RxnScribe: A Sequence Generation Model for Reaction Diagram Parsing by Qian, Yujie, Guo, Jiang, Tu, Zhengkai, Coley, Connor W, Barzilay, Regina

“…We train RxnScribe on a dataset of 1378 diagrams and evaluate it with cross validation, achieving an 80.0% soft match F1 score, with significant improvements over previous models. …”
Get full text

A multi-order derivative feature-based quality assessment model for light field image by Tian, Yu, Zeng, Huanqiang, Xing, Lu, Chen, Jing, Zhu, Jianqing, Ma, Kai-Kuang

“…Finally, the weight map is established through the maximum value of the second-order derivative feature of reference and distorted LFIs, which is further utilized to pool the similarity map for generating the final score. Extensive simulation results have demonstrated that the proposed MDFM is more consistent with the perception of the HVS on the evaluation of LFI than the classical and state-of-the-art IQA methods.…”
Get full text

Differential evolution with large initial populations by Qian, Yanfei

“…One is a traditional standard, fitness. Another is the score, which is generated from the game. This new algorithm, named OGLSHADE-CS, involves other techniques: linear population reduction, success history base adaption, multi-strategy mutation, and conservative selection. …”
Get full text

Recommendation in location based social networks by Chen, Long.

“…In this report, the author first proposes a new method of utilizing spatial sensitivity to generate dynamic weightage average score for combining the User Collaborative Filtering and the Geographical Influence in a personalized fashion for each single user. …”
Get full text

Old wives' tales, did you believe? by Lio, Jen Yun.

“…Old wives’ tales are oral tradition passed down, often from our grandmothers or mothers, that are exaggerated and untrue facts told to scare children into good behaviour. This oral tradition has only been passed around verbally, from old wives to children, with little physical documentation. …”
Get full text

Educational data mining for structured mathematical questions by Kok, Mun Kiat

“…The project aims to use latent semantic analysis and BM25F scoring algorithm in search engines to successfully identify patterns and key features of questions as well as classify a data base of O-level mathematic questions. …”
Get full text

Study of circulation of traffic agents at the road-side bus-stops by Sim, Si Hui

“…In cases where a bus-stop is considered unsafe, the Bus Stop Evaluation Index employs a derived evaluation score based on the weighted average cyclist behaviour and safety ratings. …”
Get full text

Assessing the impact of a sport for development and peace intervention on the mental and physical health of adolescents in Mullaitivu, Sri Lanka by Hamilton, A

“…Adjusting for gender, age and ethnicity did not affect the significance of the results. Mean MFT score in the [V] cohort significantly deteriorated (t (99) = 3.39 p = 0.004), yet did not change significantly in the [C] group.…”

Immunotherapy-resistant neuropathic pain and fatigue predict quality-of-life in contactin-associated protein-like 2 antibody disease by Ceronie, B, Strippel, C, Uy, C, Paneva, S, Makuch, M, Soleimani, B, Turaga, S, Binks, S, Ramanathan, S, Michael, S, Varley, J, Easton, A, Themistocleous, A, John Dawes, Bennett, DL, Irani, A, Handel, AE, Irani, SR

“…Quality-of-life varied widely for any given modified Rankin Scale score, indicating a divergence between patient and clinician assessed outcomes. …”

Technical Tender Evaluation Using Analytical Hierarchy Process (AHP) by Mohamed, Nor Hafizah, Lamsali, Hendrik, Sathyamoorthy, Dinesh

“…The findings show that AHP is more effective than the present method which employs the scoring and weighted sum model. AHP also provides more accurate results with minimal bias. …”
Get full text

Keyword and named entity recognition on emergency call texts by Hu, Wanyu

“…The dataset is fed into the model and the result is evaluated by confusion matrix and F1 score. The predicted result is visualized using a Web Application design using Python Streamlit package. …”
Get full text

An empirical comparison of structural and accounting-based credit risk models. by Leong, Wai Fun., Loh, Shueh Yi., Toh, Elaine Yi Lian.

“…This paper looks into 3 types of credit risk models: Altman Z-Score (2002), KMV-Merton (1974) and Longstaff and Schwartz (1997). …”
Get full text

CET-4 Cloze passage personalized learning by Thoo, Emilene Shu Ping

“…The CET is taken by 18 million people annually to determine the English proficiency of undergraduate and postgraduate students in China and being able to score in the CET will provide one with the option to work or study overseas where English is a native language. …”
Get full text

Lit nation by Ng, Andrea Li-Ting, Wee, Smita Shu Min, Catherine Jane Nicholas, Nur Diyanah Abdul Aziz

“…Snuffed by society in its decades-long push for progress through math and the sciences, and by students for being a “hard to score” subject, literature’s place fell behind. Yet, despite that, the literature scene has been quietly blooming on its own, with passionate characters doing their part to push literature further to the forefront of society and into the hearts of Singaporeans. …”
Get full text

Scene understanding based on heterogeneous data fusion by Zhu, Lingzhi

“…Moreover, after fine tuning process, the highest mAP score it can reach is 0.804. Experiments on testing different variables are implemented, and the results are elaborated as well. …”
Get full text

Machine learning for mathematical question difficulty classification by Pang, Jarald Qi Kai

“…The grading metrics used in this experiment are F1 Score, Precision, Recall and Accuracy. For data pre-processing three text vectorization methods, count vector, word level TF-IDF and N-gram level TF-IDF were used and tested. …”
Get full text

The effect of religiosity on climate change policies by Lim, Sue Qin, Ng, Jia Hui, Tew, Ying Sian

“…We find that religious countries tend to have less extensive and stringent climate change policies, where a 0.1 increase in religiosity is associated with a 5.30 points decrease in CLIMI score. Our results are robust to a number of considerations. …”
Get full text

Learning to detect partially overlapping instances by Arteta, C, Lempitsky, V, Noble, JA, Zisserman, A

“…Our approach is to propose a set of candidate regions, and then select regions based on optimizing a global classification score, subject to the constraint that the selected regions are non-overlapping. …”

Collaborative model of care between Orthopaedics and allied healthcare professionals in knee osteoarthritis (CONNACT) : study protocol for an effectiveness-implementation hybrid ra... by Tan, Bryan Yijia, Pereira, Michelle Jessica, Yang, Su-Yin, Hunter, David J., Skou, Soren Thorgaard, Thumboo, Julian, Car, Josip

“…Secondary outcomes include KOOS individual subscales, quality of life scoring, functional performance, global, diet and psychological related outcomes. …”
Get full text

Designing interactive augmented reality application for student's directed learning of continuous distillation process by Gao, Sitian, Lu, Yunpeng, Ooi, Ching Hui, Cai, Yiyu, Gunawan, Poernomo

“…The evaluation survey with 6-point likert scale questions shows that students had a positive experience using the mobile AR application and it has enhanced their learning experience, as suggested by a mean evaluation score of 5.18 out of 6.0.…”
Get full text