Search

In the age of information overload, recommender systems have emerged as essential tools, assisting users in decision-making processes by offering personalized suggestions. However, their effectiveness is contingent on the availability of large amounts of user data, raising significant privacy and security concerns. This review article presents an extended analysis of recommender systems, elucidating their importance and the growing apprehensions regarding privacy and data security. Federated Learning (FL), a privacy-preserving machine learning approach, is introduced as a potential solution to these challenges. Consequently, the potential benefits and implications of integrating FL with recommender systems are explored and an overview of FL, its types, and key components, are provided. Further, the privacy-preserving techniques inherent to FL are discussed, demonstrating how they contribute to secure recommender systems. By illustrating case studies and significant research contributions, the article showcases the practical feasibility and benefits of combining FL with recommender systems. Despite the promising benefits, challenges, and limitations exist in the practical deployment of FL in recommender systems. This review outlines these hurdles, bringing to light the security considerations crucial in this context and offering a balanced perspective. In conclusion, the article signifies the potential of FL in transforming recommender systems, paving the path for future research directions in this intersection of technologies.

This paper presents an advanced automatic number plate recognition (ANPR) system designed specifically for Qatar’s diverse license plate landscape and challenging environmental conditions. Leveraging the YOLOv8 deep learning model, particularly the YOLOv8s variant, we achieve state-of-the-art accuracy in both license plate detection and number recognition. Our innovative approach includes a comprehensive dataset enhancement technique that simulates adverse conditions, significantly improving the model’s robustness in real-world scenarios. We integrate edge computing using a Raspberry Pi with server-side processing, demonstrating an efficient solution for real-time ANPR applications. The system maintains greater than 93% overall performance across various environmental conditions, including night-time and rainy scenarios. We also explore the impact of various pre-processing techniques, including edge detection, k-mean thresholding, DBSCAN, and Gaussian mixture models, on the ANPR system’s performance. Our findings indicate that modern deep learning models like YOLOv8 are sufficiently robust to handle raw input images and do not significantly benefit from additional pre-processing. With its high accuracy and real-time processing capability, the proposed system represents a significant advancement in ANPR technology and is particularly suited for Qatar’s unique traffic management needs and smart city initiatives.

Recommender systems are a key technology for many applications, such as e-commerce, streaming media, and social media. Traditional recommender systems rely on collaborative filtering or content-based filtering to make recommendations. However, these approaches have limitations, such as the cold start and the data sparsity problem. This survey paper presents an in-depth analysis of the paradigm shift from conventional recommender systems to generative pre-trained-transformers-(GPT)-based chatbots. We highlight recent developments that leverage the power of GPT to create interactive and personalized conversational agents. By exploring natural language processing (NLP) and deep learning techniques, we investigate how GPT models can better understand user preferences and provide context-aware recommendations. The paper further evaluates the advantages and limitations of GPT-based recommender systems, comparing their performance with traditional methods. Additionally, we discuss potential future directions, including the role of reinforcement learning in refining the personalization aspect of these systems.

In response to the urgent requirement for rapid, precise, and cost-effective detection in intensive care units (ICUs) for ventilated patients, as well as the need to overcome the limitations of traditional detection methods, researchers have turned their attention towards advancing novel technologies. Among these, biosensors have emerged as a reliable platform for achieving accurate and early diagnoses. In this study, we explore the possibility of using Pyocyanin analysis for early detection of pathogens in ventilator-associated pneumonia (VAP) and lower respiratory tract infections in ventilated patients. To achieve this, we developed an electrochemical sensor utilizing a graphene oxide–copper oxide-doped MgO (GO − Cu − Mgo) (GCM) catalyst for Pyocyanin detection. Pyocyanin is a virulence factor in the phenazine group that is produced by Pseudomonas aeruginosa strains, leading to infections such as pneumonia, urinary tract infections, and cystic fibrosis. We additionally investigated the use of DNA aptamers for detecting Pyocyanin as a biomarker of Pseudomonas aeruginosa, a common causative agent of VAP. The results of this study indicated that electrochemical detection of Pyocyanin using a GCM catalyst shows promising potential for various applications, including clinical diagnostics and drug discovery.

Medical simulators, employed in extracorporeal membrane oxygenation (ECMO), are burdened with costly equipment and low-fidelity methodologies. This dichotomy necessitated a new approach that eliminates high-costs and integrates with the critical care environment. This is especially applicable after the Coronavirus pandemic, where resources and supplies are evermore scarce. After examining the state-of-the-art and establishing a close collaboration with Hamad Medical Corporation (HMC), the main healthcare provider in Qatar, several criteria were identified to advance the cutting-edge. In this article, a high-realism, cost-effective ECMO simulator is presented. It runs on a novel blood simulation technology along with simulation modules. An instructor tablet application enables instructors to orchestrate the training experience wirelessly with real-time performance. It also includes a novel scenario designer for implementing consistent simulation curricula. A product-level simulator with high-fidelity casings is in the final integration phases. Current results include developing and testing the simulated blood circuit, simulation modules for hemorrhaging, line chattering, air bubbles noise, and a replicated console along with an integrated communications system. Nineteen specialists rated the fidelity of the system as highly realistic during a questionnaire-based study. It is expected to run a second study to evaluate the educational efficacy of the simulator as a first-of-its-kind in the region.

Building automation and the advancement of sustainability and safety in internal spaces benefit significantly from occupancy sensing. While particular traditional Machine Learning (ML) methods have succeeded at identifying occupancy patterns for specific datasets, achieving substantial performance in other datasets is still challenging. This paper proposes an occupancy detection method using non-intrusive ambient data and a Deep Learning (DL) model. An environmental sensing board was used to gather temperature, humidity, pressure, light level, motion, sound, and Carbon Dioxide (CO2) data. The detection approach was deployed on an edge device to enable low-cost computing while increasing data security. The system was set up at a university office, which functioned as the primary case study testing location. We analyzed two Convolutional Neural Network (CNN) models to confirm the optimum alternative for edge deployment. A 2D-CNN technique was used for one day to identify occupancy in real-time. The model proved robust and reliable, with a 99.75% real-time prediction accuracy.

Non-intrusive load monitoring (NILM) techniques are central techniques to achieve the energy sustainability goals through the identification of operating appliances in the residential and industrial sectors, potentially leading to increased rates of energy savings. NILM received significant attention in the last decade, reflected by the number of contributions and systematic reviews published yearly. In this regard, the current paper provides a meta-analysis summarising existing NILM reviews to identify widely acknowledged findings concerning NILM scholarship in general and neural NILM algorithms in particular. In addition, this paper emphasizes federated neural NILM, receiving increasing attention due to its ability to preserve end-users’ privacy. Typically, by combining several locally trained models, federated learning has excellent potential to train NILM models locally without communicating sensitive data with cloud servers. Thus, the second part of the current paper provides a summary of recent federated NILM frameworks with a focus on the main contributions of each framework and the achieved performance. Furthermore, we identify the non-availability of proper toolkits enabling easy experimentation with federated neural NILM as a primary barrier in the field. Thus, we extend existing toolkits with a federated component, made publicly available and conduct experiments on the REFIT energy dataset considering four different scenarios.

In the above article [1], the fifth author, Guillaume Alinier, was missing. The author byline should have five authors: Abdullah Alsalemi, Yahya Alhomsi, Fayçal Bensaali, Guillaume Alinier, and Ali Ait Hssain.

Abstract Automatic number plate recognition (ANPR) systems are becoming vital for safety and security purposes. Typical ANPR systems are based on three stages: number plate localization (NPL), character segmentation (CS), and optical character recognition (OCR). Recently, high definition (HD) cameras have been used to improve their recognition rates. In this paper, four algorithms are proposed for the OCR stage of a real-time HD ANPR system. The proposed algorithms are based on feature extraction (vector crossing, zoning, combined zoning, and vector crossing) and template matching techniques. All proposed algorithms have been implemented using MATLAB as a proof of concept and the best one has been selected for hardware implementation using a heterogeneous system on chip (SoC) platform. The selected platform is the Xilinx Zynq-7000 All Programmable SoC, which consists of an ARM processor and programmable logic. Obtained hardware implementation results have shown that the proposed system can recognize one character in 0.63 ms, with an accuracy of 99.5% while utilizing around 6% of the programmable logic resources. In addition, the use of the heterogenous SoC consumes 36 W which is equivalent to saving around 80% of the energy consumed by the PC used in this work, whereas it is smaller in size by 95%.

Meeting application requirements under a tight power budget is of a primary importance to enable connected health internet of things applications. This paper considers using sparse representation and well-defined inequality indexes drawn from the theory of inequality to distinguish ventricular ectopic beats (VEBs) from non-VEBs. Our approach involves designing a separate dictionary for each arrhythmia class using a set of labeled training QRS complexes. Sparse representation, based on the designed dictionaries of each new test QRS complex is then calculated. Following this, its class is predicted using the winner-takes-all principle by selecting the class with the highest inequality index. The experiments showed promising results ranging between 80% and 100% for the detection of VEBs considering the patient-specific approach, 80% using cross validation and 70% on unseen data using independent sets for training and testing, respectively. An efficient hardware implementation of the alternating direction method of multipliers algorithm is also presented. The results show that the proposed hardware implementation can classify a QRS complex in 69.3 ms that use only 0.934 W energy.

Remote health monitoring is becoming indispensable, though, Internet of Things (IoTs)-based solutions have many implementation challenges, including energy consumption at the sensing node, and delay and instability due to cloud computing. Compressive sensing (CS) has been explored as a method to extend the battery lifetime of medical wearable devices. However, it is usually associated with computational complexity at the decoding end, increasing the latency of the system. Meanwhile, mobile processors are becoming computationally stronger and more efficient. Heterogeneous multicore platforms (HMPs) offer a local processing solution that can alleviate the limitations of remote signal processing. This paper demonstrates the real-time performance of compressed ECG reconstruction on ARM's big.LITTLE HMP and the advantages they provide as the primary processing unit of the IoT architecture. It also investigates the efficacy of CS in minimizing power consumption of a wearable device under real-time and hardware constraints. Results show that both the orthogonal matching pursuit and subspace pursuit reconstruction algorithms can be executed on the platform in real time and yield optimum performance on a single A15 core at minimum frequency. The CS extends the battery life of wearable medical devices up to 15.4% considering ECGs suitable for wellness applications and up to 6.6% for clinical grade ECGs. Energy consumption at the gateway is largely due to an active internet connection; hence, processing the signals locally both mitigates system's latency and improves gateway's battery life. Many remote health solutions can benefit from an architecture centered around the use of HMPs, a step toward better remote health monitoring systems.

(1) Background: Simulation-based training (SBT) is the practice of using hands-on training to immerse learners in a risk-free and high-fidelity environment. SBT is used in various fields due to its risk-free benefits from a safety and an economic perspective. In addition, SBT provides immersive training unmatched by traditional teaching the interactive visualization needed in particular scenarios. Medical SBT is a prevalent practice as it allows for a platform for learners to learn in a risk-free and cost-effective environment, especially in critical care, as mistakes could easily cause fatalities. An essential category of care is human circulatory system care (HCSC), which includes essential-to-simulate complications such as cardiac arrest. (2) Methods: In this paper, a deeper look onto existing human circulatory system medical SBT is presented to assess and highlight the important features that should be present with a focus on extracorporeal membrane oxygenation cannulation (ECMO) simulators and cardiac catheterization. (3) Results: A list of features is also suggested for an ideal simulator to bridge the gap between medical studies and simulator engineering, followed by a case study of an ECMO SBT system design. (4) Conclusions: a collection and discussion of existing work for HCSC SBT are portrayed as a guide for researchers and practitioners to compare existing SBT and recreating them effectively.

Simulators for extracorporeal membrane oxygenation (ECMO) have problems of bulky devices and low-fidelity methodologies. Hence, ongoing efforts for optimizing modern solutions focus on minimizing expenses and blending training with the intensive care unit. This is particularly evident following the coronavirus pandemic, where economic resources have been extensively cut. In this paper, as a part of an ECMO simulator for training management, an advance thermochromic ink system for medical blood simulation is presented. The system was developed and enhanced as a prototype with successful and reversible transitions between dark and bright red blood color to simulate blood oxygenation and deoxygenation in ECMO training sessions.

Current blood glucose monitoring (BGM) techniques are invasive as they require a finger prick blood sample, a repetitively painful process that creates the risk of infection. BGM is essential to avoid complications arising due to abnormal blood glucose levels in diabetic patients. Laser light-based sensors have demonstrated a superior potential for BGM. Existing near-infrared (NIR)-based BGM techniques have shortcomings, such as the absorption of light in human tissue, higher signal-to-noise ratio, and lower accuracy, and these disadvantages have prevented NIR techniques from being employed for commercial BGM applications. A simple, compact, and cost-effective non-invasive device using visible red laser light of wavelength 650 nm for BGM (RL-BGM) is implemented in this paper. The RL-BGM monitoring device has three major technical advantages over NIR. Unlike NIR, red laser light has ~30 times better transmittance through human tissue. Furthermore, when compared with NIR, the refractive index of laser light is more sensitive to the variations in glucose level concentration resulting in faster response times ~7-10 s. Red laser light also demonstrates both higher linearity and accuracy for BGM. The designed RL-BGM device has been tested for both in vitro and in vivo cases and several experimental results have been generated to ensure the accuracy and precision of the proposed BGM sensor.

Extracorporeal Membrane Oxygenation (ECMO) is a lifesaving procedure developed for the care of patients with short-term respiratory and/or cardiac issues (MacLaren et al., 2011). ECMO patients must be monitored twenty-four hours a day by an ECMO-trained multidisciplinary team. The trained healthcare professional needs to watch over fifty variables and rapidly intervene to assess and resolve any given emergency. Hence hands on training is very important for ECMO professionals to develop rapid and correct actions upon different scenarios. Simulation based training (SBT) offers ECMO practitioners an opportunity to develop the skills needed for the initiation of the ECMO procedure and the care of ECMO patients without exposing patients to undue risks (Al Disi et al., 2018). For ECMO to work, cannulation is required to reroute the blood flow to the machine rather than the lung and/or heart. Cannulation is the insertion of a cannula through the blood vessels. In collaboration with Hamad Medical Corporation (HMC), the main healthcare provider in Qatar, the aim of this project is to develop an effective, economical realistic, user-friendly, low-cost, and a multi-functional high-fidelity cannulation simulation mannequin. Keywords: Extracorporeal Membrane Oxygenation, ECMO, Medical training, Cannulation, Healthcare

Despite many advancements in extracorporeal membrane oxygenation (ECMO), the procedure is still correlated with a high risk of patient complications. Simulation-based training provides the opportunity for ECMO staff to practice on real-life scenarios without exposing ECMO patients to medical errors while practicing. At Hamad Medical Corporation (HMC) in Qatar, there is a critical need of expert ECMO staff. Thus, a modular ECMO simulator is being developed to enhance the training process in a cost-effective manner. This ECMO simulator gives the instructor the ability to control the simulation modules and run common simulation scenarios through a tablet application. The core modules of the simulation system are placed in the patient unit. The unit is designed modularly such that more modules can be added throughout the simulation sessions to increase the realism of the simulation sessions. The new approach is to enclose the patient unit in a trolley, which is custom-designed and made to include all the components in a modular fashion. Each module is enclosed in a separate box and then mounted to the main blood simulation loop box using screws, quick connect/disconnect liquid fittings, and electrical plugs. This method allows fast upgrade and maintenance for each module separately as well as upgrading modules easily without modifying the trolley’s design. The prototype patient unit has been developed for portability, maintenance, and extensibility. After implementation and testing, the prototype has proven to successfully simulate the main visual and audio cues of the real emergency scenarios, while keeping costs to a minimum.

Systems based on wireless gas sensor networks offer a powerful tool to observe and analyze data in complex environments over long monitoring periods. Since the reliability of sensors is very important in those systems, gas classification is a critical process within the gas safety precautions. A gas classification system has to react fast in order to take essential actions in the case of fault detection. This paper proposes a low latency real-time gas classification service system, which uses a multi-layer perceptron (MLP) artificial neural network to detect and classify the gas sensor data. An accurate MLP is developed to work with the data set obtained from an array of tin oxide (SnO2) gas sensor, based on convex micro hotplates. The overall system acquires the gas sensor data through radio-frequency identification (RFID), and processes the sensor data with the proposed MLP classifier implemented on a system on chip (SoC) platform from Xilinx. Hardware implementation of the classifier is optimized to achieve very low latency for real-time application. The proposed architecture has been implemented on a ZYNQ SoC using fixed-point format and the achieved results have shown that an accuracy of 97.4% has been obtained.

The use of Internet of Things (IoT) with medical devices within a connected health environment promotes the quick flow of information and enables easy access to it [...]

The Internet of Things (IoT) holds great promises to provide an edge cutting technology that enables numerous innovative services related to healthcare, manufacturing, smart cities and various human daily activities. In a typical IoT scenario, a large number of self-powered smart devices collect real-world data and communicate with each other and with the cloud through a wireless link in order to exchange information and to provide specific services. However, the high energy consumption associated with the wireless transmission limits the performance of these IoT self-powered devices in terms of computation abilities and battery lifetime. Thus, to optimize data transmission, different approaches have to be explored such as cooperative transmission, multi-hop network architectures and sophisticated compression techniques. For the latter, compressive sensing (CS) is a very attractive paradigm to be incorporated in the design of IoT platforms. CS is a novel signal acquisition and compression theory that exploits the sparsity behavior of most natural signals and IoT architectures to achieve power-efficient, real-time platforms that can grant efficient IoT applications. This paper assesses the extant literature that has aimed to incorporate CS in IoT applications. Moreover, the paper highlights emerging trends and identifies several avenues for future CS-based IoT research.