Osteoarthritis has the highest prevalence in the elderly population, with a rising tendency. Currently often special gait labs are used for objective diagnostic assessment of functional motion deficits or treatment outcome, e.g in patients suffering from gonarthrosis. The artificial lab setting and short measurement periods affect the explanatory power of this method. Inertial multi-sensor systems in contrast allow for monitoring human gait independent of a lab setting. However, recent approaches concerning important knee function parameter analyses have not been validated for long-term monitoring yet.The aim of our research for this paper is to evaluate our wearable joint kinematics measurement system (KINEMATIC-WEAR) for assessing maximum knee joint angles during extended periods of normal walking. Our prototype consists of small multi-sensor nodes with combined tri-axial accelerometer, gyroscope and magnetometer which were attached with kinesiotape to the thigh and shank of a subject while walking at different speeds on a treadmill. The computed maximum knee joint angles were compared with reference measurements performed by a physician on video frames captured during walking, as was the correlation between both value sets. Our results show an excellent correlation of 0.96 between clinical reference measurements and our computed angles. While the accuracy is good for slow walking speeds of 0.28 m/s (lkm/h, mean error: 2.6 deg±1.5) and 0.56 m/s (2km/h, mean error: 2.0 deg±1.6), our algorithm over-estimates the angles by 6.3±3.6 degrees at 0.83 m/s (3 km/h), likely induced by soft tissue motion during heel-strike. Our preliminary results show that our system allows for unobtrusive, long-term out-of-Iab monitoring of knee joint motion parameters. Further studies are necessary to evaluate the system for arthritis patients.

As an important carrier of individual information, the resume is an important data source for studying the spatio-temporal evolutionary characteristics of individual and group behaviors. This study focuses on spatio-temporal information extraction and geoparsing from resumes to provide basic technical support for spatio-temporal research based on resume text. Most current studies on resume text information extraction are oriented toward recruitment work, such as the automated information extraction, classification, and recommendation of resumes. These studies ignore the spatio-temporal information of individual and group behaviors implied in resumes. Therefore, this study takes the public resumes of teachers in key universities in China as the research data, proposes a set of spatio-temporal information extraction solutions for electronic resumes of public figures, and designs a spatial entity geoparsing method, which can effectively extract and spatially locate spatio-temporal information in the resumes. To verify the effectiveness of the proposed method, text information extraction models such as BiLSTM-CRF, BERT-CRF, and BERT-BiLSTM-CRF are selected to conduct comparative experiments, and the spatial entity geoparsing method is verified. The experimental results show that the precision of the selected models on the named entity recognition task is 96.23% and the precision of the designed spatial entity geoparsing method is 97.91%.

Event detection (ED) aims to identify events of interest described in the text. With the current explosive growth of text data on the internet, ED is increasingly practical and has gained many researchers’ attention. The existing works usually design ED as a token-level multi-class classification task. In this setting, given a sentence, ED models’ prediction for each token is relatively independent and thus cannot fully utilize sentence-level information and the association relations between multiple events in this sentence. To handle these situations, this paper proposes a multi-task learning based event detection model, which introduces an event type oriented text classification as an auxiliary task to improve the model’s understanding of sentence-level information. In addition, this model utilizes a Conditional Random Field (CRF) to explore the correlations between various event types and constrain the model’s output space. Experimental comparisons with state-of-the-art baselines on DuEE dataset demonstrate the model’s effectiveness.