Smart Home Sensor Research Articles

SMART CITY With IOT and BIG Data

The fast growth in the population density in urban areas demands more facilities and resources. To meet the needs of city development, the use of Internet of Things (IoT) devices and the smart systems is the very quick and valuable source. However, thousands of IoT devices are interconnecting and communicating with each other over the Internet results in generating a huge amount of data, termed as Big Data. To integrate IoT services and processing Big Data in an efficient way aimed at smart city is a challenging task. Therefore, in this paper, we proposed a system for smart city development based on IoT using Big Data Analytics. We use sensors deployment including smart home sensors, vehicular networking, weather and water sensors, smart parking sensor, and surveillance objects, etc. initially a four-tier architecture is proposed, which includes 1) Bottom Tier: which is responsible for IoT sources, data generations, and collections 2) Intermediate Tier-1: That is responsible for all type of communication between sensors, relays, base stations, the internet, etc. 3) Intermediate Tier 2: it is responsible for data management and processing using Hadoop framework, and 4) Top tier: is responsible for application and usage of the data analysis and results generated. The collected data from all smart system is processed at real-time to achieve smart cities using Hadoop with Spark, VoltDB, Storm or S4. We use existing datasets by various researchers including smart homes, smart parking weather, pollution, and vehicle for analysis and testing. All the datasets are replayed to test the real-time efficiency of the system. Finally, we evaluated the system by efficiency in term of throughput and processing.

A sequential deep learning application for recognising human activities in smart homes

The recent advancement and development of computer electronic devices has led to the adoption of smart home sensing systems, stimulating the demand for associated products and services. Accordingly, the increasingly large amount of data calls the machine learning (ML) field for automatic recognition of human behaviour. In this work, different deep learning (DL) models that learn to classify human activities were proposed. In particular, the long short-term memory (LSTM) was applied for modelling spatio-temporal sequences acquired by smart home sensors. Experimental results performed on the Center for Advanced Studies in Adaptive Systems datasets show that the proposed LSTM-based approaches outperform existing DL and ML methods, giving superior results compared to the existing literature.

Monitoring meaningful activities using small low-cost devices in a smart home

A challenge associated with an ageing population is increased demand on health and social care, creating a greater need to enable persons to live independently in their own homes. Ambient assistant living technology aims to address this by monitoring occupants’ ‘activities of daily living’ using smart home sensors to alert caregivers to abnormalities in routine tasks and deteriorations in a person’s ability to care for themselves. However, there has been less focus on using sensing technology to monitor a broader scope of so-called ‘meaningful activities’, which promote a person’s emotional, creative, intellectual, and spiritual needs. In this paper, we describe the development of a toolkit comprised of off-the-shelf, affordable sensors to allow persons with dementia and Parkinson’s disease to monitor meaningful activities as well as activities of daily living in order to self-manage their life and well-being. We describe two evaluations of the toolkit, firstly a lab-based study to test the installation of the system including the acuity and placement of sensors and secondly, an in-the-wild study where subjects who were not target users of the toolkit, but who identified as technology enthusiasts evaluated the feasibility of the toolkit to monitor activities in and around real homes. Subjects from the in-the-wild study reported minimal obstructions to installation and were able to carry out and enjoy activities without obstruction from the sensors, revealing that meaningful activities may be monitored remotely using affordable, passive sensors. We propose that our toolkit may enhance assistive living systems by monitoring a wider range of activities than activities of daily living.

Older women’s perceptions of wearable and smart home activity sensors

ABSTRACTIntroduction: The aim of this study was to characterize perceptions of wearable and smart home technologies of older women using semi-structured interviews.Methods and Procedures: Participants (n = 10) were shown two wearable sensors and a smart home sensor. All participants were 60 years of age or older with the exception of one participant (ages: 57–70,average age: 64.6 years). Sensor function and placement were explained. Participants were asked questions about technology, perceptions of sensors, and thoughts about the use of these types of sensors. Interview transcripts were analyzed to identify themes related to technology acceptance, perceived usefulness, and privacy issues.Main Outcome and Results: Participants perceived wearable and smart home sensors as acceptable for personal activity data collection. In general, wearable sensors were perceived as more useful than smart home sensors because most participants had high levels of activities outside their homes. Participants had few concerns about data sharing. Privacy issues related to perceived risk for break-ins or unwanted disclosure of activity levels.Conclusion: Given the higher proportion of women over men in the older adult population, and some of the aging-related health risks that women face, it is important to understand older women’s perceptions of different types of sensor technologies.

Using smart-home sensors with older adults with long-term complex multi-morbidity

Using smart-home sensors with older adults with long-term complex multi-morbidity

Using smart-home sensors with older adults with long-term complex multi-morbidity

Using smart-home sensors with older adults with long-term complex multi-morbidity

Early Detection of Mild Cognitive Impairment With In-Home Monitoring Sensor Technologies Using Functional Measures: A Systematic Review.

The aging of the world population is accompanied by a substantial increase in neurodegenerative disorders, such as dementia. Early detection of mild cognitive impairment (MCI), a clinical diagnostic that comes with an increased chance to develop dementias, could be an essential condition for promoting quality of life and independent living, as it would provide a critical window for the implementation of early pharmacological and nonpharmacological interventions. This systematic review aims to investigate the current state of knowledge on the effectiveness of smart home sensors technologies for the early detection of MCI through the monitoring of everyday life activities. This approach offers many advantages, including the continuous measurement of functional abilities in ecological environments. A systematic search of publications in MEDLINE, EMBASE, and CINAHL, before November 2017, was conducted. Seventeen studies were included in this review. Thirteen studies were based on real-life monitoring, with several sensors installed in participants' actual homes, and four studies included scenario-based assessments, in which participants had to complete various tasks in a research lab apartment. In real-life monitoring, the most used indicators of MCI were walking speed and activity/motion in the house. In scenario-based assessment, time of completion, quality of activity completion, number of errors, amount of assistance needed, and task-irrelevant behaviors during the performance of everyday activities predicted MCI in participants. Despite technological limitations and the novelty of the field, smart home technologies represent a promising potential for the early screening of MCI and could support clinicians in geriatric care.

Precise Localization of Multiple Noncooperative Objects in a Disordered Cavity by Wave Front Shaping.

Complicated multipath trajectories of waves in disordered cavities cause object localization to be very challenging with traditional ray-tracing approaches. Yet it is known that information about the object position is encoded in the Green's function. After a calibration step, traditional time-reversal approaches retrieve a source's location from a broadband impulse response measurement. Here, we show that a nonemitting object's scattering contribution to a reverberant medium suffices to localize the object. We demonstrate our finding in the microwave domain. Then, we further simplify the scheme by replacing the temporal degrees of freedom (d.o.f.) of the broadband measurement with spatial d.o.f. obtained from wave front shaping. A simple electronically reconfigurable reflectarray inside the cavity dynamically modulates parts of the cavity boundaries, thereby providing spatial d.o.f. The demonstrated ability to localize multiple noncooperative objects with a single-frequency scheme may have important applications for sensors in smart homes.

A Design and Implementation of Gateway for Smart Home Sensor Network Management

A Design and Implementation of Gateway for Smart Home Sensor Network Management

Memory, executive functions, and naturalistic assessment of activities of daily living in mild cognitive impairment using smart home sensors

Memory, executive functions, and naturalistic assessment of activities of daily living in mild cognitive impairment using smart home sensors

Ontology-based feature generation to improve accuracy of activity recognition in smart environments

In recent years, many techniques have been proposed for automatic recognition of Activities of Daily Living from smart home sensor data. However, classifiers usually use features created ad hoc. In this work, the use of ontologies is proposed for the fully automatic generation of these features. The process consists of converting the original dataset into an ontology and then combine all the concepts and relations in that ontology to obtain relevant class expressions. The high formalization of ontologies allows us to reduce the search space by discarding many meaningless expressions, such as contradictory or unsatisfiable expressions. The relevant class expressions are then used as features by the classifiers to build the classification model. To validate our proposal, we have used as reference the results obtained by four different classification algorithms that use the most commonly used features.

Predicting unusual energy consumption events from smart home sensor network by data stream mining with misclassified recall

With the popularity and affordability of ZigBee wireless sensor technology, IoT-based smart controlling system for home appliances becomes prevalent for smart home applications. From the data analytics point of view, one important objective from analyzing such IoT data is to gain insights from the energy consumption patterns, thereby trying to fine-tune the energy efficiency of the appliance usage. The data analytics usually functions at the back-end crunching over a large archive of big data accumulated over time for learning the overall pattern from the sensor data feeds. The other objective of the analytics, which may often be more crucial, is to predict and identify whether an abnormal consumption event is about to happen. For example, a sudden draw of energy that leads to hot spot in the power grid in a city, or black-out at home. This dynamic prediction is usually done at the operational level, with moving data stream, by data stream mining methods . In this paper, an improved version of very fast decision tree (VFDT) is proposed, which learns from misclassified results for the sake of filtering the noisy data from learning and maintaining sharp classification accuracy of the induced prediction model. Specifically, a new technique called misclassified recall (MR), which is a pre-processing step for self-rectifying misclassified instances, is formulated. In energy data prediction, most misclassified instances are due to data transmission errors or faulty devices. The former case happens intermittently, and the errors from the latter cause may persist for a long time. By caching up the data at the MR pre-processor, the one-pass online model learning can be effectively shielded in case of intermitting problems at the wireless sensor network; likewise the stored data could be investigated afterwards should the problem persist for long. Simulation experiments over a dataset about predicting exceptional appliances energy use in a low energy building are conducted. The reported results validate the efficacy of the new methodology VFDT + MR, in comparison to a collection of popular data stream mining algorithms from the literature.

Passive Radar for Opportunistic Monitoring in E-Health Applications.

This paper proposes a passive Doppler radar as a non-contact sensing method to capture human body movements, recognize respiration, and physical activities in e-Health applications. The system uses existing in-home wireless signal as the source to interpret human activity. This paper shows that passive radar is a novel solution for multiple healthcare applications which complements traditional smart home sensor systems. An innovative two-stage signal processing framework is outlined to enable the multi-purpose monitoring function. The first stage is to obtain premier Doppler information by using the high speed passive radar signal processing. The second stage is the functional signal processing including micro Doppler extraction for breathing detection and support vector machine classifier for physical activity recognition. The experimental results show that the proposed system provides adequate performance for both purposes, and prove that non-contact passive Doppler radar is a complementary technology to meet the challenges of future healthcare applications.

Situation Awareness Inferred From Posture Transition and Location: Derived From Smartphone and Smart home Sensors

Situation awareness may be inferred from user context such as body posture transition and location data. Smartphones and smart homes incorporate sensors that can record this information without significant inconvenience to the user. Algorithms were developed to classify activity postures to infer current situations; and to measure user's physical location, in order to provide context that assists such interpretation. Location was detected using a subarea-mapping algorithm; activity classification was performed using a hierarchical algorithm with backward reasoning; and falls were detected using fused multiple contexts (current posture, posture transition, location, and heart rate) based on two models: “certain fall” and “possible fall.” The approaches were evaluated on nine volunteers using a smartphone, which provided accelerometer and orientation data, and a radio frequency identification network deployed at an indoor environment. Experimental results illustrated falls detection sensitivity of 94.7% and specificity of 85.7%. By providing appropriate context the robustness of situation recognition algorithms can be enhanced.

Latent feature learning for activity recognition using simple sensors in smart homes

Activity recognition is an important step towards monitoring and evaluating the functional health of an individual, and it potentially promotes human-centric ubiquitous applications in smart homes particularly for senior healthcare. The nature of human activity characterized by a high degree of complexity and uncertainty, however, poses a great challenge to the design of good feature representations and the optimization of classifiers towards building a robust model for human activity recognition. In this study, we propose to exploit deep learning techniques to automatically learn high-level features from the binary sensor data under the assumption that there exist discriminative latent patterns inherent in the simple low-level features. Specifically, we extract high-level features with a stacked autoencoder that has a deep and hierarchy architecture, and combine feature learning and classifier construction into a unified framework to obtain a jointly optimized activity recognizer. Besides, we investigate two different original feature representations of the sensor data for latent feature learning. To evaluate the performance of the proposed method, we conduct extensive experiments on three publicly available smart home datasets, and compare it with a range of shallow models in terms of time-slice accuracy and class accuracy. Experimental results show that our proposed model achieves better recognition rates and generalizes better across different original feature representations, indicating its applicability to the real-world activity recognition.

Activity Recognition in Smart Homes

In recent years, activity recognition in smart homes is an active research area. It is an important problem of Human Computer Interaction (HCI), and has many applications in HCI, such as assistive living and healthcare. Recognition of users’ common behaviors allows an environment to provide personalized service. Unlike activity recognition in computer vision which uses cameras, it studies activities by embedded sensors in smart homes. In this paper, we propose a method to extract latent features from sensor data by Beta Process Hidden Markov Model (BP-HMM). The contributions of our method are twofold: 1, we extend BP-HMM by dependent Beta process, and integrate state constraints of sensors into the sampling process of BP-HMM. 2, we extract latent features automatically by our dependent BP-HMM, and train a structural support vector machine (SVM) by these features in a supervised way for activity recognition. To evaluate the proposed method, we performed experiments on the real-world smart home datasets. Our results suggest that extracting latent features from sensor data leads to good performance for activity recognition.

An Integrated Framework for Binary Sensor Placement and Inhabitants Location Tracking

This correspondence paper deals with the sensor placement optimization problem in the context of indoor multiple inhabitants location tracking to solve ambient assisted living problems. Binary sensors, like passive infrared (PIR) sensors, are used to guaranty specific coverage requirements and allow privacy respecting. Moreover, within real home environments, different kinds of obstacles (like walls, high furniture, etc.) can affect the detection capacity of PIR sensors. This paper proposes an integrated framework devoted to optimize the placement of sensors and PIR sensors in smart homes by taking into account physical topologies and coverage precision constraints. An integer linear programming problem is formalized and a case study illustrates the applicability of the proposed approach and the scalability of the optimization method.

Engaging older adults in the visualization of sensor data facilitated by an open platform for connected devices.

The use of smart home sensor systems is growing primarily due to the appeal of unobtrusively monitoring older adult health and wellness. However, integrating large-scale sensor systems within residential settings can be challenging when deployment takes place across multiple environments, requiring customization of applications, connection across various devices and effective visualization of complex longitudinal data. The objective of the study was to demonstrate the implementation of a smart home system using an open, extensible platform in a real-world setting and develop an application to visualize data real time. We deployed the open source Lab of Things platform in a house of 11 residents as a demonstration of feasibility over the course of 3 months. The system consisted of Aeon Labs Z-wave Door/Window sensors and an Aeon Labs Multi-sensor that collected data on motion, temperature, luminosity, and humidity. We applied a Rapid Iterative Testing and Evaluation approach towards designing a visualization interface engaging gerontological experts. We then conducted a survey with 19 older adult and caregiver stakeholders to inform further design revisions. Our initial visualization mockups consisted of a bar chart representing activity level over time. Family members felt comfortable using the application. Older adults however, indicated it would be difficult to learn to use the application, and had trouble identifying utility. A key for older adults was ensuring that the data collected could be utilized by their family members, physicians, or caregivers. The approach described in this work is generalizable towards future smart home deployments and can be a valuable guide for researchers to scale a study across multiple homes and connected devices, and to create personalized interfaces for end users.

A Reliable TTP-Based Infrastructure with Low Sensor Resource Consumption for the Smart Home Multi-Platform.

With the ICT technology making great progress in the smart home environment, the ubiquitous environment is rapidly emerging all over the world, but problems are also increasing proportionally to the rapid growth of the smart home market such as multiplatform heterogeneity and new security threats. In addition, the smart home sensors have so low computing resources that they cannot process complicated computation tasks, which is required to create a proper security environment. A service provider also faces overhead in processing data from a rapidly increasing number of sensors. This paper aimed to propose a scheme to build infrastructure in which communication entities can securely authenticate and design security channel with physically unclonable PUFs and the TTP that smart home communication entities can rely on. In addition, we analyze and evaluate the proposed scheme for security and performance and prove that it can build secure channels with low resources. Finally, we expect that the proposed scheme can be helpful for secure communication with low resources in future smart home multiplatforms.

One-Class Classification-Based Real-Time Activity Error Detection in Smart Homes.

Caring for individuals with dementia is frequently associated with extreme physical and emotional stress, which often leads to depression. Smart home technology and advances in machine learning techniques can provide innovative solutions to reduce caregiver burden. One key service that caregivers provide is prompting individuals with memory limitations to initiate and complete daily activities. We hypothesize that sensor technologies combined with machine learning techniques can automate the process of providing reminder-based interventions. The first step towards automated interventions is to detect when an individual faces difficulty with activities. We propose machine learning approaches based on one-class classification that learn normal activity patterns. When we apply these classifiers to activity patterns that were not seen before, the classifiers are able to detect activity errors, which represent potential prompt situations. We validate our approaches on smart home sensor data obtained from older adult participants, some of whom faced difficulties performing routine activities and thus committed errors.