Abstract: With the widespread adoption of the Internet-connected
devices, and with the prevalence of the Internet of Things (IoT)
applications, there is an increased interest in machine learning
techniques that can provide useful and interesting services in the
smart home domain. The areas that machine learning techniques
can help advance are varied and ever-evolving. Classifying smart
home inhabitants’ Activities of Daily Living (ADLs), is one
prominent example. The ability of machine learning technique to find
meaningful spatio-temporal relations of high-dimensional data is an
important requirement as well. This paper presents a comparative
evaluation of state-of-the-art machine learning techniques to classify
ADLs in the smart home domain. Forty-two synthetic datasets and
two real-world datasets with multiple inhabitants are used to evaluate
and compare the performance of the identified machine learning
techniques. Our results show significant performance differences
between the evaluated techniques. Such as AdaBoost, Cortical
Learning Algorithm (CLA), Decision Trees, Hidden Markov Model
(HMM), Multi-layer Perceptron (MLP), Structured Perceptron and
Support Vector Machines (SVM). Overall, neural network based
techniques have shown superiority over the other tested techniques.
Abstract: The Internet of things (IoT) is currently a highly
researched topic, especially within the context of the smart home.
These are small sensors that are capable of gathering data and
transmitting it to a server. The majority of smart home products use
protocols such as ZigBee or Bluetooth Low Energy (BLE). As these
small sensors are increasing in number, the need to implement these
with much more capable and ubiquitous transmission technology is
necessary. The high power consumption is the reason that holds
these small sensors back from using other protocols such as the
most ubiquitous form of communication, WiFi. Comparing the power
consumption of existing transmission technologies to one with WiFi
inbuilt, would provide a better understanding for choosing between
these technologies. We have developed a small IoT device with WiFi
capability and proven that it is much more efficient than the first
protocol, 433 MHz. We extend our work in this paper and compare
WiFi power consumption with the other most widely used protocol
BLE. The experimental results in this paper would conclude whether
the developed prototype is capable in terms of power consumption to
replace the existing protocol BLE with WiFi.
Abstract: Smart metering and demand response are gaining
ground in industrial and residential applications. Smart Appliances
have been given concern towards achieving Smart home. The success
of Smart grid development relies on the successful implementation of
Information and Communication Technology (ICT) in power sector.
Smart Appliances have been the technology under development and
many new contributions to its realization have been reported in the
last few years. The role of ICT here is to capture data in real time,
thereby allowing bi-directional flow of information/data between
producing and utilization point; that lead a way for the attainment of
Smart appliances where home appliances can communicate between
themselves and provide a self-control (switch on and off) using the
signal (information) obtained from the grid. This paper depicts the
background on ICT for smart appliances paying a particular attention
to the current technology and identifying the future ICT trends for
load monitoring through which smart appliances can be achieved to
facilitate an efficient smart home system which promote demand
response program. This paper grouped and reviewed the recent
contributions, in order to establish the current state of the art and
trends of the technology, so that the reader can be provided with a
comprehensive and insightful review of where ICT for smart
appliances stands and is heading to. The paper also presents a brief
overview of communication types, and then narrowed the discussion
to the load monitoring (Non-intrusive Appliances Load Monitoring
‘NALM’). Finally, some future trends and challenges in the further
development of the ICT framework are discussed to motivate future
contributions that address open problems and explore new
possibilities.
Abstract: Apps are today the most important possibility to adapt
mobile phones and computers to fulfill the special needs of their
users. Location- and context-sensitive programs are hereby the key to
support the interaction of the user with his/her environment and also
to avoid an overload with a plenty of dispensable information. The
contribution shows, how a trusted, secure and really bi-directional
communication and interaction among users and their environment
can be established and used, e.g. in the field of home automation.
Abstract: This paper proposes a power-controlled scheduling scheme for devices using a directional antenna in smart home. In the case of the home network using directional antenna, devices can concurrently transmit data in the same frequency band. Accordingly, the throughput increases compared to that of devices using omni-directional antenna in proportional to the number of concurrent transmissions. Also, the number of concurrent transmissions depends on the beamwidth of antenna, the number of devices operating in the network , transmission power, interference and so on. In particular, the less transmission power is used, the more concurrent transmissions occur due to small transmission range. In this paper, we considered sub-optimal scheduling scheme for throughput maximization and power consumption minimization. In the scheme, each device is equipped with a directional antenna. Various beamwidths, path loss components, and antenna radiation efficiencies are considered. Numerical results show that the proposed schemes outperform the scheduling scheme using directional antennas without power control.