Class Of Networks Research Articles

Quantum metric learning with fuzzy-informed learning

By constructing a quantum circuit with adjustable parameters, variational quantum circuits are capable of embedding input data into Hilbert space and facilitating the execution of complex deep learning tasks. Recently, a method known as quantum metric learning has emerged. It adaptively adjusts quantum embedding circuits to enable clusters of classical data from different categories to form linear separations in Hilbert space. This approach combines the advantages of kernel methods and is implementable on near-term quantum devices. However, applying quantum metric learning to more complex data presents challenges, largely due to the inherent fuzziness, uncertainty, and noise in the data itself and in the classical neural network preprocessing. To address these challenges, this paper proposes a fuzzy information-driven framework for quantum metric learning. This framework leverages fuzzy learning to accurately describe the uncertainty of data characteristics and adaptively integrates features, fuzziness, and uncertainty. Numerical experiments demonstrate that, compared to standard quantum metric learning, this framework achieves competitive performance and promising results. Furthermore, the interpretability provided by fuzzy logic aids in understanding the intrinsic mechanisms of the selected features during the quantum feature mapping process, offering new perspectives and approaches for better utilization of current quantum information processors.

Quantum Fourier networks for solving parametric PDEs

Many real-world problems, like modelling environment dynamics, physical processes, time series etc involve solving partial differential equations (PDEs) parameterised by problem-specific conditions. Recently, a deep learning architecture called Fourier neural operator (FNO) proved to be capable of learning solutions of given PDE families for any initial conditions as input. However, it results in a time complexity linear in the number of evaluations of the PDEs while testing. Given the advancements in quantum hardware and the recent results in quantum machine learning methods, we exploit the running efficiency offered by these and propose quantum algorithms inspired by the classical FNO, which result in time complexity logarithmic in the number of evaluations and are expected to be substantially faster than their classical counterpart. At their core, we use the unary encoding paradigm and orthogonal quantum layers and introduce a new quantum Fourier transform in the unary basis. We propose three different quantum circuits to perform a quantum FNO. The proposals differ in their depth and their similarity to the classical FNO. We also benchmark our proposed algorithms on three PDE families, namely Burgers’ equation, Darcy’s flow equation and the Navier–Stokes equation. The results show that our quantum methods are comparable in performance to the classical FNO. We also perform an analysis on small-scale image classification tasks where our proposed algorithms are at par with the performance of classical convolutional neural networks, proving their applicability to other domains as well.

Modelling of Timestamp Processing within Transport Network Equipment

The modern telecommunication networks are forming on the basis of different transmission and data processing technologies. High load on the transport layer nodes demands quality synchronization of equipment that works on it. The transport network is an important element which delivers the time scale to slave nodes. Using the time-division multiplexing for the high-speed channel processing with the use of wavelength division multiplexing (OTN, Optical Transport Network) and classic Ethernet networks as a transport layer systems needs the precision time synchronization which can be achieved with the use of Precision Time Protocol (PTP). The modeling apparatus of PTP messages exchanging within OTN multiplexers and IP-network based on the routers are suggested. The packet transferring through the network are given as sequence of simple processing steps. The impact of a network load on PTP information processing capacity on the routers and efficiency of the Forward Error Correction algorithm for OTN equipment are analyzed. The experimental distribution of variable delays on that network elements are given.

Leveraging a realistic synthetic database to learn Shape-from-Shading for estimating the colon depth in colonoscopy images

Colonoscopy is the choice procedure to diagnose, screening, and treat the colon and rectum cancer, from early detection of small precancerous lesions (polyps), to confirmation of malign masses. However, the high variability of the organ appearance and the complex shape of both the colon wall and structures of interest make this exploration difficult. Learned visuospatial and perceptual abilities mitigate technical limitations in clinical practice by proper estimation of the intestinal depth. This work introduces a novel methodology to estimate colon depth maps in single frames from monocular colonoscopy videos. The generated depth map is inferred from the shading variation of the colon wall with respect to the light source, as learned from a realistic synthetic database. Briefly, a classic convolutional neural network architecture is trained from scratch to estimate the depth map, improving sharp depth estimations in haustral folds and polyps by a custom loss function that minimizes the estimation error in edges and curvatures. The network was trained by a custom synthetic colonoscopy database herein constructed and released, composed of 248400 frames (47 videos), with depth annotations at the level of pixels. This collection comprehends 5 subsets of videos with progressively higher levels of visual complexity. Evaluation of the depth estimation with the synthetic database reached a threshold accuracy of 95.65%, and a mean-RMSE of 0.451cm, while a qualitative assessment with a real database showed consistent depth estimations, visually evaluated by the expert gastroenterologist coauthoring this paper. Finally, the method achieved competitive performance with respect to another state-of-the-art method using a public synthetic database and comparable results in a set of images with other five state-of-the-art methods. Additionally, three-dimensional reconstructions demonstrated useful approximations of the gastrointestinal tract geometry. Code for reproducing the reported results and the dataset are available at https://github.com/Cimalab-unal/ColonDepthEstimation.

SLTRN: Sample-level transformer-based relation network for few-shot classification

Few-shot classification recognizes novel categories with limited labeled samples. The classic Relation Network (RN) compares support-query sample pairs for few-shot classification but overlooks support set contextual information, limiting its comparison capabilities. This work reformulates learning the relationship between query samples and each support class as a seq2seq problem. We introduce a Sample-level Transformer-based Relation Network (SLTRN) that utilizes sample-level self-attention to enhance the comparison ability of the relationship module by mining potential relationships among support classes. SLTRN demonstrates comparable performance with state-of-the-art methods on benchmarks, particularly excelling in the 1-shot setting with 52.11% and 67.55% accuracy on miniImageNet and CUB, respectively. Extensive ablation experiments validate the effectiveness and optimal settings of SLTRN. The experimental code for this work is available at https://github.com/ZitZhengWang/SLTRN.

A bilevel fast-convergent optimizer via high-fidelity convex models: Application on optimal operation of all-parallel heterogeneous chiller-pump systems

To cope with buildings’ growing and diverse cooling demand, heterogeneous multi-chiller systems with non-dedicated pumps are commonly applied in large-scale centralized chiller plants. All-parallel heterogeneous systems offer high operation flexibility but pose challenges to optimal operation planning. For the deficiencies in convexity tractability, the classical neural networks (NNs) achieved great success in system identification yet were restricted in model-based optimization. In this study, an optimization-oriented convex modeling approach based on input convex neural networks (ICNN) to identify energy consumption models for energy units of chiller-pump systems was presented, which provides convex input–output mappings while leveraging the high-fidelity capability of NNs. Using the convex models, the energy minimization issue subjected to multiple constraints was formulated, the optimality of which was mathematically proven. A bilevel deterministic optimizer was developed to determine the global optimal. Comprehensive data experiments were conducted using practical and simulated operation data to evaluate the modeling and optimization performances of the proposed methods compared with conventional candidates. Numerical results suggest that the ICNN-based convex models exhibit superior modeling performances than physics-based models. A better overall energy saving ratio of 8.86 % and faster convergence time of 3.53 s for average achieved by the proposed bilevel optimizer compared with rule-based and meta-heuristic optimizers under identical external conditions.

Quantum Machine Learning for Credit Scoring

This study investigates the integration of quantum circuits with classical neural networks for enhancing credit scoring for small- and medium-sized enterprises (SMEs). We introduce a hybrid quantum–classical model, focusing on the synergy between quantum and classical rather than comparing the performance of separate quantum and classical models. Our model incorporates a quantum layer into a traditional neural network, achieving notable reductions in training time. We apply this innovative framework to a binary classification task with a proprietary real-world classical credit default dataset for SMEs in Singapore. The results indicate that our hybrid model achieves efficient training, requiring significantly fewer epochs (350) compared to its classical counterpart (3500) for a similar predictive accuracy. However, we observed a decrease in performance when expanding the model beyond 12 qubits or when adding additional quantum classifier blocks. This paper also considers practical challenges faced when deploying such models on quantum simulators and actual quantum computers. Overall, our quantum–classical hybrid model for credit scoring reveals its potential in industry, despite encountering certain scalability limitations and practical challenges.

A novel transformer-based DL model enhanced by position-sensitive attention and gated hierarchical LSTM for aero-engine RUL prediction

Accurate prediction of remaining useful life (RUL) for aircraft engines is essential for proactive maintenance and safety assurance. However, existing methods such as physics-based models, classical recurrent neural networks, and convolutional neural networks face limitations in capturing long-term dependencies and modeling complex degradation patterns. In this study, we propose a novel deep-learning model based on the Transformer architecture to address these limitations. Specifically, to address the issue of insensitivity to local context in the attention mechanism employed by the Transformer encoder, we introduce a position-sensitive self-attention (PSA) unit to enhance the model's ability to incorporate local context by attending to the positional relationships of the input data at each time step. Additionally, a gated hierarchical long short-term memory network (GHLSTM) is designed to perform regression prediction at different time scales on the latent features, thereby improving the accuracy of RUL estimation for mechanical equipment. Experiments on the C-MAPSS dataset demonstrate that the proposed model outperforms existing methods in RUL prediction, showcasing its effectiveness in modeling complex degradation patterns and long-term dependencies.

On Batch Writing in COTS RFID Systems

We study the batch writing problem in RFID systems, where the reader seeks the most time-efficient way to write information into a given subset of tags. The problem is analogous to the multicast problem in classical networks, but one-to-many transmission is not supported in COTS RFID systems. Driven by the technical challenge, this paper addresses the problem of designing batch writing algorithms for COTS RFID systems. We make three contributions. Firstly, we establish the minimal execution time for any batch writing algorithm, thus setting the theoretical performance limit. Secondly, we quantitatively compare and gauge the existing propositions applicable to our problem. Thirdly, we develop a novel batch writing algorithm with minimal 25% performance gain over the best state-of-the-art solution. Our key technicalities are designing an encoding scheme allowing the reader to efficiently perform batch writing and optimizing the batch writing sequence to minimize the overall execution time. We also perform extensive experiments to demonstrate the effectiveness of our algorithm.

Quantum-Enhanced Representation Learning: A Quanvolutional Autoencoder Approach against DDoS Threats

Motivated by the growing threat of distributed denial-of-service (DDoS) attacks and the emergence of quantum computing, this study introduces a novel “quanvolutional autoencoder” architecture for learning representations. The architecture leverages the computational advantages of quantum mechanics to improve upon traditional machine learning techniques. Specifically, the quanvolutional autoencoder employs randomized quantum circuits to analyze time-series data from DDoS attacks, offering a robust alternative to classical convolutional neural networks. Experimental results suggest that the quanvolutional autoencoder performs similarly to classical models in visualizing and learning from DDoS hive plots and leads to faster convergence and learning stability. These findings suggest that quantum machine learning holds significant promise for advancing data analysis and visualization in cybersecurity. The study highlights the need for further research in this fast-growing field, particularly for unsupervised anomaly detection.

Advanced deep operator networks to predict multiphysics solution fields in materials processing and additive manufacturing

Unlike classical artificial neural networks, which require retraining for each new set of parametric inputs, the Deep Operator Network (DeepONet), a lately introduced deep learning framework, approximates linear and nonlinear solution operators by taking parametric functions (infinite-dimensional objects) as inputs and mapping them to complete solution fields. In this paper, two newly devised DeepONet formulations with sequential learning and Residual U-Net (ResUNet) architectures are trained for the first time to simultaneously predict complete thermal and mechanical solution fields under variable loading histories, process parameters, and even variable geometries. Two real-world applications are demonstrated: 1- coupled thermo-mechanical analysis of steel continuous casting with multiple visco-plastic constitutive laws and 2- sequentially coupled directed energy deposition for additive manufacturing. Despite highly challenging spatially variable target distributions, DeepONets can infer reasonably accurate full-field temperature and stress solutions several orders of magnitude faster than traditional and highly optimized finite-element analysis (FEA), even when FEA simulations are run on the latest high-performance computing platforms. The proposed DeepONet model’s ability to provide field predictions almost instantly for unseen input parameters opens the door for future preliminary evaluation and design optimization of these vital industrial processes.

DeepCOVID: a deep learning approach for accurate COVID-19 detection in point-of-care lung ultrasound

Sickness still continued to spread through several countries when it first appeared in China. The number of COVID-19 cases is rising daily worldwide, posing a severe threat to the government and the populace. As a result of the virus’s rapid spread, doctors are having trouble recognizing positive cases. It is obvious that computer-based diagnosis must be developed to get results at a reasonable cost. The classic convolutional neural network (CNN) is used for this, utilizing the CT dataset, and the upgraded CNN model is used with the lung ultrasound (LUS) dataset. The CT and LUS COVID imaging datasets are compared in the model. The accuracy of both deep learning models is higher. We customized ResNet50, a pre-trained deep learning architecture, for a web application paradigm. First, we suggest a method for normalizing data that addresses its variability because it is collected in hospitals using various CT scanners and ultrasound machines. Second, we identify COVID-19 patients using U-Net segmentation and classification. The CNN architecture is added for deep learning purposes, and Res-Net 50 offers incredible accuracy.

Research on the Optimization of Multi-Class Land Cover Classification Using Deep Learning with Multispectral Images

With the advancement of artificial intelligence, deep learning has become instrumental in land cover classification. While there has been a notable emphasis on refining model structures to improve classification accuracy, it is imperative to also emphasize the pivotal role of data-driven optimization techniques. This paper presents an in-depth investigation into optimizing multi-class land cover classification using high-resolution multispectral images from Worldview3. We explore various optimization strategies, including refined sampling strategies, data band combinations, loss functions, and model enhancements. Our optimizations led to a substantial increase in the Mean Intersection over Union (mIoU) classification accuracy, improving from a baseline of 0.520 to a final accuracy of 0.709, which represents a 35.2% enhancement. Specifically, by optimizing the classic semantic segmentation network in four key aspects, we improved the mIoU by 15.5%. Further improvements through changes in data combinations, sampling methods, and loss functions led to an overall 17.2% increase in mIoU. The proposed model optimization methods enabled the OUNet to outperform the baseline model by providing more precise edge detection and feature representation, while reducing the model parameters scale. Experimental evidence shows that in the application of multi-class land surface classification, increasing the quantity and diversity of samples, avoiding data imbalance issues, is equally valuable for improving overall classification accuracy as it is for enhancing model performance.

A Comprehensive Approach to Brain Tumor Classification in MRI: Unifying Classical Local Binary Patterns and Convolution Neural Networks

Brain tumors, among the most perilous neurological disorders affecting the human nervous system, are categorized into glioma, meningioma, and Pituitary types. The proposed system combines Classical Local Binary Patterns (CLBP), Histogram of Oriented Gradients (HOG), and Convolutional Neural Networks (CNN) to extract texture information from MRI images. The methodology comprises three key steps: image pre-processing, feature extraction, and classification. By evaluating a publicly accessible brain tumor dataset, the proposed approach attains an impressive accuracy of 96%. The findings highlight the potential uses of the CLBP+CNN approach in clinical diagnosis and treatment planning, demonstrating the possibility of accurate and efficient brain tumor classification. The proposal introduces future extension methods like CLBPs (DLBP, ӨLBP), where the DLBP approach incorporates a 'D' parameter specifying the distance between neighboring pixels. The ӨLBP Method evaluates the pixel value by changing the 'Ө' value, i.e., 150, 450, 900 and 1200. The classification of tumors involved the application of various classification methods, namely ANN (Artificial Neural Networks), AlDE (Ant Lion Optimizer Differential Evolution), and LDA (Linear Discriminant Analysis). This classification is executed using feature extractions derived from CLBP (DLBP & ӨLBP) applied to MRI images within the dataset.

Increasing the reliability of diagnosis of diabetic retinopathy based on machine learning

This paper discusses the method of measuring and analyzing the parameters of the retina with subsequent diagnosis based on them of pathological changes due to diabetic retinopathy, which is crucial in the field of medicine to help doctors in timely detection and treatment of the disease. The main problem of biomedical image data analysis is insufficient pre-processing of images for further clear determination of informative indicators. This paper explores the application of machine learning and image processing techniques to develop an effective method for the diagnosis of diabetic retinopathy. The main focus is on obtaining the optimal model using machine learning and different types of neural networks. This paper considered and analyzed such methods of image preprocessing as: median filtering, grayscale conversion, cropping of non-informative areas of the image, selection of contours. The classification results of three rules (Classical Neural Networks (CNNs), Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) were analyzed, and through experimental studies it was determined that the ANN performed the task best (accuracy=87.1 %, reliability=84.6 %, sensitivity=91.6 %, specificity=84 %). An information model was obtained to support decision-making in assessing the condition of the retina using the processing of the obtained microscopic images and further analysis of informative parameters, and a database of more than 35,000 samples and informative features of the retina was formed. Given the sufficient quality of classification and the availability of software and hardware, this method can be developed and applied in practice in medical institutions after conducting all the necessary clinical studies

Demand-side load forecasting in smart grids using machine learning techniques.

Electrical load forecasting remains an ongoing challenge due to various factors, such as temperature and weather, which change day by day. In this age of Big Data, efficient handling of data and obtaining valuable information from raw data is crucial. Through the use of IoT devices and smart meters, we can capture data efficiently, whereas traditional methods may struggle with data management. The proposed solution consists of two levels for forecasting. The selected subsets of data are first fed into the "Daily Consumption Electrical Networks" (DCEN) network, which provides valid input to the "Intra Load Forecasting Networks" (ILFN) network. To address overfitting issues, we use classic or conventional neural networks. This research employs a three-tier architecture, which includes the cloud layer, fog layer, and edge servers. The classical state-of-the-art prediction schemes usually employ a two-tier architecture with classical models, which can result in low learning precision and overfitting issues. The proposed approach uses more weather features that were not previously utilized to predict the load. In this study, numerous experiments were conducted and found that support vector regression outperformed other methods. The results obtained were 5.055 for mean absolute percentage error (MAPE), 0.69 for root mean square error (RMSE), 0.37 for normalized mean square error (NRMSE), 0.0072 for mean squared logarithmic error (MSLE), and 0.86 for R2 score values. The experimental findings demonstrate the effectiveness of the proposed method.

Optimal quantum key distribution networks: capacitance versus security

The rate and security of quantum communications between users placed at arbitrary points of a quantum communication network depend on the structure of the network, on its extension and on the nature of the communication channels. In this work we propose a strategy for the optimization of trusted-relays based networks that intertwines classical network approaches and quantum information theory. Specifically, by suitably defining a quantum communication efficiency functional, we identify the optimal quantum communication connections through the network by balancing security and the quantum communication rate. The optimized network is then constructed as the network of the maximal quantum communication efficiency connections and its performance is evaluated by studying the scaling of average properties as functions of the number of nodes and of the network spatial extension.

MEA-EFFormer: Multiscale Efficient Attention with Enhanced Feature Transformer for Hyperspectral Image Classification

Hyperspectral image classification (HSIC) has garnered increasing attention among researchers. While classical networks like convolution neural networks (CNNs) have achieved satisfactory results with the advent of deep learning, they are confined to processing local information. Vision transformers, despite being effective at establishing long-distance dependencies, face challenges in extracting high-representation features for high-dimensional images. In this paper, we present the multiscale efficient attention with enhanced feature transformer (MEA-EFFormer), which is designed for the efficient extraction of spectral–spatial features, leading to effective classification. MEA-EFFormer employs a multiscale efficient attention feature extraction module to initially extract 3D convolution features and applies effective channel attention to refine spectral information. Following this, 2D convolution features are extracted and integrated with local binary pattern (LBP) spatial information to augment their representation. Then, the processed features are fed into a spectral–spatial enhancement attention (SSEA) module that facilitates interactive enhancement of spectral–spatial information across the three dimensions. Finally, these features undergo classification through a transformer encoder. We evaluate MEA-EFFormer against several state-of-the-art methods on three datasets and demonstrate its outstanding HSIC performance.

BerryNet-Lite: A Lightweight Convolutional Neural Network for Strawberry Disease Identification

With the rapid advancements in computer vision, using deep learning for strawberry disease recognition has emerged as a new trend. However, traditional identification methods heavily rely on manual discernment, consuming valuable time and imposing significant financial losses on growers. To address these challenges, this paper presents BerryNet-Lite, a lightweight network designed for precise strawberry disease identification. First, a comprehensive dataset, encompassing various strawberry diseases at different maturity levels, is curated. Second, BerryNet-Lite is proposed, utilizing transfer learning to expedite convergence through pre-training on extensive datasets. Subsequently, we introduce expansion convolution into the receptive field expansion, promoting more robust feature extraction and ensuring accurate recognition. Furthermore, we adopt the efficient channel attention (ECA) as the attention mechanism module. Additionally, we incorporate a multilayer perceptron (MLP) module to enhance the generalization capability and better capture the abstract features. Finally, we present a novel classification head design approach which effectively combines the ECA and MLP modules. Experimental results demonstrate that BerryNet-Lite achieves an impressive accuracy of 99.45%. Compared to classic networks like ResNet34, VGG16, and AlexNet, BerryNet-Lite showcases superiority across metrics, including loss value, accuracy, precision, F1-score, and parameters. It holds significant promise for applications in strawberry disease identification.

Bi-directional information guidance network for UAV vehicle detection

UAV vehicle detection based on convolutional neural network exits a key problem of information imbalance of different feature layers. Shallow features have spatial information that is beneficial to localization, but lack semantic information. On the contrary, deep features have semantic information that is beneficial to classification, but lack spatial information. However, accurate classification and localization for UAV vehicle detection require both shallow spatial information and high semantic information. In our work, a bi-directional information guidance network (BDIG-Net) for UAV vehicle detection is proposed, which can ensure that each feature prediction layer has abundant mid-/low-level spatial information and high-level semantic information. There are two main parts in the BDIG-Net: shallow-level spatial information guidance part and deep-level semantic information guidance part. In the shallow-level guidance part, we design a feature transform module (FTM) to supply the mid-/low-level feature information, which can guide the BDIG-Net to enhance detailed and spatial features for deep features. Furthermore, we adopt a light-weight attention module (LAM) to reduce unnecessary shallow background information, making the network more focused on small-sized vehicles. In the deep-level guidance part, we use classical feature pyramid network to supply high-level semantic information, which can guide the BDIG-Net to enhance contextual information for shallow features. Meanwhile, we design a feature enhancement module (FEM) to suppress redundant features and improve the discriminability of vehicles. The proposed BDIG-Net can reduce the information imbalance. The experimental results show that the BDIG-Net can achieve accurate classification and localization for UAV vehicles and realize the real-time application requirements.