Real Classification Research Articles

Channel noise induced stochastic effect of Hodgkin-Huxley neurons in a real classification task.

Noise is generally considered to have negative effects on information processing performance. However, it has also been proven that adding random noise or a certain level of stochastic (random) variability to a nonlinear system can increase its performance or sensitivity to weak signals. Despite the studies on this concept, called stochastic resonance in computational neuroscience, this phenomenon is still among the topics that need detailed research, especially in machine learning. In this study, the effect of noise arising from the intrinsic dynamics of the neurons forming the network in a spiking neural network consisting of Hodgkin-Huxley neurons on the image classification success of the network is investigated. In the first part of this two-part study, a practical neural network model consisting of Hodgkin-Huxley neurons is proposed and the network is tested in a 4-class real classification task. It is observed that the network consisting of Hodgkin-Huxley neurons has a classification performance at least as successful as the artificial neural network. In the second part of the study, the neurons in the network are replaced with stochastic Hodgkin-Huxley neurons, which more realistically represent the biological neuron, and the classification performance of the network at different cell membrane sizes is examined. Findings reveal that a spiking network consisting of stochastic Hodgkin-Huxley neurons, in which intrinsic noise dynamics are incorporated into the system, shows maximum classification performance at an optimal intrinsic noise level. It is called this reflection observed in the classification performance of a spiking network, which is referred to as stochastic resonance in computational neuroscience, as stochastic classification resonance in this study. This study also highlights the importance of bridging the gap between biological neuroscience and artificial neural networks for a better understanding of neurological structure.

Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective

Graph neural networks (GNNs) based on message-passing mechanisms have achieved advanced results in graph classification tasks. However, their generalization performance degrades when noisy labels are present in the training data. Most existing noisy labeling approaches focus on the visual domain or graph node classification tasks and analyze the impact of noisy labels only from a utility perspective. Unlike existing work, in this paper, we measure the effects of noise labels on graph classification from data privacy and model utility perspectives. We find that noise labels degrade the model’s generalization performance and enhance the ability of membership inference attacks on graph data privacy. To this end, we propose the robust graph neural network (RGLC) approach with noisy labeled graph classification. Specifically, we first accurately filter the noisy samples by high-confidence samples and the first feature principal component vector of each class. Then, the robust principal component vectors and the model output under data augmentation are utilized to achieve noise label correction guided by dual spatial information. Finally, supervised graph contrastive learning is introduced to enhance the embedding quality of the model and protect the privacy of the training graph data. The utility and privacy of the proposed method are validated by comparing twelve different methods on eight real graph classification datasets. Compared with the state-of-the-art methods, the RGLC method achieves at most and at least 7.8% and 0.8% performance gain at 30% noisy labeling rate, respectively, and reduces the accuracy of privacy attacks to below 60%.

Participatory Science and Machine Learning Applied to Millions of Sources in the Hobby–Eberly Telescope Dark Energy Experiment

We are merging a large participatory science effort with machine learning to enhance the Hobby–Eberly Telescope Dark Energy Experiment (HETDEX). Our overall goal is to remove false positives, allowing us to use lower signal-to-noise data and sources with low goodness-of-fit. With six million classifications through Dark Energy Explorers, we can confidently determine if a source is not real at over 94% confidence level when classified by at least 10 individuals; this confidence level increases for higher signal-to-noise sources. To date, we have only been able to apply this direct analysis to 190,000 sources. The full sample of HETDEX will contain around 2–3 million sources, including nearby galaxies ([O ii] emitters), distant galaxies (Lyα emitters or LAEs), false positives, and contamination from instrument issues. We can accommodate this tenfold increase by using machine learning with visually vetted samples from Dark Energy Explorers. We have already increased by over tenfold the number of sources that have been visually vetted from our previous pilot study where we only had 14,000 visually vetted LAE candidates. This paper expands on the previous work by increasing the visually vetted sample from 14,000 to 190,000. In addition, using our currently visually vetted sample, we generate a real or false positive classification for the full candidate sample of 1.2 million LAEs. We currently have approximately 17,000 volunteers from 159 countries around the world. Thus, we are applying participatory or citizen scientist analysis to our full HETDEX data set, creating a free educational opportunity that requires no prior technical knowledge.

A real scale application of a novel set of spatial and similarity features for detection and classification of natural seismic sources from distributed acoustic sensing data

SUMMARY Distributed acoustic sensing (DAS) turns a fibre optic into a very dense network of equally distributed seismic sensors. We focused on the high-density sampling of the seismic wavefield, expressed in strain rates, measured by DAS. Classical approaches used to identify seismic signals rely on the recorded features at one station, but it is difficult to include spatial information in case of dense seismic station networks. This work aims at introducing new spatial and similarity features for seismic event classification suitable to analyse DAS observations. We propose a processing chain based on the XGBoost algorithm and the use of specifically designed spatiotemporal and similarity features for the event classification, and Markov random field for the spatial clustering. The methodology is designated to be applied on a continuous stream of DAS observations. We tested our processing chain to detect earthquakes and quarry blasts recorded in the region by permanent seismic networks and included in the RENASS catalogue. These events are part of a strain-rate seismic survey carried out during a 3 weeks campaign of DAS measurements along à 91 km fibre optic cable deployed in the central Pyrenees mountains (France). Despite the high anthropogenic activities along the fibre optic path, the proposed method succeeded in detecting earthquakes of magnitude >0.4 and quarry blasts of magnitude >1.0 while limiting the number of false alarms. This performance is particularly noteworthy for low-magnitude events, where detection is accomplished despite a lower signal-to-noise ratio compared to traditional seismometers. The methodology opens the door to real time detection and classification of seismic events measured with long-distance fibre optic systems.

Convolutional Neural Networks for Real Time Classification of Beehive Acoustic Patterns on Constrained Devices.

Recent research has demonstrated the effectiveness of convolutional neural networks (CNN) in assessing the health status of bee colonies by classifying acoustic patterns. However, developing a monitoring system using CNNs compared to conventional machine learning models can result in higher computation costs, greater energy demand, and longer inference times. This study examines the potential of CNN architectures in developing a monitoring system based on constrained hardware. The experimentation involved testing ten CNN architectures from the PyTorch and Torchvision libraries on single-board computers: an Nvidia Jetson Nano (NJN), a Raspberry Pi 5 (RPi5), and an Orange Pi 5 (OPi5). The CNN architectures were trained using four datasets containing spectrograms of acoustic samples of different durations (30, 10, 5, or 1 s) to analyze their impact on performance. The hyperparameter search was conducted using the Optuna framework, and the CNN models were validated using k-fold cross-validation. The inference time and power consumption were measured to compare the performance of the CNN models and the SBCs. The aim is to provide a basis for developing a monitoring system for precision applications in apiculture based on constrained devices and CNNs.

Transient stability of grid following inverters: The impacts of damping and fault ride‐through

AbstractThe interaction of grid following inverters with a weak grid raises risks of transient instability. The effects of damping and fault‐ride through (FRT) make the transient dynamics more complicated. To investigate the impact of FRT on the transient stability of converters, this paper first employs the switch system theory to construct a mathematical model for the synchronous mechanism of inverters. Secondly, the method of semi‐algebraic system real root classification is comprehensively used to analyse the existence of equilibrium points (EPs) and provide necessary and sufficient conditions for their existence. Finally, based on the theory of differential geometry, a method for computing the stability domain of converters is proposed. Compared with traditional methods, the results obtained from this approach are precise and non‐conservative. The study in this paper indicates that the equivalent damping effect from the proportional control in a phase‐locked loop significantly enlarges the stability region, whereas the active current injection shrinks the stability region. The reactive current droop characteristic also has impacts on the stability region, especially with active current injection. The switchover between the droop mode and constant current mode requires extra precaution in the calculation of the EPs and critical fault clearing time.

C-reactive protein (CRP) evaluation in human urine using optical sensor supported by machine learning

The rapid and sensitive indicator of inflammation in the human body is C-Reactive Protein (CRP). Determination of CRP level is important in medical diagnostics because, depending on that factor, it may indicate, e.g., the occurrence of inflammation of various origins, oncological, cardiovascular, bacterial or viral events. In this study, we describe an interferometric sensor able to detect the CRP level for distinguishing between no-inflammation and inflammation states. The measurement head was made of a single mode optical fiber with a microsphere structure created at the tip. Its surface has been biofunctionalized for specific CRP bonding. Standardized CRP solutions were measured in the range of 1.9 µg/L to 333 mg/L and classified in the initial phase of the study. The real samples obtained from hospitalized patients with diagnosed Urinary Tract Infection or Urosepsis were then investigated. 27 machine learning classifiers were tested for labeling the phantom samples as normal or high CRP levels. With the use of the ExtraTreesClassifier we obtained an accuracy of 95% for the validation dataset. The results of real samples classification showed up to 100% accuracy for the validation dataset using XGB classifier.

AI-generated text detection and classification based on BERT deep learning algorithm

With the rapid development and wide application of deep learning technology, AI-generated text detection plays an increasingly important role in various fields. In this study, we developed an efficient AI-generated text detection model based on the BERT algorithm, which provides new ideas and methods for solving related problems. In the data preprocessing stage, a series of steps were taken to process the text, including operations such as converting to lowercase, word splitting, removing stop words, stemming extraction, removing digits, and eliminating redundant spaces, to ensure data quality and accuracy. By dividing the dataset into a training set and a test set in the ratio of 60% and 40%, and observing the changes in the accuracy and loss values during the training process, we found that the model performed well during the training process. The accuracy increases steadily from the initial 94.78% to 99.72%, while the loss value decreases from 0.261 to 0.021 and converges gradually, which indicates that the BERT model is able to detect AI-generated text with high accuracy and the prediction results are gradually approaching the real classification results. Further analysis of the results of the training and test sets reveals that in terms of loss value, the average loss of the training set is 0.0565, while the average loss of the test set is 0.0917, showing a slightly higher loss value. As for the accuracy, the average accuracy of the training set reaches 98.1%, while the average accuracy of the test set is 97.71%, which is not much different from each other, indicating that the model has good generalisation ability. In conclusion, the AI-generated text detection model based on the BERT algorithm proposed in this study shows high accuracy and stability in experiments, providing an effective solution for related fields. In the future, the model performance can be further optimised and its potential for application in a wider range of fields can be explored to promote the development and application of AI technology in the field of text detection.

Graph neural networks for text classification: a survey

Text Classification is the most essential and fundamental problem in Natural Language Processing. While numerous recent text classification models applied the sequential deep learning technique, graph neural network-based models can directly deal with complex structured text data and exploit global information. Many real text classification applications can be naturally cast into a graph, which captures words, documents, and corpus global features. In this survey, we bring the coverage of methods up to 2023, including corpus-level and document-level graph neural networks. We discuss each of these methods in detail, dealing with the graph construction mechanisms and the graph-based learning process. As well as the technological survey, we look at issues behind and future directions addressed in text classification using graph neural networks. We also cover datasets, evaluation metrics, and experiment design and present a summary of published performance on the publicly available benchmarks. Note that we present a comprehensive comparison between different techniques and identify the pros and cons of various evaluation metrics in this survey.

Real time electronic-waste classification algorithms using the computer vision based on Convolutional Neural Network (CNN): Enhanced environmental incentives

An innovative approach is needed to boost the economic value of e-waste by improving metal recovery and facilitating the separation of plastics and valuable metal components. Leveraging deep learning and computer vision technology offers a promising solution for automatically categorizing and sorting e-waste components like copper, printed circuit boards (PCB), steel, glass, and aluminum, presenting significant financial and environmental incentives for increased recycling efforts. In this instance, the real-time object identification algorithms YOLO 7 and 5 were used along with TensorFlow version 2.8.0. The e-waste dataset works incredibly well with TensorFlow and YOLO. For the detection of copper, PCBs, and plastic, the F1 values (F1 score is the harmonic mean of precision and recall; precision is the fraction of relevant instances among the retrieved instances whereas recall or sensitivity is the fraction of relevant instances that were retrieved) were as good as 1.0, whereas the score for steel and aluminum was 0.8. The mean average precision (mAP; for a set of queries, it is the mean of the average precision scores for each query) was 0.96 for all classes, with the highest precision for copper (0.99) followed by PCB (0.981). 240 e-waste objects were independently evaluated using the YOLO v7 model, achieving a remarkable ∼94 % prediction accuracy with a batch size of 16, ensuring robust performance. The real-time e-waste component detection was also done using video clips as well as webcam streaming. Deploying real-time e-waste object detection and sorting can significantly narrow the gap between e-waste accumulation and recycling rates, leading to reduced environmental strain and impact.

OPTIVISION: ENHANCING DIABETIC RETINOPATHY DETECTION USING DEEP LEARNING

The diabetic retinopathy is an eye disease associated with chronic diabetes. It is the leading cause of blindness in people. Diabetic Retinopathy is complication of diabetes that targets the eyes by damaging the retinal blood vessels. Primarily occurs when the blood sugar level is unmanageable. Therefore the person with diabetes mellitus is always at a high risk of acquiring this disease. The present work considers a deep learning methodology specifically a convolution neural network which is applied for the early detection of diabetic retinopathy is detected on time. It classifies the fundus images based n its severity levels as N0 DR, and Yes DR. The main objective of this work is t build a stable and noise compatible system for detection of diabetic retinopathy. This work employs the deep learning methodology for detecting the diabetic retinopathy based on severity level. Many processes were carried out before feeding the images to the network. Key Words: Diabetic retinopathy detection, Deep learning, CNN, Real time classification. The diabetic retinopathy is an eye disease associated with chronic diabetes. It is the leading cause of blindness in people. Diabetic Retinopathy is complication of diabetes that targets the eyes by damaging the retinal blood vessels. Primarily occurs when the blood sugar level is unmanageable. Therefore the person with diabetes mellitus is always at a high risk of acquiring this disease. The present work considers a deep learning methodology specifically a convolution neural network which is applied for the early detection of diabetic retinopathy is detected on time. It classifies the fundus images based n its severity levels as N0 DR, and Yes DR. The main objective of this work is t build a stable and noise compatible system for detection of diabetic retinopathy. This work employs the deep learning methodology for detecting the diabetic retinopathy based on severity level. Many processes were carried out before feeding the images to the network. Key Words: Diabetic retinopathy detection, Deep learning, CNN, Real time classification.

Multi-Instance Learning with One Side Label Noise

Multi-instance Learning (MIL) is a popular learning paradigm arising from many real applications. It assigns a label to a set of instances, which is called a bag, and the bag’s label is determined by the instances within it. A bag is positive if and only if it has at least one positive instance. Since labeling bags is more complicated than labeling each instance, we will often face the mislabeling problem in MIL. Furthermore, it is more common that a negative bag has been mislabeled to a positive one, since one mislabeled instance will lead to the change of the whole bag label. This is an important problem that originated from real applications, e.g., web mining and image classification, but little research has concentrated on it as far as we know. In this article, we focus on this MIL problem with one side label noise that the negative bags are mislabeled as positive ones. To address this challenging problem, we propose, to the best our our knowledge, a novel multi-instance learning method with one side label noise. We design a new double weighting approach under traditional framework to characterize the “faithfulness” of each instance and each bag in learning the classifier. Briefly, on the instance level, we employ a sparse weighting method to select the key instances, and the MIL problem with one size label noise is converted to a mislabeled supervised learning scenario. On the bag level, the weights of bags, together with the selected key instances, will be utilized to identify the real positive bags. In addition, we have solved our proposed model by an alternative iteration method with proved convergence behavior. Empirical studies on various datasets have validated the effectiveness of our method.

LSTM vs CNN in real ship trajectory classification

Abstract Ship-type identification in a maritime context can be critical to the authorities to control the activities being carried out. Although Automatic Identification Systems has been mandatory for certain vessels, if a vessel does not have them voluntarily or not, it can lead to a whole set of problems, which is why the use of tracking alternatives such as radar is fully complementary for a vessel monitoring systems. However, radars provide positions, but not what they are detecting. Having systems capable of adding categorical information to radar detections of vessels makes it possible to increase control of the activities being carried out, improve safety in maritime traffic, and optimize on-site inspection resources on the part of the authorities. This paper addresses the binary classification problem (fishing ships versus all other vessels) using unbalanced data from real vessel trajectories. It is performed from a deep learning approach comparing two of the main trends, Convolutional Neural Networks and Long Short-Term Memory. In this paper, it is proposed the weighted cross-entropy methodology and compared with classical data balancing strategies. Both networks show high performance when applying weighted cross-entropy compared with the classical machine learning approaches and classical balancing techniques. This work is shown to be a novel approach to the international problem of identifying fishing ships without context.

Adaptive graph Laplacian MTL L1, L2 and LS-SVMs

Abstract Multi-Task Learning tries to improve the learning process of different tasks by solving them simultaneously. A popular Multi-Task Learning formulation for SVM is to combine common and task-specific parts. Other approaches rely on using a Graph Laplacian regularizer. Here we propose a combination of these two approaches that can be applied to L1, L2 and LS-SVMs. We also propose an algorithm to iteratively learn the graph adjacency matrix used in the Laplacian regularization. We test our proposal with synthetic and real problems, both in regression and classification settings. When the task structure is present, we show that our model is able to detect it, which leads to better results, and we also show it to be competitive even when this structure is not present.

Interacting topological quantum chemistry in 2D with many-body real space invariants

The topological phases of non-interacting fermions have been classified by their symmetries, culminating in a modern electronic band theory where wavefunction topology can be obtained from momentum space. Recently, Real Space Invariants (RSIs) have provided a spatially local description of the global momentum space indices. The present work generalizes this real space classification to interacting 2D states. We construct many-body local RSIs as the quantum numbers of a set of symmetry operators on open boundaries, but which are independent of the choice of boundary. Using the U(1) particle number, they yield many-body fragile topological indices, which we use to identify which single-particle fragile states are many-body topological or trivial at weak coupling. To this end, we construct an exactly solvable Hamiltonian with single-particle fragile topology that is adiabatically connected to a trivial state through strong coupling. We then define global many-body RSIs on periodic boundary conditions. They reduce to Chern numbers in the band theory limit, but also identify strongly correlated stable topological phases with no single-particle counterpart. Finally, we show that the many-body local RSIs appear as quantized coefficients of Wen-Zee terms in the topological quantum field theory describing the phase.

A multi-view ensemble model based on semi-supervised feature learning for small sample classification of PolSAR images

ABSTRACT Classification with a few samples of training set has been a long-standing issue in the field of polarimetric synthetic aperture radar (PolSAR) image analysis and processing. In fact, one of the most important challenges of the PolSAR image classification task is the number of labelled samples. In essence, training network by utilizing just few numbers of training samples cannot be led to the reliable result since the neural network is so sensitive to the number of training samples. In addition, in the real PolSAR image classification task, the huge number of training samples is not accessible. On the other hand, classification performance using just small number of labelled samples is not an accurate result. So, in this paper, aiming at the small number of training samples of the PolSAR image classification task, a novel ensemble self-supervised feature-learning (ESSFL) model is designed. The designed ESSFL can automatically extract PolSAR features conducive to PolSAR image classification with a small number of training samples. In addition, it can significantly decrease the dependence of neural network algorithms on large labelled samples of training set. First, to utilize the spatial–polarimetric features of PolSAR data perfectly, the EfficientNet-B0 is presented and utilized as the main section of the deep learning (DL) model to extract DL features of PolSAR data. Then, using an optimization function that constrains the cross-correlation matrix of various distortions of each sample to the identity matrix, the designed deep learning model can obtain the effective features of homogeneous samples gathering together and heterogeneous samples separating from each other in a self-supervised manner. Moreover, two ensemble learning (EL) models, feature-level and view-level ensemble, are proposed to increase the feature extraction capability and classification result by jointly using spatial features at different scales and polarimetric information at different bands. Finally, the stack of the obtained features and the main polarimetric information of PolSAR data can be input into classifier for the classification of PolSAR data. In this paper we use two different classifiers, the first one is the Random Forest (RF) classifier and the second one is the Support Vector Machine (SVM) classifier. The advantages of SVM include that it can be used to avoid the difficulties of using linear functions in the high-dimensional feature space, and the optimization problem is transformed into dual convex quadratic programs that are so usable for an actual image classification task. In addition, among all the available classification methods, random forests provide one of the highest accuracies. The random forest technique can also handle big data with numerous variables running into thousands. In fact, it can automatically balance data sets when a class is more infrequent than other classes in the data that is so important for a real PolSAR image classification task. Experimental results on three well-known PolSAR data sets illustrate that the designed ESSFL can extract more discriminant features using the designed deep learning model. In the end, the experiments prove that the designed ESSFL has a significant classification performance compared with different deep learning models in the case of small number of training samples, and also it can achieve a better result in the case of large number of training samples by comparison with the most of the deep learning models.

An Insight into Real Time Vehicle Detection and Classification Methods using ML/DL based Approach

Vehicle detection and classification is one of the major challenges for automated traffic surveillance as well as for military defence systems to identify enemy vehicles. For efficient real-time surveillance, accurate detection and classification of many vehicle kinds, including cars, trucks, buses, and so forth are important. This paper focuses on different methods of machine learning used toidentify thevehicle and then then categorize each vehicle according to the classes. It also explores the critical insight of existing vehicle detection and classification approaches using various machine learning methods like YOLO, CNN, R-CNN, and AdaBoost. The majority of the research projects now in existence solely consider increasing image-based accuracy, which has poor real-time performance and uses more computational resources.

Using machine learning algorithms to solve data classification problems using multi-attribute dataset

This paper discusses various machine learning techniques such as decision trees, Kohonen maps neural network method, and correlation analysis. The training of neural networks and further comparative analysis was carried out using a real estate price segment classification dataset. The overall quality of the data collected in the dataset was evaluated using the correlation analysis method, while the other methods were used to predict the target variable. The obtained data were summarized in a comparative table. As a result of the work done, a relatively high accuracy was obtained using a large number of parameters in the work of almost all methods, the only exception is the neural network method, which does not work very correctly in the selected software product

Merge Loss Calculation Method for Highly Imbalanced Data Multiclass Classification.

In real classification scenarios, the number distribution of modeling samples is usually out of proportion. Most of the existing classification methods still face challenges in comprehensive model performance for imbalanced data. In this article, a novel theoretical framework is proposed that establishes a proportion coefficient independent of the number distribution of modeling samples and a general merge loss calculation method independent of class distribution. The loss calculation method of the imbalanced problem focuses on both the global and batch sample levels. Specifically, the loss function calculation introduces the true-positive rate (TPR) and the false-positive rate (FPR) to ensure the independence and balance of loss calculation for each class. Based on this, global and local loss weight coefficients are generated from the entire dataset and batch dataset for the multiclass classification problem, and a merge weight loss function is calculated after unifying the weight coefficient scale. Furthermore, the designed loss function is applied to different neural network models and datasets. The method shows better performance on imbalanced datasets than state-of-the-art methods.

Hyperparameter Recommendation Integrated With Convolutional Neural Network.

Hyperparameter recommendation via meta-learning has shown great promise in various studies. The main challenge for meta-learning is how to develop an effective meta-learner (learning algorithm) that can capture the intrinsic relationship between dataset characteristics and the empirical performance of hyperparameters. Existing meta-learners are mostly based on traditional machine-learning models that only learn data representations with a single layer, which are incapable of learning complex features from the data and often cannot capture those properties deeply embedded in data. To address this issue, in this article, we propose hyperparameter recommendation approaches by integrating the learning model with convolutional neural networks (CNNs). Specifically, we first formulate the recommendation task as a regression problem, where dataset characteristics are treated as predictors and the historical performance of hyperparameters as responses. We establish a CNN-based learning model with feature selection capability to serve as the regressor. We then develop a convolutional denoising autoencoder (ConvDAE) that can leverage the spatial structure of the entire hyperparameter performance space and evaluate the performance of hyperparameters via denoising when the performance of partial hyperparameters is available under the multidimensional framework. To make our approach being flexible in applications, we establish a comprehensive two-branch CNN model that can utilize both dataset characteristics and partial evaluations to make effective recommendations. We conduct extensive experiments on 400 real classification problems and the well-known SVM. Our proposed approaches outperform existing meta-learning baselines as well as various search algorithms, demonstrating the high effectiveness in hyperparameter recommendations via deep learning.