Improve Generalization Capability Research Articles

Intensified customer churn Prediction: Connectivity with weighted Multi-Layer Perceptron and Enhanced Multipath Back Propagation

In the telecommunication industry, forecasting customer turnover in telecom networks is crucial for maintaining customers and increasing profits. The proposed model explores the importance of predicting churn, emphasizing its financial impact and strategic significance for telecommunications companies. Manual methods for predicting churn are restricted due to their dependence on basic models and human opinion, leading to less than ideal precision and effectiveness. Artificial Intelligence (AI)-based methods have arisen as promising solutions in light of these limitations. Nevertheless, existing AI methods frequently encounter issues like over-fitting, restricted interpretability, and suboptimal generalization. The presented system introduces a novel technique, named “MBP-WMLP” abbreviated as Multipath Back Propagation with Weighted MLP, to improve prediction accuracy in telecommunication networks. The respective approach utilizes a specialized multi-layer perceptron (MLP) structure with weights, designed for managing the intricacies of telecommunications data. Moreover, an improved multipath back-propagation method is presented to improve the optimization of model training and convergence. The projected model combines weighted MLP and enhanced multipath back-propagation to achieve better prediction accuracy, increased interpretability, and improved generalization capabilities. Furthermore, the proposed technique will be applied for authentic Telco customer churn datasets containing sanitized customer activity features and churn labels indicating subscription cancellations for creating predictive models. The projected approach is intended to show potential for improving customer loyalty tactics and boosting profits for telecom companies in a more competitive market environment.

Improved Prediction of Ligand-Protein Binding Affinities by Meta-modeling.

The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity between ligands and proteins. Many computational models for binding affinity prediction have been developed, but with varying results across targets. Given that ensembling or meta-modeling approaches have shown great promise in reducing model-specific biases, we develop a framework to integrate published force-field-based empirical docking and sequence-based deep learning models. In building this framework, we evaluate many combinations of individual base models, training databases, and several meta-modeling approaches. We show that many of our meta-models significantly improve affinity predictions over base models. Our best meta-models achieve comparable performance to state-of-the-art deep learning tools exclusively based on 3D structures while allowing for improved database scalability and flexibility through the explicit inclusion of features such as physicochemical properties or molecular descriptors. We further demonstrate improved generalization capability by our models using a large-scale benchmark of affinity prediction as well as a virtual screening application benchmark. Overall, we demonstrate that diverse modeling approaches can be ensembled together to gain meaningful improvement in binding affinity prediction.

Intensified Customer Churn Prediction: Connectivity with Weighted Multi-Layer Perceptron and Enhanced Multipath Back Propagation

In the telecommunication industry, forecasting customer turnover in telecom networks is crucial for maintaining customers and increasing profits. The proposed model explores the importance of predicting churn, emphasizing its financial impact and strategic significance for telecommunications companies. Manual methods for predicting churn are restricted due to their dependence on basic models and human opinion, leading to less than ideal precision and effectiveness. Artificial Intelligence (AI)-based methods have arisen as promising solutions in light of these limitations. Nevertheless, existing AI methods frequently encounter issues like over-fitting, restricted interpretability, and suboptimal generalization. The presented system introduces a novel technique, named "MBP-WMLP” abbreviated as Multipath Back Propagation with Weighted MLP, to improve prediction accuracy in telecommunication networks. The respective approach utilizes a specialized multi-layer perceptron (MLP) structure with weights, designed for managing the intricacies of telecommunications data. Moreover, an improved multipath back-propagation method is presented to improve the optimization of model training and convergence. The projected model combines weighted MLP and enhanced multipath back-propagation to achieve better prediction accuracy, increased interpretability, and improved generalization capabilities. Furthermore, the proposed technique will be applied to authentic Telco customer churn datasets containing sanitized customer activity features and churn labels indicating subscription cancellations for creating predictive models. The projected approach is intended to shows potential for improving customer loyalty tactics and boosting profits for telecom companies in a more competitive market environment.

Single-Task Joint Learning Model for an Online Multi-Object Tracking Framework

Multi-object tracking faces critical challenges, including occlusions, ID switches, and erroneous detection boxes, which significantly hinder tracking accuracy in complex environments. To address these issues, this study proposes a single-task joint learning (STJL) model integrated into an online multi-object tracking framework to enhance feature extraction and model robustness across diverse scenarios. Employing cross-dataset training, the model has improved generalization capabilities and can effectively handle various tracking conditions. A key innovation is the refined tracker initialization strategy that combines detection and tracklet confidence, which significantly reduces the number of false positives and ID switches. Additionally, the framework employs a combination of Mahalanobis and cosine distances to optimize data association, further improving tracking accuracy. The experimental results demonstrate that the proposed model outperformed state-of-the-art methods on standard benchmark datasets, achieving superior MOTA and reduced ID switches, confirming its effectiveness in dynamic and occlusion-heavy environments.

Will Transformers change gastrointestinal endoscopic image analysis? A comparative analysis between CNNs and Transformers, in terms of performance, robustness and generalization

Gastrointestinal endoscopic image analysis presents significant challenges, such as considerable variations in quality due to the challenging in-body imaging environment, the often-subtle nature of abnormalities with low interobserver agreement, and the need for real-time processing. These challenges pose strong requirements on the performance, generalization, robustness and complexity of deep learning-based techniques in such safety–critical applications. While Convolutional Neural Networks (CNNs) have been the go-to architecture for endoscopic image analysis, recent successes of the Transformer architecture in computer vision raise the possibility to update this conclusion. To this end, we evaluate and compare clinically relevant performance, generalization and robustness of state-of-the-art CNNs and Transformers for neoplasia detection in Barrett’s esophagus. We have trained and validated several top-performing CNNs and Transformers on a total of 10,208 images (2,079 patients), and tested on a total of 7,118 images (998 patients) across multiple test sets, including a high-quality test set, two internal and two external generalization test sets, and a robustness test set. Furthermore, to expand the scope of the study, we have conducted the performance and robustness comparisons for colonic polyp segmentation (Kvasir-SEG) and angiodysplasia detection (Giana). The results obtained for featured models across a wide range of training set sizes demonstrate that Transformers achieve comparable performance as CNNs on various applications, show comparable or slightly improved generalization capabilities and offer equally strong resilience and robustness against common image corruptions and perturbations. These findings confirm the viability of the Transformer architecture, particularly suited to the dynamic nature of endoscopic video analysis, characterized by fluctuating image quality, appearance and equipment configurations in transition from hospital to hospital. The code is made publicly available at: https://github.com/BONS-AI-VCA-AMC/Endoscopy-CNNs-vs-Transformers.

Cross-Modality Person Re-Identification Method with Joint-Modality Generation and Feature Enhancement.

In order to minimize the disparity between visible and infrared modalities and enhance pedestrian feature representation, a cross-modality person re-identification method is proposed, which integrates modality generation and feature enhancement. Specifically, a lightweight network is used for dimension reduction and augmentation of visible images, and intermediate modalities are generated to bridge the gap between visible images and infrared images. The Convolutional Block Attention Module is embedded into the ResNet50 backbone network to selectively emphasize key features sequentially from both channel and spatial dimensions. Additionally, the Gradient Centralization algorithm is introduced into the Stochastic Gradient Descent optimizer to accelerate convergence speed and improve generalization capability of the network model. Experimental results on SYSU-MM01 and RegDB datasets demonstrate that our improved network model achieves significant performance gains, with an increase in Rank-1 accuracy of 7.12% and 6.34%, as well as an improvement in mAP of 4.00% and 6.05%, respectively.

Advancing software reliability with time series insights: A non‐autoregressive ANN approach

AbstractSoftware reliability is a critical factor in assessing the health of software and identifying defects. Software reliability growth models (SRGM) are used to estimate the occurrence of software faults. There are various parameterized and non‐parameterized models of SRGM. These models effectively predict fault occurrence for limited testing conditions. To resolve this problem various neural and artificial neural network (ANN) models are proposed. A problem while using ANN is over‐fitting and under‐fitting. Non‐autoregressive time series models, including ANN variants, offer promising solutions to address under‐fitting issues in SRGM, providing enhanced predictive capabilities for fault occurrence across diverse testing conditions. This study proposes a modified version with a Bayesian regularization technique to address over‐fitting. This modification aims to enhance the suitability of the Bayesian regularization framework for nonlinear autoregressive (NAR) models by carefully adjusting regularization parameters. Comprehensive testing with real‐world software failure datasets is conducted to evaluate the effectiveness of the proposed approach. The results demonstrate that our modified approach improved generalization capabilities and increased prediction accuracy. The NAR‐ANN model exhibits a lower mean squared error of 0.12935 and a higher value of 0.99853.

A Deep Learning Model for Neural Network Optimization for Glaucoma Classification Using Fundus and Oct Feature Fusion

Irreversible vision loss is a common consequence of glaucoma, demands accurate and timely diagnosis for effective management. This research aims to enhance glaucoma classification accuracy by fusing information from two distinct imaging modalities like using deep learning explores the fusion of these modalities through an innovative neural network architecture with optimization. This approach combines Deep Stochastic Variational Autoencoder Convolution Neural Networks (DSVAECNN) and Adam optimization techniques to enable robust and accurate classification of glaucoma. A multi-path architecture is designed to accommodate both imaging as optical coherence tomography (OCT) radiomics features and fundus morphological features simultaneously. To ensure the effectiveness of the model, this study investigates the implementation of advanced optimization algorithm such as Adam, to expedite convergence and alleviate the risk of over fitting. The resulting model demonstrates improved generalization capabilities, critically for accurate diagnosis across diverse patient populations. A comprehensive OCT and fundus images dataset is used to evaluate the proposed approach from a representative cohort of glaucoma patients and healthy individuals. Quantitative various metrics including sensitivity, accuracy and specificity are employed toward appraise the accomplishment of the fusion-based classification model. Comparisons with current techniques show the dominance of the proposed move toward in accurately detecting glaucoma cases. This research provides the advancement of glaucoma diagnosis by effectively harnessing the synergy between fundus image and OCT scans and findings helpful information for clinics, ultimately facilitating early detection and personalized management of glaucoma, thus preserving vision for affected individuals.

A Novel Method for Bearing Fault Diagnosis Based on a Parallel Deep Convolutional Neural Network

The symmetry of vibration signals collected from healthy machinery, which gradually degenerates with the development of faults, must be detected for timely diagnosis and prognosis. However, conventional methods may miss spatiotemporal relationships, struggle with varying sampling rates, and lack adaptability to changing loads and conditions, affecting diagnostic accuracy. A novel bearing fault diagnosis approach is proposed to address these issues, which integrates the Gramian angular field (GAF) transformation with a parallel deep convolutional neural network (DCNN). The crux of this method lies in the preprocessing of input signals, where sampling rate normalization is employed to minimize the effects of varying sampling rates on diagnostic outcomes. Subsequently, the processed signals undergo GAF transformation, converting them into an image format that effectively represents their spatiotemporal relationships in a two-dimensional space. These images serve as inputs to the parallel DCNN, facilitating feature extraction and fault classification through deep learning techniques and leading to improved generalization capabilities on test data. The proposed method achieves an overall accuracy of 96.96%, even in the absence of training data within the test set. Discussions are also conducted to quantify the effects of sampling rate normalization and model structures on diagnostic accuracy.

The Investigation of Multiple Optimization Methods on Convolutional Neural Network

In this study, the optimization of a Convolutional Neural Network (CNN) was conducted using the Fruits 360 dataset, with a specific emphasis on the impacts of Spatial Transformer Network (STN) and Stochastic Gradient Descent (SGD) optimization methods. Firstly, a baseline CNN model is built, which achieves 97.84% accuracy with a loss of 0.0999 after 50 epochs. Then, the impact of integrating STN and SGD into CNN models separately is investigated. The addition of STN slightly increased the accuracy to 97.92%, reduced the loss to 0.0994, and decreased the validation accuracy. This result suggests that while STN enhances the model's generalization ability, it may slightly reduce the maximum accuracy achievable on the validation set. After SGD optimization, the verification accuracy is increased to 98.19%, the loss is reduced to 0.0537, and the verification accuracy is increased to 98.40%. These results highlight the effectiveness of SGD in fine-tuning model parameters, resulting in more accurate models and improved generalization capabilities. A comparative analysis of these methods highlights their respective advantages. The effectiveness of the STN is rooted in its capacity to improve model generalization and mitigate overfitting, which is particularly beneficial in situations that demand robustness against varied data sets. In contrast, SGD stands out for its ability to significantly improve model accuracy and reduce loss, making it a balanced choice for comprehensive model optimization. Future research directions include exploring these optimization techniques on various datasets and investigating the potential of combining STN and SGD to achieve higher performance in CNN models.

Improving deep PROPELLER MRI via synthetic blade augmentation and enhanced generalization

In PROPELLER MRI, obtaining sufficient high-quality blade data remains a challenge, so the efficiency and generalization of deep learning-based reconstruction models are deteriorated. Due to narrow rotated and translated blades acquired in PROPELLER, the technique of data augmentation that is used for deep learning-based Cartesian MRI reconstruction cannot be directly applied. To address the issue, this paper introduces a novel approach for the generation of synthetic PROPELLER blades, and it is subsequently employed in data augmentation for undersampled blades reconstruction. The principal aim of this study is to address the challenges of reconstructing undersampled blades to enhance both image quality and computational efficiency. Evaluation metrics including PSNR, NMSE, and SSIM indicate superior performance of the model trained with augmented data compared to non-augmented counterparts. The synthetic blade augmentation significantly enhances the model's generalization capability and enables robust performance across varying imaging conditions. Furthermore, the study demonstrates the feasibility of utilizing synthetic blades exclusively in the training phase, suggesting a reduced dependency on real PROPELLER blades. This innovation in synthetic blade generation and data augmentation technique contributes to enhanced image quality and improved generalization capability of the associated deep learning model for PROPELLER MRI reconstruction.

Improving generalization capability of deep learning-based nuclei instance segmentation by non-deterministic train time and deterministic test time stain normalization

With the advent of digital pathology and microscopic systems that can scan and save whole slide histological images automatically, there is a growing trend to use computerized methods to analyze acquired images. Among different histopathological image analysis tasks, nuclei instance segmentation plays a fundamental role in a wide range of clinical and research applications. While many semi- and fully-automatic computerized methods have been proposed for nuclei instance segmentation, deep learning (DL)-based approaches have been shown to deliver the best performances. However, the performance of such approaches usually degrades when tested on unseen datasets.In this work, we propose a novel method to improve the generalization capability of a DL-based automatic segmentation approach. Besides utilizing one of the state-of-the-art DL-based models as a baseline, our method incorporates non-deterministic train time and deterministic test time stain normalization, and ensembling to boost the segmentation performance. We trained the model with one single training set and evaluated its segmentation performance on seven test datasets. Our results show that the proposed method provides up to 4.9%, 5.4%, and 5.9% better average performance in segmenting nuclei based on Dice score, aggregated Jaccard index, and panoptic quality score, respectively, compared to the baseline segmentation model.

Using Graph Neural Networks to Improve Generalization Capability of the Models for Deepfake Detection

Using Graph Neural Networks to Improve Generalization Capability of the Models for Deepfake Detection

Simulation-Aided Handover Prediction From Video Using Recurrent Image-to-Motion Networks.

Recent advances in deep neural networks have opened up new possibilities for visuomotor robot learning. In the context of human-robot or robot-robot collaboration, such networks can be trained to predict future poses and this information can be used to improve the dynamics of cooperative tasks. This is important, both in terms of realizing various cooperative behaviors, and for ensuring safety. In this article, we propose a recurrent neural architecture, capable of transforming variable-length input motion videos into a set of parameters describing a robot trajectory, where predictions can be made after receiving only a few frames. A simulation environment is utilized to expand the training database and to improve generalization capability of the network. The resulting architecture demonstrates good accuracy when predicting handover trajectories, with models trained on synthetic and real data showing better performance than when trained on real or simulated data only. The computed trajectories enable the execution of handover tasks with uncalibrated robots, which was verified in an experiment with two real robots.

Accurate and generalizable photovoltaic panel segmentation using deep learning for imbalanced datasets

The widespread adoption of photovoltaic (PV) technology for renewable energy necessitates accurate segmentation of PV panels to estimate installation capacity. However, achieving highly efficient and precise segmentation methods remains a pressing challenge. Recent advancements in artificial intelligence and remote sensing techniques have shown promise in PV segmentation. Nevertheless, real-world scenarios introduce complexities such as diverse sensing platforms, sensors, panel categories, and testing regions. These factors contribute to resolution, size, and foreground-background class imbalances, impeding accurate and generalized PV panel segmentation over large areas. To address these challenges, we propose GenPV, a deep learning model that leverages data distribution analysis and PV panel characteristics to enhance segmentation accuracy and generalization. GenPV employs a multi-scale feature learning approach, utilizing an enhanced feature pyramid network to fuse data features from multiple resolutions, effectively addressing resolution imbalance. Moreover, inductive learning is employed through a multitask approach, facilitating the detection and identification of both small and large-sized PV panels to mitigate size imbalance. To address significant class imbalance in PV panel recognition tasks, we integrate the Focal loss function for effective hard sample mining. Through experimental evaluation conducted in Heilbronn, Germany, our proposed method demonstrates superior performance compared to state-of-the-art approaches in PV panel segmentation. The results exhibit progressively higher accuracy and improved generalization capability. These findings highlight the potential of our method to serve as an advanced and practical tool for PV segmentation in the renewable energy field.

Physics-informed few-shot deep learning for elastoplastic constitutive relationships

Elastoplastic modeling is essential for accurately predicting material behavior in various engineering applications. However, existing approaches to developing intelligent models for elastoplasticity face limitations due to the scarcity of available data, particularly in cases where experiments cannot support full training of these models. To address this challenge, we propose a physics-informed few-shot learning framework that incorporates classic elastoplasticity theory as prior knowledge. Instead of directly solving specific constitutive ordinary differential equations, we utilize general mechanical inequations as physical regularization to confine the optimization space. Our framework is model-agnostic in the uniaxial scenario and free from complicated numerical implementation, preserving the advantages of the data-driven paradigm in terms of efficiency and simplicity. In the multiaxial scenario, the framework can automatically calibrate multiple interwoven material parameters of the underlying constitutive model, facilitating the generation of ample multiaxial data for downstream learning. To further improve convergence, we introduce a novel training strategy. A numerical experiments with only 32 pieces of training data validate the effectiveness of the developed framework. The trained uniaxial model exhibits exceptional generalization capabilities, achieving 44.9% higher accuracy than the purely data-driven model. For multiaxial relationships, our framework demonstrates remarkable efficiency in calibrating material constants compared to conventional machine or manual methods, and the trained model accurately reproduces highly nonlinear multiaxial elastoplastic curves. Our work addresses the pressing need for accurate elastoplastic modeling in the absence of large datasets and provides a promising new solution that can significantly improve generalization capabilities.

Non-Intrusive Load Monitoring Based on the Combination of Gate-Transformer and CNN

Non-intrusive load monitoring (NILM) is the practice of estimating power consumption of a single household appliance using data from a total power meter of the user’s house. The transformer model has emerged as a popular method for handling NILM problems. However, with the increase in data from electricity meters, there is a need for research focusing on the accuracy and computational complexity of the transformer model. To address this, this paper proposes a sequence-to-sequence load decomposition structure named GTCN, which combines the gate-transformer and convolutional neural networks (CNNs). GTCN introduces a gating mechanism to reduce the number of parameters for training the model while maintaining performance. The introduction of CNNs can effectively capture local features that the gate-transformer may not be able to capture, thereby improving the accuracy of power estimation of individual household appliances. The results of the experiments, based on the UK-DALE dataset, illustrate that GTCN not only demonstrates excellent decomposition performance but also reduces the model parameters compared to conventional transformers. Moreover, the proposed GTCN structure, despite maintaining the same number of model parameters as the traditional transformer architecture after incorporating CNNs, outperforms the conventional transformer model, as well as current seq2seq and R-LSTM technologies, and achieves enhanced prediction accuracy and improved generalization capability.

An Artificial Intelligence Driven Review of Literature on the Detection of COVID-19 Disease from Radiographic Images

Abstract: Pandemic of COVID-19 has attained significance in the field of research and innovation. After the arrival of various variants of covid 19, it demands more research for the identification and analysis of features. Medical investigations are found to be risky and costly. And so, the use of artificial intelligence techniques become more popular for the classification of covid 19 features. Such AI techniques perform recognition with accuracy and time effective in order to control diagnosis. The use of AI for COVID-19 detection has emerged as a promising solution. The proposed review of literature performs the analysis of the effectiveness of the AI models such as CNN and Inception-ResNet-V2, for the identification of COVID-19 from the radiographic scans. While these models have shown promising results, it is important to use them as an additional tool to assist medical professionals, rather than as a replacement. Ethical considerations such as reliability, transparency, and fairness must also be considered in the development of these models. Additionally, the data used to train and test these models should be diverse, representative, and validated to avoid potential biases and improve generalization capabilities. Further research and collaboration between medical professionals and AI experts are needed to advance the management and deployment of AI models for the detection of COVID-19.

Super-Resolution of Images using Contrastive Self-Learning

Abstract: Super-resolution (SR) techniques aim to enhance the resolution and quality of low-resolution images. In recent years, deep learning-based approaches have achieved remarkable success in this field. However, training deep SR models often requires large-scale datasets and computationally expensive operations, limiting their practicality. Different approaches have been proposed to tackle computation and time constraints. Our novel approach involves a combination of knowledge distillation and contrastive loss function to train a compact and efficient contrastive self-distillation (CSD) model. In the framework, a teacher network is initially trained on a large dataset using a traditional supervised learning approach. The teacher network learns to generate high-resolution images from low-resolution inputs. Subsequently, a student network is initialized with the same architecture as the teacher network but with fewer parameters. The student network is then trained to mimic the behavior of the teacher network by utilizing a contrastive loss. The contrastive loss is formulated by constructing positive and negative pairs of low-resolution and high-resolution image patches. The proposed CSD method achieves competitive performance compared to state-of-the-art SR methods while requiring significantly fewer parameters and computational resources. Furthermore, it demonstrates improved generalization capability by effectively reconstructing details in real-world images.

Multi-Scale Feature Fusion using Parallel-Attention Block for COVID-19 Chest X-ray Diagnosis

Under the global COVID-19 crisis, accurate diagnosis of COVID-19 from Chest X-ray (CXR) images is critical. To reduce intra- and inter-observer variability, during the radiological assessment, computer-aided diagnostic tools have been utilized to supplement medical decision-making and subsequent disease management. Computational methods with high accuracy and robustness are required for rapid triaging of patients and aiding radiologists in the interpretation of the collected data. In this study, we propose a novel multi-feature fusion network using parallel attention blocks to fuse the original CXR images and local-phase feature-enhanced CXR images at multi-scales. We examine our model on various COVID-19 datasets acquired from different organizations to assess the generalization ability. Our experiments demonstrate that our method achieves state-of-art performance and has improved generalization capability, which is crucial for widespread deployment.