Penalty Loss Research Articles

PSAR-SR: Patches separation and artifacts removal for improving super-resolution networks

The success of the ClassSR has led to a strategy of decomposing images being used for large image SR. The decomposed image patches have different recovery difficulties. Therefore, in ClassSR, image patches are reconstructed by different networks to greatly reduce the computational cost. However, in ClassSR, the training of multiple sub-networks inevitably increases the training difficulty. Furthermore, decomposing images with overlapping not only increases the computational cost but also inevitably produces artifacts. To address these challenges, we propose an end-to-end general framework, named patches separation and artifacts removal SR (PSAR-SR). In PSAR-SR, we propose an image information complexity module (IICM) to efficiently determine the difficulty of recovering image patches. Then, we propose a patches classification and separation module (PCSM), which can dynamically select an appropriate SR path for image patches of different recovery difficulties. Moreover, we propose a multi-attention artifacts removal module (MARM) in the network backend, which can not only greatly reduce the computational cost but also solve the artifacts problem well under the overlapping-free decomposition. Further, we propose two loss functions — threshold penalty loss (TP-Loss) and artifacts removal loss (AR-Loss). TP-Loss can better select appropriate SR paths for image patches. AR-Loss can effectively guarantee the reconstruction quality between image patches. Experiments show that compared to the leading methods, PSAR-SR well eliminates artifacts under the overlapping-free decomposition and achieves superior performance on existing methods (e.g., FSRCNN, CARN, SRResNet, RCAN and CAMixerSR). Moreover, PSAR-SR saves 53%–65% FLOPs in computational cost far beyond the leading methods. The code will be made available: https://github.com/dywang95/PSAR-SR.

Carrier-Free Ultra-Wideband Sensor Target Recognition in the Jungle Environment

Carrier-free ultra-wideband sensors have high penetrability anti-jamming solid ability, which is not easily affected by the external environment, such as weather. Also, it has good performance in the complex jungle environment. In this paper, we propose a jungle vehicle identification system based on a carrier-free ultra-wideband sensor. Firstly, a composite jungle environment with the target vehicle is modeled. From this model, the simulation obtains time-domain echoes under the excitation of carrier-free ultra-wideband sensor signals in different orientations. Secondly, the time-domain signals are transformed into MTF images through the Markov transfer field to show the statistical characteristics of the time-domain echoes. At the same time, we propose an improved RepVGG network. The structure of the RepVGG network contains five stages, which consist of several RepVGG Blocks. Each RepVGG Block is created by combining convolutional kernels of different sizes using a weighted sum. We add the self-attention module to the output of stage 0 to improve the ability to extract the features of the MTF map and better capture the complex relationship between characteristics during training. In addition, a self-attention module is added before the linear layer classification output in stage 4 to improve the classification accuracy of the network. Moreover, a combined cross-entropy loss and sparsity penalty loss function helps enhance the performance and accuracy of the network. The experimental results show that the system can recognize jungle vehicle targets well.

A Class Distance Penalty Deep Learning Method for Post-disaster Building Damage Assessment

Automatic building damage assessment can significantly aid rescue operations, attributed to booming deep learning and remote sensing technologies. However, the class imbalance of the dataset often skews prediction models towards the majority class in the segmentation of damaged buildings. This issue is further exacerbated when damaged buildings are categorized into multiple scales, intensifying biases within the models. Hence, this research adopts an algorithm-level method to improve the reliability of post-disaster damage assessment. It proposes a novel loss function named Ordinal Class Distance Penalty Loss (OCDPL), considering the ordinal relationship between classes and penalizing the misclassifications according to the class error distance. Two hyperparameters are also introduced to enable the model to fine-tune the contribution of ordinal relationships on the loss function. The satellite images of hurricane disasters in the xBD dataset were adopted as the case study. The results show that the proposed approach can improve F1 scores and Mean Absolute Error of overall damage level classes. Notably, the findings underscore the value of leveraging information on ordinal classes to facilitate the learning of minority classes and diminish class error distances. This aspect holds particular significance for emergency responses to widespread and severe disasters.

An intelligent IoT intrusion detection system using HeInit-WGAN and SSO-BNMCNN based multivariate feature analysis

Devices connected to the Internet of Things (IoT) are growing in popularity across multiple industries. IoT links intelligent homes, buildings, businesses, and communities, and also links computers and mobile devices. Cybersecurity in IoT networks remains challenging, although many intrusion detection services for assault avoidance systems have been developed. Because of enormous growth in computing resources, attack surfaces, communications infrastructure, and attack rates, IoT services encounter substantial security issues. Innovative intrusion-detection systems ensuring data security, availability, and integrity have been developed to mitigate security problems; these systems are recommended for preventing common internal and external assaults and managing IoT environments. To clearly understand any impending attacks, the data are first preprocessed. Missing values are categorized with the concordance connection coefficient, and preprocessing is applied before handling of the missing values. The unevenly distributed and overlapping data are then handled through maximum likelihood estimation-based robust scalar (MLE-RS) scaling followed by random oversampling-based cluster-initialized divisive clustering (ROS-CInitDC). This study conceptualizes a Squirrel search optimization-based Bengio Nesterov momentum convolutional neural network (SSO-BNMCNN)-based approach, which indicates the relationships among information by considering causation. It keeps an optimal processing time and correctness to get data understanding. The selected features are then tested against the categorization of a He initialization-based Wasserstein gradient penalty loss generative adversarial network (HeInit-WGAN). The HeInit-WGAN technique identifies attacks more reliably and accurately than existing methods, reducing false alarms. The proposed strategy had an F-measure of 0.91, and scores of 0.96 for precision, 0.91 for awareness, and 0.98 for explicitness. Moreover, it decreased the false acceptance rate, achieving a 0.02 false positive rate and 0.09 false negative rate.

Dynamic controllable residual generative adversarial network for low-dose computed tomography imaging.

Computed tomography (CT) imaging technology has become an indispensable auxiliary method in medical diagnosis and treatment. In mitigating the radiation damage caused by X-rays, low-dose computed tomography (LDCT) scanning is becoming more widely applied. However, LDCT scanning reduces the signal-to-noise ratio of the projection, and the resulting images suffer from serious streak artifacts and spot noise. In particular, the intensity of noise and artifacts varies significantly across different body parts under a single low-dose protocol. To improve the quality of different degraded LDCT images in a unified framework, we developed a generative adversarial learning framework with a dynamic controllable residual. First, the generator network consists of the basic subnetwork and the conditional subnetwork. Inspired by the dynamic control strategy, we designed the basic subnetwork to adopt a residual architecture, with the conditional subnetwork providing weights to control the residual intensity. Second, we chose the Visual Geometry Group Network-128 (VGG-128) as the discriminator to improve the noise artifact suppression and feature retention ability of the generator. Additionally, a hybrid loss function was specifically designed, including the mean square error (MSE) loss, structural similarity index metric (SSIM) loss, adversarial loss, and gradient penalty (GP) loss. The results obtained on two datasets show the competitive performance of the proposed framework, with a 3.22 dB peak signal-to-noise ratio (PSNR) margin, 0.03 SSIM margin, and 0.2 contrast-to-noise ratio margin on the Challenge data and a 1.0 dB PSNR margin and 0.01 SSIM margin on the real data. Experimental results demonstrated the competitive performance of the proposed method in terms of noise decrease, structural retention, and visual impression improvement.

A time-series Wasserstein GAN method for state-of-charge estimation of lithium-ion batteries

Estimating the state-of-charge (SOC) of lithium-ion batteries is essential for maintaining secure and reliable battery operation while minimizing long-term service and maintenance expenses. In this work, we present a novel Time-Series Wasserstein Generative Adversarial Network (TS-WGAN) approach for SOC estimation of lithium-ion batteries, characterized by a well-designed data preprocessing process and a distinctive WGAN-GP architecture. In the data preprocessing stage, we employ the Pearson correlation coefficient (PCC) to identify strongly associated features and apply feature scaling techniques for data normalization. Moreover, we leverage polynomial regression to expand the original features and utilize principal component analysis (PCA) to reduce the computational load and retain essential information by projecting features into a lower-dimensional subspace. Within the WGAN-GP architecture, we originally devise a Transformer as the generator and a Convolution Neural Network (CNN) as the critic to make the most of local (CNN) and global (Transformer) variables. The overall model is trained with the WGAN, incorporating gradient penalty loss for training purposes. Simulation outcomes using real-road dataset and laboratory dataset reveal that TS-WGAN surpasses all baseline methods with enhanced accuracy, stability, and robustness. The coefficient of determination (R2) for both datasets exceeds 99.50%, demonstrating its potential for practical application.

ViViD: View Prediction of Online Video Through Deep Neural Network-Based Analysis of Subjective Video Attributes

Popularity of a video in an online platform may be defined by its number of views. The total view count of a video may change throughout its presence in an online platform. However, in most cases the view count tends to saturate after a certain time. We propose a method to predict the total view of a video at saturation. We have modeled the task of finding the view count of a video at saturation as a joint classification and regression problem, which is solved via a deep neural network. The network has a classification and a regression head. The classification head decides the view band among a set of available bands, whereas the regression head outputs a tolerance view count within each band. We consider four video attributes as the input to the network, namely, the thumbnail associated with the video, the title, the audio and the video itself for the view prediction task. The attributes are fused in a hierarchical fashion in the deep neural network. We propose a custom mismatch loss function and a penalty loss function for the joint training of the classification and regression heads of the network. Experimental results show that our method is 6.47% better in view prediction than the competitive methods.

Synthetic lung ultrasound data generation using autoencoder with generative adversarial network

The goal of this study is to test the applicability of a generative adversarial network (GAN) to solve the class unbalancing problem in lung ultrasound (LUS) data. We introduce a supervised autoencoder with conditional latent space. During training, the generator utilizes the weights of the decoder and conditional latent space to generate synthetic LUS images, whereas the discriminator utilizes the weights of the encoder together with the class labels, which also allows classifying each synthetic image into the different classes. A customized gradient penalty loss function was utilised. This approach is tested on a dataset costing of 6500 LUS images, collected from 35 COVID-19 patients and labelled according to a validated 4 level scoring system [10.1109/TMI.2020.2994459]. 1000 synthetic images were generated to balance this dataset. The quality of the synthetic images was evaluated through similarity measures, computed with respect to training and unseen data. Moreover, the synthetic images were also evaluated by expert clinicians concerting their capability to mimic a realistic LUS image. In conclusion, the proposed approach appears to be capable to solve the class unbalancing problem by generating LUS images carrying novel information content, comparable to that of real data from new patients.

An Incremental SAR Target Recognition Framework via Memory-Augmented Weight Alignment and Enhancement Discrimination

Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) is one of the most important research directions in SAR image interpretation. While much existing research into SAR ATR has focused on deep learning technology, an equally important yet underexplored problem is its deployment in incremental learning scenarios. This letter proposes a new benchmark approach, termed Memory augmented weights alignment and Enhancement Discrimination Incremental Learning (MEDIL) algorithm to address this issue. Firstly, the attention mechanism is employed as part of the benchmark. Next, we discuss the problem of height deviation of weights at the fully connected layer and design a more suitable alignment of weights by guiding the memory module for contextual data processing. In addition, we leverage the incremental progressive sampling strategy to alleviate the imbalance between old and new classes during the training period. Finally, we propose to enhance the distinction among various classes with an angular penalty loss function to ensure the diversity of incremental instances. The proposed method is evaluated on MSTAR and OpenSARShip under different experimental settings. Experimental results demonstrate that our proposed approach can effectively solve catastrophic forgetting in SAR multiclass recognition problems.

Dynamic graph dropout for subgraph-based relation prediction

Relation prediction for knowledge graphs aims at predicting missing relationships between entities. Inductive relation prediction methods have received increasing attention because of their capability of handling unseen entities. Among the inductive methods, the subgraph-based algorithms have emerged, which inductively predict relations using the subgraph surrounding the target entities. Despite the effectiveness, prior subgraph-based studies rarely focus on the explainability of subgraph reasoning, with which is critical for humans to understand and trust the prediction from GNNs. One of the reasons for the weak explainability of subgraph-based methods is the existence of noisy nodes and edges, which also hinders having higher performance of the model. In this paper, we present a dynamic graph dropout algorithm that prunes irrelevant nodes and edges to find the minimum sufficient subgraph for relation prediction. By this means, the proposed algorithm provides an explanation for which parts of the subgraph the model derives its results from. Specifically, we design an estimation function to evaluate the importance of the nodes and edges. Two dropout functions, i.e., soft and hard dropouts, are elaborately designed to filter out noisy nodes and edges based on their importance. Moreover, multiple restriction losses, including topological loss and penalty loss, are proposed to regularize the generation of the pruned subgraph. In this way, our model seeks to preserve the topology information in the subgraph and meanwhile maximally eliminate the redundant information. By removing noisy information, the proposed algorithm outperforms state-of-the-art models on eight inductive datasets.

Optimizing two-dimensional polarization-diversity metagrating couplers for silicon photonics

Polarization-diversity couplers are promising industrially scalable optical devices that can couple optical signals with unknown polarization states into silicon photonic chips. Here we propose a novel, to the best of our knowledge, two-dimensional (2D) metagrating coupler (MGC) for the polarization-diversity system, which improves its coupling efficiency for both polarizations. Compared with the previously reported 2D grating couplers (GCs) with identical grating cells, the proposed apodized design gradually changes the aspect ratio and orientation angles of the elliptical patterns simultaneously. This 2D array of the varied grating cells modulates the diffracted mode field patterns and phases locally, and achieves a better overlap with the Gaussian fiber modes for both polarizations. The peak coupling loss (PCL) for the S-polarized and P-polarized light are − 1.6 d B and − 2.7 d B , respectively. The calculated polarization dependent loss is lower than 0.2 dB from 1522 nm to 1540 nm. The device is robust to the fabrication tolerance and fiber misalignment. The simulated fabrication tolerance analysis show that the etch depth error of ±20 nm results in less than 0.3 dB and 0.1 dB PCL drop, while the grating cell feature size error of ± 40 n m results in less than 0.6 dB and 0.2 dB PCL drop for both types of polarization light, respectively. The fiber misalignment should be within the range from − 2 µ m to + 2 µ m in two perpendicular directions, and the coupling angle deviation should be within the range from − 3 ∘ to + 3 ∘ , in order to assure 0.5 dB penalty loss for both polarizations. The performance of the design is insensitive to the mask misalignments. To assure 0.5 dB penalty loss for both polarizations, Δ θ is suggested to be within the range from − 3 ∘ to + 3 ∘ .

An algorithm for a no-wait flowshop scheduling problem for minimizing total tardiness with a constraint on total completion time

We consider a no-wait m-machine flowshop scheduling problem which is common in different manufacturing industries such as steel, pharmaceutical, and chemical. The objective is to minimize total tardiness since it minimizes penalty costs and loss of customer goodwill. We also consider the performance measure of total completion time which is significant in environments where reducing holding cost is important. We consider both performance measures with the objective of minimizing total tardiness subject to the constraint that total completion time is bounded. Given that the problem is NP-hard, we propose an algorithm. We conduct extensive computational experiments to compare the performance of the proposed algorithm with those of three well performing benchmark algorithms in the literature. Computational results indicate that the proposed algorithm reduces the error of the best existing benchmark algorithm by 88% under the same CPU times. The results are confirmed by extensive statistical analysis. Specifically, ANOVA analysis is conducted to justify the difference between the performances of the algorithms, and a test of hypothesis is performed to justify that the proposed algorithm is significantly better than the best existing benchmark algorithm with a significance level of 0.01.

An analysis of data breaches in the U.S. healthcare industry: diversity, trends, and risk profiling

ABSTRACT As healthcare information technology (HIT) advances, major stakeholders in the healthcare industry such as healthcare providers, health plan organizations, and business associates are generating and exchanging enormous amounts of patient data throughout the healthcare supply chain. Along with the explosive growth of electronic patient data, these stakeholders have experienced an increasing number of data breaches. Despite the significant consequences of the data breaches such as the loss of client privacy, regulatory penalty, and financial loss, there is a lack of studies on sector level trend analysis and risk profiling. This study develops a diversity index that can be used to compare the distribution of data breaches between three sectors of the healthcare industry. To enhance the understanding of the data breaches, this study utilizes a temporal aggregation of the data breaches, analyzes data breach risks, and develops a data-driven risk profile. The findings of this study can be used to improve the cybersecurity management of healthcare organizations.

WSGAN: An Improved Generative Adversarial Network for Remote Sensing Image Road Network Extraction by Weakly Supervised Processing

Road networks play an important role in navigation and city planning. However, current methods mainly adopt the supervised strategy that needs paired remote sensing images and segmentation images. These data requirements are difficult to achieve. The pair segmentation images are not easy to prepare. Thus, to alleviate the burden of acquiring large quantities of training images, this study designed an improved generative adversarial network to extract road networks through a weakly supervised process named WSGAN. The proposed method is divided into two steps: generating the mapping image and post-processing the binary image. During the generation of the mapping image, unlike other road extraction methods, this method overcomes the limitations of manually annotated segmentation images and uses mapping images that can be easily obtained from public data sets. The residual network block and Wasserstein generative adversarial network with gradient penalty loss were used in the mapping network to improve the retention of high-frequency information. In the binary image post-processing, this study used the dilation and erosion method to remove salt-and-pepper noise and obtain more accurate results. By comparing the generated road network results, the Intersection over Union scores reached 0.84, the detection accuracy of this method reached 97.83%, the precision reached 92.00%, and the recall rate reached 91.67%. The experiments used a public dataset from Google Earth screenshots. Benefiting from the powerful prediction ability of GAN, the experiments show that the proposed method performs well at extracting road networks from remote sensing images, even if the roads are covered by the shadows of buildings or trees.

ROSD: Refined Oriented Staged Detector for Object Detection in Aerial Image

Object detection in aerial image is a challenging task. Although many advanced methods based on the convolutional neural network were popular in natural scenes, the progress in aerial images is not so smooth. Unlike natural scenes, objects in aerial images have the characteristics of arbitrary orientation, densely distribution, and large scale variation, which leads to a series of problems such as feature misalignment, missed detection, and poor detection of large aspect ratio objects. In this paper, a Refined Oriented Staged Detector (ROSD) with the combination of refined horizontal detector and rotated detector is proposed to address these problems. In our refined horizontal detector, a multi-orientation Region of Interest (RoI) Align and Orientation Attention Module (OAM) are adopted to make use of the orientation information for obtaining the orientation-sensitive features in regression branch and produce the orientation-invariant features in classification branch. Considering the feature misalignment between horizontal and rotated anchors in rotated detector, Deform Inception Module (DIM) is proposed to deal with the geometric deformation problem caused by the location changes. Besides, we propose an aspect ratio guided loss which consists of a smooth L1 loss and an angular offset penalty loss to improve the detection performance of large aspect ratio objects. Comparison experiments on two public aerial images datasets (i.e., DOTA and HRSC2016) demonstrate that our method can achieve a competitive performance.

MW-ACGAN: Generating Multiscale High-Resolution SAR Images for Ship Detection.

In high-resolution Synthetic Aperture Radar (SAR) ship detection, the number of SAR samples seriously affects the performance of the algorithms based on deep learning. In this paper, aiming at the application requirements of high-resolution ship detection in small samples, a high-resolution SAR ship detection method combining an improved sample generation network, Multiscale Wasserstein Auxiliary Classifier Generative Adversarial Networks (MW-ACGAN) and the Yolo v3 network is proposed. Firstly, the multi-scale Wasserstein distance and gradient penalty loss are used to improve the original Auxiliary Classifier Generative Adversarial Networks (ACGAN), so that the improved network can stably generate high-resolution SAR ship images. Secondly, the multi-scale loss term is added to the network, so the multi-scale image output layers are added, and multi-scale SAR ship images can be generated. Then, the original ship data set and the generated data are combined into a composite data set to train the Yolo v3 target detection network, so as to solve the problem of low detection accuracy under small sample data set. The experimental results of Gaofen-3 (GF-3) 3 m SAR data show that the MW-ACGAN network can generate multi-scale and multi-class ship slices, and the confidence level of ResNet18 is higher than that of ACGAN network, with an average score of 0.91. The detection results of Yolo v3 network model show that the detection accuracy trained by the composite data set is as high as 94%, which is far better than that trained only by the original SAR data set. These results show that our method can make the best use of the original data set, improve the accuracy of ship detection.

DeftectNet: Joint loss structured deep adversarial network for thermography defect detecting system

In this paper, a novel joint loss Generative Adversarial Networks (GAN) framework is proposed for thermography nondestructive testing named Defect-Detection Network (DeftectNet). A new joint loss function that incorporates both the modified GAN loss and penalty loss is proposed. The strategy enables the training process to be more stable and to significantly improve the detection rate. The obtained result shows that the proposed joint loss can better capture the salient features in order to improve the detection accuracy. In order to verify the effectiveness and robustness of the proposed method, experimental studies have been carried out for inner debond defects on both regular and irregular shaped carbon fiber reinforced polymer/plastic (CFRP) specimens. A comparison experiment has been undertaken to study the proposed method with other current state-of-the-art deep semantic segmentation algorithms. The promising results have been obtained where the performance of the proposed method can achieve end-to-end detection of defects.

A contour self-compensated network for salient object detection

Given that existing salient object detection methods cannot effectively predict the fine contours of salient objects when extracting local or global contexts and features, we propose a novel contour self-compensated network (CSCNet) to generate a more accurate saliency map with complete contour. Unlike the common binary saliency detection, we reconstruct the salient object detection problem into a multi-classification problem of the background, the salient object, and the salient contour, where the salient contour is used as the third label for ground truth. Meanwhile, the image and its superpixel map are concatenated as the input of our network to add more edge information. Also, a penalty loss is proposed to restrict the spatial relationship between the background, objects, and their contours. Experimentally, we evaluate the proposed CSCNet on six benchmark datasets in both accuracy and efficiency and evaluate the attribute-based performance on the SOC dataset. Compared with 13 state-of-the-art algorithms, our CSCNet can detect salient objects more accurately and completely without adding too many convolutional layers and parameters.

A risk-based fuzzy boundary interval two-stage stochastic water resources management programming approach under uncertainty

Establishing an optimal water allocation scheme is a challenging yet crucial task for effective risk management of water resources. The dynamic and complex interaction among various risk-related components in a water resources management system cannot be easily modeled to characterize the system response under different risk control settings. In this study, a risk-based fuzzy boundary interval two-stage stochastic water resources management programming (RFITSWMP) model is developed for the optimization of water consumption. This model incorporates a series of risk control constraints, such as water availability, maximum allowable penalty, and allowable benefit violation constraints into a fuzzy boundary interval two-stage stochastic programming framework for water resources management. It can address the uncertainties presented as fuzzy boundary intervals and probability distributions. It can also tackle the recourse action to minimize penalties based on interactive influences of different risk control measures, further generating optimal water allocation alternatives and guiding water resources management. This developed model is applied to a case study of water consumption optimization in the middle reaches of the Heihe River Basin in China. Feasible water allocation schemes under given risk levels, as well as the associated economic benefit, actual benefit and penalty loss are generated. The results can help decision makers to gain an insight into the inherent conflicts and tradeoffs amid risk, benefit and water allocation. The performance of developed model is further demonstrated by comparing it with a fuzzy boundary interval two stage stochastic water resources management programming (FITSWMP) model. In addition, a multiple factorial analysis (MFA) approach is employed to analyze the impacts of interactive risk parameters on the optimal decisions. The result disclosed that (1) the higher individual risk-parameter levels correspond to higher water shortage, penalty loss and benefit value-at-risk but higher economic benefit. (2) The combination of risk parameters can achieve robust water allocation and economic benefit as the constraints concerned with risk parameters affect and limited by each other. (3) The condition that water violated probability (p) is 0.2, penalty violated risk level (β) is 1 and benefit violated risk level (γ) is 1 has the highest water allocation and biggest economic benefit.

Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT.

The accurate identification of malignant lung nodules on chest CT is critical for the early detection of lung cancer, which also offers patients the best chance of cure. Deep learning methods have recently been successfully introduced to computer vision problems, although substantial challenges remain in the detection of malignant nodules due to the lack of large training data sets. In this paper, we propose a multi-view knowledge-based collaborative (MV-KBC) deep model to separate malignant from benign nodules using limited chest CT data. Our model learns 3-D lung nodule characteristics by decomposing a 3-D nodule into nine fixed views. For each view, we construct a knowledge-based collaborative (KBC) submodel, where three types of image patches are designed to fine-tune three pre-trained ResNet-50 networks that characterize the nodules' overall appearance, voxel, and shape heterogeneity, respectively. We jointly use the nine KBC submodels to classify lung nodules with an adaptive weighting scheme learned during the error back propagation, which enables the MV-KBC model to be trained in an end-to-end manner. The penalty loss function is used for better reduction of the false negative rate with a minimal effect on the overall performance of the MV-KBC model. We tested our method on the benchmark LIDC-IDRI data set and compared it to the five state-of-the-art classification approaches. Our results show that the MV-KBC model achieved an accuracy of 91.60% for lung nodule classification with an AUC of 95.70%. These results are markedly superior to the state-of-the-art approaches.