Ubiquitous Sensor Research Articles

Smart persuasive school buildings: a state of the art

Integrating technology in buildings can lead to smart buildings that can affect behavioural patterns. The increasing possibilities of ubiquitous computing and sensor technology can be employed to motivate behaviour change, particularly when embedded in the environment. One (smart) environment that can be particularly influential on daily and long-term behaviour is a school. An environment that aims at changing behaviour without 'forcing' its inhabitants using smart technology, is what we call a 'smart persuasive environment'. The potential these smart persuasive school buildings hold for influencing pupil behaviours, such as learning outcomes, social interaction and physical activity seems to be substantial. This article aims to give an overview of the state of the technology, the (effect on) behaviour of pupils and the theoretical mechanisms, using social cognitive theory, that could explain the relationship between smart persuasive school buildings and behaviour change.

Hierarchical multi-view aggregation network for sensor-based human activity recognition.

Sensor-based human activity recognition aims at detecting various physical activities performed by people with ubiquitous sensors. Different from existing deep learning-based method which mainly extracting black-box features from the raw sensor data, we propose a hierarchical multi-view aggregation network based on multi-view feature spaces. Specifically, we first construct various views of feature spaces for each individual sensor in terms of white-box features and black-box features. Then our model learns a unified representation for multi-view features by aggregating views in a hierarchical context from the aspect of feature level, position level and modality level. We design three aggregation modules corresponding to each level aggregation respectively. Based on the idea of non-local operation and attention, our fusion method is able to capture the correlation between features and leverage the relationship across different sensor position and modality. We comprehensively evaluate our method on 12 human activity benchmark datasets and the resulting accuracy outperforms the state-of-the-art approaches.

Exploring the API Calls for Malware Behavior Detection using Concordance and Document Frequency

In the era of ubiquitous sensors and smart devices, detecting malware is becoming an endless battle between ever-evolving malware and antivirus programs that need to process ever-increasing security related data. Malwares are becoming persistent by creating full-fledged variants of the same or different family. Malwares belonging to same family share same characteristics in their functionality of spreading infections into the victim computer. We find that certain malicious functions are commonly included in malware even in different categories. From checking the existence of certain functions or API call sequence patterns matched, we can even detect new unknown malware. For malware detection, various approaches have been proposed. An Application Programming Interface (API) is widely is used for the software to interact with an operating system to do certain task such as opening file, deleting file etc., Users of the computers use this API to make it comfortable for their program to communicate with the operating system without having the prior knowledge of the hardware of the object system. The attacker also use the same type of APIs to create malware, hence it is very much difficult to know about these APIs. There are many researches done in this field, however, most researchers used n-gram to detect the sequence of API calls. Even though, it gave good results, it is time consuming to process through all the output. Hence, we proposed to use Concordance to search for the API call sequence of a malware because it use KWIC (Key Word in Context), thus only displayed the output based on the queried keyword. After that, Document Frequency (DF) is used to search for the most commonly used APIs in the dataset. The result of our experiment gave high accuracy than other methods and also found more categories than other methods. API call sequence can be extracted from most of the modern devices. Hence we supposed that our method can detect the malware for all types of the ubiquitous devices. The results of the experiment show that Concordance can be used to search for API call sequence as we manage to identify Eight malicious Activities (Screen Capture, Hooking, Downloader, Enumerate all process, Anti debugging, Synchronization, Key Logger and Dropper) using this method.

L1-Subspace Tracking for Streaming Data

High-dimensional data usually exhibit intrinsic low-rank structures. With tremendous amount of streaming data generated by ubiquitous sensors in the world of Internet-of-Things, fast detection of such low-rank pattern is of utmost importance to a wide range of applications. In this work, we present an L1-subspace tracking method to capture the low-rank structure of streaming data. The method is based on the L1-norm principal-component analysis (L1-PCA) theory that offers outlier resistance in subspace calculation. The proposed method updates the L1-subspace as new data are acquired by sensors. In each time slot, the conformity of each datum is measured by the L1-subspace calculated in the previous time slot and used to weigh the datum. Iterative weighted L1-PCA is then executed through a refining function. The superiority of the proposed L1-subspace tracking method compared to existing approaches is demonstrated through experimental studies in various application fields.

Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos

Learning to predict scene depth from RGB inputs is a challenging task both for indoor and outdoor robot navigation. In this work we address unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular videos, as cameras are the cheapest, least restrictive and most ubiquitous sensor for robotics.
 Previous work in unsupervised image-to-depth learning has established strong baselines in the domain. We propose a novel approach which produces higher quality results, is able to model moving objects and is shown to transfer across data domains, e.g. from outdoors to indoor scenes. The main idea is to introduce geometric structure in the learning process, by modeling the scene and the individual objects; camera ego-motion and object motions are learned from monocular videos as input. Furthermore an online refinement method is introduced to adapt learning on the fly to unknown domains.
 The proposed approach outperforms all state-of-the-art approaches, including those that handle motion e.g. through learned flow. Our results are comparable in quality to the ones which used stereo as supervision and significantly improve depth prediction on scenes and datasets which contain a lot of object motion. The approach is of practical relevance, as it allows transfer across environments, by transferring models trained on data collected for robot navigation in urban scenes to indoor navigation settings. The code associated with this paper can be found at https://sites.google.com/view/struct2depth.

MEMS-Based Vibrational Energy Harvesting and Conversion Employing Micro-/Nano-Magnetics

This paper discusses the current state-of-the-art, ongoing fundamental and technical challenges and potential roadmaps for micro-scale vibration energy harvesting and power conversion devices employing micro-/nano-magnetics. Such devices are of paramount importance as powering solution for autonomous and ubiquitous sensor nodes within the emerging “Internet of Things (IoT).” In this paper, we have reviewed the fundamental limitations, technological needs, and breakthroughs in the mentioned areas, including materials, process integration, and device design issues. Particularly, current limitations in both the relevant soft and hard (or permanent) micro-magnets, roadmaps for a complete “Magnetic MEMS” solution for energy harvesting and efficient low-power conversion for “IoT” applications, are discussed.

Phase-domain Deep Patient-ECG Image Learning for Zero-effort Smart Health Security.

Smart health is quickly boosted by technological advancements: smart sensors, body sensor network, internet of medical things and big data. Vast amounts of smart health big data from ubiquitous sensors pose unprecedented challenges to the security and privacy protection, which is extremely critical in healthcare applications. The vital signs, user daily behaviors, medicine recommendations, and so many other health data are vulnerable to different attacks, due to the fact that wearable/mobile monitors have very strict performance/power constraints, which limit the complexity of security protocols. In this paper, we study how to leverage a natural vital signal (Electrocardiogram - ECG) for user identification purpose, without introducing new hardware sensing devices. ECG is not only a gold standard cardiac signal, but also unique to each individual. We investigate a phase-domain deep patient-ECG image learning framework, to tackle key challenges in ECG biometric user identification: high diversities of ECG morphologies due to heart diseases, and time-consuming/ineffective heartbeat localization methods & manual feature engineering. The ultimate goal is to make the smart health security zero-effort: use `phase-domain transformation' to enable blind signal segmentation without localizing heartbeats; create a computer image processing-like task by `pixelating' phase-domain ECG trajectories to ECG images; and enable automatic (non-manual) `deep feature learning' using a deep convolutional neural network. Evaluated on two patient-ECG databases, this zero-effort framework achieves an accuracy as high as 97.2%, and greatly outperforms state-of-the-art studies in terms of the generalization ability and/or performance. This study is expected to enable highly challenging patient-ECG biometric user identification, by generalizable blind signal segmentation and deep feature learning strategies, in the era of smart health boosted by internet of medical things and big medical data.

How Urban Storm- and Wastewater Management Prepares for Emerging Opportunities and Threats: Digital Transformation, Ubiquitous Sensing, New Data Sources, and Beyond - A Horizon Scan.

Ubiquitous sensing will create many opportunities and threats for urban water management, which are only poorly understood today. To identify the most relevant trends, we conducted a horizon scan regarding how ubiquitous sensing will shape the future of urban drainage and wastewater management. Our survey of the international urban water community received an active response from both the academics and the professionals from the water industry. The analysis of the responses demonstrates that emerging topics for urban water will often involve experts from different communities, including aquatic ecologists, urban water system engineers and managers, as well as information and communications technology professionals and computer scientists. Activities in topics that are identified as novel will either require (i) cross-disciplinary training, such as importing new developments from the IT sector, or (ii) research in new areas for urban water specialists, for example, to help solve open questions in aquatic ecology. These results are, therefore, a call for interdisciplinary research beyond our own discipline. They also demonstrate that the water management community is not yet prepared for the digital transformation, where we will experience a data demand, i.e. a "pull" of urban water data into external services. The results suggest that a lot remains to be done to harvest the upcoming opportunities. Horizon scanning should be repeated on a routine basis, under the umbrella of an experienced polling organization.

A self-powered multi-broadcasting wireless sensing system realized with an all-in-one triboelectric nanogenerator

The ubiquitous sensors at the core network of Internet of Things (IoT) have accelerated the realization of micro/nano systems that necessitate not only the development of self-powered sensors but also requires a reliable wireless communication mode. Here, a self-powered multi-broadcasting wireless sensing system based on an all-in-one triboelectric nanogenerator (TENG) is reported, which can simultaneously power up a custom-made wireless node and act as a sensor. The whole device and the system are encapsulated in a unique compact structure, in which the top segment consists of a spring-assisted multifunctional TENG (MTENG) and, the bottom section contains an integrated energy management and Bluetooth transmitter module. Following the structural and material modifications, the top unit of the MTENG is used to detect vibration frequency and amplitude by correlation with the TENG output voltage. The device has been employed to successfully detect the running frequency of a linear shaker and various generated signals. Owing to the nanostructured material surfaces, the device yields an output current of 300 μA and a power density of 4 W/m2 with the normal hand pressing. Moreover, the developed portable MTENG is also assessed to remotely monitor automobile engine vibration and is expected to result in a myriad of applications.

A survey on big data-driven digital phenotyping of mental health

The landscape of mental health has undergone tremendous changes within the last two decades, but the research on mental health is still at the initial stage with substantial knowledge gaps and the lack of precise diagnosis. Nowadays, big data and artificial intelligence offer new opportunities for the screening and prediction of mental problems. In this review paper, we outline the vision of digital phenotyping of mental health (DPMH) by fusing the enriched data from ubiquitous sensors, social media and healthcare systems, and present a broad overview of DPMH from sensing and computing perspectives. We first conduct a systematical literature review and propose the research framework, which highlights the key aspects related with mental health, and discuss the challenges elicited by the enriched data for digital phenotyping. Next, five key research strands including affect recognition, cognitive analytics, behavioral anomaly detection, social analytics, and biomarker analytics are unfolded in the psychiatric context. Finally, we discuss various open issues and the corresponding solutions to underpin the digital phenotyping of mental health.

Next Generation Emergency Services Based on the Pan-European Mobile Emergency Application (PEMEA) Protocol: Leveraging Mobile Positioning and Context Information

In this paper, we analyze requirements of next generation 112 emergency services in the era of ubiquitous mobile devices and sensors and present the design, implementation, and piloting results of our testbed, which was developed within the H2020 project NEXES. The system leverages a multihop location-aware PEMEA routing network that finds the geographically closest responsible public service answering point (PSAP) and supports cross-border application roaming. Our reference mobile implementation utilizes multiple device and network-based positioning technologies, which, combined, both outperform traditional cell-tower based positioning and provide a means for detecting fraudulent calls. The system is extensible and can establish a variety of communication channels after the initial emergency session is set up; we demonstrate this with an interoperable WebRTC-based video call. The obtained results demonstrate the viability and flexibility of PEMEA-based over-the-top emergency services, show high user acceptance when comparing them with existing solutions, and thus pave the road for further rollout of such systems.

Smart-building management system: An Internet-of-Things (IoT) application business model in Vietnam

The accelerating significance and prevalence of IoT (Internet-of-Things) have been recently appreciated by academicians and policy makers. The emergence of ubiquitous sensors, smart devices and broad-band Internet capacity has enabled the integration of networks for synchronous data collecting and processing, which ultimately facilitates prompt decision-making and physical responses to changes in a real-time manner. The virtual interconnectedness of humans and objects exerts managerial efficiency and emotional comfort for network operators, end users and other third party actors, which results in the embrace of IoT-based platforms in production and consumption. The skyrocketing urbanization has chronically caused dense concentration of population in buildings, which yields market prospects for smart-building management system solutions based on IoT applications. Nevertheless, IoT application business models have remained nascent in emerging and transitional economies. In this paper, the authors exploit the Business Model Canvas to assess an IoT start-up in Vietnam and to establish an output Business Model Canvas for entrepreneurs. Findings indicate high competitive advantages of local enterprises and propose vertical integration in joint ventures as the entry strategy for foreign investors.

Smart Industrial Internet of Things Devices, Services, and Applications: Ubiquitous Sensing and Sensory Data, Predictive Analytics Algorithms, and Cognitive Computing Technologies

Smart Industrial Internet of Things Devices, Services, and Applications: Ubiquitous Sensing and Sensory Data, Predictive Analytics Algorithms, and Cognitive Computing Technologies

Detecting Door Events Using a Smartphone via Active Sound Sensing

Event detection of indoor objects, including doors, has a wide variety of applications, including intruder detection, HVAC control, and surveillance of independently living elderly people. Hence, this has been the focus of multiple research projects in the UbiComp research community. Herein, we propose a method to accurately detect door events in an indoor environment, without the installation and maintenance costs of using distributed ubiquitous sensors. In particular, we recognize the events of multiple doors existing in the environment via active sound probing using a disused smartphone installed in the environment. We perform event recognition by fusing the analysis of the Doppler shift caused by the moving doors with the acoustic characteristics describing the open/close states of the doors acquired via impulse response. To accurately distinguish between the events of different doors via sound probing, our method employs the time-series analysis of the Doppler shift as well as the active sound probing using directional high-frequency sine waves and stereo sound recording. In addition, by incorporating prior knowledge about the state transitions of a door object into a recognition model, we attempt to improve the accuracy of event recognition. Moreover, our method is capable of recognizing walking activities of a person related to door events in the environment, which are necessary information for applications such as HVAC control that require information about both door events and human presence.

Subthreshold-Operated Low-Voltage Organic Field-Effect Transistor for Ion-Sensing System of High Transduction Sensitivity

A combination of the ion-sensitive organic field-effect transistor (ISOFET) transducer with silicon chips can utilize the strengths of both technologies for developing ubiquitous sensor systems. For optimal design of such a system, the transduction sensitivity of the ISOFET needs to be maximized. In this article, OFETs of different subthreshold swing (SS) values are fabricated using a solution processed organic semiconductor and dielectric materials to experimentally prove the dependence of the transduction sensitivity on the SS. Further ion-sensing measurement results show that the OFET of small SS (80mVdec) realized by both large gate dielectric capacitance and significantly reduced subgate density of states at the channel can help to achieve similar sensitivity with that of the silicon FET but with two-order lower power consumption.

Sensor Fusion for Recognition of Activities of Daily Living

Activity of daily living (ADL) is a significant predictor of the independence and functional capabilities of an individual. Measurements of ADLs help to indicate one’s health status and capabilities of quality living. Recently, the most common ways to capture ADL data are far from automation, including a costly 24/7 observation by a designated caregiver, self-reporting by the user laboriously, or filling out a written ADL survey. Fortunately, ubiquitous sensors exist in our surroundings and on electronic devices in the Internet of Things (IoT) era. We proposed the ADL Recognition System that utilizes the sensor data from a single point of contact, such as smartphones, and conducts time-series sensor fusion processing. Raw data is collected from the ADL Recorder App constantly running on a user’s smartphone with multiple embedded sensors, including the microphone, Wi-Fi scan module, heading orientation of the device, light proximity, step detector, accelerometer, gyroscope, magnetometer, etc. Key technologies in this research cover audio processing, Wi-Fi indoor positioning, proximity sensing localization, and time-series sensor data fusion. By merging the information of multiple sensors, with a time-series error correction technique, the ADL Recognition System is able to accurately profile a person’s ADLs and discover his life patterns. This paper is particularly concerned with the care for the older adults who live independently.

Fully Printed and Flexible Carbon Nanotube Transistors for Pressure Sensing in Automobile Tires

As the need for an increased supply and diversity of sensors expands, printed electronics have been identified as a promising approach for low-cost, ubiquitous sensor networks. In this paper, we demonstrate the use of a fully printed carbon nanotube thin-film transistor (CNT-TFT) for sensing environmental pressure over a pressure range extending from 0 to 42 PSIg. The transconductance of the CNT-TFT was found to be linearly correlated with environmental pressure at a sensitivity of 48.1 pS/PSI. We also demonstrate the capability of wirelessly transmitting the data measured by the pressure sensor using a simple Bluetooth module. Using the Bluetooth system, we observed the sensor’s response over time as pressure was dynamically changed. Finally, we packaged the sensor along with a material thickness sensor (developed in previous work) into a fully printed smart tire sensor system capable of mapping tire pressure and tread depth differentials.

A local algorithm to approximate the global clustering of streams generated in ubiquitous sensor networks

In ubiquitous streaming data sources, such as sensor networks, clustering nodes by the data they produce gives insights on the phenomenon being monitored. However, centralized algorithms force communication and storage requirements to grow unbounded. This article presents L2GClust, an algorithm to compute local clusterings at each node as an approximation of the global clustering. L2GClust performs local clustering of the sources based on the moving average of each node’s data over time: the moving average is approximated using memory-less statistics; clustering is based on the furthest-point algorithm applied to the centroids computed by the node’s direct neighbors. Evaluation is performed both on synthetic and real sensor data, using a state-of-the-art sensor network simulator and measuring sensitivity to network size, number of clusters, cluster overlapping, and communication incompleteness. A high level of agreement was found between local and global clusterings, with special emphasis on separability agreement, while an overall robustness to incomplete communications emerged. Communication reduction was also theoretically shown, with communication ratios empirically evaluated for large networks. L2GClust is able to keep a good approximation of the global clustering, using less communication than a centralized alternative, supporting the recommendation to use local algorithms for distributed clustering of streaming data sources.

Tag Size Matters: Miniaturized RFID Tags to Connect Smart Objects to the Internet

State-of-the-art passive RF identification (RFID) technologies are used in contactless smart cards and item management. These technologies rely on the radio communication between an RFID reader and batteryless (or passive) RFID transponders (tags) and thus allow a low-cost, unique identification of objects. Current research topics in the field of passive RFID technologies focus on activities that go beyond the ID in RFID [1]. Research in the microwave community is focused on developing miniaturized passive RFID sensor tags. Tags of this kind constitute inexpensive, long-lasting, ubiquitous sensor units with unique identifiers and make it possible for smart objects to connect to the Internet. In particular, such miniaturized sensor tags enable the identification and monitoring of small objects (e.g., documents, jewelry, medicines, and diagnostic devices) that can then become part of the Internet of Things (IoT) [2].

A Future with Ubiquitous Sensing and Intelligent Systems

In this paper, we discuss the relevance of sensing and biosensing for the ongoing revolution in science and technology as a product of the merging of machine learning and Big Data into affordable technologies and accessible everyday products. Possible scenarios for the next decades are described with examples of intelligent systems for various areas, most of which will rely on ubiquitous sensing. The technological and societal challenges for developing the full potential of such intelligent systems are also addressed.