Background: The older population needs solutions for independent living and reducing the burden on caregivers while maintaining the quality and dignity of life.

Objective: The aim of this study was to design, develop, and evaluate an older adult health care app that supports trained caregivers (ie, formal caregivers) and relatives (ie, informal caregivers). We aimed to identify the factors that affect user acceptance of interfaces depending on the user’s role.

Methods: We designed and developed an app with 3 user interfaces that enable remote sensing of an older adult’s daily activities and behaviors. We conducted user evaluations (N=25) with older adults and their formal and informal caregivers to obtain an overall impression of the health care monitoring app in terms of user experience and usability. In our design study, the participants had firsthand experience with our app, followed by a questionnaire and individual interview to express their opinions on the app. Through the interview, we also identified their views on each user interface and interaction modality to identify the relationship between the user’s role and their acceptance of a particular interface. The questionnaire answers were statistically analyzed, and we coded the interview answers based on keywords related to a participant’s experience, for example, ease of use and usefulness.

Results: We obtained overall positive results in the user evaluation of our app regarding key aspects such as efficiency, perspicuity, dependability, stimulation, and novelty, with an average between 1.74 (SD 1.02) and 2.18 (SD 0.93) on a scale of −3.0 to 3.0. The overall impression of our app was favorable, and we identified that “simple” and “intuitive” were the main factors affecting older adults’ and caregivers’ preference for the user interface and interaction modality. We also identified a positive user acceptance of the use of augmented reality by 91% (10/11) of the older adults to share information with their formal and informal caregivers.

Conclusions: To address the need for a study to evaluate the user experience and user acceptance by older adults as well as both formal and informal caregivers regarding the user interfaces with multimodal interaction in the context of health monitoring, we designed, developed, and conducted user evaluations with the target user groups. Our results through this design study show important implications for designing future health monitoring apps with multiple interaction modalities and intuitive user interfaces in the older adult health care domain.

The adoption of blockchain in various industries is gaining more popularity, especially in the energy industry. With the increase of distributed energy resources (DER), energy users can generate, store, and trade their resources with others. Utility companies or energy users are influenced by blockchain-based peer-To-peer (P2P) energy trading markets. Blockchain adds transparency and immutability to the involved transactions. Smart contracts in blockchain automatically execute when the conditions are met without any third-party intervention. Motivated by these benefits, in this paper an energy trading framework is developed using Ethereum smart contracts. Energy users can trade their excess energy or buy energy using the smart contract functions. Smart contract written in solidity is compiled and deployed using remix with injected metamask provider. Ganache is used to create accounts and these accounts are imported to metamask for signing transactions. We also discuss alternative methods for smart contract deployment. Computational cost analysis is performed by evaluating the gas consumption analysis for the smart contract functions.

Real-time anomaly detection in real-time energy consumption helps identify the technical and infrastructure issues and events that result in significant energy waste and provides the end users feedback to address the issues, which reduces drift operation costs and saves energy in the building. This study proposes deep learning reconstruction models to detect anomalies in daily energy consumption data for nine school buildings. We evaluated the performance of three proposed models, stacked RNN-LSTM autoencoder, CNN-LSTM autoencoder, and LSTM Variational Autoencoder (VAE), to learn the features of normal consumption in an unsupervised manner and detect anomalies based on reconstruction error. We used Exponential Moving Average (EMA) and static threshold to detect local and global anomalies. The experimental results demonstrate that the local CNN-LSTM autoencoder performs better than the local Stacked Autoencoder(AE), with RMSE values ranging between 8-13% for electricity and 11-19% for district heating compared to 12-17% and 15-34% resulting from AE model, respectively. Local LSTM-Variational Autoencoder (VAE) outperformed both methods, with RMSE 4-6% for electricity and 5-7% for district heating. LSTM-VAE trained model on grouped training datasets of schools with similar energy consumption and building profiles has improved the local model by lowering RMSE values to 2-3% for electricity and 3-4% in district heating.

Developments such as the increasing electrical energy demand, growth of renewable energy sources, cyber–physical security threats, increased penetration of electric vehicles (EVs), and unpredictable behavior of prosumers and EV users pose a range of challenges to the electric power system. To address these challenges, a decentralized system using blockchain technology and machine learning techniques for secure communication, distributed energy management and decentralized energy trading between prosumers is required. Blockchain enables secure distributed trust platforms, addresses optimization and reliability challenges, and allows P2P distributed energy exchange as well as flexibility services between customers. On the other hand, machine learning techniques enable intelligent smart grid operations by using prediction models and big data analysis. Motivated from these facts, in this review, we examine the potential of combining blockchain technology and machine learning techniques in the development of smart grid and investigate the benefits achieved by using both techniques for the future smart grid scenario. Further, we discuss research challenges and future research directions of applying blockchain and machine learning techniques for smart grids both individually as well as combining them together. The identified areas that require significant research are demand management in power grids, improving the security of grids with better consensus mechanisms, electric vehicle charging systems, scheduling of the entire grid system, designing secure microgrids, and the interconnection of different blockchain networks.

The growing population and demand for new public buildings contribute to increased energy consumption and greenhouse emissions. In Sweden, the largest amount of energy is consumed in school buildings, i.e., where schools form the highest number of public properties (30 million m2). In total, schools consumed 4 222 GWh of district heating and about 3 GWh of electricity for heating and other purposes in 2020. These figures lead to the realization of the need to apply effective measures to meet the European Green Deal target for 2030. Accurately forecasting energy usage is important for all stakeholders to conduct economic analysis and optimize decision-making. It is equally important in maintenance operations to allocate resources and enable the staff and students to adjust their behaviours and address the issues in buildings where peak forecasts occur. This paper develops and evaluates a power and district heating consumption for a single day and multiple days forecasting using Multivariate Recurrent Neural Network (RNN)-Long-Short term memory (LSTM) and convolutional neural networks (CNNs) and Autoencoders (AE), using daily real consumption data of six public schools provided by Skelefteå municipality in Sweden. The experimental results demonstrate that the hybrid model CNN-LSTM has achieved good accuracy compared to others, with RMSE and nRMSE error between 18%-25% and 5%-6% for electricity, respectively, and between 20%-30% RMSE and 5% nRMSE for district heating.

Sleep is an essential activity that affects an individual’s health and ability to perform Activities of Daily Living (ADL). Inadequate sleep reduces cognitive capacity and leads to health-related issues such as cardiovascular diseases. Sleep disorders are more prevalent in older adults. Therefore, it is essential to recognize sleep patterns and support older adults and their caregivers. In our study, we collect data in real-world unconstrained and non-intrusive environments. This paper presents a novel sleep activity recognition method using motion sensors for recognizing nighttime and daytime sleep, which can further enable the development of insightful healthcare applications. The research objectives are to evaluate the application of using Multi-Armed Bandit methods to (i) learn normal sleep patterns, (ii) evaluate sleep quality, and (iii) detect anomalies in sleep activity for 11 elderly participants living in single-resident smart homes. We evaluate the performance of Thompson Sampling, Random Selection, and Upper Confidence Bound MAB methods. Thompson Sampling outperformed the other two methods. Our findings show most elderly participants slept between 6 and 8 hours with 85% sleep efficiency and up to 3 awakenings per night.

IoT-enabled innovative elderly healthcare facilitated by machine learning (ML) can address the challenges pertaining to the global aging population. For instance, it can enable the early detection of debilitating conditions such as Alzheimer's and dementia. This paper addresses this challenge by developing IoT and ML-based methods to recognize changes in long-term activities of daily living (ADLs) that may lead to the conditions mentioned above. In particular, we gather real-world long-term (approx. three years) data from 6 real-life single-resident elderly smart homes in Sweden, equipped with motion sensors in each room; and use unsupervised ML methods incorporating K-means clustering and local outlier factor to recognize changes in long-term behaviour efficiently. Our results have shown that K-means show similar performance in identifying outliers over all datasets while local outlier factorization fluctuates more but is more sensitive to identify small changes in living conditions. We foresee that our methods to detect long-term behaviour changes can support caregivers in carrying out their assessment for discovering the early onset of health conditions, thereby preventing further progression and providing timely treatment.

As the aging population increases, predictive health applications for the elderly can provide opportunities for more independent living, increase cost efficiency and improve the quality of health services for senior citizens. Human activity recognition within IoT-based smart homes can enable detection of early health risks related to mild cognitive impairment by providing proactive measurements and interventions to both the elderly and supporting healthcare givers. In this paper, we develop and evaluate a method to forecast activities of daily living (ADL) and detect anomalous behaviour using motion sensor data from smart homes. We build a predictive Multivariate long short term memory (LSTM) model for forecasting activities and evaluate it using data from six real-world smart homes. Further, we use Mahalanobis distance to identify anomalies in user behaviors based on predictions and actual values. In all of the datasets used for forecasting both duration of stay and level of activities using duration of activeness/stillness features, the max NMAE error was about 6%, the values show that the performance of LSTM for predicting the direct next activity versus the seven coming activities are close.

Background: One of the main challenges of health monitoring systems is the support of older persons in living independently in their homes and with relatives. Smart homes equipped with internet of things devices can allow older persons to live longer in their homes. Previous surveys used to identify sensor-based data sets in human activity recognition systems have been limited by the use of public data set characteristics, data collected in a controlled environment, and a limited number of older participants.

Objective: The objective of our study is to build a model that can learn the daily routines of older persons, detect deviations in daily living behavior, and notify these anomalies in near real-time to relatives.

Methods: We extracted features from large-scale sensor data by calculating the time duration and frequency of visits. Anomalies were detected using a parametric statistical approach, unusually short or long durations being detected by estimating the mean (μ) and standard deviation (σ) over hourly time windows (80 to 355 days) for different apartments. The confidence level is at least 75% of the tested values within two (σ) from the mean. An anomaly was triggered where the actual duration was outside the limits of 2 standard deviations (μ−2σ, μ+2σ), activity nonoccurrence, or absence of activity.

Results: The patterns detected from sensor data matched the routines self-reported by users. Our system observed approximately 1000 meals and bathroom activities and notifications sent to 9 apartments between July and August 2020. A service evaluation of received notifications showed a positive user experience, an average score of 4 being received on a 1 to 5 Likert-like scale. One was poor, two fair, three good, four very good, and five excellent. Our approach considered more than 75% of the observed meal activities were normal. This figure, in reality, was 93%, normal observed meal activities of all participants falling within 2 standard deviations of the mean.

Conclusions: In this research, we developed, implemented, and evaluated a real-time monitoring system of older participants in an uncontrolled environment, with off-the-shelf sensors and internet of things devices being used in the homes of older persons. We also developed an SMS-based notification service and conducted user evaluations. This service acts as an extension of the health/social care services operated by the municipality of Skellefteå provided to older persons and relatives.

The need for smart healthcare tools and techniques has increased due to the availability of low-cost IoT sensors and devices and the growing aging population in the world. Early detection of health conditions such as dementia and Parkinsons are important for treatment and medication. Out of the many symptoms of such health conditions, one critical behavior is sleep activity changes. In this paper, we evaluate and apply an unsupervised machine learning: K-Means, to detect changes in long-term sleep behavior in the bedroom using smart-home motion sensors installed in 6 real-life single resident elderly homes for approximately three years. Our method analyses the transformation of clusters for a participant over three years, 2019, 2020, and 2021. This is done using three features: duration of stay, the hour of the day, and duration frequency. Data clustering is used to group durations of being in the bedroom at different hours of the day. This is done to see if there is a shift in these clusters for elderly persons with healthy aging and those developing health conditions like dementia and Parkinsons. We foresee that such methods to detect long-term behavior changes can support caregivers in carrying out their assessment for discovering the early onset of health conditions, thereby preventing further progression and providing timely treatment.

With the rapid growth of the Internet of Things (IoT) applications in smart regions/cities, for example, smart healthcare, smart homes/offices, there is an increase in security threats and risks. The IoT devices solve real-world problems by providing real-time connections, data and information. Besides this, the attackers can tamper with sensors, add or remove them physically or remotely. In this study, we address the IoT security sensor tampering issue in an office environment. We collect data from real-life settings and apply machine learning to detect sensor tampering using two methods. First, a real-time view of the traffic patterns is considered to train our isolation forest-based unsupervised machine learning method for anomaly detection. Second, based on traffic patterns, labels are created, and the decision tree supervised method is used, within our novel Anomaly Detection using Machine Learning (AD-ML) system. The accuracy of the two proposed models is presented. We found 84% with silhouette metric accuracy of isolation forest. Moreover, the result based on 10 cross-validations for decision trees on the supervised machine learning model returned the highest classification accuracy of 91.62% with the lowest false positive rate.

The rise in the aging population worldwide is already negatively impacting healthcare systems due to the lack of resources. It is envisioned that the development of novel Internet of Things (IoT)-enabled smart city healthcare systems may not only alleviate the stress on the current healthcare systems but may significantly improve the overall quality of life of the elderly. As more elderly homes are fitted with IoT, and intelligent healthcare becomes the norm, there is a need to develop innovative augmented reality (AR) based applications and services that make it easier for caregivers to interact with such systems and assist the elderly on a daily basis. This paper proposes, develops, and validates an AR and IoT-enabled healthcare system to be used by caregivers. The proposed system is based on a smart city IoT middleware platform and provides a standardized, intuitive and non-intrusive way to deliver elderly person's information to caregivers. We present our prototype, and our experimental results show the efficiency of our system in IoT object detection and relevant information retrieval tasks. The average execution time, including object detection, communicating with a server, and rendering the results in the application, takes on average between 767ms and 1,283ms.

Low-power wireless networks transmit at low output power and are hence susceptible to cross-technology interference. The latter may cause packet loss which may waste scarce energy resources by requiring the retransmission of packets. Jamming attacks are even more harmful than cross-technology interference in that they may totally prevent packet reception and hence disturb or even disrupt applications. Therefore, it is important to recognize such jamming attacks. In this paper, we present JamSense. JamSense extends SpeckSense, a system that is able to detect multiple sources of interference, with the ability to classify jamming attacks. As SpeckSense, JamSense runs on resource-constrained nodes. Our experimental evaluation on real hardware shows that JamSense is able to identify jamming attacks with high accuracy while not classifying Bluetooth or WiFi interference as jamming attacks.

Elderly population across the world is on the rise and municipalities along with caregivers are struggling to provide care due to limited resources. Sweden’s elderly population is set to grow significantly by 2050 where the number of people between 65–79 years and 80 years and over is expected to increase by 45% and 87% respectively. The same trend continues within Europe where 25% of the population will be over 65 years of age by the year 2020, and the age group of 65–80 years is predicted to rise by 40% from the year 2010 to 2030. The rise in elderly population has increased the stress on municipalities and caregivers; and has created the need for new healthcare solutions that are feasible, affordable and easily accessible to all. Smart homes equipped with sensors have already made life easier for those living in them for many decades now by providing home automation solutions. We are also witnessing an increase in the use of Information Communication Technologies (ICT) to assist elderly population and decrease in operational costs. ICT systems in assisting elderly population have an immense potential for providing in-home care to the elderly. The advent of the Internet of Things (IoT) with low-cost and prolific sensors has furthered this trend of home automation and monitoring solutions being used for elderly healthcare. Alongside, the field of ambient assisted homes has continuously paved the way for providing an improved quality of life for those in need such as patients with dementia or chronic conditions as well as elderly living alone at home.

Air pollution is a severe issue in many big cities due to population growth and the rapid development of the economy and industry. This leads to the proliferating need to monitor urban air quality to avoid personal exposure and to make savvy decisions on managing the environment. In the last decades, the Internet of Things (IoT) is increasingly being applied to environmental challenges, including air quality monitoring and visualization. In this paper, we present CAVisAP, a context-aware system for outdoor air pollution visualization with IoT platforms. The system aims to provide context-aware visualization of three air pollutants such as nitrogen dioxide (NO 2 ), ozone (O 3 ) and particulate matter (PM 2.5 ) in the city of Melbourne, Australia. In addition to the primary context as location and time, CAVisAP takes into account users’ pollutant sensitivity levels and color vision impairments to provide personalized pollution maps. Experiments are conducted to validate the system and results are discussed.

Air pollution is a growing global concern that affects the health and livelihood of millions of people worldwide. The advent of the Internet of Things (IoT) has made available a plethora of data sources that provide near real-time information on air pollution. Many studies and systems have taken advantage of data stemming from the IoT and have been dedicated to enhancing the monitoring and prediction of air quality, from a fairly analytical angle, often disregarding the user's perspective in processing and presenting this data. In this paper, we research and present a novel context-aware air quality monitoring and prediction system called My Air Quality Index (MyAQI). MyAQI takes into consideration user's context (e.g. health conditions, individual sensitivities and preferences) to tailor the visualisation and notifications. We propose a context model that is used to combine user's context with air pollution data to provide context-aware recommendations to the specific user. MyAQI also incorporates a prediction algorithm based on Long Short-Term Memory Neural Network (LSTM) to predict future air quality. MyAQI is implemented as a web-based application and has the capability to consume data from a wide range of data sources including IoT devices and open data sources (via Application Programming Interfaces (API)). We demonstrate the context-aware visualisation techniques implemented in MyAQI, which adapt to changing user's context, and validate the performance of the air quality prediction algorithm.

As the Internet of Things (IoT) becomes a reality, millions of devices will be connected to IoT platforms in smart cities. These devices will cater to several areas within a smart city such as healthcare, logistics, and transportation. These devices are expected to generate significant amounts of data requests at high data rates, therefore, necessitating the performance benchmarking of IoT platforms to ascertain whether they can efficiently handle such devices. In this article, we present our results gathered from extensive performance evaluation of the cloud-based IoT platform, FIWARE. In particular, to study FIWARE’s performance, we developed a testbed and generated CoAP and MQTT data to emulate large-scale IoT deployments, crucial for future smart cities. We performed extensive tests and studied FIWARE’s performance regarding vertical and horizontal scalability. We present bottlenecks and limitations regarding FIWARE components and their cloud deployment. Finally, we discuss cost-efficient FIWARE deployment strategies that can be extremely beneficial to stakeholders aiming to deploy FIWARE as an IoT platform for smart cities.

Exploiting future opportunities and avoiding problematic upcoming events is the main characteristic of a proactively adapting system, leading to several benefits such as uninterrupted and efficient services. In the era when IoT applications are a tangible part of our reality, with interconnected devices almost everywhere, there is potential to leverage the diversity and amount of their generated data in order to act and take proactive decisions in several use cases, smart waste management as such. Our work focuses in devising a system for proactive adaptation of behavior, named ProAdaWM. We propose a reasoning model and system architecture that handles waste collection disruptions due to severe weather in a sustainable and efficient way using decision theory concepts. The proposed approach is validated by implementing a system prototype and conducting a case study.

LoRa has emerged as a prominent technology for the Internet of Things (IoT), with LoRa Wide Area Network (LoRaWAN) emerging as a suitable connection solution for smartthings. The choice of the best location for the installation of gateways, as well as a robust network server configuration, are key to the deployment of a LoRaWAN. In this paper, we present an evaluation of Received Signal Strength Indication (RSSI) values collected from the real-life LoRaWAN deployed in Skellefteå, Sweden, when compared with the values calculatedby a Radio Frequency (RF) planning tool for the Irregular Terrain Model (ITM), Irregular Terrain with Obstructions Model (ITWOM) and Okumura-Hata propagation models. Five sensors are configured and deployed along a wooden bridge, with different Spreading Factors (SFs), such as SF 7, 10 and 12. Our results show that the RSSI values calculated using the RF planning tool for ITWOM are closest to the values obtained from the real-life LoRaWAN. Moreover, we also show evidence that the choice of a propagation model in an RF planning tool has to be made with care, mainly due to the terrain conditions of the area where the network and the sensors are deployed.

LoRaWAN has become popular as an IoT enabler. The low cost, ease of installation and the capacity of fine-tuning the parameters make this network a suitable candidate for the deployment of smart cities. In northern Sweden, in the smart region of Skellefteå, we have deployed a LoRaWAN to enable IoT applications to assist the lives of citizens. As Skellefteå has a subarctic climate, we investigate how the extreme changes in the weather happening during a year affect a real LoRaWAN deployment in terms of SNR, RSSI and the use of SF when ADR is enabled. Additionally, we evaluate two propagation models (Okumura-Hata and ITM) and verify if any of those models fit the measurements obtained from our real-life network. Our results regarding the weather impact show that cold weather improves the SNR while warm weather makes the sensors select lower SFs, to minimize the time-on-air. Regarding the tested propagation models, Okumura-Hata has the best fit to our data, while ITM tends to overestimate the RSSI values.

The stochastic nature of the cloud systems makes cloud quality of service (QoS) performance diagnosis and prediction a challenging task. A plethora of factors including virtual machine types, data centre regions, CPU types, time-of-the-day, and day-of-the-week contribute to the variability of the cloud QoS. The state-of-the-art methods for cloud performance diagnosis do not capture and model complex and uncertain inter-dependencies between these factors for efficient cloud QoS diagnosis and prediction. This paper presents ALPINE, a proof-of-concept system based on Bayesian networks. Using a real-life dataset, we demonstrate that ALPINE can be utilised for efficient cloud QoS diagnosis and prediction under stochastic cloud conditions

Cloud performance diagnosis and prediction is a challenging problem due to the stochastic nature of the cloud systems. Cloud performance is affected by a large set of factors such as virtual machine types, regions, workloads, wide area network delay and bandwidth. Therefore, necessitating the determination of complex relationships between these factors. The current research in this area does not address the challenge of modeling the uncertain and complex relationships between these factors. Further, the challenge of cloud performance prediction under uncertainty has not garnered sufficient attention. This paper proposes, develops and validates ALPINE, a Bayesian system for cloud performance diagnosis and prediction. ALPINE incorporates Bayesian networks to model uncertain and complex relationships between several factors mentioned above. It handles missing, scarce and sparse data to diagnose and predict stochastic cloud performance efficiently. We validate our proposed system using extensive real data and show that it predicts cloud performance with high accuracy of 91.93%.

The rapidly emerging Internet of Things supports many diverse applications including environmental monitoring. Air quality, both indoors and outdoors, proved to be a significant comfort and health factor for people. This paper proposes a smart context-aware system for indoor air quality monitoring and prediction called DisCPAQ. The system uses data streams from air quality measurement sensors to provide real-time personalised air quality service to users through a mobile app. The proposed system is agnostic to sensor infrastructure. The paper proposes a context model based on Context Spaces Theory, presents the architecture of the system and identifies challenges in developing large scale IoT applications. DisCPAQ implementation, evaluation and lessons learned are all discussed in the paper.

Opportunistic sensing advance methods of IoT data collection using the mobility of data mules, the proximity of transmitting sensor devices and cost efficiency to decide when, where, how and at what cost collect IoT data and deliver it to a sink. This paper proposes, develops, implements and evaluates the algorithm called CollMule which builds on and extends the 3D kNN approach to discover, negotiate, collect and deliver the sensed data in an energy- and cost-efficient manner. The developed CollMule software prototype uses Android platform to handle indoor air quality data from heterogeneous IoT devices. The CollMule evaluation is based on performing rate, power consumption and CPU usage of single algorithm cycle. The outcomes of these experiments prove the feasibility of CollMule use on mobile smart devices.

Forecasting energy consumption in buildings is a key step towards the realization of optimized energy production, distribution and consumption. This paper presents a data driven approach for analysis and forecast of aggregate space and water thermal load in buildings. The analysis and the forecast models are built using district heating data unobtrusively collected from ten residential and commercial buildings located in Skellefteå, Sweden. The load forecast models are generated using supervised machine learning techniques, namely, support vector machine, regression tree, feed forward neural network, and multiple linear regression. The model takes the outdoor temperature, historical values of heat load, time factor variables and physical parameters of district heating substations as its input. A performance comparison among the machine learning methods and identification of the importance of models input variables is carried out. The models are evaluated with varying forecast horizons of every hour from 1 up to 48 hours. Our results show that support vector machine, feed forward neural network and multiple linear regression are more suitable machine learning methods with lower performance errors than the regression tree. Support vector machine has the least normalized root mean square error of 0.07 for a forecast horizon of 24 hour.

Forecasting the thermal load demand for residential buildings assists in optimizing energy production and developing demand response strategies in a smart grid system. However, the presence of a large number of factors such as outdoor temperature, district heating operational parameters, building characteristics and occupant behavior, make thermal load forecasting a challenging task. This paper presents an efficient model for thermal load forecast in buildings with different variations of heat load consumption across both winter and spring seasons using a Bayesian Network. The model has been validated by utilizing the realistic district heating data of three residential buildings from the district heating grid of the city of Skellefteå, Sweden over a period of four months. The results from our model shows that the current heat load consumption and outdoor temperature forecast have the most influence on the heat load forecast. Further, our model outperforms state-of-the-art methods for heat load forecasting by achieving a higher average accuracy of 77.97% by utilizing only 10% of the training data for a forecast horizon of 1 hour.

The ageing population worldwide is constantly rising, both in urban and regional areas. There is a need for IoT-based remote health monitoring systems that take care of the health of elderly people without compromising their convenience and preference of staying at home. However, such systems may generate large amounts of data. The key research challenge addressed in this paper is to efficiently transmit healthcare data within the limit of the existing network infrastructure, especially in remote areas. In this paper, we identified the key network requirements of a typical remote health monitoring system in terms of real-time event update, bandwidth requirements and data generation. Furthermore, we studied the network communication protocols such as CoAP, MQTT and HTTP to understand the needs of such a system, in particular the bandwidth requirements and the volume of generated data. Subsequently, we have proposed IReHMo - an IoT-based remote health monitoring architecture that efficiently delivers healthcare data to the servers. The CoAP-based IReHMo implementation helps to reduce up to 90% volume of generated data for a single sensor event and up to 56% required bandwidth for a healthcare scenario. Finally, we conducted a scalability analysis to determine the feasibility of deploying IReHMo in large numbers in regions of north Sweden.

There is a growing emphasis to find alternative non-traditional ways to manage patients to ease the burden on health care services largely fuelled by a growing demand from sections of population that is ageing. In-home remote patient monitoring applications harnessing technological advancements in the area of Internet of things (IoT), semantic web, data analytics, and cloud computing have emerged as viable alternatives. However, such applications generate large amounts of real-time data in terms of volume, velocity, and variety thus making it a big data problem. Hence, the challenge is how to combine and analyse such data with historical patient data to obtain meaningful diagnoses suggestions within acceptable time frames (considering quality of service (QoS)). Despite the evolution of big data processing technologies (e.g. Hadoop) and scalable infrastructure (e.g. clouds), there remains a significant gap in the areas of heterogeneous data collection, real-time patient monitoring, and automated decision support (semantic reasoning) based on well-defined QoS constraints. In this study, the authors review the state-of-the-art in enabling QoS for remote health care applications. In particular, they investigate the QoS challenges required to meet the analysis and inferencing needs of such applications and to overcome the limitations of existing big data processing tools.

The cloud computing paradigm is continually evolving, and with it, the size and the complexity of its infrastructure. Assessing the performance of a cloud environment is an essential but an arduous task. Further, the energy consumed by data centers is steadily increasing and major components such as the storage systems need to be more energy efficient. Cloud simulation tools have proved quite useful to study these issues. However, these simulation tools lack mechanisms to study energy efficient storage in cloud systems. This paper contributes in the area of cloud computing by extending the widely used cloud simulator CloudSim. In this paper, we propose CloudSimDisk, a scalable module for modeling and simulation of energy-aware storage in cloud systems. We show how CloudSimDisk can be used to simulate energy-aware storage, and can be extended to study new algorithms for energy-awareness in cloud systems. Our simulation results proved to be in accordance with the analytical models that were developed to model energy consumption of hard disk drives in cloud systems. The source code of CloudSimDisk is also made available for the research community for further testing and development.

Mobile devices have become an integral part of our daily lives. Applications running on these devices may avail storage and compute resources from the cloud(s). Further, a mobile device may also connect to heterogeneous access networks (HANs) such as WiFi and LTE to provide ubiquitous network connectivity to mobile applications. These devices have limited resources (compute, storage and battery) that may lead to servicedisruptions. In this context, mobile cloud computing enables offloading of computing and storage to the cloud. However, applications running on mobile devices using clouds and HANs are prone to unpredictable cloud workloads, network congestion and handoffs. To run these applications efficiently the mobile device requires the best possible cloud and network resources while roaming in HANs. This paper proposes, develops and validates a novel system called M2C2 which supports mechanismsfor: i.) multihoming, ii.) cloud and network probing, and iii.) cloudand network selection. We built a prototype system and performed extensive experimentation to validate our proposed M2C2. Our results analysis shows that the proposed system supports mobility efficiently in mobile cloud computing.

Cloud of Things (CoT) is a vision inspired by Internet of Things (IoT) and cloud computing where the IoT devices are connected to the clouds via the Internet for datastorage, processing, analytics and visualization. CoT ecosystem will encompass heterogeneous clouds, networks and devices to provide seamless service delivery, for example, in smart cites. To enable efficient service delivery, there is a need to guarantee a certain level of quality of service from both cloud and networksperspective. This paper discusses the Cloud of Things, cloud computing, networks and new quality of service management research issues arising due to realisation of CoT ecosystem vision.

Emergency management systems deal with the dynamic processing of data, where response teams must continuously adapt to the changing conditions at the scene of the emergency. Response teams must make critical decisions in highly demanding situations using large volumes of sensor data. Mobile devices have limited processing, storage, and battery resources; therefore, the sensed data from the scene of the emergency must be transmitted and processed quickly using the best available networks and clouds. Mobile cloud computing (MCC) is expected to play a critical role in the computation and storage offloading of sensor data to the best available clouds. However, applications running on mobile devices using clouds and heterogeneous access networks such as Wi-Fi and 3G are prone to unpredictable cloud workloads, network congestion, and handoffs. This article presents M2C2, a system for mobility management in MCC, that supports mechanisms for multihoming, cloud and network probing, and cloud and network selection. Through a prototype implementation and experiments, the authors show that M2C2 supports mobility efficiently in MCC scenarios such as emergency management.

The rapid increase in energy demand requires effective measures to plan and optimize resources for efficient energy production within a smart grid environment. This paper presents a data driven approach to forecasting heat load for multi- family apartment buildings in a District Heating System (DHS). The forecasting model is built using six and eleven weeks of data from five building substations. The external factors and internal factors influencing the heat load in substations are parameters used as our model’s input. Short-term forecast models are generated using four supervised Machine Learning (ML) techniques: Support Vector Regression (SVR), Regression Tree, Feed Forwards Neural Network (FFNN) and Multiple Linear Regression (MLR). Performance comparison among these ML methods was carried out. The effects of combining the internal and external factors influencing heat load at substations was studied. The models are evaluated with varying horizon up to 24-hours ahead. The results show that SVR has the best accuracy of 5.6% MAPE for the best-case scenario.

Human activity recognition using sensing technology is crucial in achieving pervasive and ubiquitous computing paradigms. It can be applied in many domains such as health-care, aged-care, personal-informatics, industry, sports and military. Activities of daily living (ADL) are those activities which users perform in their everyday life and are crucial for day-to-day living. Human users perform a large number of these complex activities at home, office and outdoors. This thesis proposes, develops and validates a mechanism which combines knowledge and data-driven approaches for the recognition of complex ADLs. This thesis focuses on the challenging task of capturing data from sensors and recognizing user’s complex activities which are concurrent, interleaved or varied-order in nature. We propose, develop and validate mechanisms and algorithms to infer complex activities which are concurrent and interleaved and build a test-bed which enables the sharing of this information on social interaction tools (SITs). In particular, we propose, develop and validate a novel context-driven activity theory (CDAT) to build atomic and complex activity definitions using domain knowledge and activity data collected from real-life experimentation. We develop a novel situation- and context-aware activity recognition system (SACAAR) which recognizes complex activities which are concurrent and interleaved and validate it by performing extensive real-life experimentation. We build a novel context-driven complex activity recognition algorithm to infer complex concurrent and interleaved activities. We build and validate an extended-SACAAR system which utilizes probabilistic and Markov chain analysis to discover complex activity signatures and associations between atomic activities, context attributes and complex activities. Our proposed algorithms achieve an average accuracy of 95.73% for complex activity recognition while maintaining Complex Activity Recognition and Context Validation within Social Interaction Tools computational efficiency. We build an ontological extension to SACAAR called semantic activity recognition system (SEMACT) which is based on CDAT and evaluate it using ontological reasoning for activity recognition. It achieves a high accuracy of 94.35% for the recognition of complex activities which are both concurrent and interleaved.We propose and develop novel mechanisms for context validation within SITs. Users might be keen on sharing their activity related information with family and friends. The wide scale use of SITs has made anytime, anywhere communication of user’s activities with family, friends and other interested parties possible. It is important that any activity-based updates based on user’s current context shared on these SITs are up-to-date, correct and not misleading. This thesis further focuses on the validation of context such as activity-based updates within social interaction tools. We validate the correctness and freshness of activity-based updates on SITs for a user by matching them against the inferred activity information by our SACAAR system. This provides the user with a mechanism to always have a correct and timely update which does not mislead their friends, family and other followers. We perform extensive experimentation and our validation algorithm is able to detect 81% of the incorrect updates made to social interaction tools. We propose, develop and implement a novel context-aware Twitter validator which checks and validates user’s tweets on Twitter. During the course of the thesis work, 9 peer-refereed international conference papers and 1 journal paper have been produced.

One of the biggest challenges in the field of activity recognition is gathering training data for building activity inference models. To address this problem, we have developed an online activity toolkit for gathering activity data from online users. We use this data to build activity definitions for use in our system which is based on Context-Driven Activity Theory. We use Markov chain analysis to assign weights to activities and context attributes of a complex activity as well as to build activity signatures based on transition and path probabilities. Our demo is intended to show how complex activities and associated atomic activities and context attributes can be described using an activity toolkit. The toolkit is used to take input from users available online and the results analysis of different complex activities can be viewed online in near real-time using the graphical user interface (GUI).

Decision support systems (DSS) are beginning to use content sourced from social networks such as Twitter to provide decision makers with information to make timely and critical decisions. Misleading information obtained from Twitter can lead to adverse outcomes as well as cause trust issues within DSSs. In this paper, we propose and investigate a context-aware Twitter validator (CATVal) system to validate credibility and authenticity of Twitter content at run-time for use in DSS. We build, store and update a credibility index for Twitter users and verify user's context information each time a user tweets. The proposed system can benefit a DSS by providing credible and dependable information while detecting misleading and false information sourced from Twitter and possible other social media.

This paper proposes a context driven activity theory (CDAT) and reasoning approach for recognition of concurrent and interleaved complex activities of daily living (ADL) which involves no training and minimal annotation during the setup phase. We develop and validate our CDAT using the novel complex activity recognition algorithm on two users for three weeks. The algorithm accuracy reaches 88.5% for concurrent and interleaved activities. The inferencing of complex activities is performed online and mapped onto situations in near real-time mode. The developed systems performance is analyzed and its behavior evaluated

This paper proposes a novel multiple activity recognition and reasoning approach where we use on-body sensor information along with other context information to infer mobile user activities which are both concurrent and interleaved. We develop and validate an activity algebra and a complex activity recognition algorithm for detecting these multiple activities. Activities are mapped onto situations using spatio-temporal analysis. We validate our approach by implementing a prototype and performing experiments in different scenarios using mobile devices

Social networks constitute an important research area where users are involved in social interactions and inform each other of activities they perform. In this paper a complex activity recognition system (SEMACT) is proposed, built and validated. Different activities performed by users form an activity hierarchy. We perform semantic reasoning by using ontological constructs and rules to recognize both concurrent and interleaved complex activities at different levels of granularity of this activity hierarchy. Different application domains require activity recognition systems to define and recognize activities at different levels of granularity. Our system tackles this problem by recognizing complex activities which are then shared across application domains using a generic API. A test-bed and prototype are built to validate our SEMACT system. Extensive experimentation is performed which demonstrates that high accuracy of 94.35% was achieved for the recognition of complex activities both concurrent and interleaved within computationally feasible time

This paper proposes a situation and context-aware complex activity recognition system where we use on-body sensor information along with other context information to infer mobile user activities which are both concurrent and interleaved. We develop and validate our complex activity recognition algorithm for detecting these multiple complex activities. Activities are mapped onto situations using spatio-temporal analysis. We further build a test-bed in the social-networking domain to test and validate our approach in different scenarios using mobile devices

This paper presents Crystal Presence (CrysP) approach wher- e we fuse presence and activity in the realm of social networking. CrysP functions on the basis of the activity-infused multi-faceted presence information. This information is derived from user's involvement in multiple activities at any point in time. We propose and develop the CrysP System (CrysPSys) to determine CrysP from the user and his/her environmental context information (mainly relating to user activity, moods/emotions and cognition/thoughts) and then sharing the relevant CrysP with the appropriate devices, services and social-networks (corporate, personal and interest networks) and blogs (text, micro, video, photo and voice). We also highlight the benefits and challenges faced in developing such a system. This paper proposes the architecture and its test-bed and prototype implementation.

Humans are engaging in information exchange related to their activities using a wide range of social interaction tools. There is a need to automate this process of exchanging information as manual updates are time consuming and intrusive.In our research, we aim to solve the problem of detecting and inferring a user’s multiple activity infused presence information and then share this with the correct social interaction tool. Humans also inherently multitask in varying time spans and their higher level activities can be formed by different types of lower level activities which can be shared with different social interaction tools accordingly. We propose a system which can infer these multiple activities fromwearable sensors as well as other context information, then determine a user’s multiple presence information, i.e. crystal presence based on these activities by spatio-temporal analysis and then automatically share the correct presence information with the correct social-interaction tool automatically.

With the growing popularity of social networking, traditional Internet Service Providers (ISPs) and telecom operators have both started exploring new opportunities to boost their revenue streams. The efforts have facilitated consumers to stay connected to their favorite social networks,be it from an ISP portal or a mobile device. The use of Web 2.0 technologies and converged communication tools has further led to a rise in both user-generated content as well as contextual information (i.e. rich presence) about users - including their current location, availability, interests and moods. In this evolving landscape, social networking players need to innovate for value-centric usage models that increase customer stickiness,along with business models to monetize the social media. To this end, we present R-U-In? - an activity-oriented social networking system for users to collaborate and participate in activities of mutual interest. Activities can be initiated and scheduled on-demand and be as ephemeral as the user interests themselves. R-U-In? leverages contextual modeling and reasoning techniques to enable "social search" based on real-time user interests and finds potential matches for the proposed activity. Further, it exploits next-generation presence and communication technologies to manage the entire activity lifecycle in real-time. Initial survey results, based on a prototype implementation of R-U-In?, attest to the promise of realtime activity-oriented social networking - both in terms of an effective collaboration tool for value-oriented social networking users and an enhanced end-user experience.

UMS can be described as a system that allows for communication between users via a number of communication technologies over heterogeneous network infrastructures[1]. It integrates networking technologies such as Ethernet, ATM, IEEE 802.11, GSM and UMTS alongwith various devices such as laptops, tablet PCs, desktops, mobile phones, smartphones, PDAs, fax machines and landline phones. In other words, it allows the users to access their different types of messages by logging into one inbox from these different devices[2]. The user is able to create, modify, access and administer messages belonging to various formats on a single device to which he/she has immediate access. This form of 'anywhere', 'anytime' access to 'anykind' of messages enables the UMS to become ubiquitous and pervasive[3, 4].