Human activity recognition (HAR) is currently recognized as a key element of more general framework designed to perform continuous monitoring human behaviors in the area ambient assisted living (AAL), well-being management, medical diagnosis, elderly care, rehabilitation, entertainment, and surveillance smart home environments. In this paper, an innovative HAR system, exploiting potential wearable devices integrated with skills deep learning techniques, presented aim recognizing most common...

Location-based services have increased in popularity recent years and can be fruitfully exploited the field of smart homes, opening doors to a wide range personalized services. In this context, radio technology widely employed since, other than connecting devices home system, it offers solutions for user localization issue without need any extra device. Techniques based on received signal strength indicator (RSSI) are often used, relying fingerprinting or proximity algorithms. paper, novel...

We evaluated the effectiveness in classifying food images of a deep-learning approach based on specifications Google's image recognition architecture Inception. The is deep convolutional neural network (DCNN) having depth 54 layers. In this study, we fine-tuned for from three well-known datasets: ETH Food-101, UEC FOOD 100, and 256. On these datasets achieved, respectively, 88.28%, 81.45%, 76.17% as top-1 accuracy 96.88%, 97.27%, 92.58% top-5 accuracy. To best our knowledge, results...

Brain–computer interface (BCI) systems aim to enable interaction with other people and the environment without muscular activation by exploitation of changes in brain signals due execution cognitive tasks. In this context, visual P300 potential appears suited control smart homes through BCI spellers. The work is evaluate whether widely used character-speller more sustainable than an icon-based one, designed operate home or communicate moods needs. Nine subjects neurodegenerative diseases no...

Among sensible goals of active and assisted living paradigm is the unobtrusive monitoring daily activities. Based on such monitoring, anomalies trends can be discovered, which possibly allows for early assessment health issues prevention policies. However, when dealing with home environment, especially older adults, obtrusiveness, usability, cost concerns are utmost relevance. Smart objects designed to this purpose deployed into home: they usually feature low data rates customarily...

The activation energy of electromigration in 'bamboo'-type, passivated Al-1% Si/TiN/Ti lines was determined by means high resolution resistance measurements at wafer level. Both the very early stages, with a nonlinear behaviour resistance, and subsequent characterized an approximately constant rate change, were analysed existing model that correlates mechanical stress evolution. An could be extracted only phase linear increase, where value 0.95 eV found. Diffusion interface between Al-Si...

The measurement of the analyte concentration in electrochemical biosensors traditionally requires costly laboratory equipment to obtain accurate results. Innovative portable solutions have recently been proposed, but usually, they lean on personal computers (PCs) or smartphones for data elaboration and exhibit poor resolution portability proprietary software. This paper presents a low-cost system, assembling an ad hoc-designed analog front end (AFE) development board equipped with system...

The trend toward technology ubiquity in human life is constantly increasing and the same tendency clear all technologies aimed at monitoring. In this framework, several smart home system architectures have been presented literature, realized by combining sensors, servers, online platforms. paper, a new architecture suitable for monitoring based on Wi-Fi connectivity introduced. proposed solution lowers costs implementation burden using Internet connection that leans standard modem-routers,...

Nowadays, lithium-ion is among the most used chemistry for batteries and shows an increasing market growth rate. However, to reduce failure or safety risks, battery State-of-Charge (SoC) must be accurately monitored predicted by a suitable Battery Management System (BMS). Artificial Intelligence (AI) techniques have been extensively applied this field with good results. Typically, AIs are trained on dynamic profile data, emulating charging discharging cycles related application under test....

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> Recently, <emphasis emphasistype="boldital">radio frequency identification</emphasis> (RFID) systems have gained popularity in manufacturing units, inventory, and logistics, as they represent an inexpensive reliable solution for automatic identification. Moreover, RFID transponders are expected to become a key element the ubiquitous computing scenario. Tags will likely be used collect sensors...

A balanced diet is the key to a healthy lifestyle and crucial for preventing or dealing with many chronic diseases such as diabetes obesity. Therefore, monitoring can be an effective way of improving people’s health. However, manual reporting food intake has been shown inaccurate often impractical. This paper presents new approach quantity estimation using image-based modeling. The modeling method consists three steps: firstly, short video taken by user’s smartphone. From video, six frames...

Nowadays, analytical techniques are moving towards the development of smart biosensing strategies for point-of-care accurate screening disease biomarkers, such as human epididymis protein 4 (HE4), a recently discovered serum marker early ovarian cancer diagnosis. In this context, present work represents first implementation competitive enzyme-labelled magneto-immunoassay exploiting homemade IoT Wi-Fi cloud-based portable potentiostat differential pulse voltammetry readout. The...

Recent advances in Internet-of-Things technology have opened the doors to new scenarios for biosensor applications. Flexibility, portability, and remote control access are of utmost importance move these devices people's homes or a Point-of-Care context rapidly share results with users their physicians. In this paper, an innovative portable device both quantitative semi-quantitative electrochemical analysis is presented. This can operate autonomously without need relying on other (e.g., PC,...

Monitoring the State of Charge (SoC) in battery cells is necessary to avoid damage and extend life. Support Vector Machine (SVM) algorithms Learning techniques general can provide real-time SoC estimation without need design a cell model. In this work, an SVM was trained by applying Ant Colony Optimization method. The obtained model 10-fold cross-validated then designed Hardware Description Language be run on FPGA devices, enabling low-cost compact hardware. Thanks choice linear kernel,...

An IoT-WiFi smart and portable electrochemical immunosensor for the quantification of SARS-CoV-2 spike protein was developed with integrated machine learning features. The immunoenzymatic sensor is based on immobilization monoclonal antibodies directed at S1 subunit Screen-Printed Electrodes functionalized gold nanoparticles. analytical protocol involves a single-step sample incubation. Immunosensor performance validated in viral transfer medium which commonly used desorption nasopharyngeal...

Liquid biopsy is a non-invasive and efficient technique for the detection of tumor biomarkers in biological fluids, which currently represents new frontier theranostics precision medicine. Among mutations KRAS oncogene, p.G12D single nucleotide variation gene plays central role early diagnosis therapeutic treatment colorectal cancer. In this context, we developed highly sensitive magneto-genosensing assay based on PNA capture probes immobilized magnetic microbeads. To detect mutation two...

The potential of a voltametric E-tongue coupled with custom data pre-processing stage to improve the performance machine learning techniques for rapid discrimination tomato purées between cultivars different economic value has been investigated. To this aim, sensor array screen-printed carbon electrodes modified gold nanoparticles (GNP), copper (CNP) and bulk subsequently poly(3,4-ethylenedioxythiophene) (PEDOT), was developed acquire be transformed by pipeline then processed set commonly...

Cheap passive radio frequency identification (RFID) tags operating in ultra high (UHF) bands are fostering innovation several field such as building access control, goods tracking and supply chains management. RFID transponders can also be coupled to tiny sensors, enabling non invasive monitoring of environmental personal parameters. To ensure the privacy highly sensitive data, encryption authentication capabilities should embedded devices, a fashion compatible with tight power budgets...