IThe Internet of Things (IoT) is a group of millions of devices having sensors and actuators linked over wired or wireless channel for data transmission. IoT has grown rapidly over the past decade with more than 25 billion devices are expected to be connected by 2020. The volume of data released from these devices will increase manyfold in the years to come. In addition to an increased volume, the IoT devices produces a large amount of data with a number of different modalities having varying data quality defined by its speed in terms of time and position dependency. In such an environment, machine learning algorithms can play an important role in ensuring security and authorization based on biotechnology, anomalous detection to improve the usability and security of IoT systems. On the other hand, attackers often view learning algorithms to exploit the vulnerabilities in smart IoT-based systems.

Security of networking in cyber-physical systems is an important feature in recent computing. Information which comes to the network needs pre-evaluation. Our solution presented in this article is based on deep learning model developed for network traffic analysis of various IoT solutions. At the level of firewall or gateway an information about current connection is gathered for the Recurrent Neural Network. The model evaluates this information and forwards decision back to the firewall to take security actions if needed. In the research we have tested our solution on two open data sets. The results confirm that our model is very efficient in recognition of potential threads reaching above 99% of accuracy even in a case of reduced number of evaluated networking features.

AI-enabled logistics unmanned aerial vehicles (UAVs) are progressively revealing their unique advantages for future smart cities. Nevertheless, the existing research on logistics UAV path planning lacks to simultaneously consider the UAV energy consumption constraints, the customer time windows, the impacts of wind speed and direction. This omission renders the existing models inappropriate for real-world transportation systems. Besides, the UAVs are still constrained by the limited payload and battery due to the highly automatic delivery process. Consequently, we investigate the effect of wind speed and direction on UAV flight states, establishes pertinent parameters and their resolution methods impacted by wind conditions, and delves into the logistics UAV path planning issue that concurrently considers the UAV energy consumption constraints, the customer time windows, and the impact of wind conditions. To resolve the proposed trajectory optimization issue, the large-scale neighborhood search algorithm (LNS) is amalgamated with the genetic algorithm (GA), forming the GA-LNS, to address the static problem, while dynamic planning concepts are employed in the decoding process of GA-LNS to solve the dynamic trajectory optimization problem. Simulation results demonstrate that the devised algorithms yield superior solutions within a plausible timeframe, reducing distribution costs by approximately 9% in comparison to the conventional GA. Unlike the no-wind and static scenarios, path planning that incorporates dynamic wind conditions circumvents issues related to energy constraints and customer satisfaction bias evident in the prior cases. Furthermore, the proposed algorithm can provide a high-efficiency, low-energy-consumption, and low-delay UAV planning strategy in the scenario of UAV-assisted data collection.

Adversary models have been fundamental to the various cryptographic protocols and methods. However, their use in most of the branches of research in computer science is comparatively restricted, primarily in case of the research in cyber physical security (e.g., vulnerability studies, position confidentiality). In this paper, we propose an energy-aware green adversary model for its use in smart industrial environment through achieving confidentiality. Even though, mutually the hardware and, the software parts of cyber-physical systems can be improved to decrease its energy consumption, this paper focuses on aspects of conserving position and information confidentiality. On the basis of our findings (assumptions, adversary goals and capabilities) from the literature, we give some testimonials to help practitioners and researchers working in cyber physical security. The proposed model that runs on real time anticipatory position-based query scheduling in order to minimize the communication and computation cost for each query thus facilitating energy consumption minimization. Moreover, we calculate the transferring/acceptance slots required for each query to avoid deteriorating slots. The experimental results confirms that, the proposed approach can diminish energy consumption up to 5 times in comparison to existing approaches.

The Covid-19 pandemic represents one of the greatest global health emergencies of the last few decades with indelible consequences for all societies throughout the world. The cost in terms of human lives lost is devastating on account of the high contagiousness and mortality rate of the virus. Millions of people have been infected, frequently requiring continuous assistance and monitoring. Smart healthcare technologies and Artificial Intelligence algorithms constitute promising solutions useful not only for the monitoring of patient care but also in order to support the early diagnosis, prevention and evaluation of Covid-19 in a faster and more accurate way. On the other hand, the necessity to realise reliable and precise smart healthcare solutions, able to acquire and process voice signals by means of appropriate Internet of Things devices in real-time, requires the identification of algorithms able to discriminate accurately between pathological and healthy subjects. In this paper, we explore and compare the performance of the main machine learning techniques in terms of their ability to correctly detect Covid-19 disorders through voice analysis. Several studies report, in fact, significant effects of this virus on voice production due to the considerable impairment of the respiratory apparatus. Vocal folds oscillations that are more asynchronous, asymmetrical and restricted are observed during phonation in Covid-19 patients. Voice sounds selected by the Coswara database, an available crowd-sourced database, have been e analysed and processed to evaluate the capacity of the main ML techniques to distinguish between healthy and pathological voices. All the analyses have been evaluated in terms of accuracy, sensitivity, specificity, F1-score and Receiver Operating Characteristic area. These show the reliability of the Support Vector Machine algorithm to detect the Covid-19 infections, achieving an accuracy equal to about 97%.

Mental health issues can lead to serious consequences like depression, self-mutilation, and worse, especially for university students who are not physically and mentally mature. Not all students with poor mental health are aware of their situation and actively seek help. Proactive detection of mental problems is a critical step in addressing this issue. However, accurate detections are hard to achieve due to the inherent complexity and heterogeneity of unstructured multi-modal data generated by campus life. Against this background, we propose a detection framework for detecting students’ mental health, named CASTLE (educational data fusion for mental health detection). Three parts are involved in this framework. First, we utilize representation learning to fuse data on social life, academic performance, and physical appearance. An algorithm, named MOON (multi-view social network embedding), is proposed to represent students’ social life in a comprehensive way by fusing students’ heterogeneous social relations effectively. Second, a synthetic minority oversampling technique algorithm (SMOTE) is applied to the label imbalance issue. Finally, a DNN (deep neural network) model is utilized for the final detection. The extensive results demonstrate the promising performance of the proposed methods in comparison to an extensive range of state-of-the-art baselines.