Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

As we are moving towards the Internet of Things (IoT), the number of sensors deployed around the world is growing at a rapid pace. Market research has shown a significant growth of sensor deployments over the past decade and has predicted a significant increment of the growth rate in the future. These sensors continuously generate enormous amounts of data. However, in order to add value to raw sensor data we need to understand it. Collection, modelling, reasoning, and distribution of context in relation to sensor data plays critical role in this challenge. Context-aware computing has proven to be successful in understanding sensor data. In this paper, we survey context awareness from an IoT perspective. We present the necessary background by introducing the IoT paradigm and context-aware fundamentals at the beginning. Then we provide an in-depth analysis of context life cycle. We evaluate a subset of projects (50) which represent the majority of research and commercial solutions proposed in the field of context-aware computing conducted over the last decade (2001-2011) based on our own taxonomy. Finally, based on our evaluation, we highlight the lessons to be learnt from the past and some possible directions for future research. The survey addresses a broad range of techniques, methods, models, functionalities, systems, applications, and middleware solutions related to context awareness and IoT. Our goal is not only to analyse, compare and consolidate past research work but also to appreciate their findings and discuss their applicability towards the IoT.

/pdf/context-aware-computing-for-the-internet-of-things-a-survey-3nibvvc921.pdf

Context Aware Computing for The Internet of Things: A Survey

Matrix Factorization Techniques for Recommender Systems

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform membership inference against a target model, we make adversarial use of machine learning and train our own inference model to recognize differences in the target model's predictions on the inputs that it trained on versus the inputs that it did not train on. We empirically evaluate our inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon. Using realistic datasets and classification tasks, including a hospital discharge dataset whose membership is sensitive from the privacy perspective, we show that these models can be vulnerable to membership inference attacks. We then investigate the factors that influence this leakage and evaluate mitigation strategies.

/pdf/membership-inference-attacks-against-machine-learning-models-2tzchejf91.pdf

Membership Inference Attacks Against Machine Learning Models

A general infrastructure that can facilitate the development of context-aware applications in smart homes is proposed. Unlike previous systems, our system builds on semantic web technologies, and it particularly concerns the contexts from human-artifact interaction. A multi-levels’ design of our ontology (called SS-ONT) makes it possible to realize context sharing and end-user-oriented customization. Using this infrastructure as a basis, we address some of the principles involved in performing context querying and context reasoning. The performance of our system is evaluated through a series of experiments. DOI: 10.4018/978-1-61692-857-5.ch015

An Ontology-Based Context-Aware Infrastructure for Smart Homes

The received signal strength (RSS) fingerprinting based localization is a widely used technique to locate mobile devices in cellular networks. However, traditional RSS finger-printing based techniques require a set of RSS values from multiple base stations (BSs) at each location, and the RSS from remote BSs is weak and easily affected by the noise and other variations of the propagation channel, which limits the localization accuracy. In this paper, we propose to utilize a reconfigurable intelligent surface (RIS) to improve the accuracy for the RSS fingerprinting based multi-user outdoor localization, which requires the RSS from only one BS. By modifying phase shifts of signals reflected by the RIS, we can create different RSS values at the same location using the signal from the nearest BS for localization. To optimize the RIS phase shifts, we formulate the localization error minimization (LEM) problem and propose an LEM algorithm. Simulation results validate the effectiveness of the proposed scheme.

RSS Fingerprinting Based Multi-user Outdoor Localization Using Reconfigurable Intelligent Surfaces

In recent years, we have seen efforts made to simultaneously monitor the respiration of multiple persons based on the channel state information (CSI) retrieved from commodity WiFi devices. However, existing approaches only work when multiple persons exhibit dramatically different respiration rates and the performance degrades significantly when the targeted subjects have similar rates. What's more, they can only obtain the average respiration rate over a period of time and fail to capture the detailed rate change over time. These two constraints greatly limit the application of the proposed approaches in real life. Different from the existing approaches that apply spectral analysis to the CSI amplitude (or phase difference) to obtain respiration rate information, we leverage the multiple antennas provided by the commodity WiFi hardware and model the multi-person respiration sensing as a blind source separation (BSS) problem. Then, we solve it using independent component analysis (ICA) to obtain the reparation information of each person. In this demo, we will demonstrate MultiSense - a multi-person respiration monitoring system using COTS WiFi devices.

A multi-person respiration monitoring system using COTS wifi devices

In recent years, wearable sensor-based gesture recognition is proliferating in the field of healthcare. It could be used to enable remote control of medical devices, contactless navigation of X-ray display and Magnetic Resonance Imaging (MRI), and largely enhance patients' daily living capabilities. However, even though a few commercial or prototype devices are available for wearable gesture recognition, none of them provides a combination of (1) fully open API for various healthcare application development, (2) appropriate form factor for comfortable daily wear, and (3) affordable cost for large scale adoption. In addition, the existing gesture recognition algorithms are mainly designed for discrete gestures. Accurate recognition of continuous gestures is still a significant challenge, which prevents the wide usage of existing wearable gesture recognition technology. In this paper, we present Gemote, a smart wristband-based hardware/software platform for gesture recognition and remote control. Due to its affordability, small size, and comfortable profile, Gemote is an attractive option for mass consumption. Gemote provides full open API access for third party research and application development. In addition, it employs a novel continuous gesture segmentation and recognition algorithm, which accurately and automatically separates hand movements into segments, and merges adjacent segments if needed, so that each gesture only exists in one segment. Experiments with human subjects show that the recognition accuracy is 99.4% when users perform gestures discretely, and 94.6% when users perform gestures continuously.

Gesture-enabled remote control for healthcare

With more and more elders in most countries, the health and safety issues become the primary concern for elderly people because ageing is often associated with physical and cognitive impairments. In order to provide intelligent assistive services for elders, in this paper, we propose an integrated service platform that can accommodate safety assurance, daily activity assistance, and health support services. Specifically, the platform takes care of anomalous events detection, daily activities tracking, and health status monitoring leveraging stationary sensors deployed in living environments and mobile sensing artifacts carried by elders. The services in this integrated platform can ensure safety and independency of elders, they can also help them sustain and/or improve health condition with personalized health support. Based on the proposed platform, we present a case study of assistive safety assurance service wandering detection, which monitors an elder's outdoor movements by using GPS sensor embedded in smart phone and recognizes the lapping or pacing movement pattern to find potential wandering behavior. The experimental results show that our method works well in detecting wandering behavior in terms of detection rate and false alarm rate.

Daqing Zhang

Papers

An Ontology-Based Context-Aware Infrastructure for Smart Homes

RSS Fingerprinting Based Multi-user Outdoor Localization Using Reconfigurable Intelligent Surfaces

A multi-person respiration monitoring system using COTS wifi devices

Gesture-enabled remote control for healthcare

An Integrated Service Platform for Pervasive Elderly Care