Smart Home Applications Research Articles

Research on the Optimization Art Design of Internet Smart Home System Based on the New Era

The rapid development of contemporary technology has subtly changed people’s way of life, and the quality of people’s life has been greatly improved. With great room for development and bright prospects for development, as the Internet develops, people are paying more and more attention to smart home experiences. However, the traditional household is increasingly ill-suited to today’s increasingly fast pace of life and there is an urgent need to develop a human smart home system. The aim of this paper is to explore the optimal design of an Internet-based smart home system for the new era. In this paper, we first present a general schematic diagram of an Internet-based smart home system. The system focuses on the main control module and uses a combination of wireless communication technologies in its design. Android will then be used as an adaptive platform, and the development of the system on the mobile side will be completed using Java and cloud services and other related technologies. The smart home system proposed in this paper actually creates a technology platform for smart home applications that monitor real-time changes in the indoor environment of the house, the security status of the house, and the remote control of the house’s electrical appliances. Finally, the experimental results obtained from testing the system proposed in this paper show that the system proposed in this paper is feasible. In this paper, the control commands of five nodes are sent 200 times cyclically, and the communication frequency of each node is more than 95%.

Scheduling Home Appliances with Integration of Hybrid Energy Sources using Intelligent Algorithms

This paper presents Home Energy Management System(HEMS) for smart homes. This system includes Photovoltaic Sources and Battery Storage Units(BSU)and scheduling Smart Home(SH) appliances with various kinds and types of residential users. In addition, a classification algorithm of energy response programs, which relies on the electricity prices, is introduced for scheduling appliances of single and multiple homes using combined the Time of Use(TOU) and Inclining Block Rate(IBR) to control the demand under the grid station capacity and energy efficacious integration of hybrid power sources in Smart Grid(SG). Four different optimization algorithms used and compared for scheduling appliances. The simulation results show that the proposed algorithm achieves the desired objectives, in which the electricity cost and the Peak Average Ratio(PAR) were lowered, waiting time to the user is minimized, reducing the electricity bill per month/year. In addition, the proposed system increases the stability and reliability of the grid and consumers satisfaction.

An Integration of feature extraction and Guided Regularized Random Forest feature selection for Smartphone based Human Activity Recognition

Human Activity Recognition (HAR) is an eminent area of research due to its extensive scope of applications in remote health monitoring, sports, smart home, and many more. Smartphone-based HAR systems use sensor data to infer human physical activities. Extraction of pertinent and essential features to identify human activities is a crucial but challenging task. Researchers continuously endeavor to extract pertinent and non-redundant features without compromising the classification accuracy. Smartphone sensor data generates high dimensional feature sets to recognize human physical activities. This work aims to build an efficient HAR model that extracts the most relevant features from the 3-axial accelerometer and gyroscope signal data and enhances the HAR system’s classification accuracy without data loss using time–frequency domain features. After feature extraction, we apply the Guided Regularized Random Forest (GRRF) feature selection method to determine the most pertinent and non-redundant features to reduce the time to recognize the human activities efficiently. After selecting the most relevant features, Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), and Decision Tree (DT) are used to identify various human physical activities. Using two different datasets, we investigate that GRRF selects relevant feature sets compared to two benchmark feature selection methods such as Relief-F and GRF, without compromising the recognition accuracy. This integration model with GRRF shows improved performance using all methods mentioned above. Our proposed strategy achieves higher accuracy values of 99.10% and 99.30% for SVM using two different datasets.

Deep attention-based neural networks for explainable heart sound classification

Cardiovascular diseases are the leading cause of death and severely threaten human health in daily life. There have been dramatically increasing demands from both the clinical practice and the smart home application for monitoring the heart status of individuals suffering from chronic cardiovascular diseases. However, experienced physicians who can perform efficient auscultation are still lacking in terms of number. Automatic heart sound classification leveraging the power of advanced signal processing and deep learning technologies has shown encouraging results. Nevertheless, a lack of explanation for deep neural networks is a limitation for the applications of automatic heart sound classification. To this end, we propose explaining deep neural networks for heart sound classification with an attention mechanism. We evaluate the proposed approach on the heart sounds shenzhen corpus. Our approach achieves an unweighted average recall of 51.2% for classifying three categories of heart sounds, i.e., normal, mild, and moderate/severe. The experimental results also demonstrate that the global attention pooling layer improves the performance of the learnt representations by estimating the contribution of each unit in high-level features. We further analyse the deep neural networks by visualising the attention tensors.

Small-Footprint Keyword Spotting for Controlling Smart Home Appliances Using TCN and CRNN Models

Smart homes feature automatic fire/smoke detection, voice-operated assets and appliances etc. More often, smart home appliances like lights, fans, etc., can be controlled through voice commands. Voice-operated devices like Alexa, Siri, and Google Assistant, are not new in the current age concerning voice command execution. However, working with these supports requires a global connection with the internet that costs time and bandwidth. Controlling home appliances need concise commands involving keywords on/off. Further, to operate the home appliances, bandwidth consumption for internet is not a wise idea. Through this paper, models based on Temporal Convolutional Networks (TCN) and Convolutional Recurrent Neural Networks (CRNN) have been studied for Keyword Spotting (KWS) by training models with keywords pronounced in different accents. The performance of these models is compared, and their ability to detect unknown words is studied. Finally, how these models are suitable for building Smart Home assistants to control home utilities with minimum bandwidth consumption is discussed.

Guided regularized random forest feature selection for smartphone based human activity recognition.

Human activity recognition (HAR) is an eminent area of research due to its extensive scope of applications in remote health monitoring, sports, smart home, and many more. Smartphone-based HAR systems use high-dimensional sensor data to infer human physical activities. Researchers continuously endeavor to select pertinent and non-redundant features without compromising the classification accuracy. In this work, our aim is to build an efficient HAR model that not only extracts the most relevant features from the 3-axial accelerometer and gyroscope signal data but also enhances the classification accuracy of the HAR system, without data loss using time-frequency domain features. We propose a feature selection method based on guided regularized random forest (GRRF) to determine the most pertinent and non-redundant features to reduce the time to recognize the human activities efficiently. After selecting the most relevant features, a support vector machine (SVM) is used to identify various human physical activities. The UCI public dataset and a self-collected dataset are used to assess the generalization capability and performance of the proposed feature selection method. Eventually, the accuracy reached 99.10% and 99.30% on the self-collected and UCI HAR datasets, respectively.

An IoT Based Smart Irrigation System

Smart home applications are fast becoming a staple of modern houses, leading to an increased interest in consumer electronics which enable the automation of common household tasks. However, high initial costs, complex solutions and closed systems, mean home automation is still out of reach for a large number of potential customers. A cheap, open, extensible solution is therefore a must if IoT is to become a standard option for modern homes. In this paper, we present an innovative solution to this problem in the form of an IoT framework called qToggle: a system for interconnecting sensors, actuators and other data sources based on open source solutions and easily accessible components. To give a practical example of the uses of the new framework, we implemented a smart irrigation system, which can simplify garden care, while reducing water and energy consumption. The article describes details of the design, instrumentation, and software (mobile application) for the real-time control of this system.

Characterization and driving of polymer-dispersed liquid-crystal sheet for smarthome applications

A commercial polymer-dispersed liquid-crystal (PDLC) sheet sample was characterized for its basic optical and electrical properties under DC and AC excitation. The results give driving voltage for 90% of transmittance for the PDLC of 10 V for DC excitation, and 9.5 Vrms for 50 Hz AC excitation. The measured contrast ratio of the PDLC is 2.55 and 2.47 under DC and AC excitation, respectively, which is suitable for smart window in a smarthome application. While it has rather similar optical properties under DC and AC excitation, it has significantly different electrical properties for DC and AC excitation. The PDLC exhibits a capacitive property which has capacitance per unit area of 18.5 μF/m2, indicating that DC excitation will give benefit compared to AC excitation which will scale with area of the PDLC. Based on these results, a DC driving circuit employing boost converter was designed to make a microcontroller-compatible driving circuit. The system was then integrated into a miniature smarthome demonstrator model exhibiting contrast ratio of 2.05 under switching from 0 to 100% of duty cycle of pulse width modulation (PWM) control signal from the microcontroller executed through voice command in an internet of things (IoT) platform.

Viability characterization of a proof-of-concept Bluetooth mesh smart building application

Bluetooth low energy is an almost ubiquitous technology currently embedded in billions of power-constrained Internet of Things devices around the world. The Bluetooth mesh profile, released by the Bluetooth Special Interest Group in July 2017, allows Bluetooth low energy devices to form a mesh network, further enabling smart home and building applications where long-range connectivity is required. However, the current release of Bluetooth mesh profile still has power and deployment constraints that limit its applicability. To explore the viability of Bluetooth mesh profile in home/building automation applications, we built the Smart Doorbell: a proof-of-concept Bluetooth mesh profile–based visitor notification system for office spaces. The Smart Doorbell was implemented using a mesh network topology with nodes distributed across office building floors, serving as a real Internet of Things deployment and as a testbed for mesh network protocols. Similar Bluetooth mesh profile evaluations found in literature use mostly development kits and/or synthetic traffic in artificial settings; we contribute by using the Smart Doorbell, a system as close as possible to a minimum viable product, to evaluate power consumption and responsiveness as a proxy for product viability. This article presents the architecture of the Smart Doorbell, the viability evaluation results, and a direct comparison with FruityMesh, a competing Bluetooth low energy mesh network protocol. Overall, the fact that Bluetooth mesh profile devices can directly communicate with a user’s mobile phone (using Bluetooth low energy) considerably eases deployment and provisioning. However, the use of flooding to forward messages across the mesh network increases power consumption, precluding the use of battery-powered nodes on the network’s backbone and severely limiting the applicability of Bluetooth mesh profile in building automation.

Enhancing Time Synchronization for Home Automation Systems

Clock synchronization techniques are in highly demand for smart home applications with the approach of the Internet of Things (IoT). The developing innovation of smart home applications built on the Internet of Things is generally constrained and scattered. Synchronization is the basic characteristic of the emerging field of IoT in smart home applications which is recommended for improving the acceptance and its use. For the clock synchronization between systems, Network Time Protocol (NTP) is used. But due to inconsistent routing and limited computing resources there can be the dominant source of error that limits time transfer uncertainty. This paper proposes an Elastic Timer Protocol for home automation system networks that performs better in terms of consumption of energy and time of convergence than other clock synchronization protocols. The proposed protocol improves the elasticity and efficiency of the network, resulting in a faster network convergence time. Furthermore, simulation results revealed that the proposed work has improved performance metrics and proved superior performance characteristics when compared to standard synchronization protocols.

Wearable multi-sensor data fusion approach for human activity recognition using machine learning algorithms

Wearable sensor based human activity recognition (HAR) has a broad range of applications in healthcare, fitness, smart home, and surveillance. In spite of the substantial amount of computational research on HAR, the open challenges in multi-sensor based activity recognition including complex temporal data, identifying discriminative feature vectors from multi-modal data and dimensionality reduction require considerable research attention. Hence, in this paper, using multi-resolution time-frequency analysis of received signal strength (RSS) between the wearable sensors, we present a supervised machine learning (ML) based activity recognition framework. The multi-sensor activity data acquired using the wireless sensor network (WSN) nodes and inertial-sensor embedded in a smartphone are decomposed using the discrete wavelet transform (DWT) and the empirical mode decomposition (EMD) techniques for extracting the prominent feature vector. Using the discriminative statistical features from DWT along with the entropy features from EMD, the four ML classifier models such as support vector machine (SVM), K-nearest neighbour (KNN), ensemble classifier (EC), and decision tree (DT) are trained to classify various human activities. The efficacy of the proposed design is assessed on a publicly available dataset from UCI. The experimental results assessed using the confusion matrix and parallel coordinate plot (PCP) substantiate that the proposed ML based HAR framework can achieve a maximum classification accuracy of 99.63% and is superior to several state-of-the-art ML techniques.

Progress of Advanced Devices and Internet of Things Systems as Enabling Technologies for Smart Homes and Health Care.

In the Internet of Things (IoT) era, various devices (e.g., sensors, actuators, energy harvesters, etc.) and systems have been developed toward the realization of smart homes/buildings and personal health care. These advanced devices can be categorized into ambient devices and wearable devices based on their usage scenarios, to enable motion tracking, health monitoring, daily care, home automation, fall detection, intelligent interaction, assistance, living convenience, and security in smart homes. With the rapidly increasing number of such advanced devices and IoT systems, achieving fully self-sustained and multimodal intelligent systems is becoming more and more important to realize a sustainable and all-in-one smart home platform. Hence, in this Review, we systematically present the recent progress of the development of advanced materials, fabrication techniques, devices, and systems for enabling smart home and health care applications. First, advanced polymer, fiber, and fabric materials as well as their respective fabrication techniques for large-scale manufacturing are discussed. After that, functional devices classified into ambient devices (at home ambiance such as door, floor, table, chair, bed, toilet, window, wall, etc.) and wearable devices (on body parts such as finger, wrist, arm, throat, face, back, etc.) are presented for diverse monitoring and auxiliary applications. Next, the current developments of self-sustained systems and intelligent systems are reviewed in detail, indicating two promising research directions in this field. Last, conclusions and outlook pinpointed on the existing challenges and opportunities are provided for the research community to consider.

Smart Homes or Real Homes: Building a Smarter Grid With “Dumb” Houses

Smart homes present numerous potential advantages for home occupants and utilities, including benefits such as energy savings, user convenience, and detailed data collection. Realizing any of these benefits requires a level of home instrumentation, such as the deployment of sensors or upgraded devices within the home. However, due to the expense and overhead of installing such equipment, instrumentation happens slowly and gradually, leading to many homes that are not particularly “smart,” yet should still function as part of the emerging smart grid. As a result, real-world smart home applications, particularly those that operate across many homes, will need to be realized in homes with modest and nonstandardized smart home capabilities. As a case study, we consider the problem of monitoring the energy use of specific devices across many homes without smart home capabilities and describe a prototype system to tackle this problem. Considering such systems may broaden our notions of what constitutes a “smart home” at all.

Microgrid energy management system for smart home using multi-agent system

This paper proposes a multi-agent system for energy management in a microgrid for smart home applications, the microgrid comprises a photovoltaic source, battery energy storage, electrical loads, and an energy management system (EMS) based on smart agents. The microgrid can be connected to the grid or operating in island mode. All distributed sources are implemented using MATLAB/Simulink to simulate a dynamic model of each electrical component. The agent proposed can interact with each other to find the best strategy for energy management using the java agent development framework (JADE) simulator. Furthermore, the proposed agent framework is also validated through a different case study, the efficiency of the proposed approach to schedule local resources and energy management for microgrid is analyzed. The simulation results verify the efficacy of the proposed approach using Simulink/JADE co-simulation.

Enhancing AES Using Chaos and Logistic Map-Based Key Generation Technique for Securing IoT-Based Smart Home

The Internet of Things (IoT) has brought new ways for humans and machines to communicate with each other over the internet. Though sensor-driven devices have largely eased our everyday lives, most IoT infrastructures have been suffering from security challenges. Since the emergence of IoT, lightweight block ciphers have been a better option for intelligent and sensor-based applications. When public-key infrastructure dominates worldwide, the symmetric key encipherment such as Advanced Encryption Standard (AES) shows immense prospects to sit with the smart home IoT appliances. As investigated, chaos motivated logistic map shows enormous potential to secure IoT aligned real-time data communication. The unpredictability and randomness features of the logistic map in sync with chaos-based scheduling techniques can pave the way to build a particular dynamic key propagation technique for data confidentiality, availability and integrity. After being motivated by the security prospects of AES and chaos cryptography, the paper illustrates a key scheduling technique using a 3-dimensional S-box (substitution-box). The logistic map algorithm has been incorporated to enhance security. The proposed approach has applicability for lightweight IoT devices such as smart home appliances. The work determines how seeming chaos accelerates the desired key-initiation before message transmission. The proposed model is evaluated based on the key generation delay required for the smart-home sensor devices.

Design and Build Internet of Things Smart Home For Android Based Electronic Equipment Management System

Energy consumption apart from the use of low-power consumption devices, it is also necessary to use energy-saving behavior that supports sustainable energy. Unwise use of electricity will of course have an impact on the high use of electricity, this also affects the depletion of electrical energy supplies because the need for electrical energy is greater than the supply of electrical energy, for that it is hoped that every community understands the efforts to use electricity wisely. Problems faced by households in managing the use of electrical energy include: Not using LED lights (Light Emitting Diodes); Using unnecessary electronic equipment; It is not wise to use equipment that requires electrical energy. The purpose of this research, among others, is how to monitor the use of electrical energy in the household by utilizing IoT and connected to the Android application to make monitoring easier. The contribution given by the researcher is how to combine microcontroller hardware, internet and android applications so that they can support the use of smart homes at home. Research Methodology includes data collection, needs analysis, program development, tool design, testing. Conclusions that can be drawn based on research that has been done include: Smart home that has been made can help turn on and turn off electronic equipment at home, Smart home applications that are made can be connected to the internet network, Smart Home applications can be installed on Smartphones with operating systems Android versions Android 7.0 – 7.1 (Nougat), Android 8.0 – 8.1 (Oreo), Android 9 (Pie), Android 10 (Android Q). For the implementation of using the application, the user must prepare the IoT Smarthome Hardware that has been designed and then connected to the internet. If so, household electronic equipment can be accessed via Android Mobile. In working on the Internet of Things Smart Home For Android, the author follows the path of the Research Methodology.

MotorBeat

More and more home appliances are now connected to the Internet, thus enabling various smart home applications. However, a critical problem that may impede the further development of smart home is overlooked: Small appliances account for the majority of home appliances, but they receive little attention and most of them are cut off from the Internet. To fill this gap, we propose MotorBeat, an acoustic communication approach that connects small appliances to a smart speaker. Our key idea is to exploit direct current (DC) motors, which are common components of small appliances, to transmit acoustic messages. We design a novel scheme named Variable Pulse Width Modulation (V-PWM) to drive DC motors. MotorBeat achieves the following 3C goals: (1) Comfortable to hear, (2) Compatible with multiple motor modes, and (3) Concurrent transmission. We implement MotorBeat with commercial devices and evaluate its performance on three small appliances and ten DC motors. The results show that the communication range can be up to 10 m.

Optimization scheduling of home appliances in smart home: A model based on a niche technology with sharing mechanism

Smart appliances bring convenience to people’s lives, but the high electricity cost and high peak load are still drawbacks. The scheduling optimization of household electricity tasks can effectively alleviate those drawbacks. Therefore, this paper proposes a scheduling optimization model of smart home appliances to reduce the load peak value and electricity cost. Herein, the electricity tasks are defined by the set theory and classified by the operational characteristics of the loads. Then, a hybrid coding genetic algorithm based on the niche technology is proposed for scheduling optimization problems of electricity tasks. Different coding and cross-mutation operation strategies are designed for different electricity tasks. Finally, a tracing Pareto method based on weighted sum approach is proposed to solve the multi-objective optimization problem. The experimental results show that the proposed algorithm has a good performance in reducing load peaks and electricity costs. In cases A, B, and C, the load peak value is reduced by 54.7%, 45.7%, and 20.7%, respectively; the electricity cost is reduced by 5.98%, 12.00%, and 16.12%, respectively. Furthermore, a series of Pareto optimal solutions are also identified, which can help users better understand the trade-off relation between the load peak value and electricity cost.

Multilabel Classification Methods for Human Activity Recognition: A Comparison of Algorithms.

As the world’s population is aging, and since access to ambient sensors has become easier over the past years, activity recognition in smart home installations has gained increased scientific interest. The majority of published papers in the literature focus on single-resident activity recognition. While this is an important area, especially when focusing on elderly people living alone, multi-resident activity recognition has potentially more applications in smart homes. Activity recognition for multiple residents acting concurrently can be treated as a multilabel classification problem (MLC). In this study, an experimental comparison between different MLC algorithms is attempted. Three different techniques were implemented: RAkEL, classifier chains, and binary relevance. These methods are evaluated using the ARAS and CASAS public datasets. Results obtained from experiments have shown that using MLC can recognize activities performed by multiple people with high accuracy. While RAkEL had the best performance, the rest of the methods had on-par results.

Human-computer interaction for augmentative communication using a visual feedback system

Brain-computer interface (BCI) has been considered a positive opportunity for schooling, cognitive learning, and remote contact in medical (e.g., neuronal reintegration).One of the most common uses of a computer is creating a brain-computer interface (BCI). This device can read brain activity signals, analyze them, and send out commands to an output device for execution. A BCI could be controlled by any type of brain signal for the most part. Due to the complexity of a head unit, classification precision is lower, costs are higher, and the work is more complicated. BCI is often challenging to use in everyday life. In this research, a Hybrid BCI using a visual feedback system (HBCI-VFS) proposed a control scheme of two brain impulses that take on electrodes and basic activities, requiring the participant to concentrate on stimulation and eye gaze. The stimulation is used to pick instructions by visually producing a steady-state visual evoked potential (SSVEP). The SSVEP control is calibrated by the single eye gaze (collection confirmation) and both eye gaze (i.e., negation and recollection). The neural network architectures are used to extract and analyze functionality in Fourier transformation and confusion for a short time. The findings show that the proposed device can give 38 instructions with a 3 s window period and 98.92% precision via a single bipolar electroencephalogram (EEG) channel.This study introduces a new BCI model based on SSVEP and eye gaze indications for the Smart home application, which could be helpful for Augmentative Communication. The technique presented in this study can support the other BCI-managed applications with high precision, multiple instructions, and fast response.