Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. It can be applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). Then, we outline a few important applications of UQ methods. Finally, we briefly highlight the fundamental research challenges faced by UQ methods and discuss the future research directions in this field.

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges

Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model learns how to extract high-quality features. In recent years, due to the rapid development of internet technology, we are in an era of information torrents and we have massive amounts of data. In this way, DL has aroused strong interest of researchers and has been rapidly developed. Compared with DL, researchers have relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples. Therefore, early AL is difficult to reflect the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to the publicity of the large number of existing annotation datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, which is not allowed in some fields that require high expertise, especially in the fields of speech recognition, information extraction, medical images, etc. Therefore, AL has gradually received due attention. A natural idea is whether AL can be used to reduce the cost of sample annotations, while retaining the powerful learning capabilities of DL. Therefore, deep active learning (DAL) has emerged. Although the related research has been quite abundant, it lacks a comprehensive survey of DAL. This article is to fill this gap, we provide a formal classification method for the existing work, and a comprehensive and systematic overview. In addition, we also analyzed and summarized the development of DAL from the perspective of application. Finally, we discussed the confusion and problems in DAL, and gave some possible development directions for DAL.

A Survey of Deep Active Learning

The vast proliferation of sensor devices and Internet of Things enables the applications of sensor-based activity recognition. However, there exist substantial challenges that could influence the performance of the recognition system in practical scenarios. Recently, as deep learning has demonstrated its effectiveness in many areas, plenty of deep methods have been investigated to address the challenges in activity recognition. In this study, we present a survey of the state-of-the-art deep learning methods for sensor-based human activity recognition. We first introduce the multi-modality of the sensory data and provide information for public datasets that can be used for evaluation in different challenge tasks. We then propose a new taxonomy to structure the deep methods by challenges. Challenges and challenge-related deep methods are summarized and analyzed to form an overview of the current research progress. At the end of this work, we discuss the open issues and provide some insights for future directions.

Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities

"This is the pre-peer reviewed version of the following article: Ramasamy Ramamurthy S, Roy N. Recent trends in machine learning for human activity recognition—A survey. WIREs Data Mining Knowl Discov. 2018;e1254. https://doi.org/10.1002/widm.1254, which has been published in final form at https://doi.org/10.1002/widm.1254. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving."

https://par.nsf.gov/servlets/purl/10087464

Recent trends in machine learning for human activity recognition—A survey

In activity recognition, it is often expensive and time-consuming to acquire sufficient activity labels. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labels. Existing approaches typically consider learning a global domain shift while ignoring the intra-affinity between classes, which will hinder the performance of the algorithms. In this paper, we propose a novel and general cross-domain learning framework that can exploit the intra-affinity of classes to perform intra-class knowledge transfer. The proposed framework, referred to as Stratified Transfer Learning (STL), can dramatically improve the classification accuracy for cross-domain activity recognition. Specifically, STL first obtains pseudo labels for the target domain via majority voting technique. Then, it performs intra-class knowledge transfer iteratively to transform both domains into the same subspaces. Finally, the labels of target domain are obtained via the second annotation. To evaluate the performance of STL, we conduct comprehensive experiments on three large public activity recognition datasets (i.e., OPPORTUNITY, PAMAP2, and UCI DSADS), which demonstrates that STL significantly outperforms other state-of-the-art methods w.r.t. classification accuracy (improvement of 7.68%). Furthermore, we extensively investigate the performance of STL across different degrees of similarities and activity levels between domains. And we also discuss the potential of STL in other pervasive computing applications to provide empirical experience for future research.

Stratified Transfer Learning for Cross-domain Activity Recognition

Activity recognition in smart environment has been investigated rigorously in recent years. Researchers are enhancing the underlying activity discovery and recognition process by adding various dimensions and functionalities. But one significant barrier still persists which is collecting the ground truth information. Ground truth is very important to initialize a supervised learning of activities. Due to a large variety in number of Activities of Daily Living (ADLs), acknowledging them in a supervised way is a non-trivial research problem. Most of the previous researches have referenced a subset of ADLs and to initialize their model, they acquire a vast amount of informative labeled training data. On the other hand to collect ground truth and differentiate ADLs, human intervention is indispensable. As a result it takes an immense effort and raises privacy concerns to collect a reasonable amount of labeled data. In this paper, we propose to use active learning to alleviate the labeling effort and ground truth data collection in activity recognition pipeline. We investigate and analyze different active learning strategies to scale activity recognition and propose a dynamic k-means clustering based active learning approach. Experimental results on real data traces from a retirement community-(IRB #HP-00064387) help validate the early promise of our approach.

/pdf/active-learning-enabled-activity-recognition-24e3vt14qn.pdf

Active learning enabled activity recognition

Deep learning architectures have been applied increasingly in multi-modal problems which has empowered a large number of application domains needing much less human supervision in the process. As unlabeled data are abundant in most of the application domains, deep architectures are getting increasingly popular to extract meaningful information out of these large volume of data. One of the major caveat of these architectures is that the training phase demands both computational time and system resources much higher than shallow learning algorithms and it is posing a difficult challenge for the researchers to implement the architectures in low-power resource constrained devices. In this paper, we propose a deep and active learning enabled activity recognition model, DeActive, which is optimized according to our problem domain and reduce the resource requirements. We incorporate active learning in the process to minimize the human supervision along with the effort needed for compiling ground truth. The DeActive model has been validated using real data traces from a retirement community center (IRB #HP-00064387) and 4 public datasets. Our experimental results show that our model can contribute better accuracy while ensuring less amount of resource usages in reduced time compared to other traditional deep learning approaches in activity recognition.

https://dl.acm.org/doi/pdf/10.1145/3214269

DeActive: Scaling Activity Recognition with Active Deep Learning

Machine learning models are bounded by the credibility of ground truth data used for both training and testing. Regardless of the problem domain, this ground truth annotation is objectively manual and tedious as it needs considerable amount of human intervention. With the advent of Active Learning with multiple annotators, the burden can be somewhat mitigated by actively acquiring labels of most informative data instances. However, multiple annotators with varying degrees of expertise poses new set of challenges in terms of quality of the label received and availability of the annotator. Due to limited amount of ground truth information addressing the variabilities of Activity of Daily Living (ADLs), activity recognition models using wearable and mobile devices are still not robust enough for real-world deployment. In this paper, we first propose an active learning combined deep model which updates its network parameters based on the optimization of a joint loss function. We then propose a novel annotator selection model by exploiting the relationships among the users while considering their heterogeneity with respect to their expertise, physical and spatial context. Our proposed model leverages model-free deep reinforcement learning in a partially observable environment setting to capture the action-reward interaction among multiple annotators. Our experiments in real-world settings exhibit that our active deep model converges to optimal accuracy with fewer labeled instances and achieves ~8% improvement in accuracy in fewer iterations.

https://dl.acm.org/doi/pdf/10.1145/3292500.3330688

Active Deep Learning for Activity Recognition with Context Aware Annotator Selection

The use of smartphone and wearable devices in various sporting events is an optimistic opportunity to profile player's physical fitness and physiological health conditioning attributes. Recently a variety of commercial wearables with respect to different sports are available in the market. As these wearables differ for distinctive sports, it becomes a hassle to effectively profile them for multiple sports sessions in day to day practice events. Wrist worn devices like smartwatches are becoming a trend in sports analytics recently and researchers are leveraging them to infer various contexts of the players to improve the quality, tactics, strategy of playing matches against the opponents. Visual observation is the most popular way to track a player's abilities in soccer, but as a player it is not always possible to self-assess your own strengths and weaknesses in a field. In this paper, we propose to exploit the wrist worn devices with built in accelerometer to help represent attributes of technical judgement, tactical awareness and physical aspects of a soccer player. We propose to use deep learning to build our classification model which analyzes different soccer events like in-possession, pass, kick, sprint, run and dribbling. Based on these soccer events, we evaluate the overall ability of a soccer player. Our experiments show that, these wearable technology guided attributes profiling can help a coach or scout to better understand the competence of a player in addition to traditional visual observation.

/pdf/soccermate-a-personal-soccer-attribute-profiler-using-c57qwj8rh3.pdf

SoccerMate: A personal soccer attribute profiler using wearables

Predicting the occupancy related information in an environment has been investigated to satisfy the myriad requirements of various evolving pervasive, ubiquitous, opportunistic and participatory sensing applications. Infrastructure and ambient sensors based techniques have been leveraged largely to determine the occupancy of an environment incurring a significant deployment and retrofitting costs. In this paper, we advocate an infrastructure-less zero-configuration multimodal smartphone sensor-based techniques to detect fine-grained occupancy information. We propose to exploit opportunistically smartphones' acoustic sensors in presence of human conversation and motion sensors in absence of any conversational data. We develop a novel speaker estimation algorithm based on unsupervised clustering of overlapped and non-overlapped conversational data to determine the number of occupants in a crowded environment. We also design a hybrid approach combining acoustic sensing opportunistically with locomotive model to further improve the occupancy detection accuracy. We evaluate our algorithms in different contexts, conversational, silence and mixed in presence of 10 domestic users. Our experimental results on real-life data traces collected from 10 occupants in natural setting show that using this hybrid approach we can achieve approximately 0.76 error count distance for occupancy detection accuracy on average.

/pdf/sensepresence-infrastructure-less-occupancy-detection-for-2cu2kicufv.pdf

H M Sajjad Hossain

Papers

Active learning enabled activity recognition

DeActive: Scaling Activity Recognition with Active Deep Learning

Active Deep Learning for Activity Recognition with Context Aware Annotator Selection

SoccerMate: A personal soccer attribute profiler using wearables

SensePresence: Infrastructure-Less Occupancy Detection for Opportunistic Sensing Applications