Text-To-Speech (TTS) generation plays a crucial role in human-robot interaction by allowing robots to communicate naturally with humans. Researchers have developed various TTS models to enhance speech generation. More recently, diffusion models have emerged as a powerful generative framework, achieving state-of-the-art performance in tasks such as image and video generation. However, their application in TTS has been limited by its slow inference speeds due to their iterative denoising process. Previous work has applied diffusion models to Mel-Spectrograms with an additional vocoder to convert them into waveforms. To address these limitations, we propose LatentSpeech, a novel diffusion-based TTS framework that operates directly in a latent space. This space is significantly more compact and information-rich than raw Mel-Spectrograms. Furthermore, we introduce an alternative latent space of Pseudo-Quadrature Mirror Filters (PQMF), which decomposes speech into multiple subbands. By leveraging PQMF’s near-perfect waveform reconstruction capability, LatentSpeech eliminates the need for a separate vocoder and reduces both model size and inference time. Our PQMF-based LatentSpeech model reduces inference time by 45% and model size by 77% compared to Mel-Spectrogram diffusion models. On benchmark datasets, it achieves 25% lower WER and 58% higher MOS using the same training data. These results highlight LatentSpeech as an efficient, high-quality TTS solution for real-time and human-robot interaction. Code and models are available here.

Traditionally, body dissatisfaction interventions have been designed with a focus on females from Western cultures. However, with growing research indicating that body dissatisfaction is experienced across society, regardless of gender and cultural background, it is increasingly important that future interventions incorporate a broader range of socio-cultural experiences. We conducted a two-phase co-design study with thirteen participants (seven females, six males), aged 18-24, from diverse cultural backgrounds. Phase 1 aimed to understand the influencing factors that frame the development of body image perceptions. Drawing on insights from Phase 1, Phase 2, then explicitly focused on gathering design insights for digital tools for body dissatisfaction interventions. Four narrative design concepts were used to provoke discussions and ideate around potential digital interventions. Through this paper, we contribute unique insights into the experiences and digital intervention preferences of underrepresented people in body image research and highlight future directions to create more inclusive digital interventions.

With increased deployment of IoT application on cloud platforms, assessing the performance of such application is an open problem. Currently, approaches are limited to legacy database-based applications and does not cater for the needs of IoT applications. This paper proposes, implements and validates a framework namely, IoTQGen, that can generate situation-based queries to conduct performance evaluation of IoT application hosted by cloud IoT middleware platform. The framework comprises: (i) a model to capture the query requirements of IoT applications; (ii) a data generator to generate IoT data based on specified configuration; and (iii) a set of queries designed to represent data analytic IoT applications. The framework supports different query types that can be typically used to represent and address IoT application scenarios. An important functionality of the framework is its ability to issue queries based on dynamic changes in the state of IoT entities (situations). The framework is evaluated based on two smart city use cases to highlight how the framework can be used to generate complex and dynamic queries tailored for IoT application scenarios.

Clinical diagnosis of dementia is typically delayed and limited in accuracy, despite assessing cognitive impairments through neurological exams, brain imaging, and functional tests such as Activities of Daily Living. Recent advances in digital health and multimodal behavioral analytics are beginning to provide more sensitive, objective, unobtrusive and continuous assessment of functional abilities while people remain in a familiar setting such as their home, at work, or in the community. These new techniques analyze natural behaviors like speech, language, gait, eye gaze, hand movements, and facial expressions. This review compares existing clinical assessment methods with emerging behavioral analytic techniques that offer powerful capabilities for earlier and more precise diagnosis of dementia. It summarizes state-of-the-art multimodal behavioral analytics research for dementia diagnosis, including predictive features present in different human behaviors and the performance advantages of combining them into multimodal diagnostic systems. The many behavioral predictors documented in the literature are interpreted as deriving from six common cognitive deficits that are well known hallmarks of dementia. The review also discusses long-term trends in multimodal behavioral analytics research, and the five main areas requiring future work to realize the promise of earlier, more accurate, and widely accessible dementia diagnostic systems.

The significant advances in the Internet of Things (IoT) have led to IoT applications being widely used in various scenarios ranging from smart city, smart farming, to Industrial IoT (IIoT) solutions. With the explosion of IoT application development, IoT middleware platforms are increasingly being used for hosting such IoT applications. This has given rise to the need for developing benchmarking solutions to analyze and test the performance of different middleware platforms that host these IoT applications. To develop such benchmarks, there are a number of key components that are needed. One of these components is an IoT dataset. To generate such datasets, representing IoT application requirements in a general and formal way is important. In this paper, we propose a framework to model the IoT Applications Requirements and enable Data Generation(ARDG-IoT). The framework supports a formal way to capture IoT application requirements and use these requirements to generate IoT data that can be used to create benchmarks for different IoT middleware platforms. ARDG-IoT consists of our proposed model, IoTSySML, which captures the application requirements, and an IoT data simulator tool, which is used to generate IoT data. We present an evaluation of the framework using a real world Industrial IoT application case study.

The traditional brick-and-mortar retail stores seek options to expand when they reach a certain point of growth. Such expansions can be in the form of a bigger retail store or opening additional retail stores. Most businesses leverage heuristics-based decisions to expand (often driven by financial performance). Existing literature on retail store expansion decisions fails to provide a complete view of factors that can influence the decision-making process. To address this gap in literature, this paper aims to identify the key factors that influence retail store expansion decisions. Our case study-based methodology is developed around a decade of data collected from 500 service-based brick-and-mortar retail stores operating in Australia and New-Zealand. Through an in-depth analysis of the literature and insights drawn from 10 years of operational data, we establish a list of factors that need to be considered to support retail store expansion decisions and drill down on the key factors that influence the decision-making process. Lessons learnt from the analysis of the data concludes the paper.

Smart mobile devices coupled with the Internet of Things (IoT) and Artificial Intelligence (AI) have emerged as a key enabler of modern digital health applications. While cloud computing is now a well established paradigm for analysing IoT captured data in mobile health applications, on-board analysis of data using AI approaches such as Deep Learning (DL) is gaining significant momentum. This is driven primarily by advances in on-board resources enabling modern mobile devices to execute complex DL models, while also offering improved response time and accuracy for rapid decision-making, and enhanced user privacy. While the number of mobile digital health applications that use IoT and DL is increasing, progress is currently impeded by a lack of framework for profiling and evaluating the performance of DL models on mobile devices. To this end, we propose MobDL, a framework for profiling and evaluating DL models running on smart mobile devices. We present the architecture of this framework and devise a novel evaluation methodology for conducting quantitative comparisons of various DL models running on mobile devices. Three diverse digital health applications using heterogeneous data (e.g. image, time series) are introduced. We conduct extensive experimental evaluations using several DL models that have been developed using the data sets obtained for the three digital health applications to validate the effectiveness of the proposed MobDL framework.

The advancement in mobile technologies, especially smartphones, has brought a huge change to data collection methods in recent years. The ubiquity of smartphones makes them a useful tool for collecting data in real-time. Ecological Momentary Assessment (EMA) is an effective data collection method that involves repeated sampling of an individual's behavior, symptoms, and experiences in real-time in their natural environment, maximizing ecological validity. However, the burden that smartphone-based EMA imposes on individuals could result in high numbers of dropouts and limit its use in research and clinical practice. Investigating and identifying the reasons and factors that contribute to the individual's dropout could highly benefit the outcomes of EMA studies. This study applies the Model of Technology Appropriation (MTA) as a theoretical lens to explain the process of individual's appropriation of smartphones for the EMA data collection. We report the results of our user study on a group of volunteers.

This article reviews two decades of research in topics in Information Visualisation emerging from the Data Visualisation and Immersive Analytics Lab at Monash University Australia (Monash IA Lab). The lab has been influential with contributions in algorithms, interaction techniques and experimental results in Network Visualisation, Interactive Optimisation and Geographic and Cartographic visualisation. It has also been a leader in the emerging topic of Immersive Analytics, which explores natural interactions and immersive display technologies in support of data analytics. We reflect on advances in these areas but also sketch our vision for future research and developments in data visualisation more broadly.

With increasing electricity demand, implementing smart energy saving strategies in residential houses becomes more important than ever before. Real-time and context-aware recommendation systems can provide residents with useful information to monitor their energy consumption, predict future usage, and recommend shifting their load to another time period. This study aims to improve the management of residential loads at the consumer level while at the same time providing energy providers with an overview of energy usage at the household and substation levels. This includes real time, historical and predicted usage. In this paper we introduce a Context-Aware Smart Energy Recommender (CASER) that consists of a client-side mobile app and a backend web portal. The implementation uses alternative visualization techniques to provide electricity usage information and recommendations for the consumers and the energy providers. The accuracy of our context-aware prediction was evaluated using publicly available smart meter data.

The global urbanization imposes unprecedented pressure on urban infrastructure and public resources. The population explosion has made it challenging to satisfy the daily needs of urban residents. 'Smart City' is a solution that utilizes different types of data collection sensors to help manage assets and resources intelligently and more efficiently. Under the Smart City umbrella, the primary research initiative in improving the efficiency of car-hailing services is to predict the citywide passenger demand to address the imbalance between the demand and supply. However, predicting the passenger demand requires analysis on various data such as historical passenger demand, crowd outflow, and weather information, and it remains challenging to discover the latent relationships among these data. To address this challenge, we propose to improve the passenger demand prediction via learning the salient spatial-temporal dynamics within a reinforcement learning framework. Our model employs an information selection mechanism to focus on the most distinctive data in historical observations. This mechanism can automatically adjust the information zone according to the prediction performance to find the optimal choice. It also ensures the prediction model to take full advantage of the available data by introducing the positive and excluding the negative correlations. We have conducted experiments on a large-scale real-world dataset that covers 1.5 million people in a major city in China. The results show our model outperforms state-of-the-art and a series of baselines by a large margin.

Taxonomy learning is an important task for knowledge acquisition, sharing, and classification as well as application development and utilization in various domains. To reduce human effort to build a taxonomy from scratch and improve the quality of the learned taxonomy, we propose a new taxonomy learning approach, namedTaxoFinder. TaxoFinder takes three steps to automatically build a taxonomy. First, it identifies domain-specific concepts from a domain text corpus. Second, it builds a graph representing how such concepts are associated together based on their co-occurrences. As the key method in TaxoFinder, we propose a method for measuring associative strengths among the concepts, which quantify how strongly they are associated in the graph, using similarities between sentences and spatial distances between sentences. Lastly, TaxoFinder induces a taxonomy from the graph using a graph analytic algorithm. TaxoFinder aims to build a taxonomy in such a way that it maximizes the overall associative strengths among the concepts in the graph to build a taxonomy. We evaluate TaxoFinder using gold-standard evaluation on three different domains:emergency management for mass gatherings,autism research, anddiseasedomains. In our evaluation, we compare TaxoFinder with a state-of-the-art subsumption method and show that TaxoFinder is an effective approach significantly outperforming the subsumption method.

The ubiquity of mobile devices coupled with the advances in Internet of Things (IoT) technologies has led to the development of large-scale applications that can collect information about people and their environments in real-time. Such applications are referred to as Mobile Crowdsensing (MCS). In MCS, tasks are allocated to participants (mobile devices) by a remote server according to the application requirements. The key challenge is reducing the energy consumption of the participating mobile devices. One of the effective approaches to reduce energy consumption of MCS applications is to improve efficiency of task allocation. An efficient task allocation approach can optimize several aspects of MCS applications such as task coverage (minimum number of participants required for a MCS task), data quality, and sensing costs. In this paper, we propose a novel Context-Aware Task Allocation (CATA) approach that aims to allocate sensing tasks to the best participant set while improving energy efficiency in MCS applications. Another important feature of the proposed CATA approach is that it preserves the privacy of participants' by only disclosing the less sensitive data to the server. The proposed approach employs local and global task allocation methods to enable two levels of data sharing and privacy. We describe the series of experiments that were conducted to validate our proposed approach in terms of coverage and efficiency.

Recent advances in mobile computing coupled with the widespread availability of inexpensive mobile devices are the key motivating factors for the development of mobile health monitoring systems. However, to leverage the full potential of such systems for continuous and real time monitoring, there ar

In resource-constrained devices, adaptation of data stream processing to variations of data rates and availability of resources is crucial for consistency and continuity of running applications. However, to enhance and maximize the benefits of adapta