Abstract:Prediction tasks about students such as predicting students' academic performances have practical real-world significance at both the student level and the college level. With the rapid construction of smart campuses, colleges not only offer residence and academic programs but also record students' daily life. The digital footprints provide an opportunity to offer better solutions for prediction tasks. In this paper, we aim to propose a general deep neural network which can jointly model student heterogeneous … Show more
“…where F(•) is the residual function (i.e., two combinations of "FC+PReLU+Dropout") and λ is the block index. The dimensions of X (λ−1) and F(X (λ−1) ) must be equal in Equation (18). If the dimensions are not equal, we can perform a linear transformation by the skip connection:…”
Section: Interaction Modelingmentioning
confidence: 99%
“…• JMBS [18]: JMBS is proposed in our preliminary work. It leverages multiple context-aware LSTMs and an attention mechanism to model daily behavior sequences.…”
Section: Baselinesmentioning
confidence: 99%
“…We investigate the influence of the activation functions on the proposed model. We replace PReLU with ReLU or tanh in Equation ( 16), (18), and (19). Figure 13 shows the results.…”
Section: Effect Of Hyper-parametersmentioning
confidence: 99%
“…To address the above challenges, we first propose a general neural network called JMBS in our preliminary work [18]. More specifically, each kind of daily behavior sequence is modeled by a variant of LSTM.…”
Behavior prediction based on historical behavioral data have practical real-world significance. It has been applied in recommendation, predicting academic performance, etc. With the refinement of user data description, the development of new functions, and the fusion of multiple data sources, heterogeneous behavioral data which contain multiple types of behaviors become more and more common. In this paper, we aim to incorporate heterogeneous user behaviors and social influences for behavior predictions. To this end, this paper proposes a variant of Long-Short Term Memory (LSTM) which can consider context information while modeling a behavior sequence, a projection mechanism which can model multi-faceted relationships among different types of behaviors, and a multi-faceted attention mechanism which can dynamically find out informative periods from different facets. Many kinds of behavioral data belong to spatio-temporal data. An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed. Moreover, a residual learning-based decoder is designed to automatically construct multiple high-order cross features based on social behavior representation and other types of behavior representations. Qualitative and quantitative experiments on real-world datasets have demonstrated the effectiveness of this model.
“…where F(•) is the residual function (i.e., two combinations of "FC+PReLU+Dropout") and λ is the block index. The dimensions of X (λ−1) and F(X (λ−1) ) must be equal in Equation (18). If the dimensions are not equal, we can perform a linear transformation by the skip connection:…”
Section: Interaction Modelingmentioning
confidence: 99%
“…• JMBS [18]: JMBS is proposed in our preliminary work. It leverages multiple context-aware LSTMs and an attention mechanism to model daily behavior sequences.…”
Section: Baselinesmentioning
confidence: 99%
“…We investigate the influence of the activation functions on the proposed model. We replace PReLU with ReLU or tanh in Equation ( 16), (18), and (19). Figure 13 shows the results.…”
Section: Effect Of Hyper-parametersmentioning
confidence: 99%
“…To address the above challenges, we first propose a general neural network called JMBS in our preliminary work [18]. More specifically, each kind of daily behavior sequence is modeled by a variant of LSTM.…”
Behavior prediction based on historical behavioral data have practical real-world significance. It has been applied in recommendation, predicting academic performance, etc. With the refinement of user data description, the development of new functions, and the fusion of multiple data sources, heterogeneous behavioral data which contain multiple types of behaviors become more and more common. In this paper, we aim to incorporate heterogeneous user behaviors and social influences for behavior predictions. To this end, this paper proposes a variant of Long-Short Term Memory (LSTM) which can consider context information while modeling a behavior sequence, a projection mechanism which can model multi-faceted relationships among different types of behaviors, and a multi-faceted attention mechanism which can dynamically find out informative periods from different facets. Many kinds of behavioral data belong to spatio-temporal data. An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed. Moreover, a residual learning-based decoder is designed to automatically construct multiple high-order cross features based on social behavior representation and other types of behavior representations. Qualitative and quantitative experiments on real-world datasets have demonstrated the effectiveness of this model.
“…Modularity 6-Internet of things (IoTs) and smart buildings (Sources:[29,54,77,[94][95][96][97][98][99][100][101][102][103]). Modularity 8-Performance measurement and forecasting (Sources:[12,35,43,58,99,[110][111][112][113][114]). Modularity 9-Smart campus applications (Sources:[2,90,99,[115][116][117][118][119]).…”
Sustainable development can be attained at a microlevel and having smart campuses around the world presents an opportunity to achieve city-wide smartness. In the process of attaining smartness on campuses, the elements requiring attention must be investigated. There are many publications on smart campuses, and this investigation used the bibliometric analysis method to identify such publications produced over the last decade. A matrix of 578 nodes and 3217 edges was developed from 285 publications on smart campus construction and procurement. Fifteen cluster themes were produced from the bibliometric analysis. The findings revealed that China contributed 48.4% of all published articles on the smart campus. The findings presented a framework from the cluster themes under the four broad infrastructure areas of building construction or repurposing, technology and IT network, continuous improvement, and smart learning and teaching management. The implications of the findings identified that IT project management, traditional procurement strategy, and standard forms of contracts such as the New Engineering Contract (NEC) and the Joint Contract Tribunal (JCT) are applicable in the procurement of smart cities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.