Sustainable Health-Related Quality of Life in Older Adults as Supported by the vINCI Technology.

The vINCI technology represents an innovative instrument developed specifically but not exclusively for older adults by technology researchers together with a medical team specialized in geriatrics and gerontology. It was designed to be independently and effortlessly used by older adults in the comfort and safety of their own environment. It is a modular and flexible platform that can integrate a large array of various sensors and can easily adapt to specific healthcare needs. The pilot study tested sensors and standardized instruments capable of evaluating several care-related parameters and of generating personalized feedback for the user dedicated to optimizing physical activity level, social interaction, and health-related quality of life. Moreover, the system was able to detect and signal events and health-related aspects that would require medical assistance. This paper presents how the innovative vINCI technology improves quality of life in older adults. This is evidenced by the results obtained following the clinical validation of the vINCI technology by older adults admitted to the Ana Aslan National Institute of Gerontology and Geriatrics (NIGG) in Bucharest.

Latent profile analysis for quality of life in older patients.

BACKGROUND: Quality of life (QOL) is a complex concept known for being influenced by socio-demographic characteristics, individual needs, perceptions and expectations. The study investigates influences of such heterogeneous variables and aims to identify and describe subgroups of older patients who share similar response patterns for the four domains (physical health, psychological health, social relationships and environment) of World Health Organization Quality of Life instrument, Short Form (WHOQOL-BREF). METHODS: The sample used included older Romanian patients (N = 60; equal numbers of men and women; mean age was 71.95, SD = 5.98). Latent Profile Analysis (LPA) was conducted to explore quality of life profiles with the four WHOQOL-BREF domains as input variables. Differences between profiles were analysed by MANOVA and ANOVAs as a follow-up. RESULTS: The LPA results showed that the three-profile model was the most suitable and supported the existence of three distinct QOL profiles: low and very low (28.3%), moderate (63.3%) and high (8.4%). The relative entropy value was high (0.86), results pointed to a good profile solution and the three profiles differed significantly from one another. CONCLUSION: Our results reveal heterogeneity within the older adult sample and provide meaningful information to better tailor QOL improvement programs to the needs of older patient groups, especially those designed for patients of profiles related to poorer QOL in different domains.

IoT and AI-Based Application for Automatic Interpretation of the Affective State of Children Diagnosed with Autism.

In the context in which it was demonstrated that humanoid robots are efficient in helping children diagnosed with autism in exploring their affective state, this paper underlines and proves the efficiency of a previously developed machine learning-based mobile application called PandaSays, which was improved and integrated with an Alpha 1 Pro robot, and discusses performance evaluations using deep convolutional neural networks and residual neural networks. The model trained with MobileNet convolutional neural network had an accuracy of 56.25%, performing better than ResNet50 and VGG16. A strategy for commanding the Alpha 1 Pro robot without its native application was also established and a robot module was developed that includes the communication protocols with the application PandaSays. The output of the machine learning algorithm involved in PandaSays is sent to the humanoid robot to execute some actions as singing, dancing, and so on. Alpha 1 Pro has its own programming language-Blockly-and, in order to give the robot specific commands, Bluetooth programming is used, with the help of a Raspberry Pi. Therefore, the robot motions can be controlled based on the corresponding protocols. The tests have proved the robustness of the whole solution.

Upper and Lower Leaf Side Detection with Machine Learning Methods.

Recent studies have approached the identification of foliar plant diseases using artificial intelligence, but in these works, classification is achieved using only one side of the leaf. Phytopathology specifies that there are diseases that show similar symptoms on the upper part of the leaf, but different ones on the lower side. An improvement in accuracy can be achieved if the symptoms of both sides of the leaf are considered when classifying plant diseases. In this context, it is necessary to establish whether the captured image represents the leaf on its upper or lower side. From the research conducted using botany books, we can conclude that a useful classification feature is color, because the sun-facing part is greener, while the opposite side is shaded. A second feature is the thickness of the primary and secondary veins. The veins of a leaf are more prominent on the lower side, compared to the upper side. A third feature corresponds to the concave shape of the leaf on its upper part and its convex shape on the lower part. In this study, we aim to achieve upper and lower leaf side classification using both deep learning methods and machine learning models.

Opportunistic Network Algorithms for Internet Traffic Offloading in Music Festival Scenarios.

Constant Internet connectivity has become a necessity in our lives. Hence, music festival organizers allocate part of their budget for temporary Wi-Fi equipment in order to sustain the high network traffic generated in such a small geographical area, but this naturally leads to high costs that need to be decreased. Thus, in this paper, we propose a solution that can help offload some of that traffic to an opportunistic network created with the attendees' smartphones, therefore minimizing the costs of the temporary network infrastructure. Using a music festival-based mobility model that we propose and analyze, we introduce two routing algorithms which can enable end-to-end message delivery between participants. The key factors for high performance are social metrics and limiting the number of message copies at any given time. We show that the proposed solutions are able to offer high delivery rates and low delivery delays for various scenarios at a music festival.

Vehicle Detection in Overhead Satellite Images Using a One-Stage Object Detection Model.

In order to improve the traffic in large cities and to avoid congestion, advanced methods of detecting and predicting vehicle behaviour are needed. Such methods require complex information regarding the number of vehicles on the roads, their positions, directions, etc. One way to obtain this information is by analyzing overhead images collected by satellites or drones, and extracting information from them through intelligent machine learning models. Thus, in this paper we propose and present a one-stage object detection model for finding vehicles in satellite images using the RetinaNet architecture and the Cars Overhead With Context dataset. By analyzing the results obtained by the proposed model, we show that it has a very good vehicle detection accuracy and a very low detection time, which shows that it can be employed to successfully extract data from real-time satellite or drone data.

Gait Recognition as an Authentication Method for Mobile Devices.

With the rate at which smartphones are currently evolving, more and more of human life will be contained in these devices. At a time when data privacy is extremely important, it is crucial to protect one's mobile device. In this paper, we propose a new non-intrusive gait recognition based mechanism that can enhance the security of smartphones by rapidly identifying users with a high degree of confidence and securing sensitive data in case of an attack, with a focus on a potential architecture for such an algorithm for the Android environment. The motion sensors on an Android device are used to create a statistical model of a user's gait, which is later used for identification. Through experimental testing, we prove the capability of our proposed solution by correctly classifying individuals with an accuracy upwards of 90% when tested on data recorded during multiple activities. The experiments, conducted on a low sampling rate and at short time intervals, show the benefits of our solution and highlight the feasibility of an efficient gait recognition mechanism on modern smartphones.

Blockchain-based Reputation for Intelligent Transportation Systems.

A disruptive technology often used in finance, Internet of Things (IoT) and healthcare, blockchain can reach consensus within a decentralised network-potentially composed of large amounts of unreliable nodes-and to permanently and irreversibly store data in a tamper-proof manner. In this paper, we present a reputation system for Intelligent Transportation Systems (ITS). It considers the users interested in traffic information as the main actors of the architecture. They securely share their data which are collectively validated by other users. Users can choose to employ either such crowd-sourced validated data or data generated by the system to travel between two locations. The data saved is reliable, based on the providers' reputation and cannot be modified. We present results with a simulation for three cities: San Francisco, Rome and Beijing. We have demonstrated the impact of malicious attacks as the average speed decreased if erroneous information was stored in the blockchain as an implemented routing algorithm guides the honest cars on other free routes, and thus crowds other intersections.

Human Physical Activity Recognition Using Smartphone Sensors.

Because the number of elderly people is predicted to increase quickly in the upcoming years, "aging in place" (which refers to living at home regardless of age and other factors) is becoming an important topic in the area of ambient assisted living. Therefore, in this paper, we propose a human physical activity recognition system based on data collected from smartphone sensors. The proposed approach implies developing a classifier using three sensors available on a smartphone: accelerometer, gyroscope, and gravity sensor. We have chosen to implement our solution on mobile phones because they are ubiquitous and do not require the subjects to carry additional sensors that might impede their activities. For our proposal, we target walking, running, sitting, standing, ascending, and descending stairs. We evaluate the solution against two datasets (an internal one collected by us and an external one) with great effect. Results show good accuracy for recognizing all six activities, with especially good results obtained for walking, running, sitting, and standing. The system is fully implemented on a mobile device as an Android application.

Identifying Stops and Moves in WiFi Tracking Data.

There are multiple methods for tracking individuals, but the classical ones such as using GPS or video surveillance systems do not scale or have large costs. The need for large-scale tracking, for thousands or even millions of individuals, over large areas such as cities, requires the use of alternative techniques. WiFi tracking is a scalable solution that has gained attention recently. This method permits unobtrusive tracking of large crowds, at a reduced cost. However, extracting knowledge from the data gathered through WiFi tracking is not simple, due to the low positional accuracy and the dependence on signals generated by the tracked device, which are irregular and sparse. To facilitate further data analysis, we can partition individual trajectories into periods of stops and moves. This abstraction level is fundamental, and it opens the way for answering complex questions about visited locations or even social behavior. Determining stops and movements has been previously addressed for tracking data gathered using GPS. GPS trajectories have higher positional accuracy at a fixed, higher frequency as compared to trajectories obtained through WiFi. However, even with the increase in accuracy, the problem, of separating traces in periods of stops and movements, remains similar to the one we encountered for WiFi tracking. In this paper, we study three algorithms for determining stops and movements for GPS-based datasets and explore their applicability to WiFi-based data. We propose possible improvements to the best-performing algorithm considering the specifics of WiFi tracking data.