Student Dropout Prediction (SDP) is pivotal in mitigating withdrawals in Massive Open Online Courses. Previous studies generally modeled the SDP problem as a binary classification task, providing a single prediction outcome. Accordingly, some attempts introduce survival analysis methods to achieve continuous and consistent predictions over time. However, the volatility and sparsity of data always weaken the models’ performance. Prevailing solutions rely heavily on data pre-processing independent of predictive models, which are labor-intensive and may contaminate authentic data. This paper proposes a Survival Analysis based Volatility and Sparsity Modeling Network (SAVSNet) to address these issues in an end-to-end deep learning framework. Specifically, SAVSNet smooths the volatile time series by convolution network while preserving the original data information using Long-Short Term Memory Network (LSTM). Furthermore, we propose a Time-Missing-Aware LSTM unit to mitigate the impact of data sparsity by integrating informative missingness patterns into the model. A survival analysis loss function is adopted for parameter estimation, and the model outputs monotonically decreasing survival probabilities. In the experiments, we compare the proposed method with state-of-the-art methods in two real-world MOOC datasets, and the experiment results show the effectiveness of our proposed model.

In recent years, the development of IoT (Internet of Things) technology has given people many ways to obtain information through various types of physical devices. In parallel with that trend, people rely more on context-aware service and devices in many aspects, such as health care and elderly home care. However, traditional sensors are typically locked into closed systems, which hinder the access to such sensors that can be available in other information systems. Establishing free communication between human and physical things will help build a network with hybrid intelligence and amazing services. In order to share information and enable the communication between both physical devices and human, we proposed a SWoT (Social Web of Thing) framework in this paper that establishes social networking between embedded devices, services and human. Through the supernetwork approach, we discussed the service discovery in the SWoT system with heterogeneous social relations. At last, we introduced the MagicHome prototype of SWoT.

Living Lab is an emerging user-centric innovation approach and has been widely used to facilitate ICT innovations. Although there are many definitions for it from different perspectives, a holistic view is still forming. This paper explores a set of Living Lab innovation principles by extending the Web 2.0 principles proposed by O’reilly. Furthermore we test these principles against two Living Lab cases. This paper contributes by providing a holistic view towards Living Lab and the evolution from Web 2.0 to Living Lab.