Fast Classification Research Articles

Untrained and Unmatched: Fast and Accurate Zero-Training Classification for Tabular Engineering Data

Abstract In engineering design, navigating complex decision-making landscapes demands a thorough exploration of the design, performance, and constraint spaces, often impeded by resource-intensive simulations. Data-driven methods can mitigate this challenge by harnessing historical data to delineate feasible domains, accelerate optimization, or evaluate designs. However, the implementation of these methods usually demands machine learning expertise and multiple trials to choose the right method and hyperparameters. This makes them less accessible for numerous engineering situations. Additionally, there is an inherent trade-off between training speed and accuracy, with faster methods sometimes compromising precision. In our paper, we demonstrate that a recently released general-purpose transformer-based classification model, TabPFN, is both fast and accurate. Notably, it requires no dataset-specific training to assess new tabular data. TabPFN is a prior-data fitted network, which undergoes a one-time offline training across a broad spectrum of synthetic datasets and performs in-context learning. We evaluated TabPFN’s efficacy across eight engineering design classification problems, contrasting it with seven other algorithms, including a state-of-the-art automated machine learning (AutoML) method. For these classification challenges, TabPFN consistently outperforms in speed and accuracy. It is also the most data-efficient and provides the added advantage of being differentiable and giving uncertainty estimates. Our findings advocate for the potential of pre-trained models that learn from synthetic data and require no domain-specific tuning to make data-driven engineering design accessible to a broader community and open ways to efficient general-purpose models valid across applications. Furthermore, we share a benchmark problem set for evaluating new classification algorithms in engineering design.

Optimized deep learning for steel bridge bolt corrosion detection and classification

Corrosion of steel bridge bolts poses a major threat to structural integrity. As a key component, bridge bolts are susceptible to corrosion and detachment, necessitating close monitoring during maintenance. However, the vast number of corroded bolts presents challenges. Conventional detection relies on subjective visual inspection without unified assessment criteria. Fast and accurate localization and classification of bolt corrosion levels thus became a research priority for bridge maintenance. This study puts forward a new two-stage corrosion detection method, integrating Deep Convolutional Generative Adversarial Network (DCGAN) and improved You Only Look Once version 5 (YOLOv5) networks, which enables rapid categorization of bridge bolts by different corrosion extents, providing an intelligent solution for bridge maintenance. First, in the image preprocessing stage, a DCGAN with least squares loss generates simulated corroded bolt images through adversarial learning to expand the dataset. Second, three corrosion levels are defined based on visual features and percentage of surface rust, with this classification scheme applied in dataset annotation. Finally, the annotated images are input into an enhanced YOLOv5 model named YOLOv5-SE for corrosion identification. To improve accuracy, Squeeze-and-Excitation blocks are added after each residual block in the YOLOv5 backbone. Comparative experiments prove YOLOv5-SE's superior performance over YOLOv5 and other models like Faster R-CNN and VGG16. A pytorch system enables model deployment for corrosion detection. The integration of DCGAN simulation and attention-optimized YOLOv5-SE enables precise classification and localization of corroded bolts. This study represented a significant step towards intelligent upgrades in steel bridge maintenance.

Analysis of unsupervised learning approach for classification of vehicle fuel type using psychoacoustic features

Much research has been done in the field of classifying vehicles based on their fuel type. One of the many potential applications is to improve the quality of life in urban areas by separating vehicles based on their pollution level. Real-time classification and implementation of appropriate on-site IoT measurement devices is critical to developing a system that accurately identifies vehicle's fuel type without violating driver privacy. In this paper, a classification system based on psychoacoustic features extracted from sound recordings is investigated. Unsupervised learning was implemented as it is able to detect hidden connections within the input space without relying on labelling data. Our goal was to develop and explore a relatively fast classification system, focusing on a short acquisition time. A self-organizing map with a 10-dimensional input space was used and effective classification with five single-valued features was demonstrated. The analysis of the input space shows the difficulty and complexity of such an approach and leaves room for further improvement.

Multi-Fault Diagnosis of Electric Vehicle Power Battery Based on Double Fault Window Location and Fast Classification

As energy supply units, lithium-ion batteries have been widely used in the electric vehicle industry. However, the safety of lithium-ion batteries remains a significant factor limiting their development. To achieve rapid fault diagnosis of lithium-ion batteries, this paper presents a comprehensive fault diagnosis process. Firstly, an interleaved voltage sensor topology structure is utilized to acquire battery voltage data. An improved complete ensemble empirical mode decomposition with adaptive noise method is introduced to process data. Then, the reconstructed voltage data sequence is used to eliminate the influence of noise. A fault location is performed using dichotomy correlation coefficient and time window correlation coefficient. Afterwards, principal component analysis is used to select the principal components with high contribution rate as classification features. The gray wolf optimization algorithm is used to find the parameters of the least squares support vector machine, constructing an optimal classifier for fault classification. A fault experiment platform is established to realize the physical triggering of faults such as external short circuit, internal circuit, and connection of experimental battery packs. Finally, the accuracy and reliability of the method are verified by the results of fault localization and fault type determination.

MiCId GUI: The Graphical User Interface for MiCId, a Fast Microorganism Classification and Identification Workflow with Accurate Statistics and High Recall.

Although many user-friendly workflows exist for identifications of peptides and proteins in mass-spectrometry-based proteomics, there is a need of easy to use, fast, and accurate workflows for identifications of microorganisms, antimicrobial resistant proteins, and biomass estimation. Identification of microorganisms is a computationally demanding task that requires querying thousands of MS/MS spectra in a database containing thousands to tens of thousands of microorganisms. Existing software can't handle such a task in a time efficient manner, taking hours to process a single MS/MS experiment. Another paramount factor to consider is the necessity of accurate statistical significance to properly control the proportion of false discoveries among the identified microorganisms, and antimicrobial-resistant proteins, and to provide robust biomass estimation. Recently, we have developed Microorganism Classification and Identification (MiCId) workflow that assigns accurate statistical significance to identified microorganisms, antimicrobial-resistant proteins, and biomass estimation. MiCId's workflow is also computationally efficient, taking about 6-17 minutes to process a tandem mass-spectrometry (MS/MS) experiment using computer resources that are available in most laptop and desktop computers, making it a portable workflow. To make data analysis accessible to a broader range of users, beyond users familiar with the Linux environment, we have developed a graphical user interface (GUI) for MiCId's workflow. The GUI brings to users all the functionality of MiCId's workflow in a friendly interface along with tools for data analysis, visualization, and to export results.

Utilising VGG-16 of Convolutional Neural Network for Medical Image Classification

Medical image classification, which involves accurately classifying anomalies or abnormalities within images, is an important area of attention in healthcare domain. It requires a fast and exact classification to ensure appropriate and timely treatment to the patients. This paper introduces a model based on Convolutional Neural Network (CNN) that utilises the VGG16 architecture for medical image classification, specifically in brain tumour and Alzheimer dataset. The VGG16 architecture, is known for its remarkable ability to extract important features, that is crucial in medical image classification. To enhance the precision of diagnosis, a detailed experimental setup is conducted, which includes the careful selection and organisation of a collection of medical images that cover different illnesses and anomalies to the dataset. The architecture of the model is then adjusted to achieve optimal performance in for image classification. The results show the model's efficiency in identifying anomalies in medical images especially for brain tumour dataset. The sensitivity, specificity, and F1-score evaluation metrics are presented, emphasising the model's ability to accurately differentiate between various medical image diseases.

OptiClass : An Optimized Classifier for Application Layer Protocols Using Bit Level Signatures

Network traffic classification has many applications, such as security monitoring, quality of service, traffic engineering, and so on. For the aforementioned applications, Deep Packet Inspection (DPI) is a popularly used technique for traffic classification because it scrutinizes the payload and provides comprehensive information for accurate analysis of network traffic. However, DPI-based methods reduce network performance because they are computationally expensive and hinder end-user privacy as they analyze the payload. To overcome these challenges, bit-level signatures are significantly used to perform network traffic classification. However, most of these methods still need to improve performance as they perform one-by-one signature matching of unknown payloads with application signatures for classification. Moreover, these methods become stagnant with the increase in application signatures. Therefore, to fill this gap, we propose OptiClass , an optimized classifier for application protocols using bit-level signatures. OptiClass performs parallel application signature matching with unknown flows, which results in faster, more accurate, and more efficient network traffic classification. OptiClass achieves twofold performance gains compared to the state-of-the-art methods. First, OptiClass generates bit-level signatures of just 32 bits for all the applications. This keeps OptiClass swift and privacy-preserving. Second, OptiClass uses a novel data structure called BiTSPLITTER for signature matching for fast and accurate classification. We evaluated the performance of OptiClass on three datasets consisting of twenty application protocols. Experimental results report that OptiClass has an average recall, precision, and F1-score of 97.36%, 97.38%, and 97.37%, respectively, and an average classification speed of 9.08 times faster than five closely related state-of-the-art methods.

Practicality of in-kernel/user-space packet processing empowered by lightweight neural network and decision tree

Integrating machine learning (ML) into kernel packet processing, such as extended Berkeley Packet Filter (eBPF) and eXpress Data Path (XDP), represents a promising strategy for achieving fast and intelligent networking on generic hardware. This includes tasks like automating network operations and discerning traffic classification, exemplified by intrusion detection systems (IDS) combining Decision Tree (DT) and eBPF. However, the potential of ML-empowered packet processing remains to be fully explored. To ensure the integrity and security of kernel operations, eBPF/XDP programs must adhere to stringent constraints such as the maximum number of jump instructions, maximum stack space, and exclusion of floating-point arithmetic. These constraints pose challenges for implementing more intricate ML techniques (e.g., neural networks (NNs)) within eBPF/XDP programs. In such scenarios, AF_XDP provides an alternative solution by allowing XDP programs to redirect packets to user-space applications, bypassing the network stack. This paper initiates an exploration into fast packet classification through two distinct approaches: (1) an in-kernel approach employing eBPF/XDP and (2) a user-space approach assisted by AF_XDP. Specifically, to tackle the eBPF constraints, the in-kernel NN classifier adopts (1) quantization of trained model in the user space, (2) executing the integer-arithmetic-only NN within the kernel space, and (3) sequential layer operations through tail calls. These approaches are evaluated based on factors including packet processing speed, resource efficiency, and detection performance. Notably, our experimental findings demonstrate that (1) Classifiers relying solely on integer arithmetic, such as NN and DT, significantly reduce inference time while maintaining binary classification performance; (2) The lightweight NN classifier can improve the detection performance for most of attacks in case of the multi-class classification compared to the lightweight DT classifier; (3) In single-core scenarios, the DT-empowered in-kernel method can almost achieve the maximum packets per second (pps), i.e., about 800,000pps, whereas the NN-empowered one exhibits lower pps (i.e., about 450,000pps); (4) In multi-core scenarios, the NN-empowered packet processing can almost achieve the maximum pps with two or more cores in the AF_XDP approach and four or more cores in the in-kernel approaches.

Deep learning analysis for rapid detection and classification of household plastics based on Raman spectroscopy

The overuse of plastics releases large amounts of microplastics. These tiny and complex pollutants may cause immeasurable damage to human social life. Raman spectroscopy detection technology is widely used in the detection, identification and analysis of microplastics due to its advantages of fast speed, high sensitivity and non-destructive. In this work, we first recorded the Raman spectra of eight common plastics in daily life. By adjusting parameters such as laser wavelength, laser power, and acquisition time, the Raman data under different acquisition conditions were diversified, and the corresponding Raman spectra were obtained, and a database of eight household plastics was established. Combined with deep learning algorithms, an accurate, fast and simple classification and identification method for 8 types of plastics is established. Firstly, the acquired spectral data were preprocessed for baseline correction and noise reduction, Then, four machine learning algorithms, linear discriminant analysis (LDA), decision tree, support vector machine (SVM) and one-dimensional convolutional neural network (1D-CNN), are used to classify and identify the preprocessed data. The results showed that the classification accuracy of the three machine learning models for the Raman spectra of standard plastic samples were 84%, 93% and 93% respectively. The 1D-CNN model has an accuracy rate of up to 97% for Raman spectroscopy. Our study shows that the combination of Raman spectroscopy detection techniques and deep learning algorithms is a very valuable approach for microplastic classification and identification.

Gearbox fault diagnosis method based on lightweight channel attention mechanism and transfer learning

In practical engineering, the working conditions of gearbox are complex and variable. In varying working conditions, the performance of intelligent fault diagnosis model is degraded because of limited valid samples and large data distribution differences of gearbox signals. Based on these issues, this research proposes a gearbox fault diagnosis method integrated with lightweight channel attention mechanism, and further realizes the cross-component transfer learning. First, time–frequency distribution of original signals is obtained by wavelet transform. It could intuitively reflect local characteristics of signals. Secondly, based on a local cross-channel interaction strategy, a lightweight efficient channel attention mechanism (LECA) is designed. The kernel size of 1D convolution is affected by channel number and coefficients. Multi-scale feature input is used to retain more detailed features of different dimensions. A lightweight convolutional neural network is constructed. Finally, a transfer learning method is applied to freeze lower structures of the network and fine-tune higher structures of the model using small samples. Through experimental verification, the proposed model could effectively utilize samples. The application of transfer learning could realize accurate and fast fault classification of small samples, and achieve good gearbox fault diagnosis effect under varying working conditions and cross-component conditions.

High precision and fast classification of different dimensions of Baijiu using an OptGSCV quadratic optimization network combined with AS-LIBS

For the traditional Baijiu qualitative analysis problem, a high-precision fast classification method for different dimensional Baijiu based on AS-LIBS combined with Optimized Grid Search Cross-Validation (Opt-GSCV) is proposed.

Fast Multiview Semi-Supervised Classification With Optimal Bipartite Graph

Fast Multiview Semi-Supervised Classification With Optimal Bipartite Graph

Fast and Storage-Optimized Compressed Domain Vibration Detection and Classification for Distributed Acoustic Sensing

Fast and Storage-Optimized Compressed Domain Vibration Detection and Classification for Distributed Acoustic Sensing

An Alternative Fast Seismic Site Classification Method Based on Geological Maps: A Case Study in Shandong Province, North China

An Alternative Fast Seismic Site Classification Method Based on Geological Maps: A Case Study in Shandong Province, North China

Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields

Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields

An improved pistachio detection approach using YOLO-v8 Deep Learning Models

Pistachios are an agricultural product widely used in the food industry. It is very important that pistachios are presented to the consumer in good quality on time. At the same time, whether the shells of pistachios are open or closed is an important criterion from a commercial industrial point of view. Pistachios with their shells open have a high unsaturated fat content, a high maturity level and an expensive market value. In this study, the open or closed status of pistachios was determined by using Artificial Intelligence-based deep learning models. For pistachio detection, 423 image data belonging to the Pesteh dataset were classified using models of the Yolov8 algorithm, which detects objects using convolutional neural networks. The data set is divided into 80% training, 10% validation and 10% testing. The performances of the models were evaluated with precision, recall, F1 and mAP score metrics. The highest test mAP value of the Yolov8 algorithm, which was run with image data consisting of pistachios, was obtained with the Yolov8-m model with 94.8%. The Yolov8-m model achieved a very successful result with 49.6 MB weight size, 11.0 ms inference time value and 0.33 hours training time value. In addition, the model's fast classification performance and small file size facilitate its applicability in the industrial field. The results show that the classification and detection of open and closed shell pistachios has been successfully carried out with Yolo models.

Accurate and Fast Classification of Natural Disasters using CNN-LSTM and Inference Acceleration

Accurate and Fast Classification of Natural Disasters using CNN-LSTM and Inference Acceleration

Fast and Accurate Hyperspectral Image Classification with Window Shape Adaptive Singular Spectrum Analysis

Hyperspectral classification is a task of significant importance in the field of remote sensing image processing, with attaining high precision and rapid classification increasingly becoming a research focus. The classification accuracy depends on the degree of raw HSI feature extraction, and the use of endless classification methods has led to an increase in computational complexity. To achieve high accuracy and fast classification, this study analyzes the inherent features of HSI and proposes a novel spectral–spatial feature extraction method called window shape adaptive singular spectrum analysis (WSA-SSA) to reduce the computational complexity of feature extraction. This method combines similar pixels in the neighborhood to reconstruct every pixel in the window, and the main steps are as follows: rearranging the spectral vectors in the irregularly shaped region, constructing an extended trajectory matrix, and extracting the local spatial and spectral information while removing the noise. The results indicate that, given the small sample sizes in the Indian Pines dataset, the Pavia University dataset, and the Salinas dataset, the proposed algorithm achieves classification accuracies of 97.56%, 98.34%, and 99.77%, respectively. The classification speed is more than ten times better than that of other methods, and a classification time of only about 1–2 s is needed.

Eucalyptus Species Discrimination Using Hyperspectral Sensor Data and Machine Learning

The identification of tree species is very useful for the management and monitoring of forest resources. When paired with machine learning (ML) algorithms, species identification based on spectral bands from a hyperspectral sensor can contribute to developing technologies that enable accurate forest inventories to be completed efficiently, reducing labor and time. This is the first study to evaluate the effectiveness of classification of five eucalyptus species (E. camaldulensis, Corymbia citriodora, E. saligna, E. grandis, and E. urophyla) using hyperspectral images and machine learning. Spectral readings were taken from 200 leaves of each species and divided into three dataset sizes: one set containing 50 samples per species, a second with 100 samples per species, and a third set with 200 samples per species. The ML algorithms tested were multilayer perceptron artificial neural network (ANN), decision trees (J48 and REPTree algorithms), and random forest (RF). As a control, a conventional approach by logistic regression (LR) was used. Eucalyptus species were classified by ML algorithms using a randomized stratified cross-validation with 10 folds. After obtaining the percentage of correct classification (CC) and F-measure accuracy metrics, the means were grouped by the Scott–Knott test at 5% probability. Our findings revealed the existence of distinct spectral curves between the species, with the differences being more marked from the 700 nm range onwards. The most accurate ML algorithm for identifying eucalyptus species was ANN. There was no statistical difference for CC between the three dataset sizes. Therefore, it was determined that 50 leaves would be sufficient to accurately differentiate the eucalyptus species evaluated. Our study represents an important scientific advance for forest inventories and breeding programs with applications in both forest plantations and native forest areas as it proposes a fast, accurate, and large-scale species-level classification approach.

A fast and time-efficient machine learning approach to dark matter searches in compressed mass scenario

Various analyses for searching for the signature of SUSY or exotic particles have been carried out by the experiments at CERN. These analyses made use of traditional cut and count methods. While this method has yielded promising results, it has been challenging in the region where the mass difference between SUSY particles is small. Deep learning is currently widely employed in most data analysis tasks, including high energy physics, and has made significant advances in almost all fields for collecting and interpreting huge data samples. In this paper, a fast and time-efficient classification technique is proposed, utilizing machine learning algorithms to distinguish dark matter signal from SM background in compressed mass spectra scenarios at a center-of-mass energy of 14 TeV. A classification model was built in a short amount of time using 2D histograms produced with less amount of data, effectively reducing computational costs through the transfer learning of pre-trained deep models while maintaining a high level of classification accuracy.