This study aims to explore the potential of Internet of Things (IoT) devices and explainable Artificial Intelligence (AI) techniques in predicting biomarker values associated with GDM when measured 13-16 weeks prior to diagnosis. We developed a system that forecasts biomarkers such as LDL, HDL, triglycerides, cholesterol, HbA1c, and results from the Oral Glucose Tolerance Test (OGTT) including fasting glucose, 1-hour, and 2-hour post-load glucose values. These biomarker values are predicted based on sensory measurements collected around week 12 of pregnancy, including continuous glucose levels, short physical movement recordings, and medical background information. To the best of our knowledge, this is the first study to forecast GDM-associated biomarker values 13 to 16 weeks prior to the GDM screening test, using continuous glucose monitoring devices, a wristband for activity detection, and medical background data. We applied machine learning models, specifically Decision Tree and Random Forest Regressors, along with Coupled-Matrix Tensor Factorisation (CMTF) and Elastic Net techniques, examining all possible combinations of these methods across different data modalities. The results demonstrated good performance for most biomarkers. On average, the models achieved Mean Squared Error (MSE) between 0.29 and 0.42 and Mean Absolute Error (MAE) between 0.23 and 0.45 for biomarkers like HDL, LDL, cholesterol, and HbA1c. For the OGTT glucose values, the average MSE ranged from 0.95 to 2.44, and the average MAE ranged from 0.72 to 0.91. Additionally, the utilisation of CMTF with Alternating Least Squares technique yielded slightly better results (0.16 MSE and 0.07 MAE on average) compared to the well-known Elastic Net feature selection technique. While our study was conducted with a limited cohort in South Africa, our findings offer promising indications regarding the potential for predicting biomarker values in pregnant women through the integration of wearable devices and medical background data in the analysis. Nevertheless, further validation on a larger, more diverse cohort is imperative to substantiate these encouraging results.

This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Initially, our system begins with audio feature extraction using Gammatone and Continuous Wavelet transformation. This step aims to transform the respiratory sound input into a two-dimensional spectrogram where both spectral and temporal features are presented. Then, our proposed system integrates Inception-residual-based backbone models combined with multi-head attention and multi-objective loss to classify respiratory anomalies. Instead of applying a simple concatenation approach by combining results from various spectrograms, we propose a linear combination, which has the ability to regulate equally the contribution of each individual spectrogram throughout the training process. To evaluate the performance, we conducted experiments over the benchmark dataset of SPRSound (The Open-Source SJTU Paediatric Respiratory Sound) proposed by the IEEE BioCAS 2022 challenge. As regards the Score computed by an average between the average score and harmonic score, our proposed system gained significant improvements of 9.7%, 15.8%, 17.8%, and 16.1% in Task 1–1, Task 1–2, Task 2–1, and Task 2–2, respectively, compared to the challenge baseline system. Notably, we achieved the Top-1 performance in Task 2–1 and Task 2–2 with the highest Score of 74.5% and 53.9%, respectively.

In this study, we present a cohort study involving 106 COPD patients using portable environmental sensor nodes with attached air pollution sensors and activity-related sensors, as well as daily symptom records and peak flow measurements to monitor patients' activity and personal exposure to air pollution. This is the first study which attempts to predict COPD symptoms based on personal air pollution exposure. We developed a system that can detect COPD patients' symptoms one day in advance of symptoms appearing. We proposed using the Probabilistic Latent Component Analysis (PLCA) model based on 3-dimensional and 4-dimensional spectral dictionary tensors for personalised and population monitoring, respectively. The model is combined with Linear Dynamic Systems (LDS) to track the patients' symptoms. We compared the performance of PLCA and PLCA-LDS models against Random Forest models in the identification of COPD patients' symptoms, since tree-based classifiers were used for remote monitoring of COPD patients in the literature. We found that there was a significant difference between the classifiers, symptoms and the personalised versus population factors. Our results show that the proposed PLCA-LDS-3D model outperformed the PLCA and the RF models between 4 and 20% on average. When we used only air pollutants as input, the PLCA-LDS-3D forecasting results in personalised and population models were 48.67 and 36.33% accuracy for worsening of lung capacity and 38.67 and 19% accuracy for exacerbation of COPD patients' symptoms, respectively. We have shown that indicators of the quality of an individual's environment, specifically air pollutants, are as good predictors of the worsening of respiratory symptoms in COPD patients as a direct measurement.

An increasing number of cities are confronted with challenges resulting from the rapid urbanization and new demands that a rapidly growing digital economy imposes on current applications and information systems. Smart city applications enable city authorities to monitor, manage, and provide plans for public resources and infrastructures in city environments, while offering citizens and businesses to develop and use intelligent services in cities. However, providing such smart city applications gives rise to several issues, such as semantic heterogeneity and trustworthiness of data sources, and extracting up-to-date information in real time from large-scale dynamic data streams. In order to address these issues, we propose a novel framework with an efficient semantic data processing pipeline, allowing for real-time observation of the pulse of a city. The proposed framework enables efficient semantic integration of data streams, and complex event processing on top of real-time data aggregation and quality analysis in a semantic Web environment. To evaluate our system, we use real-time sensor observations that have been published via an open platform called Open Data Aarhus by the City of Aarhus. We examine the framework utilizing symbolic aggregate approximation to reduce the size of data streams, and perform quality analysis taking into account both single and multiple data streams. We also investigate the optimization of the semantic data discovery and integration based on the proposed stream quality analysis and data aggregation techniques.

The advent of Internet of Things, has resulted in the development of infrastructure for capturing and storing data from domains ranging from smart devices (e.g. smartphones) to smart cities. This data is often available publicly and has enabled a wider range of data consumers to utilise such data sets for applications ranging from scientific experimentation to enhancing commercial activity for businesses. Accordingly this has resulted in the need for the development data analysis tools that are both simple to use and provide the most effective tools for a given data set. To this end, we introduce data analysis tools as web service, that enables the data consumer to make a simple HTTP request for processing data over the internet. By providing such tools as a web service, we demonstrate the potential of such a system to aid both the advanced and novice data consumer. Furthermore, this work provides an use case example of the proposed tool on publicly available data extracted from the smart city CityPulse IoT project.

With the growing popularity of information and communications technologies and information sharing and integration, cities are evolving into large interconnected ecosystems by using smart objects and sensors that enable interaction with the physical world. However, it is often difficult to perform real-time analysis of large amount on heterogeneous data and sensory information that are provided by various resources. This paper describes a framework for real-time semantic annotation and aggregation of data streams to support dynamic integration into the Web using the advanced message queuing protocol. We provide a comprehensive analysis on the effect of adaptive and nonadaptive window size in segmentation of time series using SensorSAX and symbolic aggregate approximation (SAX) approaches for data streams with different variation and sampling rate in real-time processing. The framework is evaluated with three parameters, namely window size parameter of the SAX algorithm, sensitivity level, and minimum window size parameters of the SensorSAX algorithm based on the average data aggregation and annotation time, CPU consumption, data size, and data reconstruction rate. Based on a statistical analysis, a detailed comparison between various sensor points is made to investigate the memory and computational cost of the stream-processing framework. Our results suggests that regardless of utilized segmentation approach, due to the fact that each geographically different sensory environment has got a different dynamicity level, it is desirable to find the optimal data aggregation parameters in order to reduce the energy consumption and improve the data aggregation quality.

In this paper we present a novel hybrid system that involves a formal method of automatic ontology generation for web-based audio signal processing applications. An ontology is seen as a knowledge management structure that represents domain knowledge in a machine interpretable format. It describes concepts and relationships within a particular domain, in our case, the domain of musical instruments. However, the different tasks of ontology engineering including manual annotation, hierarchical structuring and organization of data can be laborious and challenging. For these reasons, we investigate how the process of creating ontologies can be made less dependent on human supervision by exploring concept analysis techniques in a Semantic Web environment. In this study, various musical instruments, from wind to string families, are classified using timbre features extracted from audio. To obtain models of the analysed instrument recordings, we use K-means clustering to determine an optimised codebook of Line Spectral Frequencies (LSFs), or Mel-frequency Cepstral Coefficients (MFCCs). Two classification techniques based on Multi-Layer Perceptron (MLP) neural network and Support Vector Machines (SVM) were tested. Then, Formal Concept Analysis (FCA) is used to automatically build the hierarchical structure of musical instrument ontologies. Finally, the generated ontologies are expressed using the Ontology Web Language (OWL). System performance was evaluated under natural recording conditions using databases of isolated notes and melodic phrases. Analysis of Variance (ANOVA) were conducted with the feature and classifier attributes as independent variables and the musical instrument recognition F-measure as dependent variable. Based on these statistical analyses, a detailed comparison between musical instrument recognition models is made to investigate their effects on the automatic ontology generation system. The proposed system is general and also applicable to other research fields that are related to ontologies and the Semantic Web.