component analysis to remove ambiguity between two similar types of gestures and given emphasis to detect movement epenthesis by means optical flow technique.

Coronary heart disease (CHD) is a severe cardiac disease, and hence, its early diagnosis is essential as it improves treatment results and saves money on medical care. The prevailing development of quantum computing and machine learning (ML) technologies may bring practical improvement to the performance of CHD diagnosis. Quantum machine learning (QML) is receiving tremendous interest in various disciplines due to its higher performance and capabilities. Techniques for QML have the potential to forecast cardiac disease and help in early detection. To predict the risk of coronary heart disease, a hybrid approach utilising an ensemble machine learning model based on QML classifiers is presented in this paper. Our approach, with its unique ability to address multidimensional healthcare data, reassures the method’s robustness by fusing quantum and classical ML algorithms in a multi-step inferential framework. Reducing cardiac morbidity and mortality requires early detection of heart disease. In this research, a hybrid approach utilises techniques with quantum computing capabilities to tackle complex problems that are not amenable to conventional ML algorithms and to minimise computational expenses. The proposed method has been developed in the Raspberry Pi 4B Graphics Processing Unit (GPU) platform and tested on a broad dataset that integrates clinical and imaging data from patients suffering from CHD and healthy controls. The proposed research is developed with a hybrid approach that combines different machine learning algorithms, such as KNN + RF, DT + RF, LR + RF, and Adaboost + RF, for diagnosing coronary illness with higher accuracy through feature selection. The proposed system performance obtained an accuracy of 99%, utilising 20000 datasets with 14 attributes from various datasets collected from the Local Pathology Lab in the Muzaffarnagar District of Uttar Pradesh, India. Compared to classical machine learning models, the accuracy, sensitivity, F1 score, and specificity of the proposed hybrid QML model used with CHD are manifold higher.

This research study explores the effects of various resampling techniques with different machine learning classifiers on the accuracy of multi-class classification of Diabetes using an imbalanced dataset. The diabetes dataset of Mendeley is a multi-class dataset with information about patients with no diabetes, pre-diabetes, and diabetes. The dataset is imbalanced, where the majority class is diabetic. This study is a comparative analysis of various oversampling techniques, undersampling techniques, and hybrid techniques with different machine learning algorithms to accurately classify the person as diabetic, pre-diabetic, or non-diabetic. Eight machine-learning algorithms and ten resampling techniques were applied to the dataset to classify the patient accurately. The result indicates that the combination of XGBoost with K mean smote and smote N attains the highest accuracy of 99.2%. It also suggests that oversampling techniques perform better than undersampling techniques and hybrid techniques.