With the development of natural language processing tech- niques(NLP), automatic diagnosis of eye diseases using ophthalmology electronic medical records (OEMR) has become possible. It aims to evaluate the condition of both eyes of a patient respectively, and we formulate it as a particular multi-label classification task in this paper. Although there are a few related studies in other diseases, automatic diagnosis of eye diseases exhibits unique characteristics. First, descriptions of both eyes are mixed up in OEMR documents, with both free text and templated asymptomatic descriptions, resulting in sparsity and clutter of information. Second, OEMR documents contain multiple parts of descriptions and have long document lengths. Third, it is critical to provide explainability to the disease diagnosis model. To overcome those challenges, we present an effective automatic eye disease diagnosis framework, NEEDED. In this framework, a preprocessing module is integrated to improve the density and quality of information. Then, we design a hierarchical transformer structure for learning the contextualized representations of each sentence in the OEMR document. For the diagnosis part, we propose an attention-based predictor that enables traceable diagnosis by obtaining disease-specific information. Experiments on the real dataset and comparison with several baseline models show the advantage and explainability of our framework.

Given the rapid development of internet and dramatic change it has brought to human life, this study examines the effect of internet use on well-being in rural China. Findings indicate that the act of engaging with internet and the increase in its usage frequency both have significant positive effects on well-being in rural China, whereas the effect attenuates with the increase of usage frequency. These results imply that internet use features diminishing marginal returns. In the sub-groups divided by education and age, the higher educated and the younger groups use internet more frequently. However, internet use significantly promotes well-being of the lower educated, the middle-aged and the elderly groups, and its effect on the higher educated and the younger groups is insignificant. A further analysis uncovers that internet use increase well-being through relieving loneliness. This study affirms the benefits of internet in rural China, but obsessive internet use could offset the benefits. Thus, the implication of using internet appropriately are highlighted.

Automatic Eating Detection (AED) provides an important tool to help users regulate their dietary behavior for many health applications, such as weight management. In this paper we propose an AED solution using a head-mount and a wrist-worn accelerometers that are commonly available in commercial wearable devices. Experimental results, using Google Glass and Pebble Watch, validated that the proposed approach is highly effective to detect head motion from chewing and to detect hand-to-mouth (HtM) gestures when eating, resulting in 89.5% to 95.1% detection accuracy. Further we combined the features from both devices to achieve 97% cross-person eating detection accuracy and the average error when predicting duration of eating meals was only 105 seconds.

Despite the continued technology advances for smartphones, there are still few tools available to end users for understanding the causes of the network problems when encountered. The users often have to rely on the signal bars, which unfortunately is a poor indicator of real network issues that may arise even when the signal is good. In this paper, we present a network troubleshooting system for Android platform, which can automatically collect network measurements and perform on-device diagnosis of likely causes of the network problems. The diagnosis model is based on a decision tree that was constructed with domain knowledge and the model's thresholds were learned statistically from empirical performance analysis. Experimental results show that the proposed approach is effective in troubleshooting network problems on smartphones. By continuously using this app, end users can make informed decisions to upgrade service plans, change mobile devices, or switch service providers.