Journal of Ambient Intelligence and Smart Environments

Alzheimer’s disease (AD) is an incurable disease and a type of dementia. About 55 million people around the world have AD. However, technologies have been used to assist in the healthcare of AD, supporting physicians in the palliative care of patients. This article presents a systematic mapping study (SMS) to identify articles that use technologies to monitor patients with AD in order to show an overview of the literature, identifying gaps and research opportunities in this field. The scientific contribution of this work is to identify monitoring technologies related to AD and highlight current trends on the subject. The paper uses the term technologies as hardware infrastructure and devices or systems without considering software technologies. In addition, this article proposes a taxonomy for the domain of technologies applied to AD patients. The SMS study was conducted in six databases, including articles from 1997 to 2021. An initial search resulted in 7,781 articles. After applying filter criteria, throwing automatic selection on databases, and manual assortment, 171 articles were selected. Subsequently, a second search was performed to reduce the list of articles and filter by the specific search objective of articles focused on technologies for monitoring with tracking, resulting in 74 works. The main results obtained are: (1) a relevant number of articles (43.42%) reported solutions used in sensor-based devices; (2) several works (33.33%) have the interaction focus on Position/Distance/Proximity/Location sensor type; (3) another group of articles has a secondary focus on Emergency help (18.97%). The results indicated the need for technologies to help caregivers monitor patients, in addition to evidence of research opportunities in palliative care and support for the daily activities of AD patients.

Over the last fifty years, societies across the world have experienced multiple periods of energy insufficiency with the most recent one being the 2022 global energy crisis. In addition, the electric power industry has been experiencing a steady increase in electricity consumption since the second industrial revolution because of the widespread usage of electrical appliances and devices. Newer devices are equipped with sensors and actuators, they can collect a large amount of data that could help in power management. However, current energy management approaches are mostly applied to limited types of devices in specific domains and are difficult to implement in other scenarios. They fail when it comes to their level of autonomy, flexibility, and genericity. To address these shortcomings, we present, in this paper, an automated energy management approach for connected environments based on generating power estimation models, representing a formal description of energy-related knowledge, and using reinforcement learning (RL) techniques to accomplish energy-efficient actions. The architecture of this approach is based on three main components: power estimation models, knowledge base, and intelligence module. Furthermore, we develop algorithms that exploit knowledge from both the power estimator and the ontology, to generate the corresponding RL agent and environment. We also present different reward functions based on user preferences and power consumption. We illustrate our proposal in the smart home domain. An implementation of the approach is developed and two validation experiments are conducted. Both case studies are deployed in the context of smart homes: (a) a living room with a variety of devices and (b) a smart home with a heating system. The obtained results show that our approach performs well given the low convergence period, the high level of user preferences satisfaction, and the significant decrease in energy consumption.

This paper discusses the development and design of two wheeled-type In-Pipe Inspection Robots (IPIRs), Kuzhali I and Kuzhali II, which were created to address the limitations of traditional human inspection methods and earlier robot designs. Specifically, the robots aim to overcome the motion singularity experienced by IPIRs when navigating through curved pipes. Kuzhali I was developed with wheels mounted at an asymmetric angle, which enables the wheels to maintain contact with the pipe’s surface, preventing motion singularity. However, Kuzhali I had limitations due to its prismatic mechanism, and thus Kuzhali II was developed with a telescopic mechanism to allow it to pass through vertical pipes with obstacles. Motion analysis was conducted on both robots to demonstrate how they overcome motion singularity and navigate through straight and curved pipelines. Simulation results showed that the forces acting on the robots’ wheels fell within 5 N to 12 N, demonstrating stability while navigating pipeline junctions. Experimental tests were conducted on Kuzhali II, and the results were compared to simulation results, showing an error of less than 5%. The results of the experiments indicate that Kuzhali II is safe to use for pipeline inspection, can navigate through vertical pipelines with ease and can overcome motion singularity in curved pipes. These robots offer a faster, more accurate, and safer alternative to human inspection, which can reduce the risk of pipeline failures and associated environmental and safety hazards.

Gas masks are essential respiratory protective equipment commonly used by laborers who work in harsh environments. However, respiratory diseases and accidents can occur due to the absence of gas masks. To prevent these accidents, this paper developed an object detector that uses convolutional neural networks (CNNs) to detect whether workers are wearing gas masks. To achieve this goal, a gas mask detection dataset was constructed derived from real industrial scenarios and Faster R-CNN was improved for gas mask wearing detection. Firstly, to address the multi-scale problem in real scenes, the Feature Pyramid Network was introduced into Faster R-CNN to effectively fuse features between different levels and improve the detection ability of small objects. Secondly, the Online Hard Sample Mining algorithm was used to alleviate the class imbalance problems in the dataset. Finally, Mixup and Mosaic were used in the training process to augment the data and make the model better adapt to different scenes and complex backgrounds. After multiple experiments, the combination of the three optimization strategies improved the mAP 0.5 : 0.95 by 23.2%. This work is an initial attempt at gas mask wearing detection and there is still much room for improvement in terms of model and dataset.

Due to the abundance of the Internet of Things (IoT), smart devices are widely utilized which helps to manage human surroundings and senses inside and outside environments. The huge amount of data generated from the IoT device attracts cyber-criminals in order to gain information from the significant relationship between people and smart devices. Cyber-attacks on IoT pose a severe challenge for forensic experts. Researchers have invented many techniques to solve IoT forensic challenges and to have an in-depth knowledge of all the facts internal as-well-as external architecture of IoT needs to be understood. In this paper, an attempt has been made to understand the relationship between security and forensics incorporating its strengths and weaknesses, which has not been explored till date to the best of our knowledge. An attempt has also been made to classify literature into three categories: physical level, network level, and cloud level. These include evidence sources, areas of IoT forensics, potential forensic information, evidence extraction techniques, investigation procedures, and legal issues. Also, some prominent IoT forensic use cases have been recited along with providing the key requirements for forensic investigation. Finally, possible research problems in IoT forensic have been identified.

Since its introduction by Mark Weiser, ubiquitous computing has received increased interest in the dawn of technological advancement. Supported by wireless technology advancement, embedded systems, miniaturization, and the integration of various intelligent and communicative devise, context-aware ubiquitous applications actively and intelligently use rich contextual information to assist their users. However, their designs are subject to continuous changes imposed by external factors. Nowadays, software engineering, particularly in the fields of Model-Driven Engineering, displays a strong tendency towards developing applications for pervasive computing. This trend is also fueled by the rise of generative artificial intelligence, paving the way for a new generation of no-code development tools and models specifically trained on open-source code repositories to generate applications from their descriptions. The specificities of our approach lies in starting with a graphical model expressed using a domain-specific language (DSL) composed of symbols and formal notations. This allows for graphically instantiating and editing applications, guiding and assisting experts from various engineering fields in defining ubiquitous applications that are eventually transformed into peculiar models. We believe that creating intelligent models is the best way to promote software development efficiency. We have used and evaluated recurrent neural networks, leveraging the recurrence of processing the same contextual information collected within this model, and enabling iterative adaptation to future evolutions in ubiquitous systems. We propose a prototype instantiated by our meta-model which tracks the movements of individuals who were positive for COVID-19 and confirmed to be contagious. Different deep learning models and classical machine learning techniques are considered and compared for the task of detection/classification of COVID-19. Results obtained from all techniques were evaluated with confusion matrices, accuracy, precision, recall and F1-score. In summary, most of the results are very impressive. Our deep learning approach used a RNN architecture produced up to 92.1% accuracy.

With the recent development of OpenAI Codex, optimized for programming languages, we provided the same requirements to the Codex model and asked it to generate the source code for the COVID-19 application, comparing it with the application generated by our workshop.