National University of Singapore

About: National University of Singapore is a education organization based out in Singapore, Singapore. It is known for research contribution in the topics: Population & Catalysis. The organization has 74269 authors who have published 165426 publications receiving 5474934 citations. The organization is also known as: NUS & Universiti Kebangsaan Singapura.

Context-Dependent Sentiment Analysis in User-Generated Videos.

Abstract: Multimodal sentiment analysis is a developing area of research, which involves the identification of sentiments in videos. Current research considers utterances as independent entities, i.e., ignores the interdependencies and relations among the utterances of a video. In this paper, we propose a LSTM-based model that enables utterances to capture contextual information from their surroundings in the same video, thus aiding the classification process. Our method shows 5-10% performance improvement over the state of the art and high robustness to generalizability.

Cell type-specific channelrhodopsin-2 transgenic mice for optogenetic dissection of neural circuitry function

Abstract: Optogenetic methods have emerged as powerful tools for dissecting neural circuit connectivity, function and dysfunction. We used a bacterial artificial chromosome (BAC) transgenic strategy to express the H134R variant of channelrhodopsin-2, ChR2(H134R), under the control of cell type–specific promoter elements. We performed an extensive functional characterization of the newly established VGAT-ChR2(H134R)-EYFP, ChAT-ChR2(H134R)-EYFP, Tph2-ChR2(H134R)-EYFP and Pvalb(H134R)-ChR2-EYFP BAC transgenic mouse lines and demonstrate the utility of these lines for precisely controlling action-potential firing of GABAergic, cholinergic, serotonergic and parvalbumin-expressing neuron subsets using blue light. This resource of cell type–specific ChR2(H134R) mouse lines will facilitate the precise mapping of neuronal connectivity and the dissection of the neural basis of behavior.

Electrochemical Delamination of CVD-Grown Graphene Film: Toward the Recyclable Use of Copper Catalyst

Abstract: The separation of chemical vapor deposited (CVD) graphene from the metallic catalyst it is grown on, followed by a subsequent transfer to a dielectric substrate, is currently the adopted method for device fabrication. Most transfer techniques use a chemical etching method to dissolve the metal catalysts, thus imposing high material cost in large-scale fabrication. Here, we demonstrate a highly efficient, nondestructive electrochemical route for the delamination of CVD graphene film from metal surfaces. The electrochemically delaminated graphene films are continuous over 95% of the surface and exhibit increasingly better electronic quality after several growth cycles on the reused copper catalyst, due to the suppression of quasi-periodical nanoripples induced by copper step edges. The electrochemical delamination process affords the advantages of high efficiency, low-cost recyclability, and minimal use of etching chemicals.

Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics

Abstract: In numerous industrial applications where safety, efficiency, and reliability are among primary concerns, condition-based maintenance (CBM) is often the most effective and reliable maintenance policy. Prognostics, as one of the key enablers of CBM, involves the core task of estimating the remaining useful life (RUL) of the system. Neural networks-based approaches have produced promising results on RUL estimation, although their performances are influenced by handcrafted features and manually specified parameters. In this paper, we propose a multiobjective deep belief networks ensemble (MODBNE) method. MODBNE employs a multiobjective evolutionary algorithm integrated with the traditional DBN training technique to evolve multiple DBNs simultaneously subject to accuracy and diversity as two conflicting objectives. The eventually evolved DBNs are combined to establish an ensemble model used for RUL estimation, where combination weights are optimized via a single-objective differential evolution algorithm using a task-oriented objective function. We evaluate the proposed method on several prognostic benchmarking data sets and also compare it with some existing approaches. Experimental results demonstrate the superiority of our proposed method.