Eiman KanjoImperial College London | Imperial · Department of Computing
Eiman Kanjo
Professor in tinyMLPervasive Computing UK
About
137
Publications
112,119
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,298
Citations
Introduction
Looking for new ways to make smart phones and embedded devices smarters for environmental monitoring, smart spaces, wellbeing and behaviour change, and to make sense of outdoor places using IoT technology, data science and on-device processing.
Main research interests are: tinyML, Edge Computing, Edge AI, on-device learning, Efficient AI, Mobile Sensing, data science pervasive computing, digital phenotyping, temporal-spatial analysis, multimodel and information fusion, tangible interfaces.
Additional affiliations
January 2014 - present
October 2006 - January 2010
August 2004 - October 2006
Publications
Publications (137)
People living with dementia are at risk of social isolation, and conversational AI agents can potentially support such individuals by reducing their loneliness. In our study, a conversational AI agent, called MindTalker, co-designed with therapists and utilizing the GPT-4 Large Language Model (LLM), was developed to support people with early-stage...
Smart Farming is a progressive domain marked by extensive research and solutions. The predominant approach involves the use of LPWANs for communication, with subsequent data transfer to a cloud server once Internet connectivity is established. In this letter, we present the design and development of a novel smart farming sensor system that combines...
As stress continues to be a major health concern, there is growing interest in developing effective stress management systems that can detect and mitigate stress. Deep Neural Networks (DNNs) have shown their effectiveness in accurately classifying stress, but most existing solutions rely on the cloud or large obtrusive devices for inference. The em...
The Internet of Things (IoT) and wearable computing are crucial elements of modern information systems and applications in which advanced features for user interactivity and monitoring are required. However, in the fields of pervasive gaming, IoT has had limited real-world applications. In this work, we present a prototype of a wearable platform fo...
The devastating effects of climate change and human activity on the planet’s biodiversity have led to a mass extinction event, which is when species vanish much faster than they are replaced.
This is defined as about 75 percent of the world’s species being lost in a short period of geological time—less
than 2.8 million years [1]. The Eden Portland...
As the research community increasingly focuses on quantifying emotional states in real-world scenarios, there is a growing need for edge computing. In this work, we present a novel approach to on-device emotion classification through the development of a low-cost hand-held device. This device incorporates a range of environmental air quality factor...
The quantification of emotional states is an important step to understanding wellbeing. Time series data from multiple modalities such as physiological and motion sensor data have proven to be integral for measuring and quantifying emotions. Monitoring emotional trajectories over long periods of time inherits some critical limitations in relation t...
The quantification of emotional states is an important step to understanding wellbeing. Time series data from multiple modalities such as physiological and motion sensor data have proven to be integral for measuring and quantifying emotions. Monitoring emotional trajectories over long periods of time inherits some critical limitations in relation t...
Involving and engaging people with learning disabilities on issues relating to their mental wellbeing can bechallenging. This research explores how participatory design techniques and principles can be used to engagepeople with learning disabilities in designing technological solutions relevant to them that could monitorand aid their mental wellbei...
As stress continues to be a major health concern, there is growing interest in developing effective stress management systems that can detect and mitigate stress in real-world environments. Deep Neural Networks (DNNs) have shown their effectiveness in accurately classifying stress, but most existing solutions rely on the cloud or large obtrusive de...
Tag With Me is an innovative IoT and AI-based proximity-based gaming platform that offers personalised trails and activities, tailored to host venues like museums, hospitals, parks, and cities. Leveraging short-range communication and on-device AI-driven object recognition, the platform revolutionises the gaming experience by promoting physical act...
With the increase in energy prices and the drive to reduce carbon emission, this paper presents an investigation of the use of smart office environments to monitor and evaluate the sustainability and behaviour of employees and the utilisation of space and resources. This paper presents analysis of data in an office environment in a company in Derby...
In this paper we introduce "Tag in the Park", a mobile platform merging short-range wireless communication and Artificial Intelligence (AI) to create an interactive gamified experience through virtual treasure hunts. Central to this is a mobile app that revolves around the interaction with a network of Bluetooth Low Energy (BLE) beacons and Near Fi...
The ubiquity of mobile sensing and smartphone capabilities offer a significant opportunity to obtain real-world sensor data and momentary mental wellbeing fused at the point of exposure. In this paper, we present the design, implementation and evaluation and user experiences of Urban Wellbeing; a cross-platform mobile application, which aids in qua...
Mobile devices are ubiquitous for users in everyday life, often with individuals throughout their daily routine. The widespread use of mobile devices allows novel technologies to be designed to improve personal security and safety. The research presented in this paper provides additional functionality through pervasive sensors on mobile devices, ma...
The edge computing paradigm has become increasingly popular due to its benefits over cloud computing, particularly in the context of AI and IoT applications. Its harmonising with AI to form Edge intelligence (EI) has opened up possible
application areas for further development. Tiny machine learning
(tinyML) is a specific focus within EI that targe...
Over the past few years, embedded systems and machine
learning communities have come together to make AI ubiquitous
and available near the data source, unlocking many untapped
application areas that await development. As a result, hardware,
software, and research have changed extremely rapidly with
many recent releases of ML-enabled microcontroller...
The use of technology within the area of Farming is becoming a
more widely discussed area usually referred to as Smart
Farming. As more technologies are being introduced into the area
and more proposals are made, the area of smart farming is
allowing farmers to increase their overall yield.
The use of tinyML could bring real benefits to smart farmi...
As stress continues to be a major health concern, there is growing interest in developing effective stress management systems that can detect and mitigate stress in real-world environments. Deep Neural Networks (DNNs) have shown their effectiveness in accurately classifying stress, but most existing solutions rely on the cloud or large obtrusive de...
The increasing level of air pollutants (e.g. particulates, noise and gases) within the atmosphere are impacting mental wellbeing. In this poster, we define the term 'TinyDigitalExposome' that takes us closer towards understanding the opportunity between environment and wellbeing using constrained microcontrollers. Specifically, we propose the oppor...
Our work focuses on using tinyML for detecting
violent language on edge devices, such as mobile
phones and wearables, in the context of preventing
domestic violence. Our multimodal algorithm uses
natural language processing (NLP) and audio
processing to detect violent conversation from short
audio-text segments.
The algorithm is converted to a tiny...
The increasing level of air pollutants (e.g. particulates, noise and gases) within the atmosphere are impacting mental wellbeing. In this paper, we define the term ’DigitalExposome’ as a conceptual framework that takes us closer towards understanding the relationship between environment, personal characteristics, behaviour and wellbeing using multi...
In this letter, we present the development and evaluation of the
Urban Wellbeing
mobile application that employs real-world, momentary assessment of the environment and it's link to wellbeing using multi-model sensor data and self-report wellbeing. Several industry standard environmental sensors comprised of Particulate Matter, Ozone and Nitrogen...
Mobile devices are nearly ubiquitous for users in everyday life, often being
with individuals throughout their daily routine, including use during work, social, and home activities. The widespread use of mobile devices allows novel
technologies to be designed to improve personal security and safety. Existing
solutions in this area include applicati...
The ubiquity of location tracking on smartphones allows us to monitor, collect, and analyse large trajectory data in real-time. Time series classification and clustering is an efficient way to analyse trajectories. A remarkable amount of research on the relationship between urban environments, health or wellbeing has been conducted including our pr...
Between the sensors gathering data and the cloud computing services processing data, there is an array of new technologies emerging. These technologies allow for complex processing and storage, closer to where data is collected – right at the edge. While Cloud Computing has received tremendous attention from both academia and industry for connectin...
Between the sensors gathering data and the cloud computing services processing data, there is an array of new technologies emerging. These technologies allow for complex processing and storage, closer to where data is collected - right at the edge. While Cloud Computing has received tremendous attention from both academia and industry for connectin...
Smart portable and wearable devices have become more and more popular in our lives due to their ability to "Wear and Use On-the-Go". However, in order to collect data and perform momentarily assessment of users' data, they require to be light weight, compact size with multiple sensors and higher processing capabilities. Edge computing provides an o...
Introduction
It is estimated that 55 million people are living with dementia worldwide in 2021, and the numbers are expected to rise to 78 million in 2030 and 139 million in 2050 (Siriaraya et al., 2022; World Health Organisation, 2022). Dementia is an umbrella term that describes neurodegenerative disorders that impact memory, cognition, language...
Mindless eating, or the lack of awareness of the food we are consuming, has been linked to health problems attributed to unhealthy eating behaviour, including obesity. Traditional approaches used to moderate eating behaviour often rely on inaccurate self-logging, manual observations or bulky equipment. Overall, there is a clear unmet clinical need...
Automatic recognition of human emotions is not a trivial process. There are many factors
affecting emotions internally and externally. Expressing emotions could also be performed in many
ways such as text, speech, body gestures or even physiologically by physiological body responses.
Emotion detection enables many applications such as adaptive user...
Natural Language Processing has recently made understanding human interaction easier, leading to improved sentimental analysis and behaviour prediction. However, the choice of words and vocal cues in conversations presents an underexplored rich source of natural language data for personal safety and crime prevention. When accompanied by audio analy...
Exergames are video games that require physical movement to play with AR presenting many opportunities for promoting physical activities as it can be used to engage players and encourage exploration. Multiplayer Augmented Reality (AR) games allow players to occupy a shared physical environment populated with interactive digital 3D models. We propos...
With the ever-increasing elderly population, human activity trackers can help monitor the daily physical activities performed by the elderly in order to contribute towards improvements in independent living and quality of life.
Historically, research has explored activity recognition using either multimodal wearable sensors or
Historically resear...
Vertebrate retinas are highly-efficient in processing trivial visual tasks such as detecting moving objects, yet a complex task for modern computers. The detection of object motion is done by specialised retinal ganglion cells named Object-motion-sensitive ganglion cells (OMS-GC). OMS-GC process continuous signals and generate spike patterns that a...
Ubiquitous access to the internet is provided to students via WiFi to enhance their learning experience. Internet use is central to education, however when overused for distraction it can be problematic and negatively affect students’ academic performance and well-being.
A spatial-temporal analysis of actual behaviour on a University WiFi examines...
Emerging technological innovations have been developed in recent years to prevent crime and enhance public safety. This paper evaluates the recent advances in ubiquitous sensing and pervasive computing to ultimately propose a multimodal crime prevention tool that incorporates several technologies into a single wearable device. The crime prevention...
An exergame is a genre of gaming that combinesexercising with digital game play. The ubiquity of mobile devicesmake them ideal platforms for these games to promote physicalactivities. Advances in Internet of Things (IoT) technologiesincluding Bluetooth Low Energy (BLE) beacons can be utilisedfor proximity detection to promote physical activities an...
Maintaining social distancing in public spaces plays a pivotal role in decreasing COVID-19 contagion and viral spread. COVID-19 has required many countries around the world to close work places, schools and public spaces. This has prompted policy makers, venue managers and local authorities to investigate practical mitigation strategies using techn...
The proliferation of miniaturized electronics has fuelled a shift toward environmental sensing technologies ranging from pollution to weather monitoring at higher granularity. However, little consideration has been given around the relationship between environmental stressors (e.g. air pollution) and mental wellbeing. In this paper, we aim at captu...
Time series data from multiple modalities such as physiological and motion sensor data have proven to be integral for measuring mental wellbeing however individual differences between people limit the generalisability of deep learning models especially for those with intellectual disabilities. It is impractical, time consuming and extremely challen...
Maintaining social distancing in public spaces plays a pivotal role in decreasing COVID-19 contagion and viral spread. COVID-19 has required many countries around the world to close work places, schools and public spaces. This has prompted policy makers, venue managers and local authorities to investigate practical mitigation strategies using techn...
Next generation wireless systems have witnessed significant R&D attention from academia and industries to enable wide range of applications for connected environment around us. The technical design of next generation wireless systems in terms of relay and transmit power control is very critical due to the ever-reducing size of these sensor enabled...
Introduction: The immediate impact of coronavirus 2019 (COVID-19) on morbidity and mortality has raised the need for accurate and real-time data monitoring and communication. The aim of this study is to document the initial observations from multiple digital services providers during the COVID-19 crisis, especially those related to mental health an...
Criminal activity is a prevalent issue in contemporary culture and society, with most nations facing unacceptable levels of crime. Technological innovation has been one of the main driving forces leading to the continuous improvement of crime control and crime prevention strategies (e.g. GPS tracking and tagging, video surveillance, etc.). Given th...
Introduction: The immediate impact of COVID-19 on morbidity and mortality has raised the need for accurate and real time data monitoring and communication. The aim of this study is to document initial observations from multiple digital services providers during the COVID-19 crisis, especially those related to mental health and wellbeing. Materials...
The increasing level of air pollutants (e.g. particulates, noise and gases) within the atmosphere are impacting mental wellbeing. In this paper, we define the term ’DigitalExposome’ as a conceptual framework that takes us closer towards understanding the relationship between environment, personal characteristics, behaviour and wellbeing using multi...
Involving and engaging people with learning disabilities on issues relating to their mental wellbeing can bechallenging. This research explores how participatory design techniques and principles can be used to engagepeople with learning disabilities in designing technological solutions relevant to them that could monitorand aid their mental wellbei...
Involving and engaging people with learning disabilities on issues relating to their mental wellbeing can bechallenging. This research explores how participatory design techniques and principles can be used to engagepeople with learning disabilities in designing technological solutions relevant to them that could monitorand aid their mental wellbei...
Emerging technological innovations have been developed in recent years to prevent crime and enhance public safety. This paper evaluates the recent advances in ubiquitous sensing and pervasive computing to ultimately propose a multimodal crime prevention tool which incorporates several technologies into a single wearable device. The crime prevention...
The ability to unobtrusively measure mental wellbeing states using non-invasive sensors has the potential to greatly improve mental wellbeing by alleviating the effects of high stress levels. Multiple sensors, such as electrodermal activity, heart rate and accelerometers, embedded within tangible devices pave the way to continuously and non-invasiv...
The novel coronavirus, designated by the World Health Organization as COVID-19 has required many countries around the world to close work spaces, schools and public venues. This has required policy makers and venue managers to investigate practical mitiga-tion strategies using technology to exit the lockdown safely and enable the reopening of publi...
In recent years, machine learning has developed rapidly, enabling the development of applications with high levels of recognition accuracy relating to the use of speech and images. However, other types of data to which these models can be applied have not yet been explored as thoroughly. Labelling is an indispensable stage of data pre-processing th...
Children can find it challenging to communicate their emotions especially when experiencing mental health challenges. Technological solutions may help children communicate digitally and receive support from one another as advances in networking and sensors enable the real-time transmission of physical interactions. In this work, we pursue the desig...
COVID-19 has shown a relatively low case fatality rate in young healthy individuals, with the majority of this group being asymptomatic or having mild symptoms. However, the severity of the disease among the elderly as well as in individuals with underlying health conditions has caused significant mortality rates worldwide. Understanding this varia...
Mental health problems are on the rise globally and strain national health systems worldwide. Mental disorders are closely associated with fear of stigma, structural barriers such as financial burden, and lack of available services and resources which often prohibit the delivery of frequent clinical advice and monitoring. Technologies for mental we...
Children can find it challenging to communicate their emotions especially when experiencing mental health challenges. Technological solutions may help children communicate digitally and receive support from one another as advances in networking and sensors enable the real-time transmission of physical interactions. In this work, we pursue the desig...
The growth of mobile sensor technologies have made it possible for city councils to understand peoples' behaviour in urban spaces which could help to reduce stress around the city. We present a quantitative approach to convey a collective sense of urban places. The data was collected at a high level of granularity, navigating the space around a hig...
COVID-19 has shown a relatively low mortality rate in young healthy individuals, with the majority of this group being asymptomatic or having mild symptoms, while the severity of the disease among individuals with underlying health conditions has caused signiffcant mortality rates worldwide. Understanding these differences in mortality amongst diff...
UNSTRUCTURED
COVID-19 has shown a relatively low case fatality rate in young healthy individuals, with the majority of this group being asymptomatic or having mild symptoms. However, the severity of the disease among the elderly as well as in individuals with underlying health conditions has caused significant mortality rates worldwide. Understandi...
Stress is a growing concern in modern society adversely impacting the wider population more than ever before. The accurate inference of stress may result in the possibility for personalised interventions. However, individual differences between people limits the generalisability of machine learning models to infer emotions as people's physiology wh...
This Special Issue calls for high-quality, multidisciplinary research papers in the field of human-centred computing, engineering and life sciences which aim to address issues associated with dementia with novel technologies. We are interested in submissions focusing on emerging technologies to support dementia care, diagnosis, early intervention,...
n recent years, machine learning has made leaps and bounds enabling applications with high recognitionaccuracy for speech and images. However, other types of data to which these models can be applied have not yetbeen explored as thoroughly. Labelling is an indispensable stage of data pre-processing that can be even morechallenging in single or mult...
Stress is a growing concern in modern society adversely impacting the wider population more than ever before. The accurate inference of stress may result in the possibility for personalised interventions. However, individual differences between people limits the generalisability of machine learning models to infer emotions as people's physiology wh...
Abstract
—The proliferation of mobile sensor technologies
makes it possible for retailers to understand customers’ behavior
as they visit their stores, which in turns could help improving
customers’ shopping experiences. In this paper, we present a
novel quantitative approach to convey a collective sense of
shopping places. The data was collected a...
Abstract—The Retail industry is being heavily disrupted
by technology such as IoT, and the spread of smart phones
sensor technologies which creates infinite possibilities specially
for merchants to figure out their customers actions and habits
while visiting their shops. This gives sights on how to enhance
the customers shopping experiences. In thi...
Given the prominent role that smartphones have in everyday life, research in the field has proliferated. From a theoretical perspective, problematic smartphone use (PSPU) is described as a multi-faceted phenomenon entailing a variety of dysfunctional manifestations (e.g., addictive, antisocial and dangerous use). To date, however, there is still a...
In recent years, machine learning has made leaps and bounds enabling applications with high recognition accuracy for speech and images. However, other types of data to which these models can be applied have not yet been explored as thoroughly. In particular, it can be relatively challenging to accurately classify single or multi-model, real-time se...