The increasing misuse of drones poses significant safety and security risks, including illegal transportation of prohibited goods, interference with manned aircraft, and threats to public safety. This has raised concerns about the increased use of unmanned aerial vehicles (UAVs) due to their small size. Addressing these concerns has sparked significant research into developing effective drone detection systems. Deep learning, especially YOLO, is known as a lightweight model that offers real-time detection capabilities. Attention mechanisms have proven effective in many studies for detecting objects. This research focused on optimizing the YOLOv8n-based model by incorporating the Attention Module into the neck and improving the detection head by adding a tiny detection head, making the model work efficiently in detecting objects of tiny size. To obtain the most effective model, multiple training sets have been experimented with involving different types of attention modules, such as the Convolutional Block Attention Module (CBAM), ResBlock CBAM, Global Attention Mechanism (GAM), and Efficient Channel Attention (ECA). Therefore, based on the results, YOLOv8n + ResCBAM + high-resolution detection head, called P2-YOLOv8n-ResCBAM significantly improves the mean Average Accuracy (mAP) from 90.3% to 92.6%. Although the increased model complexity reduced frames per second (fps) from 263 to 166, the detection speed remains suitable for real-time applications. The proposed model effectively distinguishes drones from birds and recognizes them at long distances, demonstrating its potential for enhancing aerial surveillance and security measures.

Recommender systems are currently a relevant tool for facilitating access for online users, to information items in search spaces overloaded with possible options. With this goal in mind, they have been used in diverse domains such as e-commerce, e-learning, e-tourism, e-health, etc. Specifically, in the case of the e-health scenario, the computer science community has been focused on building recommender systems tools for supporting personalized nutrition by delivering user-tailored foods and menu recommendations, incorporating the health-aware dimension to a larger or lesser extent. However, it has been also identified the lack of a comprehensive analysis of the recent advances specifically focused on food recommendations for the domain of diabetic patients. This topic is particularly relevant, considering that in 2021 it was estimated that 537 million adults were living with diabetes, being unhealthy diets a major risk factor that leads to such an issue. This paper is centered on presenting a survey of food recommender systems for diabetic patients, supported by the PRISMA 2020 framework, and focused on characterizing the strengths and weaknesses of the research developed in this direction. The paper also introduces future directions that can be followed in the next future, for guaranteeing progress in this necessary research area.

Medical cyber-physical systems (MCPS) represent a platform through which patient health data are acquired by emergent Internet of Things (IoT) sensors, preprocessed locally, and managed through improved machine intelligence algorithms. Wireless medical cyber-physical systems are extensively adopted in the daily practices of medicine, where vast amounts of data are sampled using wireless medical devices and sensors and passed to decision support systems (DSSs). With the development of physical systems incorporating cyber frameworks, cyber threats have far more acute effects, as they are reproduced in the physical environment. Patients’ personal information must be shielded against intrusions to preserve their privacy and confidentiality. Therefore, every bit of information stored in the database needs to be kept safe from intrusion attempts. The IWMCPS proposed in this work takes into account all relevant security concerns. This paper summarizes three years of fieldwork by presenting an IWMCPS framework consisting of several components and subsystems. The IWMCPS architecture is developed, as evidenced by a scenario including applications in the medical sector. Cyber-physical systems are essential to the healthcare sector, and life-critical and context-aware health data are vulnerable to information theft and cyber-okayattacks. Reliability, confidence, security, and transparency are some of the issues that must be addressed in the growing field of MCPS research. To overcome the abovementioned problems, we present an improved wireless medical cyber-physical system (IWMCPS) based on machine learning techniques. The heterogeneity of devices included in these systems (such as mobile devices and body sensor nodes) makes them prone to many attacks. This necessitates effective security solutions for these environments based on deep neural networks for attack detection and classification. The three core elements in the proposed IWMCPS are the communication and monitoring core, the computational and safety core, and the real-time planning and administration of resources. In this study, we evaluated our design with actual patient data against various security attacks, including data modification, denial of service (DoS), and data injection. The IWMCPS method is based on a patient-centric architecture that preserves the end-user’s smartphone device to control data exchange accessibility. The patient health data used in WMCPSs must be well protected and secure in order to overcome cyber-physical threats. Our experimental findings showed that our model attained a high detection accuracy of 92% and a lower computational time of 13 sec with fewer error analyses.

Internet of Things devices, platform programs, and network applications are all vulnerable to cyberattacks (digital attacks), which can be prevented at different levels by using cybersecurity protocol. In the Internet of Things (IoT), cyberattacks are specifically intended to retrieve or change/destroy sensitive information that may exceed the IoT’s advantages. Furthermore, the design of a lightweight cybersecurity mechanism experiences a critical challenge that would perfectly fit resource-constrained IoT devices. For instance, identifying the compromised devices and the users’ data and services protection are the general challenges of cybersecurity on an IoT system that should be considered. This paper proposes a secure cybersecurity system based on the integration of cryptography with authentication (ELCA) that utilizes elliptic curve Diffie–Hellman (ECDH) to undertake key distribution while the weak bits problem in the shared secret key is resolved. In this paper, three systems of integration are investigated, while ELCA proposes secure integration between authentication and encryption to facilitate confidentiality and authenticity transfer messages between IoT devices over an insecure communication channel. Furthermore, the security of ELCA is proven mathematically using the random oracle model and IoT adversary model. The findings of the emulation results show the effectiveness of ELCA performance in terms of a reduced CPU execution time by 50%, reduced storage cost by 32–19.6%, and reduced energy consumption by 41% compared to the baseline cryptographic algorithms.

Medical image fusion (MIF) techniques are proficient in combining medical images in distinct morphologies to obtain a reliable medical analysis. A single modality image could not offer adequate data for an accurate analysis. Therefore, a novel multimodal MIF-based artificial intelligence (AI) method has been presented. MIF approaches fuse multimodal medical images for exact and reliable medical recognition. Multimodal MIF improves diagnostic accuracy and clinical decision-making by combining complementary data in different imaging modalities. This article presents a new multimodal medical image fusion model utilizing Modified DWT with an Arithmetic Optimization Algorithm (MMIF-MDWTAOA) approach. The MMIF-MDWTAOA approach aims to generate a fused image with the significant details and features from each modality, leading to an elaborated depiction for precise interpretation by medical experts. The bilateral filtering (BF) approach is primarily employed for noise elimination. Next, the image decomposition process uses a modified discrete wavelet transform (MDWT) approach. However, the approximation coefficient of modality_1 and the detailed coefficient of modality_2 can be fused interchangeably. Furthermore, a fusion rule is derived from combining the multimodality data, and the AOA model is enforced to ensure the optimum selection of the fusion rule parameters. A sequence of simulations is accomplished to validate the enhanced output of the MMIF-MDWTAOA technique. The investigational validation of the MMIF-MDWTAOA technique showed the highest entropy values of 7.568 and 7.741 bits/pixel over other approaches.