ELVISort: Encoding Latent Variables for Instant Sorting, an Artificial Intelligence-Based End-to-End Solution

A comprehensive empirical study on bug characteristics of deep learning frameworks

Deep learning methods have become popular among researchers in the field of fault detection. However, their performance depends on the availability of big datasets. To overcome this problem researchers started applying transfer learning to achieve good performance from small available datasets, by leveraging multiple prediction models over similar machines and working conditions. However, the influence of negative transfer limits their application. Negative transfer among prediction models increases when the environment and working conditions are changing continuously. To overcome the effect of negative transfer, we propose a novel deep transfer learning method, coined deep boosted transfer learning, for wind turbine gearbox fault detection that prevents negative transfer and only focuses on relevant information from the source machine. The proposed method is an instance-based deep transfer learning method that updates the weights of the source and the target machine training samples separately. The weights of different source training samples are gradually decreased to reduce the impact on the final model. The proposed method is verified by the Case Western Reserve University bearing and real field wind farm datasets. The results show that the proposed method ignores negative transfer and achieves higher accuracy compared to standard deep learning and deep transfer learning methods.

Deep learning (DL) frameworks serve as the backbone for a wide range of artificial intelligence applications. However, bugs within DL frameworks can cascade into critical issues in higher-level applications, jeopardizing reliability and security. While numerous techniques have been proposed to detect bugs in DL frameworks, research exploring common API patterns across frameworks and the potential risks they entail remains limited. Notably, many DL frameworks expose similar APIs with overlapping input parameters and functionalities, rendering them vulnerable to shared bugs, where a flaw in one API may extend to analogous APIs in other frameworks. To address this challenge, we propose MirrorFuzz, an automated API fuzzing solution to discover shared bugs in DL frameworks. MirrorFuzz operates in three stages: First, MirrorFuzz collects historical bug data for each API within a DL framework to identify potentially buggy APIs. Second, it matches each buggy API in a specific framework with similar APIs within and across other DL frameworks. Third, it employs large language models (LLMs) to synthesize code for the API under test, leveraging the historical bug data of similar APIs to trigger analogous bugs across APIs. We implement MirrorFuzz and evaluate it on four popular DL frameworks (TensorFlow, PyTorch, OneFlow, and Jittor). Extensive evaluation demonstrates that MirrorFuzz improves code coverage by 39.92% and 98.20% compared to state-of-the-art methods on TensorFlow and PyTorch, respectively. Moreover, MirrorFuzz discovers 315 bugs, 262 of which are newly found, and 80 bugs are fixed, with 52 of these bugs assigned CNVD IDs.

Deep learning has gained huge traction in recent years because of its potential to make informed decisions. A large portion of today’s deep learning systems are based on centralized servers and fall short in providing operational transparency, traceability, reliability, security, and trusted data provenance features. Also, training deep learning models by utilizing centralized data is vulnerable to the single point of failure problem. In this paper, we explore the importance of integrating blockchain technology with deep learning. We review the existing literature focused on the integration of blockchain with deep learning. We classify and categorize the literature by devising a thematic taxonomy based on seven parameters; namely, blockchain type, deep learning models, deep learning specific consensus protocols, application area, services, data types, and deployment goals. We provide insightful discussions on the state-of-the-art blockchain-based deep learning frameworks by highlighting their strengths and weaknesses. Furthermore, we compare the existing blockchain-based deep learning frameworks based on four parameters such as blockchain type, consensus protocol, deep learning method, and dataset. Finally, we present important research challenges which need to be addressed to develop highly trustworthy deep learning frameworks.

Objective: To design a deep transfer learning framework for modeling fluence map predictions for stereotactic body radiation therapy (SBRT) of adrenal cancer and similar sites that usually have a small number of cases. Approach: We developed a transfer learning framework for adrenal SBRT planning that leverages knowledge in a pancreas SBRT planning model. Treatment plans from the two sites had different dose prescriptions and beam settings but both prioritized gastrointestinal sparing. A base framework was first trained with 100 pancreas cases. This framework consists of two convolutional neural networks (CNN), which predict individual beam doses (BD-CNN) and fluence maps (FM-CNN) sequentially for 9-beam intensity-modulated radiation therapy (IMRT) plans. Forty-five adrenal plans were split into training/validation/test sets with the ratio of 20/10/15. The base BD-CNN was re-trained with transfer learning using 5/10/15/20 adrenal training cases to produce multiple candidate adrenal BD-CNN models. The base FM-CNN was directly used for adrenal cases. The deep learning (DL) plans were evaluated by several clinically relevant dosimetric endpoints, producing a percentage score relative to the clinical plans. Main results: Transfer learning significantly reduced the number of training cases and training time needed to train such a DL framework. The adrenal transfer learning model trained with 5/10/15/20 cases achieved validation plan scores of 85.4/91.2/90.7/89.4, suggesting that model performance saturated with 10 training cases. Meanwhile, a model using all 20 adrenal training cases without transfer learning only scored 80.5. For the final test set, the 5/10/15/20-case models achieved scores of 73.5/75.3/78.9/83.3. Significance: It is feasible to use deep transfer learning to train an IMRT fluence prediction framework. This technique could adapt to different dose prescriptions and beam configurations. This framework potentially enables DL modeling for clinical sites that have a limited dataset, either due to few cases or due to rapid technology evolution.

Change detection with heterogeneous remote sensing images (Hete-CD) plays a significant role in practical applications, particularly in cases where homogenous remote sensing images are unavailable. However, directly comparing bitemporal heterogeneous remote sensing images (HRSIs) to measure the change magnitude is unfeasible. Numerous deep learning methods require substantial samples to train the module adequately. Moreover, the process of labeling a large number of samples for land cover change detection using HRSIs is time-consuming and labor-intensive. Consequently, deep learning networks face challenges in achieving satisfactory performance in Hete-CD due to the limited number of training samples. This study proposes a novel deep-learning framework for Hete-CD to achieve satisfactory performance even with a limited number of initial samples. We developed a multiscale network with a selected kernel-attention module. This design allows us to effectively capture different change targets characterized by diverse sizes and shapes. In addition, a simple yet effective non-parameter sample-enhanced algorithm that utilizes the Pearson correlation coefficient is proposed to explore the potential samples surrounding every initial sample. The proposed network and sample-enhanced algorithm are integrated into an iterative framework to improve change detection performance with a limited number of small samples. The experimental results were achieved based on four pairs of real HRSIs, which were acquired with Landsat-5, Radarsat-2, and Sentinel-2 satellites with optical and SAR sensors. Results indicated that the proposed framework could achieve competitive accuracy with a small number of samples compared with some state-of-the-art methods, including three traditional methods and nine state-of-the-art deep learning methods. For example, the improvement rates are approximately 3.38% and 1.99% compared with the selected traditional methods and deep learning methods, respectively.

Less than 10% of patients with cancer have detectable pathogenic germline alterations, which may be partially due to incomplete pathogenic variant detection. To evaluate if deep learning approaches identify more germline pathogenic variants in patients with cancer. A cross-sectional study of a standard germline detection method and a deep learning method in 2 convenience cohorts with prostate cancer and melanoma enrolled in the US and Europe between 2010 and 2017. The final date of clinical data collection was December 2017. Germline variant detection using standard or deep learning methods. The primary outcomes included pathogenic variant detection performance in 118 cancer-predisposition genes estimated as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The secondary outcomes were pathogenic variant detection performance in 59 genes deemed actionable by the American College of Medical Genetics and Genomics (ACMG) and 5197 clinically relevant mendelian genes. True sensitivity and true specificity could not be calculated due to lack of a criterion reference standard, but were estimated as the proportion of true-positive variants and true-negative variants, respectively, identified by each method in a reference variant set that consisted of all variants judged to be valid from either approach. The prostate cancer cohort included 1072 men (mean [SD] age at diagnosis, 63.7 [7.9] years; 857 [79.9%] with European ancestry) and the melanoma cohort included 1295 patients (mean [SD] age at diagnosis, 59.8 [15.6] years; 488 [37.7%] women; 1060 [81.9%] with European ancestry). The deep learning method identified more patients with pathogenic variants in cancer-predisposition genes than the standard method (prostate cancer: 198 vs 182; melanoma: 93 vs 74); sensitivity (prostate cancer: 94.7% vs 87.1% [difference, 7.6%; 95% CI, 2.2% to 13.1%]; melanoma: 74.4% vs 59.2% [difference, 15.2%; 95% CI, 3.7% to 26.7%]), specificity (prostate cancer: 64.0% vs 36.0% [difference, 28.0%; 95% CI, 1.4% to 54.6%]; melanoma: 63.4% vs 36.6% [difference, 26.8%; 95% CI, 17.6% to 35.9%]), PPV (prostate cancer: 95.7% vs 91.9% [difference, 3.8%; 95% CI, -1.0% to 8.4%]; melanoma: 54.4% vs 35.4% [difference, 19.0%; 95% CI, 9.1% to 28.9%]), and NPV (prostate cancer: 59.3% vs 25.0% [difference, 34.3%; 95% CI, 10.9% to 57.6%]; melanoma: 80.8% vs 60.5% [difference, 20.3%; 95% CI, 10.0% to 30.7%]). For the ACMG genes, the sensitivity of the 2 methods was not significantly different in the prostate cancer cohort (94.9% vs 90.6% [difference, 4.3%; 95% CI, -2.3% to 10.9%]), but the deep learning method had a higher sensitivity in the melanoma cohort (71.6% vs 53.7% [difference, 17.9%; 95% CI, 1.82% to 34.0%]). The deep learning method had higher sensitivity in the mendelian genes (prostate cancer: 99.7% vs 95.1% [difference, 4.6%; 95% CI, 3.0% to 6.3%]; melanoma: 91.7% vs 86.2% [difference, 5.5%; 95% CI, 2.2% to 8.8%]). Among a convenience sample of 2 independent cohorts of patients with prostate cancer and melanoma, germline genetic testing using deep learning, compared with the current standard genetic testing method, was associated with higher sensitivity and specificity for detection of pathogenic variants. Further research is needed to understand the relevance of these findings with regard to clinical outcomes.

The clinical utility of regional strain measurements in echocardiography is challenged by suboptimal reproducibility. In this study, we aimed to evaluate the test-retest reproducibility of regional longitudinal strain (RLS) per coronary artery perfusion territory (RLSTerritory) and basal-to-apical level of the left ventricle (RLSLevel), measured by a novel fully automated deep learning (DL) method based on point tracking. We measured strain in a dual-centre test-retest data set that included 40 controls and 40 patients with suspected non-ST elevation acute coronary syndrome. Two consecutive echocardiograms per subject were recorded by different operators. The reproducibility of RLSTerritory and RLSLevel measured by the DL method and by three experienced observers using semi-automatic software (2D Strain, EchoPAC, GE HealthCare) was evaluated as minimal detectable change (MDC). The DL method had MDC for RLSTerritory and RLSLevel ranging from 3.6 to 4.3%, corresponding to a 33-35% improved reproducibility compared with the inter- and intraobserver scenarios (MDC 5.5-6.4% and 4.9-5.4%). Furthermore, the DL method had a lower variance of test-retest differences for both RLSTerritory and RLSLevel compared with inter- and intraobserver scenarios (all P < 0.001). Bland-Altman analyses demonstrated superior reproducibility by the DL method for the whole range of strain values compared with the best observer scenarios. The feasibility of the DL method was 93% and measurement time was only 1 s per echocardiogram. The novel DL method provided fully automated measurements of RLS, with improved test-retest reproducibility compared with semi-automatic measurements by experienced observers. RLS measured by the DL method has the potential to advance patient care through a more detailed, more efficient, and less user-dependent clinical assessment of myocardial function.

Accurate prediction and confirmation of mechanical properties are critical for the reliable design and deployment of sustainable aluminum–agro-waste composites (AWCs). This study presents a confirmatory analytical–experimental–deep machine learning (DML) framework for the identification of true material properties under multi-response conditions. Experimental characterization yielded mean tensile strength of 190.61 MPa, compressive strength of 287.16 MPa, flexural strength of 243.94 MPa, wear rate of 5.46 × 10⁻⁶ mm³ /N·m, coefficient of friction of 0.34, and fatigue life of 5.86 × 10⁵ cycles, with low variability observed in strength-related properties and higher dispersion in tribological and fatigue responses. Isolated analytical predictions produced comparable estimates for tensile (189.60 MPa), compressive (296.42 MPa), flexural (255.75 MPa), and fatigue properties (5.97 × 10⁵ cycles), but failed to reliably capture tribological behavior, yielding a non-physical negative wear rate (− 4.06 mm³/N·m) and an overestimated coefficient of friction (0.45). Consolidated analytical modeling improved agreement for tensile (187.60 MPa), compressive (285.63 MPa), flexural (244.88 MPa), and fatigue life (5.86 × 10⁵ cycles), yet significantly deviated in tribological predictions, producing unrealistically high wear rate (0.20 mm³/N·m) and coefficient of friction (2.84). To resolve these discrepancies, DML models—implemented via a deep convolutional neural network (ID-CNN) and a hybrid residual CNN guided by a residual-based loss function—were employed to reconcile analytical (isolated/consolidated) predictions with experimental data. The DML framework successfully minimized analytical–experimental residuals and confirmed true predictive reliability for compressive strength, flexural strength, coefficient of friction, and fatigue life, while consistently identifying wear rate as falsely predicted across analytical frameworks. These findings establish DML as both a predictive and diagnostic tool, enabling discrimination between truly confirmed and analytically unstable properties. The proposed framework offers a scalable, data-informed pathway for optimized composite design, process refinement, and industrial adoption, with potential extension to multi-scale modeling and real-time process monitoring. Residual-based DML loss quantifies and minimizes analytical–experimental prediction errors. • Residual-based DML loss quantifies and minimizes analytical–experimental prediction errors. • Integrated analytical–DML modeling confirms strength, fatigue, and friction properties. • Bulk properties converge, while wear rate shows persistent tribological uncertainty. • The framework supports reliable certification and sustainable composite design.

This review paper examines the current state of lung disease diagnosis based on deep learning (DL) methods. Lung diseases, such as Pneumonia, TB, Covid-19, and lung cancer, are significant causes of morbidity and mortality worldwide. Accurate and timely diagnosis of these diseases is essential for effective treatment and improved patient outcomes. DL methods, which utilize artificial neural networks to extract features from medical images automatically, have shown great promise in improving the accuracy and efficiency of lung disease diagnosis. This review discusses the various DL methods that have been developed for lung disease diagnosis, including convolutional neural networks (CNNs), deep neural networks (DNNs), and generative adversarial networks (GANs). The advantages and limitations of each method are discussed, along with the types of medical imaging techniques used, such as X-ray and computed tomography (CT). In addition, the review discusses the most commonly used performance metrics for evaluating the performance of DL for lung disease diagnosis: the area under the curve (AUC), sensitivity, specificity, F1-score, accuracy, precision, and the receiver operator characteristic curve (ROC). Moreover, the challenges and limitations of using DL for lung disease diagnosis, including the limited availability of annotated data, the variability in imaging techniques and disease presentation, and the interpretability and generalizability of DL models, are highlighted in this paper. Furthermore, strategies to overcome these challenges, such as transfer learning, data augmentation, and explainable AI, are also discussed. The review concludes with a call for further research to address the remaining challenges and realize DL's full potential for improving lung disease diagnosis and treatment.

Among the broad assortment of Machine Learning approaches, deep learning has recently attracted attention particularly in the domain of user behavior analysis. The notion to study user behavior from the unstructured tweets shared on social media is an interesting yet challenging task. A social platform such as Twitter yield access to the unprompted views of the wide-ranging users on particular events like election. These views cater government and corporates to remold strategies, assess the areas where better measures need to be put forward and monitor common opinion. With the advent of the general election in India (largest democracy) people tend to articulate their views or issues. Tweets related to general elections 2019 of India is used as data corpus for the study. Multi-class classification fabricated with novel deep learning approach is implemented to analyses the user opinion. Here, we have used nine different classes, which is representing larger issues in the nation for election agenda. Moreover, comparative analysis between tradition approaches such as Naive Bayes, SVM, decision tree, logistic regression and employed approach with deep learning method is presented. Experimental results revels that the proposed model can reach up to 98.70% accuracy on multiclass based prediction in machine learning. The results assist the government and businesses to know about grave issue offering a shot to revise strategic policy and make welfare scheme program.

Detection of moisture content in salted sea cucumbers by hyperspectral and low field nuclear magnetic resonance based on deep learning network framework

Developers of deep learning applications (shortened as application developers) commonly use deep learning frameworks in their projects. However, due to time pressure, market competition, and cost reduction, developers of deep learning frameworks (shortened as framework developers) often have to sacrifice software quality to satisfy a shorter completion time. This practice leads to technical debt in deep learning frameworks, which results in the increasing burden to both the application developers and the framework developers in future development.In this paper, we analyze the comments indicating technical debt (self-admitted technical debt) in 7 of the most popular open-source deep learning frameworks. Although framework developers are aware of such technical debt, typically the application developers are not. We find that: 1) there is a significant number of technical debt in all the studied deep learning frameworks. 2) there is design debt, defect debt, documentation debt, test debt, requirement debt, compatibility debt, and algorithm debt in deep learning frameworks. 3) the majority of the technical debt in deep learning framework is design debt (24.07% - 65.27%), followed by requirement debt (7.09% - 31.48%) and algorithm debt (5.62% - 20.67%). In some projects, compatibility debt accounts for more than 10%. These findings illustrate that technical debt is common in deep learning frameworks, and many types of technical debt also impact the deep learning applications. Based on our findings, we highlight future research directions and provide recommendations for practitioners.

Automatic assessment of pain based on deep learning methods: A systematic review

Simple SummaryPapillary thyroid carcinoma is the most common type of thyroid cancer and could be cured if diagnosed and treated early. In clinical practice, the primary method for determining diagnosis of papillary thyroid carcinoma is manual visual inspection of cytopathology slides, which is difficult, time consuming and subjective with a high inter-observer variability and sometimes causes suboptimal patient management due to false-positive and false-negative results. This study presents a fast, fully automatic and efficient deep learning framework for fast screening of cytological slides for thyroid cancer diagnosis. We confirmed the robustness and effectiveness of the proposed method based on evaluation results from two different types of slides: thyroid fine needle aspiration smears and ThinPrep slides.Thyroid cancer is the most common cancer in the endocrine system, and papillary thyroid carcinoma (PTC) is the most prevalent type of thyroid cancer, accounting for 70 to 80% of all thyroid cancer cases. In clinical practice, visual inspection of cytopathological slides is an essential initial method used by the pathologist to diagnose PTC. Manual visual assessment of the whole slide images is difficult, time consuming, and subjective, with a high inter-observer variability, which can sometimes lead to suboptimal patient management due to false-positive and false-negative. In this study, we present a fully automatic, efficient, and fast deep learning framework for fast screening of papanicolaou-stained thyroid fine needle aspiration (FNA) and ThinPrep (TP) cytological slides. To the authors’ best of knowledge, this work is the first study to build an automated deep learning framework for identification of PTC from both FNA and TP slides. The proposed deep learning framework is evaluated on a dataset of 131 WSIs, and the results show that the proposed method achieves an accuracy of 99%, precision of 85%, recall of 94% and F1-score of 87% in segmentation of PTC in FNA slides and an accuracy of 99%, precision of 97%, recall of 98%, F1-score of 98%, and Jaccard-Index of 96% in TP slides. In addition, the proposed method significantly outperforms the two state-of-the-art deep learning methods, i.e., U-Net and SegNet, in terms of accuracy, recall, F1-score, and Jaccard-Index (). Furthermore, for run-time analysis, the proposed fast screening method takes 0.4 min to process a WSI and is 7.8 times faster than U-Net and 9.1 times faster than SegNet, respectively.