Enhanced CNN Models for Binary and Multiclass Student Classification on Temporal Educational Data at the Program Level

In educational data mining, student classification is an important and popular task by predicting final study status of each student. In the existing works, this task has been considered in many various contexts at both course and program levels with different learning approaches. However, its real-world characteristics such as temporal aspects, data imbalance, data overlapping, and data shortage with sparseness have not yet been fully investigated. Making the most of deep learning, our work is the first one addressing those challenges for the program-level student classification task. In a simple but effective manner, convolutional neural networks (CNNs) are proposed to exploit their well-known advantages on images for temporal educational data. As a result, the task is resolved by our enhanced CNN models with more effectiveness and practicability on real datasets. Our CNN models outperform other traditional models and their various variants on a consistent basis for program-level student classification.

Download Full-text

Deep convolutional neural networks for cardiovascular vulnerable plaque detection

MATEC Web of Conferences ◽

10.1051/matecconf/201927702024 ◽

2019 ◽

Vol 277 ◽

pp. 02024 ◽

Cited By ~ 1

Author(s):

Lincan Li ◽

Tong Jia ◽

Tianqi Meng ◽

Yizhe Liu

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Vulnerable Plaque ◽

Recall Rate ◽

Superior Performance ◽

Learning Approaches ◽

Deep Convolutional Neural Networks ◽

Vulnerable Plaques ◽

Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

Download Full-text

Pretrained Convolutional Neural Networks Perform Well in a Challenging Test Case: Identification of Plant Bugs (Hemiptera: Miridae) Using a Small Number of Training Images

Insect Systematics and Diversity ◽

10.1093/isd/ixab004 ◽

2021 ◽

Vol 5 (2) ◽

Author(s):

Alexander Knyshov ◽

Samantha Hoang ◽

Christiane Weirauch

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Training Image ◽

Species Level ◽

Identification Accuracy ◽

Support Vector ◽

Test Case ◽

Learning Approaches ◽

Lower Accuracy ◽

Neural Network Classifiers

Abstract Automated insect identification systems have been explored for more than two decades but have only recently started to take advantage of powerful and versatile convolutional neural networks (CNNs). While typical CNN applications still require large training image datasets with hundreds of images per taxon, pretrained CNNs recently have been shown to be highly accurate, while being trained on much smaller datasets. We here evaluate the performance of CNN-based machine learning approaches in identifying three curated species-level dorsal habitus datasets for Miridae, the plant bugs. Miridae are of economic importance, but species-level identifications are challenging and typically rely on information other than dorsal habitus (e.g., host plants, locality, genitalic structures). Each dataset contained 2–6 species and 126–246 images in total, with a mean of only 32 images per species for the most difficult dataset. We find that closely related species of plant bugs can be identified with 80–90% accuracy based on their dorsal habitus alone. The pretrained CNN performed 10–20% better than a taxon expert who had access to the same dorsal habitus images. We find that feature extraction protocols (selection and combination of blocks of CNN layers) impact identification accuracy much more than the classifying mechanism (support vector machine and deep neural network classifiers). While our network has much lower accuracy on photographs of live insects (62%), overall results confirm that a pretrained CNN can be straightforwardly adapted to collection-based images for a new taxonomic group and successfully extract relevant features to classify insect species.

Download Full-text

Artificial Neural Networks on FPGAs for Real-Time Energy Reconstruction of the ATLAS LAr Calorimeters

Computing and Software for Big Science ◽

10.1007/s41781-021-00066-y ◽

2021 ◽

Vol 5 (1) ◽

Author(s):

Georges Aad ◽

Anne-Sophie Berthold ◽

Thomas Calvet ◽

Nemer Chiedde ◽

Etienne Marie Fortin ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Real Time ◽

Hadron Collider ◽

Liquid Argon ◽

Learning Approaches ◽

High Luminosity ◽

Proton Proton ◽

Real Time Processing ◽

Energy Reconstruction

AbstractThe ATLAS experiment at the Large Hadron Collider (LHC) is operated at CERN and measures proton–proton collisions at multi-TeV energies with a repetition frequency of 40 MHz. Within the phase-II upgrade of the LHC, the readout electronics of the liquid-argon (LAr) calorimeters of ATLAS are being prepared for high luminosity operation expecting a pileup of up to 200 simultaneous proton–proton interactions. Moreover, the calorimeter signals of up to 25 subsequent collisions are overlapping, which increases the difficulty of energy reconstruction by the calorimeter detector. Real-time processing of digitized pulses sampled at 40 MHz is performed using field-programmable gate arrays (FPGAs). To cope with the signal pileup, new machine learning approaches are explored: convolutional and recurrent neural networks outperform the optimal signal filter currently used, both in assignment of the reconstructed energy to the correct proton bunch crossing and in energy resolution. The improvements concern in particular energies derived from overlapping pulses. Since the implementation of the neural networks targets an FPGA, the number of parameters and the mathematical operations need to be well controlled. The trained neural network structures are converted into FPGA firmware using automated implementations in hardware description language and high-level synthesis tools. Very good agreement between neural network implementations in FPGA and software based calculations is observed. The prototype implementations on an Intel Stratix-10 FPGA reach maximum operation frequencies of 344–640 MHz. Applying time-division multiplexing allows the processing of 390–576 calorimeter channels by one FPGA for the most resource-efficient networks. Moreover, the latency achieved is about 200 ns. These performance parameters show that a neural-network based energy reconstruction can be considered for the processing of the ATLAS LAr calorimeter signals during the high-luminosity phase of the LHC.

Download Full-text

A Method for Image Forgery Detection Based on Error Level Analysis (ELA) Technique

Knowledge Innovation Through Intelligent Software Methodologies, Tools and Techniques - Frontiers in Artificial Intelligence and Applications ◽

10.3233/faia200557 ◽

2020 ◽

Author(s):

Emanuele Morra ◽

Roberto Revetria ◽

Danilo Pecorino ◽

Gabriele Galli ◽

Andrea Mungo ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Digital Imaging ◽

Imaging Techniques ◽

Automated System ◽

Learning Approaches ◽

Forgery Detection ◽

Error Level ◽

Detection Algorithms ◽

Level Analysis

In the last years, there has been growing a large increase in digital imaging techniques, and their applications became more and more pivotal in many critical scenarios. Conversely, hand in hand with this technological boost, imaging forgeries have increased more and more along with their level of precision. In this view, the use of digital tools, aiming to verify the integrity of a certain image, is essential. Indeed, insurance is a field that extensively uses images for filling claim requests and a robust forgery detection is essential. This paper proposes an approach which aims to introduce a full-automated system for identifying potential splicing frauds in images of car plates by overcoming traditional problems using artificial neural networks (ANN). For instance, classic fraud-detection algorithms are impossible to fully automatize whereas modern deep learning approaches require vast training datasets that are not available most of the time. The method developed in this paper uses Error Level Analysis (ELA) performed on car license plates as an input for a trained model which is able to classify license plates in either original or forged.

Download Full-text

Computerised Decision Support for Women’s Health Informatics

Machine Learning ◽

10.4018/978-1-60960-818-7.ch513 ◽

2012 ◽

pp. 1404-1416 ◽

Cited By ~ 1

Author(s):

David Parry

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Decision Making ◽

Decision Support ◽

Expert Systems ◽

Decision Analysis ◽

Health Informatics ◽

Learning Approaches ◽

Learning From Data ◽

Computerized Records

Decision analysis techniques attempt to utilize mathematical data about outcomes and preferences to help people make optimal decisions. The increasing uses of computerized records and powerful computers have made these techniques much more accessible and usable. The partnership between women and clinicians can be enhanced by sharing information, knowledge, and the decision making process in this way. Other techniques for assisting with decision making, such as learning from data via neural networks or other machine learning approaches may offer increased value. Rules learned from such approaches may allow the development of expert systems that actually take over some of the decision making role, although such systems are not yet in widespread use.

Download Full-text

A Systematic Study on Tertiary Level Student Tuition Fee Waiver Management During Pandemic Using Machine Learning Approaches

Advances in Information, Communication and Cybersecurity - Lecture Notes in Networks and Systems ◽

10.1007/978-3-030-91738-8_25 ◽

2022 ◽

pp. 259-273

Author(s):

Asif Khan Shakir ◽

Shanjoy Sutradhar ◽

Ahsanul Hoque Sakib ◽

Washim Akram ◽

Md. Abu Saleh ◽

...

Keyword(s):

Machine Learning ◽

Systematic Study ◽

Tertiary Level ◽

Learning Approaches ◽

Level Student ◽

Tuition Fee

Download Full-text

MSpectraAI: a powerful platform for deciphering proteome profiling of multi-tumor mass spectrometry data by using deep neural networks

BMC Bioinformatics ◽

10.1186/s12859-020-03783-0 ◽

2020 ◽

Vol 21 (1) ◽

Author(s):

Shisheng Wang ◽

Hongwen Zhu ◽

Hu Zhou ◽

Jingqiu Cheng ◽

Hao Yang

Keyword(s):

Mass Spectrometry ◽

Neural Networks ◽

Large Scale ◽

Deep Neural Networks ◽

Spectral Feature ◽

Mass Spectrometry Data ◽

Learning Approaches ◽

Proteomics Data ◽

Proteome Profiling ◽

Analytical Technique

Abstract Background Mass spectrometry (MS) has become a promising analytical technique to acquire proteomics information for the characterization of biological samples. Nevertheless, most studies focus on the final proteins identified through a suite of algorithms by using partial MS spectra to compare with the sequence database, while the pattern recognition and classification of raw mass-spectrometric data remain unresolved. Results We developed an open-source and comprehensive platform, named MSpectraAI, for analyzing large-scale MS data through deep neural networks (DNNs); this system involves spectral-feature swath extraction, classification, and visualization. Moreover, this platform allows users to create their own DNN model by using Keras. To evaluate this tool, we collected the publicly available proteomics datasets of six tumor types (a total of 7,997,805 mass spectra) from the ProteomeXchange consortium and classified the samples based on the spectra profiling. The results suggest that MSpectraAI can distinguish different types of samples based on the fingerprint spectrum and achieve better prediction accuracy in MS1 level (average 0.967). Conclusion This study deciphers proteome profiling of raw mass spectrometry data and broadens the promising application of the classification and prediction of proteomics data from multi-tumor samples using deep learning methods. MSpectraAI also shows a better performance compared to the other classical machine learning approaches.

Download Full-text

Computerised Decision Support for Women's Health Informatics

Medical Informatics in Obstetrics and Gynecology ◽

10.4018/978-1-60566-078-3.ch015 ◽

2009 ◽

pp. 302-314

Author(s):

David Parry

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Decision Making ◽

Decision Support ◽

Expert Systems ◽

Decision Analysis ◽

Health Informatics ◽

Learning Approaches ◽

Learning From Data ◽

Computerized Records

Download Full-text

OPUS-TASS: a protein backbone torsion angles and secondary structure predictor based on ensemble neural networks

Bioinformatics ◽

10.1093/bioinformatics/btaa629 ◽

2020 ◽

Vol 36 (20) ◽

pp. 5021-5026 ◽

Cited By ~ 3

Author(s):

Gang Xu ◽

Qinghua Wang ◽

Jianpeng Ma

Keyword(s):

Neural Networks ◽

Secondary Structure ◽

Structure Prediction ◽

Secondary Structure Prediction ◽

Supplementary Information ◽

Learning Approaches ◽

Protein Backbone ◽

Torsion Angles ◽

Secondary Structure Predictions ◽

The Mean

Abstract Motivation Predictions of protein backbone torsion angles (ϕ and ψ) and secondary structure from sequence are crucial subproblems in protein structure prediction. With the development of deep learning approaches, their accuracies have been significantly improved. To capture the long-range interactions, most studies integrate bidirectional recurrent neural networks into their models. In this study, we introduce and modify a recently proposed architecture named Transformer to capture the interactions between the two residues theoretically with arbitrary distance. Moreover, we take advantage of multitask learning to improve the generalization of neural network by introducing related tasks into the training process. Similar to many previous studies, OPUS-TASS uses an ensemble of models and achieves better results. Results OPUS-TASS uses the same training and validation sets as SPOT-1D. We compare the performance of OPUS-TASS and SPOT-1D on TEST2016 (1213 proteins) and TEST2018 (250 proteins) proposed in the SPOT-1D paper, CASP12 (55 proteins), CASP13 (32 proteins) and CASP-FM (56 proteins) proposed in the SAINT paper, and a recently released PDB structure collection from CAMEO (93 proteins) named as CAMEO93. On these six test sets, OPUS-TASS achieves consistent improvements in both backbone torsion angles prediction and secondary structure prediction. On CAMEO93, SPOT-1D achieves the mean absolute errors of 16.89 and 23.02 for ϕ and ψ predictions, respectively, and the accuracies for 3- and 8-state secondary structure predictions are 87.72 and 77.15%, respectively. In comparison, OPUS-TASS achieves 16.56 and 22.56 for ϕ and ψ predictions, and 89.06 and 78.87% for 3- and 8-state secondary structure predictions, respectively. In particular, after using our torsion angles refinement method OPUS-Refine as the post-processing procedure for OPUS-TASS, the mean absolute errors for final ϕ and ψ predictions are further decreased to 16.28 and 21.98, respectively. Availability and implementation The training and the inference codes of OPUS-TASS and its data are available at https://github.com/thuxugang/opus_tass. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text