Human action recognition using machine learning by Cao, QingTian

“…Additionally, it is easy to train while still be able to learn the important information of the source data.…”
Get full text

Financial forecasting using meta-cognitive fuzzy neural networks by Singh Akhand Pratap

“…Some potential ways to address the above issues could be usage of synthetic data through time-series models to train the model till the test date; usage of manual inferences drawn from the indicators to make judgements about the present day; usage of multiple machine learning models and combining the results from all; usage of dynamic feature selection mechanism to make improvements to the prediction; and usage of dynamic thresholds that are dependent on the market conditions. …”
Get full text

Semantic mapping for articulated objects by Luar, Shui Song

“…As an extension of semantic segmentation problem, there is still an unexplored field of identifying joints of an articulated object within an image. …”
Get full text

15.269 Literature, Ethics and Authority, Fall 2005 by Hafrey, Leigh

“…Readings include work by Robert Bolt, Jane Smiley, Virginia Woolf, Ursula LeGuin, Wole Soyinka, and others; films include "Three Kings," "Crouching Tiger, Hidden Dragon," "Hotel Rwanda," and others. …”
Get full text

Effects of individual research practices on fNIRS signal quality and latent characteristics by Bizzego, Andrea, Carollo, Alessandro, Lim, Mengyu, Esposito, Gianluca

“…However, the reproducibility and comparability of fNIRS studies is still an open issue in the scientific community. …”
Get full text

A study of deep learning on many-core processors by Chen, Peng

“…Some problems in deep learning are still challenging research topics. With big data, training time is one of the major concerns to design a deep network. …”
Get full text

Mobile landmark recognition for information retrieval by Aung, Pyae Sone

“…Even reducing the resolution still gives the best result for dense sampling.…”
Get full text

Advanced control of wind power systems by Dang, Dinh Quy

“…The control algorithm for aerodynamics drive-train and dc-link voltage is therefore of the research interest. …”
Get full text

Rail (real) safety issues: predictive maintenance for Singapore railway by Khoo, Alyna Yi Jie

“…The quest to predict railway faults in Singapore is still underway, spearheaded by the Rail Enterprise Asset Management System (REAMS) project jointly led by SIEMENS and ST Engineering Consortium formed in 2018. …”
Get full text

The Malay Standard Framework (KSBM) as a measure of Malay writing mastery in third form activity books by Abd. Nasir, Siti Noridayu, Abdul Halim, Hazlina

“…This activity books is used by the Imtiyaz Tuition Centre in Putrajaya to train students at the third level for five month from early January to Mei. …”
Get full text

Lubrication mechanisms in offshore wind turbines by Gadgil, Abhiruchi

“…The lubricant is one of the components of the drive-train based systems. Lubricant interaction with the bearing and gears has been studied extensively to improve design parameters. …”
Get full text

Dynamic Time Warping fixed - frame coefficient with pitch feature for speech recognition system with neural network by Sudirman, Rubita

Get full text

Implementation of low sampling rate algorithm by Tan, Michael Teck Xin

“…When these models are trained with a large number of images, it is highly inefficient as it could take extremely long durations of time to train or require a very powerful computer to complete the process. …”
Get full text

A study on open set recognition methods by Sun, Xin

“…Deep learning has achieved state-of-the-art performance in many computer vision tasks, but there are still multiple challenges when applying deep learning to real-world problems. …”
Get full text

Neural combinatorial optimization: from routing to integer programming by Wu, Yaoxin

“…Although there is already abundant literature in such domain, some challenging aspects are still not tackled well. For example, the current deep models are generally still inferior to highly-specialized solvers in some specific COPs, and meanwhile it is still difficult for NCO methods to solve general COPs, especially the ones with uncertainty and multiple objectives. …”
Get full text

Prediction of stable perovskite quantum dots (QDs) using machine learning (ML) algorithms by Cheong, Ivan

“…Use of this new technology in the materials industry is still in its infancy, with many studies incorporating it as a supplement instead of substitution. …”
Get full text

Unveiling the future of budget hotels in Singapore by Chua, Hwee Lian, Kew, Wong Yip, Soh, Wee Li

“…The SHA can assist by providing ample staff training support, and the STPB could ensure adequate publishing and dissemination of information concerning budget hotels. …”
Get full text

Effective and efficient topic mining and exploration from geo-textual data by Zhao, Kaiqi

“…Some studies propose to learn geographical topic models to uncover latent regions and geographical topics. However, training these models is time consuming. It often takes months to train a model of moderate size (e.g., thousands of topics and thousands of regions) on millions of documents. …”
Get full text

Mobile coaching app for powerlifting by Wang, Longfei

“…As a competitive strength sport, despite it doe not require as much technique as weightlifting, powerlifting training is still very taxing physically and mentally, so it requires proper programming to progress and avoid injuries as well as balance between daily life and training. …”
Get full text

Design of intrusion detection systems for vehicular networks by Liang, Junwei

“…In addition, the performance of the IDS with FM-HMM is still remarkable even when rogue vehicles are 40% of the total. …”
Get full text