Searcharxiv⌕ Search

arXiv subjects

Boon Leong Lan

Publications and source records attributed to Boon Leong Lan.

14 recordsLinked to original sources
arXiv2022

A modified peer instruction protocol: peer versus teacher's instruction

Peer Instruction (PI) was introduced by Mazur to help students learn physics concepts during lectures. Besides physics, PI has also been adopted in other STEM fields. In this approach, students answer a related question individually after a concept has been presented. Before they revote on the same question individually, they are asked to convince others their answer is correct during peer discussion. The percentage of correct answer typically increased after peer discussion. However, Smith et al. highlighted that the improvement may be due to copying, not because students actually learned how to reason correctly. To exclude copying, Smith et al. modified Mazur's PI protocol by adding a second question Q2 after the students revote on the first question Q1. Q2 is 'isomorphic' to Q1, meaning that it requires the application of the same concept but the 'cover story' is different. The answer to Q1 is not revealed until after the individual vote on Q2. Here, we simplify Smith et al.'s PI protocol by removing the revote on Q1. Moreover, our Q1 and Q2 are similar, i.e. the same but some information given is different. Our PI protocol is thus the same as Mazur's, except the pre and post discussion questions are not exactly the same. We compare the effectiveness of PI, in our protocol, to teacher's instruction (TI) for a pair of similar questions, involving Lenz's law, using Hake's normalized gain and a statistical test.

physics.ed-ph↗
arXiv2022

Epileptic Seizure Classification Using Combined Labels and a Genetic Algorithm

Epilepsy affects 50 million people worldwide and is one of the most common serious neurological disorders. Seizure detection and classification is a valuable tool for diagnosing and maintaining the condition. An automated classification algorithm will allow for accurate diagnosis. Utilising the Temple University Hospital (TUH) Seizure Corpus, six seizure types are compared; absence, complex partial, myoclonic, simple partial, tonic and tonic- clonic models. This study proposes a method that utilises unique features with a novel parallel classifier - Parallel Genetic Naive Bayes (NB) Seizure Classifier (PGNBSC). The PGNBSC algorithm searches through the features and by reclassifying the data each time, the algorithm will create a matrix for optimum search criteria. Ictal states from the EEGs are segmented into 1.8 s windows, where the epochs are then further decomposed into 13 different features from the first intrinsic mode function (IMF). The features are compared using an original NB classifier in the first model. This is improved upon in a second model by using a genetic algorithm (Binary Grey Wolf Optimisation, Option 1) with a NB classifier. The third model uses a combination of the simple partial and complex partial seizures to provide the highest classification accuracy for each of the six seizures amongst the three models (20%, 53%, and 85% for first, second, and third model, respectively).

eess.SP↗
arXiv2021

Seizure Classification of EEG based on Wavelet Signal Denoising Using a Novel Channel Selection Algorithm

Epilepsy is a disorder of the nervous system that can affect people of any age group. With roughly 50 million people worldwide diagnosed with the disorder, it is one of the most common neurological disorders. The EEG is an indispensable tool for diagnosis of epileptic seizures in an ideal case, as brain waves from an epileptic person will present distinct abnormalities. However, in real world situations there will often be biological and electrical noise interference, as well as the issue of a multichannel signal, which introduce a great challenge for seizure detection. For this study, the Temple University Hospital (TUH) EEG Seizure Corpus dataset was used. This paper proposes a novel channel selection method which isolates different frequency ranges within five channels. This is based upon the frequencies at which normal brain waveforms exhibit. A one second window was selected, with a 0.5 second overlap. Wavelet signal denoising was performed using Daubechies 4 wavelet decomposition, thresholding was applied using minimax soft thresholding criteria. Filter banking was used to localise frequency ranges from five specific channels. Statistical features were then derived from the outputs. After performing bagged tree classification using 500 learners, a test accuracy of 0.82 was achieved.

q-bio.PE↗
arXiv2021

CASPIANET++: A Multidimensional Channel-Spatial Asymmetric Attention Network with Noisy Student Curriculum Learning Paradigm for Brain Tumor Segmentation

Convolutional neural networks (CNNs) have been used quite successfully for semantic segmentation of brain tumors. However, current CNNs and attention mechanisms are stochastic in nature and neglect the morphological indicators used by radiologists to manually annotate regions of interest. In this paper, we introduce a channel and spatial wise asymmetric attention (CASPIAN) by leveraging the inherent structure of tumors to detect regions of saliency. To demonstrate the efficacy of our proposed layer, we integrate this into a well-established convolutional neural network (CNN) architecture to achieve higher Dice scores, with less GPU resources. Also, we investigate the inclusion of auxiliary multiscale and multiplanar attention branches to increase the spatial context crucial in semantic segmentation tasks. The resulting architecture is the new CASPIANET++, which achieves Dice Scores of 91.19% whole tumor, 87.6% for tumor core and 81.03% for enhancing tumor. Furthermore, driven by the scarcity of brain tumor data, we investigate the Noisy Student method for segmentation tasks. Our new Noisy Student Curriculum Learning paradigm, which infuses noise incrementally to increase the complexity of the training images exposed to the network, further boosts the enhancing tumor region to 81.53%. Additional validation performed on the BraTS2020 data shows that the Noisy Student Curriculum Learning method works well without any additional training or finetuning.

eess.IV↗
arXiv2020

A new semi-supervised self-training method for lung cancer prediction

Background and Objective: Early detection of lung cancer is crucial as it has high mortality rate with patients commonly present with the disease at stage 3 and above. There are only relatively few methods that simultaneously detect and classify nodules from computed tomography (CT) scans. Furthermore, very few studies have used semi-supervised learning for lung cancer prediction. This study presents a complete end-to-end scheme to detect and classify lung nodules using the state-of-the-art Self-training with Noisy Student method on a comprehensive CT lung screening dataset of around 4,000 CT scans. Methods: We used three datasets, namely LUNA16, LIDC and NLST, for this study. We first utilise a three-dimensional deep convolutional neural network model to detect lung nodules in the detection stage. The classification model known as Maxout Local-Global Network uses non-local networks to detect global features including shape features, residual blocks to detect local features including nodule texture, and a Maxout layer to detect nodule variations. We trained the first Self-training with Noisy Student model to predict lung cancer on the unlabelled NLST datasets. Then, we performed Mixup regularization to enhance our scheme and provide robustness to erroneous labels. Results and Conclusions: Our new Mixup Maxout Local-Global network achieves an AUC of 0.87 on 2,005 completely independent testing scans from the NLST dataset. Our new scheme significantly outperformed the next highest performing method at the 5% significance level using DeLong's test (p = 0.0001). This study presents a new complete end-to-end scheme to predict lung cancer using Self-training with Noisy Student combined with Mixup regularization. On a completely independent dataset of 2,005 scans, we achieved state-of-the-art performance even with more images as compared to other methods.

eess.IV↗
arXiv2019

Lung Nodule Classification using Deep Local-Global Networks

Purpose: Lung nodules have very diverse shapes and sizes, which makes classifying them as benign/malignant a challenging problem. In this paper, we propose a novel method to predict the malignancy of nodules that have the capability to analyze the shape and size of a nodule using a global feature extractor, as well as the density and structure of the nodule using a local feature extractor. Methods: We propose to use Residual Blocks with a 3x3 kernel size for local feature extraction, and Non-Local Blocks to extract the global features. The Non-Local Block has the ability to extract global features without using a huge number of parameters. The key idea behind the Non-Local Block is to apply matrix multiplications between features on the same feature maps. Results: We trained and validated the proposed method on the LIDC-IDRI dataset which contains 1,018 computed tomography (CT) scans. We followed a rigorous procedure for experimental setup namely, 10-fold cross-validation and ignored the nodules that had been annotated by less than 3 radiologists. The proposed method achieved state-of-the-art results with AUC=95.62%, while significantly outperforming other baseline methods. Conclusions: Our proposed Deep Local-Global network has the capability to accurately extract both local and global features. Our new method outperforms state-of-the-art architecture including Densenet and Resnet with transfer learning.

cs.CV↗
arXiv2005

Power spectrum of the fluctuation of Chebyshev's prime counting function

The one-sided power spectrum of the fluctuation of Chebyshev's weighted prime counting function is numerically estimated based on samples of the fluctuating function of different sizes. The power spectrum is also estimated analytically for large frequency based on Riemann hypothesis and the exact formula for the fluctuating function in terms of all the non-trivial Riemann zeroes. Our analytical estimate is consistent with our numerical estimate of a 1/f^2 power spectrum.

math.GM↗
arXiv2003

Einstein was Wrong: Newtonian Dynamics Can Disagree Completely with Relativistic Dynamics at Low Speed

According to Einstein, the trajectory of a particle that is predicted by special relativistic mechanics is well approximated by the trajectory predicted by Newtonian mechanics if the particle speed is low, i.e., much less than the speed of light. However, in this paper, it is shown with a counterexample Hamiltonian dynamical system that Newtonian dynamics can eventually disagree completely with relativistic dynamics even though the particle speed is low. After the breakdown of the agreement, either the Newtonian description is no longer correct or the relativistic description is no longer correct or both descriptions are no longer correct for the low speed motion.

physics.class-ph↗
arXiv2003

Grandma's local realistic theory for the Einstein-Podolsky-Rosen-Bohm experiment

A local realistic theory is presented for Mermin's special case of the EPRB experiment. The theory, which is readily extended to the general EPRB experiment, reproduces all the predictions of quantum theory. It also reveals that Bell, and also Hess and Philipp, had made an error in the mathematical formulation of Einstein's locality or no action at a distance principle.

quant-ph↗
arXiv2003

Grandma's local realistic theory for the Greenberger-Horne-Zeilinger experiment

A realistic theory is constructed for the GHZ experiment. It is shown that the theory is local and it reproduces all the probabilistic predictions of quantum theory. This local realistic theory shows that GHZ had formulated Einstein's locality or no-action-at-a-distance principle incorrectly in their local realistic theory for the experiment.

quant-ph↗
arXiv2003

Realistic interpretation of a superposition state does not imply a mixture

Contrary to previous claims, it is shown that, for an ensemble of either single-particle systems or multi-particle systems, the realistic interpretation of a superposition state that mathematically describes the ensemble does not imply that the ensemble is a mixture. Therefore it cannot be argued that the realistic interpretation is wrong on the basis that some predictions derived from the mixture are different from the corresponding predictions derived from the superposition state.

quant-ph↗
arXiv2002

A realist view of the canonical EPRB experiment based on quantum theory and its consequences

A realist view of the Einstein-Podolsky-Rosen-Bohm experiment with spins based on quantum theory is presented. This view implies that there is no action at a distance. It also implies that the measurement result A (B) for particle 1 (2) depends on both magnet angles, and hence the probability of obtaining the result A (B) also depends on both magnet angles. In light of these realist implications, it is clear that what is wrong at least with local realistic theory is not the locality or no action-at-a-distance assumption itself but rather the formal implementation of that assumption.

quant-ph↗