arXiv subjects

Yuchen Zhao

Publications and source records attributed to Yuchen Zhao.

27 records · Page 2Linked to original sources

arXiv2021

Designing A Clinically Applicable Deep Recurrent Model to Identify Neuropsychiatric Symptoms in People Living with Dementia Using In-Home Monitoring Data

Agitation is one of the neuropsychiatric symptoms with high prevalence in dementia which can negatively impact the Activities of Daily Living (ADL) and the independence of individuals. Detecting agitation episodes can assist in providing People Living with Dementia (PLWD) with early and timely interventions. Analysing agitation episodes will also help identify modifiable factors such as ambient temperature and sleep as possible components causing agitation in an individual. This preliminary study presents a supervised learning model to analyse the risk of agitation in PLWD using in-home monitoring data. The in-home monitoring data includes motion sensors, physiological measurements, and the use of kitchen appliances from 46 homes of PLWD between April 2019-June 2021. We apply a recurrent deep learning model to identify agitation episodes validated and recorded by a clinical monitoring team. We present the experiments to assess the efficacy of the proposed model. The proposed model achieves an average of 79.78% recall, 27.66% precision and 37.64% F1 scores when employing the optimal parameters, suggesting a good ability to recognise agitation events. We also discuss using machine learning models for analysing the behavioural patterns using continuous monitoring data and explore clinical applicability and the choices between sensitivity and specificity in-home monitoring applications.

cs.LG↗

arXiv2021

Semi-supervised Federated Learning for Activity Recognition

Training deep learning models on in-home IoT sensory data is commonly used to recognise human activities. Recently, federated learning systems that use edge devices as clients to support local human activity recognition have emerged as a new paradigm to combine local (individual-level) and global (group-level) models. This approach provides better scalability and generalisability and also offers better privacy compared with the traditional centralised analysis and learning models. The assumption behind federated learning, however, relies on supervised learning on clients. This requires a large volume of labelled data, which is difficult to collect in uncontrolled IoT environments such as remote in-home monitoring. In this paper, we propose an activity recognition system that uses semi-supervised federated learning, wherein clients conduct unsupervised learning on autoencoders with unlabelled local data to learn general representations, and a cloud server conducts supervised learning on an activity classifier with labelled data. Our experimental results show that using a long short-term memory autoencoder and a Softmax classifier, the accuracy of our proposed system is higher than that of both centralised systems and semi-supervised federated learning using data augmentation. The accuracy is also comparable to that of supervised federated learning systems. Meanwhile, we demonstrate that our system can reduce the number of needed labels and the size of local models, and has faster local activity recognition speed than supervised federated learning does.

cs.LG↗

arXiv2021

Preparation of superconducting thin films of infinite-layer nickelate Nd$_{0.8}$Sr$_{0.2}$NiO$_{2}$

The recent observation of superconductivity in infinite-layer nickelate Nd$_{0.8}$Sr$_{0.2}$NiO$_{2}$ has received considerable attention. Despite the many efforts to understand the superconductivity in infinite-layer nickelates, a consensus on the underlying mechanism for the superconductivity has yet to be reached, partly owing to the challenges with the material synthesis. Here, we report the successful growth of superconducting infinite-layer Nd$_{0.8}$Sr$_{0.2}$NiO$_{2}$ films by pulsed-laser deposition and soft chemical reduction. The details on growth process will be discussed.

cond-mat.supr-con↗

arXiv2020

Yielding, Rigidity, and Tensile Stress in Sheared Columns of Hexapod Granules

Granular packings of non-convex or elongated particles can form free-standing structures like walls or arches. For some particle shapes, such as staples, the rigidity arises from interlocking of pairs of particles, but the origins of rigidity for non-interlocking particles remains unclear. We report on experiments and numerical simulations of sheared columns of "hexapods," particles consisting of three mutually orthogonal sphero-cylinders whose centers coincide. We vary the length-to-diameter aspect ratio, $α$, of the sphero-cylinders and subject the packings to quasistatic direct shear. For small $α$, we observe a finite yield stress. For large $α$, however, the column becomes rigid when sheared, supporting stresses that increase sharply with increasing strain. Analysis of X-ray micro-computed tomography (Micro-CT) data collected during the shear reveals that the stiffening is associated with a tilted, oblate cluster of hexapods near the nominal shear plane in which particle deformation and average contact number both increase. Simulation results show that the particles are collectively under tension along one direction even though they do not interlock pairwise. These tensions comes from contact forces carrying large torques, and they are perpendicular to the compressive stresses in the packing. They counteract the tendency to dilate, thus stabilize the particle cluster.

cond-mat.soft↗

arXiv2020

A Library for Constraint Consistent Learning

This paper introduces the first, open source software library for Constraint Consistent Learning (CCL). It implements a family of data-driven methods that are capable of (i) learning state-independent and -dependent constraints, (ii) decomposing the behaviour of redundant systems into task- and null-space parts, and (iii) uncovering the underlying null space control policy. It is a tool to analyse and decompose many everyday tasks, such as wiping, reaching and drawing. The library also includes several tutorials that demonstrate its use with both simulated and real world data in a systematic way. This paper documents the implementation of the library, tutorials and associated helper methods. The software is made freely available to the community, to enable code reuse and allow users to gain in-depth experience in statistical learning in this area.

cs.RO↗

arXiv2019

Using Metrics Suites to Improve the Measurement of Privacy in Graphs

Social graphs are widely used in research (e.g., epidemiology) and business (e.g., recommender systems). However, sharing these graphs poses privacy risks because they contain sensitive information about individuals. Graph anonymization techniques aim to protect individual users in a graph, while graph de-anonymization aims to re-identify users. The effectiveness of anonymization and de-anonymization algorithms is usually evaluated with privacy metrics. However, it is unclear how strong existing privacy metrics are when they are used in graph privacy. In this paper, we study 26 privacy metrics for graph anonymization and de-anonymization and evaluate their strength in terms of three criteria: monotonicity indicates whether the metric indicates lower privacy for stronger adversaries; for within-scenario comparisons, evenness indicates whether metric values are spread evenly; and for between-scenario comparisons, shared value range indicates whether metrics use a consistent value range across scenarios. Our extensive experiments indicate that no single metric fulfills all three criteria perfectly. We therefore use methods from multi-criteria decision analysis to aggregate multiple metrics in a metrics suite, and we show that these metrics suites improve monotonicity compared to the best individual metric. This important result enables more monotonic, and thus more accurate, evaluations of new graph anonymization and de-anonymization algorithms.

cs.CR↗

arXiv2015

Packings of 3D stars: Stability and structure

We describe a series of experiments involving the creation of cylindrical packings of star-shaped particles, and an exploration of the stability of these packings. The stars cover a broad range of arm sizes and frictional properties. We carried out three different kinds of experiments, all of which involve columns that are prepared by raining star particles one-by-one into hollow cylinders. As an additional part of the protocol, we sometimes vibrated the column before removing the confining cylinder. We rate stability in terms of r, the ratio of the mass of particles that fall off a pile when it collapsed, to the total particle mass. The first experiment involved the intrinsic stability of the pile when the confining cylinder was removed. The second kind of experiment involved adding a uniform load to the top of the column, and then determining the collapse properties. A third experiment involved testing stability to tipping of the piles. We find a stability diagram relating the pile height, h, vs. pile diameter, delta, where the stable and unstable regimes are separated by a boundary that is roughly a power-law in h vs. delta with an exponent that is less than one. Increasing friction and vibration both tend to stabilize piles, while increasing particle size can destabilize the system under certain conditions.

cond-mat.soft↗

arXiv2013

Latent Networks Fusion based Model for Event Recommendation in Offline Ephemeral Social Networks

With the growing amount of mobile social media, offline ephemeral social networks (OffESNs) are receiving more and more attentions. Offline ephemeral social networks (OffESNs) are the networks created ad-hoc at a specific location for a specific purpose and lasting for short period of time, relying on mobile social media such as Radio Frequency Identification (RFID) and Bluetooth devices. The primary purpose of people in the OffESNs is to acquire and share information via attending prescheduled events. Event Recommendation over this kind of networks can facilitate attendees on selecting the prescheduled events and organizers on making resource planning. However, because of lack of users preference and rating information, as well as explicit social relations, both rating based traditional recommendation methods and social-trust based recommendation methods can no longer work well to recommend events in the OffESNs. To address the challenges such as how to derive users latent preferences and social relations and how to fuse the latent information in a unified model, we first construct two heterogeneous interaction social networks, an event participation network and a physical proximity network. Then, we use them to derive users latent preferences and latent networks on social relations, including like-minded peers, co-attendees and friends. Finally, we propose an LNF (Latent Networks Fusion) model under a pairwise factor graph to infer event attendance probabilities for recommendation. Experiments on an RFID-based real conference dataset have demonstrated the effectiveness of the proposed model compared with typical solutions.

cs.SI↗

arXiv2013

On Graph Stream Clustering with Side Information

Graph clustering becomes an important problem due to emerging applications involving the web, social networks and bio-informatics. Recently, many such applications generate data in the form of streams. Clustering massive, dynamic graph streams is significantly challenging because of the complex structures of graphs and computational difficulties of continuous data. Meanwhile, a large volume of side information is associated with graphs, which can be of various types. The examples include the properties of users in social network activities, the meta attributes associated with web click graph streams and the location information in mobile communication networks. Such attributes contain extremely useful information and has the potential to improve the clustering process, but are neglected by most recent graph stream mining techniques. In this paper, we define a unified distance measure on both link structures and side attributes for clustering. In addition, we propose a novel optimization framework DMO, which can dynamically optimize the distance metric and make it adapt to the newly received stream data. We further introduce a carefully designed statistics SGS(C) which consume constant storage spaces with the progression of streams. We demonstrate that the statistics maintained are sufficient for the clustering process as well as the distance optimization and can be scalable to massive graphs with side attributes. We will present experiment results to show the advantages of the approach in graph stream clustering with both links and side information over the baselines.

cs.DB↗