Integrating User Preference Into Improved Home Appliance Scheduling

Primary Question – How can smart appliance networks integrate human preference to enhance appliance scheduling? To deal with user preference variability, where the physical network interacts with human behavior, the most effective method is a flexible Graphical User Interface (GUI), or dashboard. In this work a dashboard is developed to make a more flexible model, this dashboard can account for variability in load preference, goal preference and appliance specifications, allowing consumers to plan loads on their specific network of household appliances in order to schedule a preferred time and evaluate the costs of certain load timing, given the desire to minimize the cost of electricity, avoid exceeding a peak load with minimal deviations from the user preferred schedule. As a result, uncertainty due to users is mitigated, such that only uncertainty in the load cycles themselves had to be managed, and that management could be done with greater robustness and computational efficiency. Consequently, this provides a model for developing more computationally efficient and robust scheduling patterns for household appliances. In this paper, household appliances are treated as an interdependent network to find satisficing solutions for timing loads to minimize electric cost, peak load, and deviation from the preferred time of scheduling.

Semi-supervised Intrusive Appliance Load Monitoring in Smart Energy Monitoring System

Intrusive Load Monitoring (ILM) is a method to measure and collect the energy consumption data of individual appliances via smart plugs or smart sockets. A major challenge of ILM is automatic appliance identification, in which the system is able to determine automatically a label of the active appliance connected to the smart device. Existing ILM techniques depend on labels input by end-users and are usually under the supervised learning scheme. However, in reality, end-users labeling is laboriously rendering insufficient training data to fit the supervised learning models. In this work, we propose a semi-supervised learning (SSL) method that leverages rich signals from the unlabeled dataset and jointly learns the classification loss for the labeled dataset and the consistency training loss for unlabeled dataset. The samples fit into consistency learning are generated by a transformation that is built upon weighted versions of DTW Barycenter Averaging algorithm. The work is inspired by two recent advanced works in SSL in computer vision and combines the advantages of the two. We evaluate our method on the dataset collected from our developed Internet-of-Things based energy monitoring system in a smart home environment. We also examine the method’s performances on 10 benchmark datasets. As a result, the proposed method outperforms other methods on our smart appliance datasets and most of the benchmarks datasets, while it shows competitive results on the rest datasets.

Implementation of Smart Mirror using Raspberry PI

Smart appliance design that includes multimedia intelligence to deliver comfortable, convenient, and secure personal services in the home is becoming increasingly crucial in the age of information and communication technology. This research looks at the design and execution of a novel interactive multimedia mirror system called as "smart mirror." The glass that will be used is the foundation of the design of a smart mirror. Two-way glass is suggested because it allows the visuals on the display to be seen more clearly. Our way of life has evolved to the point where making the best use of one's time is critical. Based on user surveys and prototype implementation, we propose the development of an innovative appliance that incorporates interactive information services delivered via a user interface on the surface of a mirror. Our work is based on the assumption that we all check ourselves in the mirror before leaving the house, so why shouldn't the mirror be intelligent? Smart Mirrors will eventually replace regular mirrors, providing users with both mirror and computer-assisted information services as technology improves. Because of the Raspberry Pi microcontroller cards aboard, the devices can connect to the internet, download data from the internet, and show that data on the mirror. Weather data, time and location data, current event data, and user data gathered from web services using a Raspberry Pi 3 microcontroller card are all included in the designed intelligent mirror system. The mirror will light up when the user steps in front of it. When thinking about this project, phrases like Smart Mirror, Interactive services, Raspberry Pi , and Web services come to mind.

Home Automation using Augmented Reality (HAAR)

The development of Smart Home Controllers has seen rapid growth in recent years, especially for smart devices, that can utilize the Internet of Things (IoT). However, a large portion of the household devices and appliances already in use, are not IoT enabled, and therefore, requires their default control mechanisms for the devices to operate. This paper proposes a smart appliance controller that uses Augmented Reality, MQTT, and other up-to-date platforms to control aftermarket home appliances in the most efficient manner. The proposed work integrates mobile AR with IoT, to control household appliances, with the help of infrared (IR) signals. The characteristics of the system are evaluated through a series of tests and performance measures. The results of the test highlight th quick response time of MQTT for the implementation of a Home Automation System, when compared to the request-reply protocol: CoAP (4 times as fast).

Development Experience of a Context-Aware System for Smart Irrigation Using CASO and IRRIG Ontologies

The rapid development of information and communication technologies and wireless sensor networks has transformed agriculture practices. New tools and methods are used to support farmers in their activities. This paper presents a context-aware system that automates irrigation decisions based on sensor measurements. Automatic irrigation overcomes the water shortage problem, and automatic sensor measurements reduce the observational work of farmers. This paper focuses on a method for developing context-aware systems using ontologies. Ontologies are used to solve heterogeneity issues in sensor measurements. Their main goal is to propose a shared data schema that precisely describes measurements to ease their interpretations. These descriptions are reusable by any machine and understandable by humans. The context-aware system also contains a decision support system based on a rules inference engine. We propose two new ontologies: The Context-Aware System Ontology addresses the development of the context-aware system in general. The Irrigation ontology automates a manual irrigation method named IRRINOV®. These ontologies reuse well-known ontologies such as the Semantic Sensor Network (SSN) and Smart Appliance REFerence (SAREF). The decision support system uses a set of rules with ontologies to infer daily irrigation decisions for farmers. This project uses real experimental data to evaluate the implementation of the decision support system.

Novel authentication framework for securing communication in internet-of-things

Internet-of-Things (IoT) offers a big boon towards a massive network of connected devices and is considered to offer coverage to an exponential number of the smart appliance in the very near future. Owing to the nascent stage of evolution of IoT, it is shrouded by security loopholes because of various reasons. Review of existing research-based solution highlights the usage of conventional cryptographic-based solution over the traditional mechanism of data forwarding process between IoT nodes and gateway. The proposed system presents a novel solution to this problem by a model that is capable of performing a highly secured and cost-effective authentication process. The proposed system introduces Authentication Using Signature (AUS) as well as Security with Complexity Reduction (SCR) for the purpose to resist participation of any form of unknown threats. The outcome of the model shows better security strength with faster response time and energy saving of the IoT nodes.

Service-Led Model for the Activation of Smart TV: Case Study in Korea

<p><strong>Purpose:</strong> This study explores the characteristics of STV service to empirically examine effects of the services on adoption and usage of STV to lead sustained growth of the STV industry.</p><p><strong>Methodology/Approach:</strong> This study employs structural equation modeling as a quantitative approach, to examine causal relationships between service characteristics and user intentions. The survey collects 212 data only from actual users of STV, who have experienced STV functions or services, in South Korea.</p><p><strong>Findings:</strong> The results of service-oriented model based on extended Technology Acceptance Model (TAM) indicate that ‘interactivity’, ‘content quality’, and ‘simplicity’ as service characteristics influence intention to use STV.</p><p><strong>Research Limitation/implication:</strong> First, the STV industry should establish a distribution structure that generates sufficient profits for content providers as done in Smartphone market. Second, Services of STV should be provided to allow two-way communication and to allow users to engage in active interactions with other users.</p><strong>Originality/Value of paper:</strong> This study makes contributions to research on both new products and service adoption by providing richer explanations of the mechanisms acting on the actual use of STV. Given that STV is considered a key appliance for the next generation of social media and smart appliance, our findings offer new directions on how to realize high quality services in the STV industry.