Improving BLE-Based Passive Human Sensing with Deep Learning.

Passive Human Sensing (PHS) is an approach to collecting data on human presence, motion or activities that does not require the sensed human to carry devices or participate actively in the sensing process. In the literature, PHS is generally performed by exploiting the Channel State Information variations of dedicated WiFi, affected by human bodies obstructing the WiFi signal propagation path. However, the adoption of WiFi for PHS has some drawbacks, related to power consumption, large-scale deployment costs and interference with other networks in nearby areas. Bluetooth technology and, in particular, its low-energy version Bluetooth Low Energy (BLE), represents a valid candidate solution to the drawbacks of WiFi, thanks to its Adaptive Frequency Hopping (AFH) mechanism. This work proposes the application of a Deep Convolutional Neural Network (DNN) to improve the analysis and classification of the BLE signal deformations for PHS using commercial standard BLE devices. The proposed approach was applied to reliably detect the presence of human occupants in a large and articulated room with only a few transmitters and receivers and in conditions where the occupants do not directly occlude the Line of Sight between transmitters and receivers. This paper shows that the proposed approach significantly outperforms the most accurate technique found in the literature when applied to the same experimental data.

A Perspective on Passive Human Sensing with Bluetooth.

Passive human sensing approaches based on the analysis of the radio signals emitted by the most common wireless communication technologies have been steadily gaining momentum during the last decade. In this context, the Bluetooth technology, despite its widespread adoption in mobile and IoT applications, so far has not received all the attention it deserves. However, the introduction of the Bluetooth direction finding feature and the application of Artificial Intelligence techniques to the processing and analysis of the wireless signal for passive human sensing pave the way for novel Bluetooth-based passive human sensing applications, which will leverage Bluetooth Low Energy features, such as low power consumption, noise resilience, wide diffusion, and relatively low deployment cost. This paper provides a reasoned analysis of the data preprocessing and classification techniques proposed in the literature on Bluetooth-based remote passive human sensing, which is supported by a comparison of the reported accuracy results. Building on such results, the paper also identifies and discusses the multiple factors and operating conditions that explain the different accuracy values achieved by the considered techniques, and it draws the main research directions for the near future.

The role of a virtual avatar in attention and memory tasks in Rett syndrome.

BACKGROUND: Since subjects with Rett syndrome (RTT) focus their attention mainly on the faces of people with whom they interact, in this study the role of a human-like smart interactive agent (an avatar) in enhancing cognitive processes is examined. More in depth, this study aimed to understand if, and to what extent, the use of an avatar can improve attention and memory abilities in subjects with RTT. METHOD: Thirty-six subjects with RTT participated in the study. All participants performed over-selectivity and memory tasks, for a total of six trials. These trials were randomly presented in two different conditions: with and without virtual avatar. RESULTS: The results indicated that the participants improved their attention and memory abilities when they performed the tasks with the avatar. There were no improvements when they performed the tasks without the avatar. DISCUSSION: The results were discussed considering the relationship between motivation, attention and memory in RTT.

Atypical Visual Scan Path Affects Remembering in ADHD.

OBJECTIVE: Several studies agree on the link between attention and eye movements during reading. It has been well established that attention and working memory (WM) interact. A question that could be addressed to better understand these relationships is: to what extent can an attention deficit affect eye movements and, consequently, remembering a word? The main aims of the present study were (1) to compare visual patterns of word stimuli between children with Attention Deficit Hyperactivity Disorder (ADHD) and typically developing (TD) children, during a visual task on word stimuli; (2) to examine the WM accuracy of the word stimuli; and (3) to compare the dynamic of visual scan path in both groups. METHOD: A total of 49 children with ADHD, age and sex matched with 32 TD children, were recruited. We used eye-tracking technology in which the Word Memory Test was implemented. To highlight the scan path of participants, two measures were used: the ordered direction of reading and the entropy index. RESULTS: ADHD groups showed a poorer WM than TD group. They did not follow a typical scan path across the words compared with TD children, but their visual scanning was discontinuous, uncoordinated, and chaotic. ADHD groups showed an index of entropy among the four categories of saccades higher than TD group. CONCLUSIONS: The findings were discussed in light of two directions: the relationship between atypical visual scan path and WM and the training implications related to the necessity of redirecting the dynamic of visual scan path in ADHD to improve WM.

Predicting trends in HIV-1 sexual transmission in sub-Saharan Africa through the Drug Resource Enhancement Against AIDS and Malnutrition model: antiretrovirals for 5 reduction of population infectivity, incidence and prevalence at the district level.

BACKGROUND: The use of antiretrovirals to reduce the incidence of human immunodeficiency virus (HIV) infection has been evaluated in mathematical models as potential strategies for curtailing the epidemic. Cohort data from the Drug Resource Enhancement Against AIDS and Malnutrition (DREAM) Program was used to generate a realistic model for the HIV epidemic in sub-Saharan Africa. METHODS: Two combined stochastic models were developed: patient and epidemic models. Models were combined using virus load as a parameter of infectivity. DREAM data that assessed patient care in Mozambique and Malawi were used to generate measures of infectivity, survival, and adherence. The Markov chain prediction model was used for the analysis of disease progression in treated and untreated patients. A partnership model was used to assess the probability that an infected individual would transmit HIV. RESULTS: Data from 26565 patients followed up from January 2002 through July 2009 were analyzed with the model; 63% of patients were female, the median age was 35 years, and the median observation time was 25 months. In the model, a 5-fold reduction in infectivity (from 1.6% to 0.3%) occurred within 3 years when triple ART was used. The annual incidence of HIV infection declined from 7% to 2% in 2 years, and the prevalence was halved, from 12% to 6%, in 11 years. Mortality in HIV-infected individuals declined by 50% in 5 years. A cost analysis demonstrated economic efficiency after 4 years. CONCLUSIONS: Our model, based on patient data, supports the hypothesis that treatment of all infected individuals translates into a drastic reduction in incident HIV infections. A targeted implementation strategy with massive population coverage is feasible in sub-Saharan Africa.

Comparing Advanced with Basic Telerehabilitation Technologies for Patients with Rett Syndrome-A Pilot Study on Behavioral Parameters.

The aim of this study is to compare the performances of patients with Rett syndrome that were undergoing advanced telerehabilitation (ATR) and patients that were undergoing basic telerehabilitation (BTR). It was hypothesized that patients that were undergoing ATR training would have better improvement in nearly all the motor and cognitive scale scoring activities that were administered, thus showing reduced disability. A total of 20 young girls and women with a diagnosis of RTT, ranging from age 4 to 31 years old (Median: 12.50; IQR: 9.50-17.25) underwent a pre-test, treatment post-test 1, treatment, and post-test 2 procedure. The treatment consisted of either ATR or BTR, lasting 10 weeks with three sessions a week of about an hour. The results showed that the group with advanced telerehabilitation improved their performance better than the control group only in some neuropsychological measurements. The results are discussed in the light of critical factors of telerehabilitation.

Social and Cognitive Interactions Through an Interactive School Service for RTT Patients at the COVID-19 Time.

Background: The closure of all educational institutions and most rehabilitation centres represents a precautionary measure to face the COVID-19 pandemic, but the isolation and social distancing may be particularly challenging for children with special needs and disabilities (SEND), such as Rett Syndrome (RTT). The main aim of this study was to promote cognitive and social interactions among children with RTT through an interactive school program. Methods: The Interactive School palimpsest was composed of moments in which a teacher spoke directly to children with RTT and expected a response through eye gaze, and moments in which storeys-cartoon were presented while tracking the eye gaze of children. We investigated behavioural, social and cognitive parameters. Results: Children participated in both social and cognitive tasks with the spontaneous reduction of stereotypies and with increase in attention. They recalled more significant indexes when music or a song was presented together with a cartoon or a cognitive task. Conclusions: This study provides initial insights in promoting cognitive and social interactions and in the support needs of families with a child with RTT during the COVID-19 pandemic.

A global approach to the management of EMR (electronic medical records) of patients with HIV/AIDS in sub-Saharan Africa: the experience of DREAM software.

BACKGROUND: The DREAM Project operates within the framework of the national health systems of several sub-Saharan African countries and aims to introduce the essential components of an integrated strategy for the prevention and treatment of HIV/AIDS. The project is intended to serve as a model for a wide-ranging scale-up in the response to the epidemic. This paper aims to show DREAM's challenges and the solutions adopted. One of the solutions is the efficient management of the clinical data regarding the treatment of the patients and epidemiological analyses. METHODS: Specific software for the management of the patients' EMR has been created within the DREAM programme in order to deal with the challenges deriving from the context in which DREAM operates. Setting up a computer infrastructure in health centres, providing a power supply, as well as managing the data and the project resources efficiently and reliably, are some of the questions that have been analysed in this study. RESULTS: Over the years this software has proved that it is able to respond to the need for efficient management of the clinical data and organization of the health centres. Today it is used in 10 countries in sub-Saharan Africa by thousands of professionals and by now it has reached its fourth version. The medical files of over 73,000 assisted patients are managed by this software and the data collected with it have become essential for the epidemiological research that is carried out to improve the effectiveness of the therapy. CONCLUSION: Sub-Saharan Africa is the region hardest hit by HIV and AIDS in the world. However, the resources and responses adopted so far, to confront the epidemic, have at times been rather minimalist. The DREAM project has faced the battle against the epidemic by equipping itself with qualitative standards comparable to Western ones. The experience of DREAM has revealed that it is indeed possible to guarantee levels of excellence in developing countries, also in the sphere of ICT (Information and Communication Technology), thus making the intervention even more effective and contributing to bridging the digital divide.

Interactive Avatar Boosts the Performances of Children with Attention Deficit Hyperactivity Disorder in Dynamic Measures of Intelligence.

This study examined both children with attention deficit hyperactivity disorder (ADHD) and typically developing students in dynamic measures of intelligence through the use of a virtual avatar. Three conditions were compared: in the first condition, the avatar simply gave the instructions; in the second condition, the avatar presented the instructions and gave feedback on the attention of the learner; in the third condition, the avatar was not presented. Results indicated that ADHD subtypes do not differ in problem solving and the interactive avatar improved the performance of groups with ADHD in the dynamic intelligence test. Overall, these results support the hypothesis that the function of regulation and feedback of the avatar improve the attention process and, consequently, boosts performance.

The burden of nephrotoxic drug prescriptions in patients with chronic kidney disease: a retrospective population-based study in Southern Italy.

BACKGROUND: The use of nephrotoxic drugs can further worsening renal function in chronic kidney disease (CKD) patients. It is therefore imperative to explore prescribing practices that can negatively affect CKD patients. AIM: To analyze the use of nephrotoxic drugs in CKD patients in a general population of Southern Italy during the years 2006-2011. METHODS: The general practice "Arianna" database contains data from 158,510 persons, registered with 123 general practitioners (GPs) of Caserta. CKD patients were identified searching: CKD-related ICD-9 CM codes among causes of hospitalization; CKD-relevant procedures undergone in hospital (e.g. dialysis); drug prescriptions issued for a CKD-related indication. A list of nephrotoxic drugs was compiled and validated by pharmacologists and nephrologists. The summary of product characteristics was used to classify drugs as 'contraindicated' or 'to be used with caution' in renal diseases. Frequency of nephrotoxic drug use, overall, by drug class and single compounds, by GPs within one year prior or after first CKD diagnosis and within one year after dialysis entry was calculated. RESULTS: Overall, 1,989 CKD patients and 112 dialysed patients were identified. Among CKD patients, 49.8% and 45.2% received at least one prescription for a contraindicated nephrotoxic drug within one year prior or after first CKD diagnosis, respectively. In detail, 1,119 CKD patients (56.3%) had at least one nonsteroidal anti-inflammatory drugs (NSAIDs) prescription between CKD diagnosis and end of follow-up. A large proportion of CKD patients (35.6%) were treated with NSAIDs for periods exceeding 90 days. Contraindicated nephrotoxic drugs were used commonly in CKD, with nimesulide (16.6%) and diclofenac (11.0%) being most frequently used. CONCLUSIONS: Contraindicated nephrotoxic drugs were highly prescribed in CKD patients from a general population of Southern Italy. CKD diagnosis did not seem to reduce significantly the prescription of nephrotoxic drugs, which may increase the risk of preventable renal function deterioration.