ABSTRACT Time series analysis has become crucial in various fields, from engineering and finance to healthcare and social sciences. Due to their multidimensional nature, time series often need to be embedded into a fixed‐dimensional feature space to enable processing with various machine learning algorithms. In this paper, we present a comprehensive review and quantitative evaluation of time series embedding methods for effective representations in machine learning and deep learning models. We introduce a taxonomy of embedding techniques, categorizing them based on their theoretical foundations and application contexts. Our work provides a quantitative evaluation of representative methods from each category by assessing their performance on downstream classification tasks across diverse real‐world datasets. Our experimental results demonstrate that the performance of embedding methods varies significantly depending on the dataset and classification algorithm used, highlighting the importance of careful model selection and extensive experimentation for specific applications. This study contributes to the field by offering a systematic comparison of time series embedding techniques, guiding practitioners in selecting appropriate methods for their specific applications, and providing a foundation for future advancements in time series analysis. To facilitate further research and practical applications, we provide an open‐source code repository implementing these embedding methods: https://github.com/imics‐lab/time‐series‐embedding .

The Activities of Daily Living (ADL) include activities such as brushing teeth, sweeping, and walking that are critical to on-going health, especially in older adults. Activities may be determined using recorded video and 2D-CNNs, however video recordings present privacy and coverage challenges in personal spaces. Smartphones and newer wristworn devices that record motion data can also be used for activity recognition tasks. Ankle or shoe-based devices such as the retired Nike+ sensor are less common, however ear-based devices which may record head movement are gaining popularity. In this work we use accelerometer data from a recently released dataset using devices placed on the ankle, hip, and wrist. First, we evaluate a simple 1D-CNNs ability to classify the 17 included activities in subject-dependent and subject-independent analysis. Then we process the accelerometer data from the three sensors individually to evaluate each location’s ability to predict activities. Finally, we develop a functional model which independently executes a 1D-CNN for each sensor’s data and combines the results using Global Average Pooling. The functional model achieves a subject-independent accuracy of 70.7%.

Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear gap exists in the current literature on evaluating the relative bias in the performance of multi-class classifiers. In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the class-wise bias of two models in comparison to one another. By evaluating the performance of these new metrics and by demonstrating their practical application, we show that they can be used to measure fairness as well as bias. These demonstrations show that our metrics can address specific needs for measuring bias in multi-class classification. Demonstration code is available at https://github.com/gentry-atkinson/CEV_SDE_demo.git.

The majority of current smart health applications are deployed on a smartphone paired with a smartwatch. The phone is used as the computation platform or the gateway for connecting to the cloud while the watch is used mainly as the data sensing device. In the case of fall detection applications for older adults, this kind of setup is not very practical since it requires users to always keep their phones in proximity while doing the daily chores. When a person falls, in a moment of panic, it might be difficult to locate the phone in order to interact with the Fall Detection App for the purpose of indicating whether they are fine or need help. This paper demonstrates the feasibility of running a real-time personalized deep-learning-based fall detection system on a smartwatch device using a collaborative edge-cloud framework. In particular, we present the software architecture we used for the collaborative framework, demonstrate how we automate the fall detection pipeline, design an appropriate UI on the small screen of the watch, and implement strategies for the continuous data collection and automation of the personalization process with the limited computational and storage resources of a smartwatch. We also present the usability of such a system with nine real-world older adult participants.

A significant portion of the veteran population suffers from PTSD, a mental illness that is often accompanied by social anxiety disorder. Student veterans are especially vulnerable as they struggle to adapt to a new, less structured college lifestyle. In order to assist psychologists and social workers in the treatment of social anxiety disorder we use machine learning to analyze transcribed interview text and apply topic modelling to highlight common stress factors for student veterans. The results detailed in this paper also have broader impacts in fields such as pedagogy and public health.

This article presents an in-depth experimental study of Ensemble Deep Learning techniques on small datasets for the analysis of time-series data generated by wearable devices. Deep Learning networks generally require large datasets for training. In some health care applications, such as the real-time smartwatch-based fall detection, there are no publicly available, large, annotated datasets that can be used for training, due to the nature of the problem (i.e., a fall is not a common event). We conducted a series of offline experiments using two different datasets of simulated falls for training various ensemble models. Our offline experimental results show that an ensemble of Recurrent Neural Network (RNN) models, combined by the stacking ensemble technique, outperforms a single RNN model trained on the same data samples. Nonetheless, fall detection models trained on simulated falls and activities of daily living performed by test subjects in a controlled environment, suffer from low precision due to high false-positive rates. In this work, through a set of real-world experiments, we demonstrate that the low precision can be mitigated via the collection of false-positive feedback by the end-users. The final Ensemble RNN model, after re-training with real-world user archived data and feedback, achieved a significantly higher precision without reducing much of the recall in a real-world setting.

The Internet of Things (IoT) provides the ability for humans and computers to learn and interact from billions of things that include sensors, actuators, services, and other Internet-connected objects. The realization of IoT systems will enable seamless integration of the cyber world with our physical world and will fundamentally change and empower human interaction with the world. A key technology in the realization of IoT systems is middleware, which is usually described as a software system designed to be the intermediary between IoT devices and applications. In this paper, we first motivate the need for an IoT middleware via an IoT application designed for real-time prediction of blood alcohol content using smartwatch sensor data. This is then followed by a survey on the capabilities of the existing IoT middleware. We further conduct a thorough analysis of the challenges and the enabling technologies in developing an IoT middleware that embraces the heterogeneity of IoT devices and also supports the essential ingredients of composition, adaptability, and security aspects of an IoT system.

Array comparative genomic hybridization (aCGH) is a newly introduced method for the detection of copy number abnormalities associated with human diseases with special focus on cancer. Specific patterns in DNA copy number variations (CNVs) can be associated with certain disease types and can facilitate prognosis and progress monitoring of the disease. Machine learning techniques have been used to model the problem of tissue typing as a classification problem. Feature selection is an important part of the classification process, because many biological features are not related to the diseases and confuse the classification tasks. Multiple feature selection methods have been proposed in the different domains where classification has been applied. In this work, we will present a new feature selection method based on structured sparsity-inducing norms to identify the informative aCGH biomarkers which can help us classify different disease subtypes. To validate the performance of the proposed method, we experimentally compare it with existing feature selection methods on four publicly available aCGH data sets. In all empirical results, the proposed sparse learning based feature selection method consistently outperforms other related approaches. More important, we carefully investigate the aCGH biomarkers selected by our method, and the biological evidences in literature strongly support our results.

This paper presents a new, publicly available eye tracking dataset, aimed to be used as a benchmark for Point of Gaze (PoG) detection algorithms. The dataset consists of a set of videos recording the eye motion of human test subjects as they were looking at, or following, a set of predefined points of interest on a computer visual display unit. The eye motion was recorded using a Mobile Eye, head mounted, infrared monocular camera. The ground truth of the point of gaze and head location and direction in the three dimensional space are provided together with the data. The ground truth regarding the point of gaze at is known in advance since the subjects are always looking at predefined targets, whereas, the head position in 3D is captured using a Vicon Motion Tracking System.