Smart Mirrors Research Articles

Use of Artificial Intelligence in Fashion Sales Techniques

This article discusses the prominent elements of artificial intelligence innovation in fashion sales techniques and details artificial intelligence-supported sales strategies such as virtual reality, augmented reality, virtual try-on rooms, smart mirrors, artificial intelligence-supported style consultants, visual search technologies and chatbot. This study was written with the compilation method. The compilation method is written with the aim of collecting the literature written so far on the research subjects from a scientific perspective and making a collective contribution to the literature. While virtual reality and augmented reality offer customers interactive shopping experiences and the opportunity to try products in their own environment without going to the store, virtual trial rooms and smart mirrors; Studies have shown that it has the potential to make online and face-to-face shopping easier, faster and more interactive. It has been stated that visual search technologies enable customers to easily find the products in the style they want, and artificial intelligence-supported style consultants and chatbots play an important role in optimizing the shopping experience by making personalized suggestions to customers. New and innovative solutions can be produced by conducting studies that encourage interdisciplinary collaboration between fashion designers, software developers and academicians. In this period when we live intertwined with technology, artificial intelligence-focused modules can be added to academic curricula for students studying in the field of design, and these modules will provide benefits for students to gain knowledge and skills on how to integrate artificial intelligence technologies into fashion design. The effective use of artificial intelligence in fashion sales techniques will provide a competitive advantage against competitors in the industry.

CNN-LSTM for MFCC-based Speech Recognition on Smart Mirrors for Edge Computing Command

Smart mirrors are conventional mirrors that are augmented with embedded system capabilities to provide comfort and sophistication for users, including introducing the speech command function. However, existing research still applies the Google Speech API, which utilizes the cloud and provides sub-optimal processing time. Our research aim is to design speech recognition using Mel-frequency cepstral coefficients (MFCC) and convolutional neural network–long short-term memory (CNN-LSTM) to be applied to smart mirror edge devices for optimum processing time. Our first step was to download a synthetic speech recognition dataset consisting of waveform audio files (WAVs) from Kaggle, which included the utterances “left,” “right,” “yes,” “no,” “on,” and “off. ” We then designed speech recognition by involving Fourier transformation and low-pass filtering. We benchmark MFCC with linear predictive coding (LPC) because both are feature extraction methods on speech datasets. Then, we benchmarked CNN-LSTM with LSTM, simple recurrent neural network (RNN), and gated recurrent unit (GRU). Finally, we designed a smart mirror system complete with GUI and functions. The test results show that CNN-LSTM performs better than the three other methods with accuracy, precision, recall, and an f1-score of 0.92. The speech command with the best precision is "no," with a value of 0.940. Meanwhile, the command with the best recall is "off," with a value of 0.963. On the other hand, the speech command with the worst precision and recall is "other," with a value of 0.839. The contribution of this research is a smart mirror whose speech commands are carried out on the edge device with CNN-LSTM.

Mirror, Mirror on the Wall: Automating Dental Smile Analysis with AI in Smart Mirrors

Mirror, Mirror on the Wall: Automating Dental Smile Analysis with AI in Smart Mirrors

Viologen-functionalized biomass-based furan trimer as a multi-coloring electrochromic material

The ability of electrochromic devices (ECD) to undergo a reversible color change when exposed to different voltage conditions has rendered them suitable for applications in smart mirrors, energy-efficient windows, and multi-color displays. While most of the compounds used for ECD fabrication are inorganic metal oxides, various studies have demonstrated that organic materials can also be promising candidates for ECD applications. Recently, our research group introduced a trifuran oligomer that can undergo reversible colorations at lower voltage ranges. However, the decoloration ability of the compound for a better color transition upon reduction remains a challenge. In this study, we successfully synthesized a viologen-functionalized biomass-based trimer and explored its electrochromic properties. Based on our findings, the novel compound exhibited a red to transmissive yellow to deep blue multi-coloring ability when it undergoes oxidation and reduction by virtue of its electrochromic components. Additionally, the introduction of viologen to the structure of the trifuran moiety enhanced the decoloration capacity of the ECD, therefore rendering the color transitions more visible.

Motion Activated Smart Mirror – with Real Time Alerts and Notifications

Smart mirrors combine modern technology with traditional home furnishings, creating a harmonious blend of style and function. These cutting-edge gadgets are revitalizing spaces such as restrooms and dressing rooms, transforming them into interactive information hubs. By combining Telegram notifications with motion detection, the newly presented solution improves the functionality of the smart mirror using ESP8266 NodeMCU boards. The integrated solution uses motion sensors and the popular Telegram communication network to instantly notify users on their smartphones whenever motion is detected near the smart mirror. This innovative approach not only simplifies daily life but also enhances security by alerting users to any movement in front of the mirror, whether it's a family member or a potential intruder. The design and implementation process of this integration, along with its range of applications and implications, are thoroughly examined. From enhancing home automation to strengthening security measures, there are numerous ways to expand the capabilities of these cutting-edge devices and improve user experience by combining motion detection with Telegram notifications in smart mirrors.

IoT Based Digital Smart Mirror

Everyone knows what a mirror is. It is an object found in most people’s homes. In mirrors we see our reflections. But what happens when you combine the idea of a mirror with technology. Here smart mirror comes in picture. This project has been developed with the idea of making home smart to save time and make your mirror more productive. The device that has been researched and designed is called Smart Mirror. It is a wall mounted mirror which displays relevant items to the user such as weather, time, date, temperature, humidity and news and other fields of interest. Smart Mirror emerged the idea of remotely monitoring objects through the Internet. This mirror is intended to collect this information during the preparation of a morning routine in order to do so more efficiently and easily. As technology advances, smart mirrors will eventually replace traditional mirrors, providing users with both mirror and computer-assisted information services.

IRS-assisted vehicular visible light communications systems: channel modeling and performance analysis.

Visible light communications (VLC) is a promising solution as an alternative for the fully occupied radio frequency bands in the near future. The rear (tail) and front of vehicles have lamps that can be used for vehicular visible light communications (VVLC) systems. However, one of the main challenges of VLC systems is the line-of-sight (LoS) blockage issue. In this paper, we propose the installation of intelligent reflecting surfaces (IRSs) (i.e.,smart mirrors) on the back of vehicles to overcome the issue in VVLC systems. We assume three different patterns of angular distribution for the radiation intensity: a commercially available LED with an asymmetrical pattern (Philips Luxeon Rebel), a symmetrical Lambertian pattern, and an asymmetrical Gaussian pattern. In the first section of this paper, we obtain the channel model for the IRS-assisted VVLC systems, then we investigate the path loss results versus link distance under different conditions such as weather type (clear, rainy, moderate fog, and thick fog) and radiation patterns. Moreover, the impact of system parameters such as the aperture size of the photodetector (PD), side-to-side and front-to-front distances, the number of IRS elements, and the IRS area are studied. In the second part, we derive a closed-form expression for the maximum achievable link distance versus the probability of error for the IRS-assisted VVLC systems. In addition, in this section we analyze the impact of the parameters in a single-photon avalanche diode (SPAD), background noise, and the system parameters for the path loss.

The challenge of integrating “intelligent” technologies in luxury shopping contexts: The role of brand personality appeal and consumers’ status consumption orientation

Current opportunities enabled by combining the Internet of Things and the Artificial Intelligence may allow marketers and managers to completely redesign shopping environments by integrating new interactive technologies in shopping environments. However, luxury brands have been typically skeptical to the implementation of technology, because of its conceptual contrast with the ideas of craftsmanship and human touch. To advance knowledge on the potential role of advanced technologies in the context of luxury, this study investigates the effect luxury shopping environment level of intelligence (low vs. high), in the shopping context of a luxury brand, on consumers' perceived personality appeal and, therefore, on their intention to buy. Additionally, this study sheds light on the moderating role of consumers' status consumption orientation, that is a relevant consumer-related characteristic in field of luxury consumption. Results of two experiments, conducted with international participants recruited online, where the level of technological intelligence is manipulated through Voice Assistants (Study 1) and Smart Mirrors (Study 2), show that the high (vs. low) luxury shopping environment's intelligence level positively affects consumers' willingness to buy through the effect of their perceived brand personality appeal. Moreover, this effect is moderated by consumers' status consumption orientation. Theoretical implications are discussed, together with managerial implications useful for effectively manage advanced technologies in luxury shopping environments.

A Novel Approach to Smart Mirror Technology for Enhanced Elderly Health Monitoring

Abstract—The integration of smart mirror technology for health monitoring in elderly populations discusses the benefits and challenges of using smart mirrors as a proactive healthcare solution. The study emphasizes features such as facial recognition, posture analysis, and skin condition detection, enabling real-time data collection and personalized recommendations for preventive care. Usability, privacy concerns, and integration issues are considered. Through a review of relevant research, the paper highlights the potential of smart mirrors for proactive health monitoring in the elderly. It offers insights to researchers and healthcare professionals seeking innovative solutions for personalized care. Keywords—Smart mirror, smart assistant, health issues, elderly care, human healthcare, IoT, emotion recognition, mental monitoring

Mirror‐Transcending Aerial Imaging (MiTAi): An optical system that freely crosses the boundary between mirrored and real spaces

AbstractMany optical systems for displaying digital information on mirrors have been proposed, but information can only be displayed in either mirrored or real space and cannot move back and forth between the two. We have therefore developed a new optical system called mirror‐transcending aerial imaging (MiTAi) that freely crosses the boundary between mirrored and real spaces. MiTAi is based on an existing aerial‐imaging system consisting of a retro‐reflector, a beam splitter, and a moving display. MiTAi is designed as a space‐saving design by changing the orientation and position of the moving display as the light source. We implemented a prototype MiTAi to evaluate the luminance of the displayed aerial images and found that the aerial image formed by the prototype is able to move freely between both mirrored and real spaces. Moreover, the luminance of the image is not significantly lower than that formed by the existing aerial‐imaging system. MiTAi will enable the creation of a new user experience by integrating smart mirrors and real‐space aerial images.

Smart Mirror using Raspberry Pi

Abstract: This project has been developed within the context of a time where every day we see more and more connected devices. The Internet transformed our lives by connecting us more easily to information and other people in the virtual world. Mobile phones then became smartphones and since then this concept has erupted and morphed into the Internet of Things, things that connect us to everyday objects. There is no end to objects that could be made “smarter”, some being more suited to this than others. Mirrors, for example, provide a large surface ideal for displaying information and interacting with it. Most people have mirrors at home so the concept of a smart mirror that you can interact with is attractive and has been fantasized about in many futuristic movies. Smart mirrors, such as Magic Mirror and Home Mirror, have been only developed by people in the Maker community, with varying degrees of interactivity. However, so far, the features of these mirrors have been limited. This final year project describes how a smart mirror was built from scratch using a Raspberry Pi for the hardware and custom software built on top of Raspbian, a Linux distribution. The goal of the project was to create a Smart Mirror device that people could interact with but also to further develop the technology so that it would let you install and develop your own applications for it. Overall, results were good because a higher level of interactivity has been achieved by being able to use voice commands, gestures, and smartphones. A few problems arose in the construction and software side of the project, such as the glass not being reflective enough and the gesture recognition being unreliable, but these drawbacks can be addressed by doing more tests and trials to further develop the Smart Mirror

Empirical Study on Effects of Gratification on Continuous Usage Intention of AR Avatars in Smart Mirrors: Focus on Generation Z

Smart mirrors remain in the early stages of market formation and the expansion thereof exhibits limitations. To address this issue, avatars based on augmented reality (AR) of smart mirrors are attracting attention as an innovative retail marketing tool, with a focus on Generation Z customers who have large potential purchasing capabilities. However, no study has empirically identified the continuous usage intention of AR avatars for actual users. Hence, in this study, an empirical analysis was performed based on the uses and gratifications theory. A laboratory experiment that reflected an actual shopping scenario was implemented and a survey of 168 people from Generation Z was conducted. Consequently, important directions are suggested for system developers and marketers in the use of smart mirrors. Moreover, this study offers novel insights into identifying the continuous usage intention of AR avatar contents in smart mirrors.

Smart Mirror using IoT and Raspberry Pi

Abstract: Smart mirrors as a concept are growing rapidly. These mirrors directly affect the day to day lives of the people as it provides customization and a luxurious lifestyle. With the help of devices like smart mirrors people are getting exposed to technology and are in turn contributing to a tech supported lifestyle. The smart mirror is one such device where a normal mirror acts as a smart device which consists of a user interface with which the user can interact. This paper proposes a model which is robust and can be utilized by individuals in their day to day lives. The proposed model in this paper is in the form of a mirror developed with a combination of hardware and software. The mirror incorporates Oracle VM Virtual Box which supports the Raspbian OS. The model uses the Magic Mirror Module on the software part to implement different features like Calendar, Music App, Weather Forecast, News etc. These features are implemented using their respective API’s. The proposed model can be scaled to add more and more features thus making it more robust, also the model is very cost effective. With the help of this people would be able to ease their lifestyle a bit and automate things as much as possible.

The power of multifunctional metal hydrides: A key enabler beyond hydrogen storage

The metal-hydrogen interaction and its equilibrium conditions allow for distinct properties in metal hydrides (MHs). Based on these properties, MHs have been found to enable a range of novel technologies from thermal compression to sensors, and catalysis. Ni-MH batteries are currently the main application of hydrides in the market. However, new battery concepts such as Li-MgH 2 , Mn-MH, and hydride-based solid electrolytes have emerged. Fuel cells based on hydrides have also been proposed to convert the chemical “hydride energy” into electrical energy. Based on their unique thermodynamic properties, MHs are also the basis of new concepts in hydrogen compression, heat pumps, cooling systems, and thermal energy storage. Other important applications, including catalysis and chemical speciation have also been considered owing the chemical properties of hydrides. Sensors and smart mirrors based on the dynamic optical, structural, and electrical properties of MHs have been developed. This review summarizes current state-of-the-art along the multiple applications of MHs and provides recommendations on the future progress required to enable a more widespread adoption of MHs beyond their use as hydrogen storage materials. • Hydrides have a broad range of applications. • Enabling alternative applications beyond hydrogen storage could help in finally enabling the commercialization of hydrides. • The continuous development of new hydrides materials remains a critical enabler.

Design Of Interactive Smart Mirror System for Digital Information Display Based on Multitasking Approach Using Raspberry Pi

The average time humans look in the mirror is in the early morning when they will get ready for work. A person can rarely focus on other activities such as watching television for the latest news, checking the clock for the correct time, or even checking the weather forecast. Therefore, the purpose of this research is to design an interactive smart mirror that functions as a personal digital assistant to provide a schedule of daily activities, including recognizing the owner's face for access to the smart mirror, displaying weather forecasts, displaying the date and time, as well as the latest news. Unlike most smart mirrors in previous studies, this smart mirror design is connected to a facial recognition system. This will work for such security systems that the user will be granted access to the system only when the system detects that it is the owner. The method used in the research is the agile methodology for the project's flexibility and structured work organization. Experiments will be carried out on all test data starting from the accuracy of turning the smart mirror on and off, loading the weather on average 5 seconds after internet connection, making sure the Pi-camera component is active, and checking for face profiles. The system will test the data on each unit individually and as a whole to ensure efficiency and reliability. The experimental results in this study provide an accurate value of 100%.

Error-Resistant Movement Detection Algorithm for the Elderly with Smart Mirror

As the elderly population increases globally, the demand for systems and algorithms that target the elderly is increasing. Focusing on the extendibility of smart mirrors, our purpose is to create a motion detection system based on video input by an attached device (an RGB camera). The motion detection system presented in this paper is based on an algorithm that returns a Boolean value indicating the detection of motion based on skeletal information. We analyzed the problems that occur when the adjacent frame subtraction method (AFSM) is used in the motion detection algorithm based on the skeleton-related output of the pose estimation model. We compared and tested the motion recognition rate for slow-motion with the previously used AFSM and the vector sum method (VSM) proposed in this paper. As an experimental result, the slow-motion detection rate showed an increase of 30–70%.

Evaluation of Reconfigurable Intelligent Surface-Assisted Underwater Wireless Optical Communication System

Reconfigurable intelligent surfaces (RISs) are an emerging technology aimed to enhance the energy and spectrum efficiency of wireless communication links by reconfiguring the propagation environment of radio-frequency (RF)/optical waves. Planar phased meta-material surfaces or reflect-arrays for RF RIS and multiple smart mirrors have been used for activating optical RIS. In this article, we analyze the underwater optical wireless communication (UWOC) system performance in terms of bit error rate (BER), outage probability (OP) and channel capacity (CC) under the influence of underwater turbulence, beam attenuation, pointing errors and occlusion or blockage due to obstacles. A RIS-assisted UWOC proposed to mitigate the effects obstacles, pointing errors and turbulence and improve the system performances. The probability density function and cumulative distribution functions of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$N$</tex-math></inline-formula> RIS elements based UWOC system are evaluated over the underwater turbulence, pointing errors and blockage due to obstacles. The novel closed-form expressions for BER under binary phase shift keying and binary frequency shift keying modulation schemes using with and without coherent detection, OP, and CC for intensity modulation-direct detection and heterodyne detection cases are obtained and plotted according to the number of RIS elements with respect to the average signal-to-noise ratio. The numerical BER results are validated with the Monte-Carlo simulations.

Augmented assistive technology: the importance of tailoring technology solutions for people living with dementia at home

This research investigates the benefits of personalised augmented assistive technology to support people living with dementia in their daily activities in the home. With the aim to achieve a tailored and person-centred technology solution for each participant, we discuss the challenges and potential benefits of Augmented Reality (AR) for people living with dementia. We highlight the need to take a human-centred design approach for this user group and demonstrate how AR technology should not drive the research focus in this challenging field but should instead be responsive to the needs and goals of stakeholders. The qualitative approach demonstrates the benefits of using modular technology for the shifting needs of individuals with dementia. The breadth of tailored solutions is described via two detailed participant stories. We discuss the multi-sensory dimensions of AR and how this is important to maintain and increase independence for the user group. We investigate the challenges and benefits of using technologies including Microsoft HoloLens, digital projectors, smart mirrors, Amazon Alexa, and aroma diffusers for assistive purposes.

Comparative Analysis and Development of Voice-based Chatbot System for Differently-abled

One technology that improved humans’ lifestyle is a Chatbot System, an AI-based system that conducts people’s conversations. Chatbots are used in a wide range of applications-assistive technologies, customer service, home automation, education, medical bots, entertainment, etc. Such technology could be beneficial to differently-abled for teaching, assistance, etc. But when it comes to people with a slight speech disorder or autism, available chatbot systems aren’t very effective. This paper investigates the existing speech recognition APIs based on WER and CER and tries to improve results by adding a personalized layer for the user. This chatbot system can be embedded with existing technologies-domestic robots, smart mirrors, home automation, medical applications, etc. It will open these technologies to a wide range of audiences. The proposed Chatbot will use the existing speech recognition API and improve the results based on the above performance measures.

MobilePhys

Camera-based contactless photoplethysmography refers to a set of popular techniques for contactless physiological measurement. The current state-of-the-art neural models are typically trained in a supervised manner using videos accompanied by gold standard physiological measurements. However, they often generalize poorly out-of-domain examples (i.e., videos that are unlike those in the training set). Personalizing models can help improve model generalizability, but many personalization techniques still require some gold standard data. To help alleviate this dependency, in this paper, we present a novel mobile sensing system called MobilePhys, the first mobile personalized remote physiological sensing system, that leverages both front and rear cameras on a smartphone to generate high-quality self-supervised labels for training personalized contactless camera-based PPG models. To evaluate the robustness of MobilePhys, we conducted a user study with 39 participants who completed a set of tasks under different mobile devices, lighting conditions/intensities, motion tasks, and skin types. Our results show that MobilePhys significantly outperforms the state-of-the-art on-device supervised training and few-shot adaptation methods. Through extensive user studies, we further examine how does MobilePhys perform in complex real-world settings. We envision that calibrated or personalized camera-based contactless PPG models generated from our proposed dual-camera mobile sensing system will open the door for numerous future applications such as smart mirrors, fitness and mobile health applications.