On the use of simple geometric descriptors provided by RGB-D sensors for re-identification

[EN]The re-identification problem has been commonly accomplished using appearance features based on salient points and color information. In this paper, we focus on the possibilities that simple geometric features obtained from depth images captured with RGB-D cameras may offer for the task, particularly working under severe illumination conditions. The results achieved for different sets of simple geometric features extracted in a top-view setup seem to provide useful descriptors for the re-identification task, which can be integrated in an ambient intelligent environment as part of a sensor network.

Spectrum shaping and its application: spread-spectrum clock generator and circuits for ultra wide band

Electromagnetic spectrum can be identified as a resource for the designer, as well as for the manufacturer, from two complementary points of view: first, because it is a good in great demand by many different kind of applications; second, because despite its scarce availability, it may be advantageous to use more spectrum than necessary. This is the case of Spread-Spectrum Systems, those systems in which the transmitted signal is spread over a wide frequency band, much wider, in fact, than the minimum bandwidth required to transmit the information being sent. Part I of this dissertation deals with Spread-Spectrum Clock Generators (SSCG) aiming at reducing Electro Magnetic Interference (EMI) of clock signals in integrated circuits (IC) design. In particular, the modulation of the clock and the consequent spreading of its spectrum are obtained through a random modulating signal outputted by a chaotic map, i.e. a discrete-time dynamical system showing chaotic behavior. The advantages offered by this kind of modulation are highlighted. Three different prototypes of chaos-based SSCG are presented in all their aspects: design, simulation, and post-fabrication measurements. The third one, operating at a frequency equal to 3GHz, aims at being applied to Serial ATA, standard de facto for fast data transmission to and from Hard Disk Drives. The most extreme example of spread-spectrum signalling is the emerging ultra-wideband (UWB) technology, which proposes the use of large sections of the radio spectrum at low amplitudes to transmit high-bandwidth digital data. In part II of the dissertation, two UWB applications are presented, both dealing with the advantages as well as with the challenges of a wide-band system, namely: a chaos-based sequence generation method for reducing Multiple Access Interference (MAI) in Direct Sequence UWB Wireless-Sensor-Networks (WSNs), and design and simulations of a Low-Noise Amplifier (LNA) for impulse radio UWB. This latter topic was studied during a study-abroad period in collaboration with Delft University of Technology, Delft, Netherlands.

Impatto della propagazione elettromagnetica sulle prestazioni delle reti M3N

Con il termine Smart Grid si intende una rete urbana capillare che trasporta energia, informazione e controllo, composta da dispositivi e sistemi altamente distribuiti e cooperanti. Essa deve essere in grado di orchestrare in modo intelligente le azioni di tutti gli utenti e dispositivi connessi al fine di distribuire energia in modo sicuro, efficiente e sostenibile. Questo connubio fra ICT ed Energia viene comunemente identificato anche con il termine Smart Metering, o Internet of Energy. La crescente domanda di energia e l’assoluta necessità di ridurre gli impatti ambientali (pacchetto clima energia 20-20-20 [9]), ha creato una convergenza di interessi scientifici, industriali e politici sul tema di come le tecnologie ICT possano abilitare un processo di trasformazione strutturale di ogni fase del ciclo energetico: dalla generazione fino all’accumulo, al trasporto, alla distribuzione, alla vendita e, non ultimo, il consumo intelligente di energia. Tutti i dispositivi connessi, diventeranno parte attiva di un ciclo di controllo esteso alle grandi centrali di generazione così come ai comportamenti dei singoli utenti, agli elettrodomestici di casa, alle auto elettriche e ai sistemi di micro-generazione diffusa. La Smart Grid dovrà quindi appoggiarsi su una rete capillare di comunicazione che fornisca non solo la connettività fra i dispositivi, ma anche l’abilitazione di nuovi servizi energetici a valore aggiunto. In questo scenario, la strategia di comunicazione sviluppata per lo Smart Metering dell’energia elettrica, può essere estesa anche a tutte le applicazioni di telerilevamento e gestione, come nuovi contatori dell’acqua e del gas intelligenti, gestione dei rifiuti, monitoraggio dell’inquinamento dell’aria, monitoraggio del rumore acustico stradale, controllo continuo del sistema di illuminazione pubblico, sistemi di gestione dei parcheggi cittadini, monitoraggio del servizio di noleggio delle biciclette, ecc. Tutto ciò si prevede possa contribuire alla progettazione di un unico sistema connesso, dove differenti dispositivi eterogenei saranno collegati per mettere a disposizione un’adeguata struttura a basso costo e bassa potenza, chiamata Metropolitan Mesh Machine Network (M3N) o ancora meglio Smart City. Le Smart Cities dovranno a loro volta diventare reti attive, in grado di reagire agli eventi esterni e perseguire obiettivi di efficienza in modo autonomo e in tempo reale. Anche per esse è richiesta l’introduzione di smart meter, connessi ad una rete di comunicazione broadband e in grado di gestire un flusso di monitoraggio e controllo bi-direzionale esteso a tutti gli apparati connessi alla rete elettrica (ma anche del gas, acqua, ecc). La M3N, è un’estensione delle wireless mesh network (WMN). Esse rappresentano una tecnologia fortemente attesa che giocherà un ruolo molto importante nelle futura generazione di reti wireless. Una WMN è una rete di telecomunicazione basata su nodi radio in cui ci sono minimo due percorsi che mettono in comunicazione due nodi. E’ un tipo di rete robusta e che offre ridondanza. Quando un nodo non è più attivo, tutti i rimanenti possono ancora comunicare tra di loro, direttamente o passando da uno o più nodi intermedi. Le WMN rappresentano una tipologia di rete fondamentale nel continuo sviluppo delle reti radio che denota la divergenza dalle tradizionali reti wireless basate su un sistema centralizzato come le reti cellulari e le WLAN (Wireless Local Area Network). Analogamente a quanto successo per le reti di telecomunicazione fisse, in cui si è passati, dalla fine degli anni ’60 ai primi anni ’70, ad introdurre schemi di rete distribuite che si sono evolute e man mano preso campo come Internet, le M3N promettono di essere il futuro delle reti wireless “smart”. Il primo vantaggio che una WMN presenta è inerente alla tolleranza alla caduta di nodi della rete stessa. Diversamente da quanto accade per una rete cellulare, in cui la caduta di una Base Station significa la perdita di servizio per una vasta area geografica, le WMN sono provviste di un’alta tolleranza alle cadute, anche quando i nodi a cadere sono più di uno. L'obbiettivo di questa tesi è quello di valutare le prestazioni, in termini di connettività e throughput, di una M3N al variare di alcuni parametri, quali l’architettura di rete, le tecnologie utilizzabili (quindi al variare della potenza, frequenza, Building Penetration Loss…ecc) e per diverse condizioni di connettività (cioè per diversi casi di propagazione e densità abitativa). Attraverso l’uso di Matlab, è stato quindi progettato e sviluppato un simulatore, che riproduce le caratteristiche di una generica M3N e funge da strumento di valutazione delle performance della stessa. Il lavoro è stato svolto presso i laboratori del DEIS di Villa Grifone in collaborazione con la FUB (Fondazione Ugo Bordoni).

From fall-risk assessment to fall detection: inertial sensors in the clinical routine and daily life

Falls are caused by complex interaction between multiple risk factors which may be modified by age, disease and environment. A variety of methods and tools for fall risk assessment have been proposed, but none of which is universally accepted. Existing tools are generally not capable of providing a quantitative predictive assessment of fall risk. The need for objective, cost-effective and clinically applicable methods would enable quantitative assessment of fall risk on a subject-specific basis. Tracking objectively falls risk could provide timely feedback about the effectiveness of administered interventions enabling intervention strategies to be modified or changed if found to be ineffective. Moreover, some of the fundamental factors leading to falls and what actually happens during a fall remain unclear. Objectively documented and measured falls are needed to improve knowledge of fall in order to develop more effective prevention strategies and prolong independent living. In the last decade, several research groups have developed sensor-based automatic or semi-automatic fall risk assessment tools using wearable inertial sensors. This approach may also serve to detect falls. At the moment, i) several fall-risk assessment studies based on inertial sensors, even if promising, lack of a biomechanical model-based approach which could provide accurate and more detailed measurements of interests (e.g., joint moments, forces) and ii) the number of published real-world fall data of older people in a real-world environment is minimal since most authors have used simulations with healthy volunteers as a surrogate for real-world falls. With these limitations in mind, this thesis aims i) to suggest a novel method for the kinematics and dynamics evaluation of functional motor tasks, often used in clinics for the fall-risk evaluation, through a body sensor network and a biomechanical approach and ii) to define the guidelines for a fall detection algorithm based on a real-world fall database availability.

Tracking di target multipli in reti di sensori radar

Viene proposta una possibile soluzione al problema del tracking multitarget, tramite una rete di sensori radar basata su tecnoligia ultra wide-band. L'area sorvegliata ha una superficie pari a 100 metri quadri e all'interno di essa si vuole tracciare la traiettoria di più persone.

Caratterizzazione sperimentale di trasduttori piezoelettrici mediante circuiti equivalenti elettromeccanici

Attualmente la costante diffusione delle sensor network e lo sviluppo di apparati elettronici a basso consumo di energia hanno fatto in modo di motivare la ricerca nel campo dell’elettronica che tenta di spiegare il concetto dell'energy harvesting per raccogliere energia dall'ambiente circostante. I sistemi che raccolgono quella energia che normalmente va persa sono di diversi tipi.

Progettazione ed implementazione di una piattaforma per il monitoraggio della copertura internet mobile attraverso un approccio di data-crowdsourcing

L'obiettivo di questa Tesi di laurea è di creare un applicativo che informi gli utenti sulle reti circostanti, in particolare sulla qualità del segnale, sulle zone in cui la rete mobile è carente e sui punti d'accesso aperti. Per l'implementazione del servizio, è stato adottato un modello di business, il Crowdsourcing, per raccogliere informazioni sui sistemi di connessione, affinché qualsiasi utente dotato di Smartphone possa aggiungere elementi al dataset.

On the accuracy of Software-based Energy Estimation Techniques

This paper examines the accuracy of software-based on-line energy estimation techniques. It evaluates today’s most widespread energy estimation model in order to investigate whether the current methodology of pure software-based energy estimation running on a sensor node itself can indeed reliably and accurately determine its energy consumption - independent of the particular node instance, the traffic load the node is exposed to, or the MAC protocol the node is running. The paper enhances today’s widely used energy estimation model by integrating radio transceiver switches into the model, and proposes a methodology to find the optimal estimation model parameters. It proves by statistical validation with experimental data that the proposed model enhancement and parameter calibration methodology significantly increases the estimation accuracy.

Service Descriptions and Linked Data for Integrating WSNs into Enterprise IT

This paper presents our ongoing work on enterprise IT integration of sensor networks based on the idea of service descriptions and applying linked data principles to them. We argue that using linked service descriptions facilitates a better integration of sensor nodes into enterprise IT systems and allows SOA principles to be used within the enterprise IT and within the sensor network itself.

Entwicklung von energieautarken, intelligenten Ladehilfsmitteln am Beispiel des inBin

Das autonome, intelligente Ladehilfsmittel verkörpert die Idee des Internets der Dinge in der Intralogistik in Reinform. Am Beispiel des inBin wird das Energy-Harvesting in der Intralogistik betrachtet und gezeigt, dass ein Behälter mit komplexen logistischen Funktionen unter realistischer Umgebungsbeleuchtung durch Solarzellen betrieben werden kann.

NodePM: A Remote Monitoring Alert System for Energy Consumption Using Probabilistic Techniques

In this paper, we propose an intelligent method, named the Novelty Detection Power Meter (NodePM), to detect novelties in electronic equipment monitored by a smart grid. Considering the entropy of each device monitored, which is calculated based on a Markov chain model, the proposed method identifies novelties through a machine learning algorithm. To this end, the NodePM is integrated into a platform for the remote monitoring of energy consumption, which consists of a wireless sensors network (WSN). It thus should be stressed that the experiments were conducted in real environments different from many related works, which are evaluated in simulated environments. In this sense, the results show that the NodePM reduces by 13.7% the power consumption of the equipment we monitored. In addition, the NodePM provides better efficiency to detect novelties when compared to an approach from the literature, surpassing it in different scenarios in all evaluations that were carried out.

Integration of WSNs into enterprise systems based on semantic physical business entities

Internet of Things based systems are anticipated to gain widespread use in industrial applications. Standardization efforts, like 6L0WPAN and the Constrained Application Protocol (CoAP) have made the integration of wireless sensor nodes possible using Internet technology and web-like access to data (RESTful service access). While there are still some open issues, the interoperability problem in the lower layers can now be considered solved from an enterprise software vendors' point of view. One possible next step towards integration of real-world objects into enterprise systems and solving the corresponding interoperability problems at higher levels is to use semantic web technologies. We introduce an abstraction of real-world objects, called Semantic Physical Business Entities (SPBE), using Linked Data principles. We show that this abstraction nicely fits into enterprise systems, as SPBEs allow a business object centric view on real-world objects, instead of a pure device centric view. The interdependencies between how currently services in an enterprise system are used and how this can be done in a semantic real-world aware enterprise system are outlined, arguing for the need of semantic services and semantic knowledge repositories. We introduce a lightweight query language, which we use to perform a quantitative analysis of our approach to demonstrate its feasibility.

A web-based non-intrusive ambient system to measure and classify activities of daily living.

BACKGROUND The number of older adults in the global population is increasing. This demographic shift leads to an increasing prevalence of age-associated disorders, such as Alzheimer's disease and other types of dementia. With the progression of the disease, the risk for institutional care increases, which contrasts with the desire of most patients to stay in their home environment. Despite doctors' and caregivers' awareness of the patient's cognitive status, they are often uncertain about its consequences on activities of daily living (ADL). To provide effective care, they need to know how patients cope with ADL, in particular, the estimation of risks associated with the cognitive decline. The occurrence, performance, and duration of different ADL are important indicators of functional ability. The patient's ability to cope with these activities is traditionally assessed with questionnaires, which has disadvantages (eg, lack of reliability and sensitivity). Several groups have proposed sensor-based systems to recognize and quantify these activities in the patient's home. Combined with Web technology, these systems can inform caregivers about their patients in real-time (e.g., via smartphone). OBJECTIVE We hypothesize that a non-intrusive system, which does not use body-mounted sensors, video-based imaging, and microphone recordings would be better suited for use in dementia patients. Since it does not require patient's attention and compliance, such a system might be well accepted by patients. We present a passive, Web-based, non-intrusive, assistive technology system that recognizes and classifies ADL. METHODS The components of this novel assistive technology system were wireless sensors distributed in every room of the participant's home and a central computer unit (CCU). The environmental data were acquired for 20 days (per participant) and then stored and processed on the CCU. In consultation with medical experts, eight ADL were classified. RESULTS In this study, 10 healthy participants (6 women, 4 men; mean age 48.8 years; SD 20.0 years; age range 28-79 years) were included. For explorative purposes, one female Alzheimer patient (Montreal Cognitive Assessment score=23, Timed Up and Go=19.8 seconds, Trail Making Test A=84.3 seconds, Trail Making Test B=146 seconds) was measured in parallel with the healthy subjects. In total, 1317 ADL were performed by the participants, 1211 ADL were classified correctly, and 106 ADL were missed. This led to an overall sensitivity of 91.27% and a specificity of 92.52%. Each subject performed an average of 134.8 ADL (SD 75). CONCLUSIONS The non-intrusive wireless sensor system can acquire environmental data essential for the classification of activities of daily living. By analyzing retrieved data, it is possible to distinguish and assign data patterns to subjects' specific activities and to identify eight different activities in daily living. The Web-based technology allows the system to improve care and provides valuable information about the patient in real-time.

Recognition of activities of daily living in healthy subjects using two ad-hoc classifiers

Activities of daily living (ADL) are important for quality of life. They are indicators of cognitive health status and their assessment is a measure of independence in everyday living. ADL are difficult to reliably assess using questionnaires due to self-reporting biases. Various sensor-based (wearable, in-home, intrusive) systems have been proposed to successfully recognize and quantify ADL without relying on self-reporting. New classifiers required to classify sensor data are on the rise. We propose two ad-hoc classifiers that are based only on non-intrusive sensor data. METHODS: A wireless sensor system with ten sensor boxes was installed in the home of ten healthy subjects to collect ambient data over a duration of 20 consecutive days. A handheld protocol device and a paper logbook were also provided to the subjects. Eight ADL were selected for recognition. We developed two ad-hoc ADL classifiers, namely the rule based forward chaining inference engine (RBI) classifier and the circadian activity rhythm (CAR) classifier. The RBI classifier finds facts in data and matches them against the rules. The CAR classifier works within a framework to automatically rate routine activities to detect regular repeating patterns of behavior. For comparison, two state-of-the-art [Naïves Bayes (NB), Random Forest (RF)] classifiers have also been used. All classifiers were validated with the collected data sets for classification and recognition of the eight specific ADL. RESULTS: Out of a total of 1,373 ADL, the RBI classifier correctly determined 1,264, while missing 109 and the CAR determined 1,305 while missing 68 ADL. The RBI and CAR classifier recognized activities with an average sensitivity of 91.27 and 94.36%, respectively, outperforming both RF and NB. CONCLUSIONS: The performance of the classifiers varied significantly and shows that the classifier plays an important role in ADL recognition. Both RBI and CAR classifier performed better than existing state-of-the-art (NB, RF) on all ADL. Of the two ad-hoc classifiers, the CAR classifier was more accurate and is likely to be better suited than the RBI for distinguishing and recognizing complex ADL.

Invited Abstract: Issues with State-based Energy Consumption Modelling

Energy consumption modelling by state based approaches often assume constant energy consumption values in each state. However, it happens in certain situations that during state transitions or even during a state the energy consumption is not constant and does fluctuate. This paper discusses those issues by presenting some examples from wireless sensor and wireless local area networks for such cases and possible solutions.