Creating functionally graded concrete materials with varying 3D printing parameters by Tay, Daniel Yi Wei, Lim, Jian Hui, Li, Mingyang, Tan, Ming Jen

Get full text

Lightweight transformers for clinical natural language processing by Rohanian, O, Nouriborji, M, Jauncey, H, Kouchaki, S, Nooralahzadeh, F, Clifton, L, Merson, L, Clifton, DA

“…Specialised pre-trained language models are becoming more frequent in Natural language Processing (NLP) since they can potentially outperform models trained on generic texts. BioBERT (Sanh et al., Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. …”

Learning automations in game engine by Ju, Peng

“…First, design and develop a server-client software version of Beer Game using Java. Second, develop a software entity (AI agent) in the Beer Game software utilizing Memetic approach. …”
Get full text

AI based stock market trending analysis by Goon, Redmond Aldric Yonghao

“…The evaluation of the final model-comprising BERT and a multivariate LSTM- shows a small improvement in evaluation results for stock price forecasting when incorporating news sentiment acquired through BERT as compared to without sentiments.…”
Get full text

MMSE multiuser detection for uplink DS-CDMA with regenerative cooperative relaying by Liu, Yan.

“…Max-Cooperation achieves the lowest BER among the three methods. When the number of users increases, the BER performance with direct transmission gets worse, but the BER performance of Max-Cooperate improves significantly. …”
Get full text

Object-oriented indoor navigation for delivery robot by Li, Yuanwei

“…Although the BERT model has good performance in VLN, the mismatch between instructions and visual information at the input leads to navigation errors for robots in similar scenes. …”
Get full text

Generalized AutoNLP model for name entity recognition task by Wong, Yung Shen

“…In this project, we have proposed an architecture of a combination of deep-learning based approach word embeddings, BERT with static word embeddings, GloVe. Experiments are conducted to study the performance of our proposed architecture with BERT word embeddings on AutoNLP name entity recognition tasks.…”
Get full text

Bit-error rate simulation and analysis of various frequency-hopped multiple-access receivers by Wang, Kaiyuan

“…In the end, we get the results of BER performances in different situations. In each channel, we have 3 figures illustrating the BER performance of MRC, EGC and SC with multiple users. …”
Get full text

Novel receiver design for suppression of frequency-hopped multiple-access (FHMA) systems by Muhammad Faizal Razali

“…We include five diversity combining techniques and simulate the results in order to study if they help improve the BER of the FHMA system. Based on the Matlab simulations, the addition of diversity combining techniques helps to improve the BER of the system. …”
Get full text

An overview of stock trading with sentiment analysis by Tang, Yi Qwan

“…Utilising multiple sentiment analysis models like Sentic API, TextBlob, VADER, BERT, and FinBERT, alongside varying preprocessing methods and news formats, the research explores optimal trading signals for high-frequency trading. …”
Get full text

Transmission of multimedia content over wireless network by Lim, Calvin Yong Poo.

“…BER shows the rate at which the receiver receiving an erroneous bit. …”
Get full text

Investigation on orthogonal frequency division multiplexing with index modulation by Fan, Rui

“…To be specific, in low SNR region, OFDM-IM's BER performance is not as good as classical OFDM's while in high SNR region, OFDM-IM outperforms classical OFDM in terms of BER performance. …”
Get full text

Public opinion trend analysis on nuclear energy via aspect-based sentiment analysis methods by Huang, Fan

“…The Bidirectional Encoder Representation Transformers (BERT) model was applied to detect the sentiment polarities of collected tweets. …”
Get full text

Sentiment analysis for COVID-19 vaccination news by Lim, Pei Yan

“…Different sentiment analysis models, TextBlob, VADER, Flair and CT-BERT, are used. Several rules are defined through analysis to improve the models' accuracy. …”
Get full text

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

“…The model used for this project is the Bidirectional Representations from Transformers (BERT) model. 75% of the Emergency Call Texts dataset is obtained online. …”
Get full text

Influence of presumed influence on thinness as a beauty ideal for girls. by Soh, Wai Siong.

“…On the other hand, if the “influence on significant others or female peers” exerts an impact on “influence on self”, it will result in desire to be thin.…”
Get full text

Interference suppression of coded frequency hopped system by Ong, Johnson Soon Ann

“…The purpose of this report is to study the bit error rate (BER) of the frequency hopped (FH) system with a non-coherent MFSK or M-ary frequency-shift-keyed modulation and how to improve the BER, with the usage of some channel coding techniques. …”
Get full text

Symbol-error performance and bit-error performance for 2-dimensional signals by Ilakkiyaa D/O Gunasekaran

“…The main purpose of this project is to compare the SER and BER performances for different Phase Shift Keying (PSK) and Quadrature Amplitude Modulation (QAM) schemes. …”
Get full text

Topological data analysis for fake news detection by Deng, Ran

“…For this task, three individual models have been used: least absolute shrinkage and selection operator (LASSO) using 0th Dimensional Persistent Image (PI) vectors, Bidirectional Long Short-Term Memory (BiLSTM), and Bidirectional Encoder Representations from Transformers (BERT). Two ensemble models were also used to improve performances by supplementing contextual information from deep-learning models with structural information from PI vectors: BiLSTM + TDA and BERT + TDA. …”
Get full text

Nonlinear channel equalization for wireless communication systems using Legendre neural networks by Patra, Jagdish Chandra, Meher, Pramod Kumar, Chakraborty, Goutam

“…The functional link NN (FLANN) for nonlinear channel equalization which we had proposed earlier, offers faster mean square error (MSE) convergence and better bit error rate (BER) performance compared to multilayer perceptron (MLP). …”
Get full text
Get full text