Matching-constrained active contours with affine-invariant shape prior by Yeung, Sai-Kit, Wang, Junyan, Chan, Kap Luk

“…To obtain a unified optimization model for this task, we additionally formulate the matching score as a constraint to active contour model, resulting in our matching-constrained active contour. …”
Get full text
Get full text
Get full text

Identification of genetic effects underlying type 2 diabetes in South Asian and European populations by Loh, Marie, Zhang, Weihua, Ng, Hong Kiat, Schmid, Katharina, Lamri, Amel, Tong, Lin, Meraj Ahmad, Lee, Jung-Jin, Ng, Maggie C. Y., Petty, Lauren E., Spracklen, Cassandra N., Takeuchi, Fumihiko, Md. Tariqul Islam, Jasmine, Farzana, Kasturiratne, Anuradhani, Muhammad Kibriya, Mohlke, Karen L., Paré, Guillaume, Prasad, Gauri, Mohammad Shahriar, Chee, Miao Ling, de Silva, H. Janaka, Engert, James C., Gerstein, Hertzel C., Mani, K. Radha, Sabanayagam, Charumathi, Vujkovic, Marijana, Wickremasinghe, Ananda R., Wong, Tien Yin, Yajnik, Chittaranjan S., Salim Yusuf, Habibul Ahsan, Bharadwaj, Dwaipayan, Anand, Sonia S., Below, Jennifer E., Boehnke, Michael, Bowden, Donald W., Chandak, Giriraj R., Cheng, Ching-Yu, Kato, Norihiro, Mahajan, Anubha, Sim, Xueling, McCarthy, Mark I., Morris, Andrew P., Kooner, Jaspal S., Saleheen, Danish, Chambers, John C.

“…The loci are enriched for regulatory features, including DNA methylation and gene expression in relevant tissues, and highlight CHMP4B, PDHB, LRIG1 and other genes linked to adiposity and glucose metabolism. A polygenic risk score based on South Asian-derived summary statistics shows ~4-fold higher risk for T2D between the top and bottom quartile. …”
Get full text

Gender-based multi-aspect sentiment detection using multilabel learning by Kumar, J. Ashok, Trueman, Tina Esther, Cambria, Erik

“…Results show that traditional multilabel transformation methods achieve better performance for small amounts of data and long-range sequence in terms of samples and labels, and that deep learning models achieve better performance in terms of mean test accuracy, AUC Score, RL, and average precision using GloVe word embedding features in both datasets.…”
Get full text

Deep learning-enhanced jewelry material jadeite jade quality assessment by Meng, Liang, Raja Ahmad Effendi, Raja Ahmad Azmeer, Sun, Wei, Mo, Lili, Abdul Rahman, Ahmad Rizal, Hsu, Yu-Lin, Barron, Deirdre

“…The outcomes were promising, with the model achieving notable performance indicators: an accuracy rate of approximately 84.75%, a recall rate of about 84.94%, and an F1 score of roughly 73.76% in jade image classification tasks. …”

Detection and Measurement System for Button Mushrooms Using Convolutional Neural Network by Yong, Lio Wei, Ambar, Radzi, Abd Wahab, Mohd Helmy, Abd Jamil, Muhammad Mahadi, Choon, Chew Chang

“…The model with 2000 iterations demonstrated the most effective performance based on Recall, Precision, F1-score, Time and Mean Average Precision metrics. The model was used in a small-scale experimental setup to evaluate the button mushroom detection and measurement system’s performance. …”
Get full text

User Profiling Based on Nonlinguistic Audio Data by Shen, Jiaxing, Cao, Jiannong, Lederman, Oren, Tang, Shaojie, Pentland, Alex

“…According to the experimental evaluation of 100 people in 273 meetings, we achieved 0.759 and 0.652 in F1-score for gender identification and personality recognition, respectively.…”
Get full text

Generating Molecular Fragmentation Graphs with Autoregressive Neural Networks by Goldman, Samuel, Li, Janet, Coley, Connor W

“…We introduce a physically grounded neural approach that learns to predict each breakage event and score the most relevant subset of molecular fragments quickly and accurately. …”
Get full text

Understanding the usage of physical activity tracking devices by Lam, Pui Shan

“…Participants who used a tracker for more than a year before eventually stopping usage had a significantly higher score for device breakage (p = 0.030) or having experienced negative psychological impacts (p = 0.001) as compared to those who used a tracker for less than a year before stopping usage. …”
Get full text

Evaluating the quality of evidence for intelligent tutoring systems in the tutoring of math for children aged 6 to 12 : a systematic review by Cheng, Janice Shu Hui, Lee, Keith Yong Wei

“…From these 14 studies, 4 of them showed “sufficient” evidence to support their findings on the incorporation of ITSs into mainstream classrooms, but went on to score poorly on other additional quality indicators. …”
Get full text

Object detection in car cabin environment by Lee, Wai Yeong

“…The results were satisfactory, with the EfficientDet-D3 achieving a COCO mAP score of 64.6 on the manually annotated Drive & Act dataset with a latency of 35.4ms.…”
Get full text

Study of feature selection for angle-closure glaucoma detection by Gercke, Norman.

“…Existing feature selection algorithms such as Minimum Redundancy Maximum Relevance (MRMR) and Laplacian Score offer promising feature selection capabilities. …”
Get full text

Inertia measurement unit based sensing module for CPT training kit by Lee, Gabriel Wei Jian

“…Additionally even professionals achieved only 70% average score in their basic life support skill examinations. …”
Get full text

Coach-athlete relationship and athletes’ motivation: moderating effects of individual and team sports by Yee, Yun Shawn

“…Team sport athletes had a higher mean score on both CART-Q and SMS, indicating high levels of interdependency between coach and athlete in both types of sport. …”
Get full text

A comparison of Google translate and Youdao translation : a case study of sentences Selected from Financial Times by Zhang, Xue Qing

“…In particular, Youdao outperformed Google by an average of 22.9% BLEU score while the total number of linguistic errors produced by Youdao was 48 fewer than that produced by Google. …”
Get full text

Knowledge of autism spectrum disorder among parents in Hospital Universiti Sains Malaysia by Diah, Nazihah Mohmad

“…A sample size of 94 parents was selected. A knowledge score was categorized into low level, medium level and high level of knowledge. …”
Get full text

Pandemic Marine Risks Assessment for Marine Spatial Planning (MSP): A Case Study of Northport, Malaysia by Parmen, Ayati, Mohamad, Nazirah, Ismail, Badrul Hisham, Opaluwa, Yusuf Drisu

“…According to the findings, the Vehicle's Terminal zone had the highest score of 17.72, indicating it to be the most severely impacted zone, followed by the Passenger's Terminal zone (15.88), Distribution Centre zone (14.62), Bulk zone (14.52), Dangerous Good zone (14.13), Free Zone (14.10), Ancillary Service zone (13.65), and Container zone (13.39). …”

Transforming education with deep learning: A systematic review on predicting student performance and critical challenges by Nazir, M., Noraziah, Ahmad, Rahmah, Mokhtar, Fakherldin, Mohammed, Khawaji, Ahmad

“…Subsequently, the aim, technique used, dataset used, performance score attained, significance, and limitations of the existing studies were discussed in this review.…”
Get full text

Online learning for search and classification by Nguyen, Thanh Tam

“…(i) Feature selection: we have investigated a number of newly supervised term weighting methods to improve the performance of text classification; (ii) Online classification: we have proposed several online learning algorithms that can be used for topic classification; (iii) Two-view online learning: we have proposed a two-view online learning algorithm, which can work on two-view datasets; (iv) Online learning-to-rank: for search engine, we have proposed an online learning-to-rank algorithm, which was to learn a scoring function to re-rank the search result.…”
Get full text

The impact of anxiety and challenge on quiet eye in tenpin bowling by Lim, Bernice Hui Ying

“…The anxiety inducing condition required players to achieve a target score, while bowling on non-preferred oiling pattern was the high challenge condition. …”
Get full text

Phenotypic vs. genetic mismatch of BMI and type 2 diabetes: evidence from two perspective cohort studies by Li, A, Gong, S, Yu, C, Pei, P, Yang, L, Millwood, IY, Walters, RG, Chen, Y, Du, H, Yang, X, Hou, W, Chen, J, Chen, Z, Lv, J, Li, L, Sun, D, China Kadoorie Biobank Collaborative Group

“…We therefore used data from the China Kadoorie Biobank and UK Biobank and calculated BMI-PGM for each participant as the difference between the percentile for adjusted BMI at baseline and the percentile for adjusted polygenic risk score for BMI. Participants were categorized into discordantly low (BMI-PGM< the 1st quartile), concordant (the 1st quartile ≤BMI-PGM< the 3rd quartile), and discordantly high (BMI-PGM≥the 3rd quartile) groups. …”