Accuracy Performance Degradation in Image Classification Models due to Concept Drift

Deep learning networks were employed to predict the maximum differential deflection of stiffened and waffle rafts due to reactive soil movements, Δmax. Four deep learning networks were used to predict Δmax, these are (1) stiffened rafts on shrinking soil, (2) stiffened rafts on swelling soil, (3) waffle rafts on shrinking soil, and (4) waffle rafts on swelling soil. The deep learning models were used to create design lines, which showed that both soil and structural features strongly influence the stiffened rafts. In contrast, waffle rafts showed a strong dependence on soil features in shrinking soils and beam depth in swelling soils. This demonstrates that the finite element-based deep learning networks captured the effect of the embedment of the beams. The results of the deep learning models led to non-linear design curves, which are disparate from the suggested standard Australian design. These results suggest that increasing the value of beam depth can have a positive or negative impact on the global residential slab depending on the type of substructure and whether the founding reactive soil is shrinking or swelling. Global sensitivity analyses of the deep learning models showed that for stiffened rafts on shrinking soil, the slab length, slab width and active depth zone of reactive soil had the most significant influence on Δmax, whilst for stiffened rafts on swelling soil, the primary drivers are ground movement, beam depth, and slab width. The prediction of Δmax for waffle rafts on shrinking soil was driven by the surface characteristic and mound movements, and the active depth zone, whilst waffle rafts on swelling soil was driven by the beam depth. Overall, the finite element-based deep learning showed the capacity to estimate Δmax in both shrinking and swelling design scenarios for different types of residential footing systems to further understand the characteristic behaviour of shallow residential slab foundations on reactive soils leading to improved designs.

BackgroundTo determine if mammographic features from deep learning networks can be applied in breast cancer to identify groups at interval invasive cancer risk due to masking beyond using traditional breast density measures.MethodsFull-field digital screening mammograms acquired in our clinics between 2006 and 2015 were reviewed. Transfer learning of a deep learning network with weights initialized from ImageNet was performed to classify mammograms that were followed by an invasive interval or screen-detected cancer within 12 months of the mammogram. Hyperparameter optimization was performed and the network was visualized through saliency maps. Prediction loss and accuracy were calculated using this deep learning network. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were generated with the outcome of interval cancer using the deep learning network and compared to predictions from conditional logistic regression with errors quantified through contingency tables.ResultsPre-cancer mammograms of 182 interval and 173 screen-detected cancers were split into training/test cases at an 80/20 ratio. Using Breast Imaging-Reporting and Data System (BI-RADS) density alone, the ability to correctly classify interval cancers was moderate (AUC = 0.65). The optimized deep learning model achieved an AUC of 0.82. Contingency table analysis showed the network was correctly classifying 75.2% of the mammograms and that incorrect classifications were slightly more common for the interval cancer mammograms. Saliency maps of each cancer case found that local information could highly drive classification of cases more than global image information.ConclusionsPre-cancerous mammograms contain imaging information beyond breast density that can be identified with deep learning networks to predict the probability of breast cancer detection.

Detecting subtle signals from small earthquakes triggered by transient stresses from the surface waves of large magnitude earthquakes can contribute to a more general understanding of how earthquakes nucleate and interact with each other. However, searching for signals from such small earthquakes in thousands of seismograms is overwhelming, and discriminating them from a miscellany of noise is challenging. Here, we explore how we can automate the detection of such dynamically triggered earthquakes using a simple, diagnostic signal-to-noise ratio (SNR) threshold as well as a convolutional deep metric learning network. Our analysis shows that the deep learning network was more reliable at detecting small earthquakes than the SNR method.

Convolutional neural network with transfer learning approach for detection of unfavorable driving state using phase coherence image

SummarySoftware Defined‐DCN (SD‐DCN) is a layered topology with logically centralized control which provides intelligence thro‐ugh programmability. The controller in SD‐DCN provides different network management skills by decoupling of control plane and data plane. However, the controller applies traditional artificial intelligence approaches and neural network approaches for routing strategies in recent systems. To manage dynamic changes in the network, deep learning approaches provide deep analysis and prediction to enhance the existing network performance. In convolutional neural network (CNN) deep learning model, the learning process executes based on present traffic data and forgets the inputs for the future learning phase. To overcome CNN limitation, in this article, different recurrent neural network (RNN) deep learning models are used to improve the routing computation for SD‐DCN topology. The long short‐term memory (LSTM)‐ RNN and bi‐directional long short‐term memory (BiLSTM)‐RNN deep learning models provide forget gate to analyze periodic network traffic datasets and improve routing by delivering dynamic and intelligent routing paths in the network. The proposed system is implemented in a simulation scenario, and the proposed work improves the network performance in hot‐spot traffic as compared to the existing mechanisms. Moreover, error analysis of different deep learning models is presented in the evaluation results.

Raman spectroscopy has attracted much attention due to its wide applications in drug detection and many other fields. However, Raman spectra often contain background noise, which poses significant challenges for subsequent analysis and processing. Although various methods for removing background noise have been proposed and have improved analysis accuracy to some extent, these mathematical model-based methods often rely on parameter adjustments based on spectral data to achieve the desired de-noising effect. The introduction of deep learning technology has provided new ideas to solve this problem, breaking through the limitations of traditional methods in parameter dependency. Different deep learning structures exhibit unique advantages when processing different types of data. In this study, we propose a static dropout triangular deep convolutional network (SD-TDCN). This deep learning network can maintain superior performance while significantly reducing the size of model parameters by statically discarding some convolutional blocks in the deep learning network. In addition, this deep learning network also lays an experimental foundation for the subsequent development of deep learning structures with adaptive dropout mechanisms.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Image segmentation is the process of delineating the regions occupied by objects of interest in a given image. This operation is a fundamentally required first step in numerous applications of medical imagery. In the medical imaging field, this activity has a rich literature that spans over 45 years. In spite of numerous advances, including deep learning (DL) networks (DLNs) in recent years, the problem has defied a robust, fail-safe, and satisfactory solution, especially for objects that are manifest with low contrast, are spatially sparse, have variable shape among individuals, or are affected by imaging artifacts, pathology, or post-treatment change in the body. Although image processing techniques, notably DLNs, are uncanny in their ability to harness low-level intensity pattern information on objects, they fall short in the high-level task of identifying and localizing an entire object as a gestalt. This dilemma has been a fundamental unmet challenge in medical image segmentation. In this paper, we demonstrate that by synergistically marrying the unmatched strengths of high-level human knowledge (i.e., natural intelligence (NI)) with the capabilities of DL networks (i.e., artificial intelligence (AI)) in garnering intricate details, these challenges can be significantly overcome. Focusing on the object recognition task, we formulate an anatomy-guided DL object recognition approach named Automatic Anatomy Recognition-Deep Learning (AAR-DL) which combines an advanced anatomy-modeling strategy, model-based non-DL object recognition, and DL object detection networks to achieve expert human-like performance.

In order to study the deep learning model of urban planning image data processing and health intelligent system, based on existing remote sensing image change detection methods, the author introduces and proposes the use of deep belief networks in deep learning to classify high-resolution remote sensing images and analyze urban expansion change detection. Compared with traditional methods, deep learning has the highest overall accuracy and Kappa coefficient. Deep learning has the highest producer accuracy and relatively low misjudgment rate, making it the most suitable for studying the trend of urban built-up areas. By calculating the information entropy of the image to predict the number of hidden layer nodes, the time for deep learning is greatly reduced. Under the same experimental conditions, the training time for each image can be shortened by 12 525 seconds has improved classification efficiency and made a significant contribution to research on urban expansion applications. Finally, the improved deep belief network was applied to classify and detect changes in the three phase remote sensing images of Beijing, and the urban expansion trend and characteristics of Beijing were analyzed. Provide technical reference and inspiration for urban planning and land use protection.

The recent ground-breaking advances in deep learning networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the computation into the cloud is often infeasible due to privacy concerns, high latency, or the lack of connectivity. As such, there is a critical need to find a way to effectively execute the DNN models locally on the devices. This paper presents an adaptive scheme to determine which DNN model to use for a given input, by considering the desired accuracy and inference time. Our approach employs machine learning to develop a predictive model to quickly select a pre-trained DNN to use for a given input and the optimization constraint. We achieve this by first training off-line a predictive model, and then use the learnt model to select a DNN model to use for new, unseen inputs. We apply our approach to the image classification task and evaluate it on a Jetson TX2 embedded deep learning platform using the ImageNet ILSVRC 2012 validation dataset. We consider a range of influential DNN models. Experimental results show that our approach achieves a 7.52% improvement in inference accuracy, and a 1.8x reduction in inference time over the most-capable single DNN model.

Rapid progress and widespread outbreak of COVID-19 have caused devastating influence on the health systems all around the world. The importance of countermeasures to tackle this problem lead to widespread use of Computer Aided Diagnosis (CADs) applications using deep neural networks. The unprecedented success of machine learning techniques, especially deep learning networks in medical images, have led to their recent prominence in improving efficient diagnosis of COVID-19 with increased detection accuracy. However, recent studies in the field of security of AI-based systems revealed that these deep learning models are vulnerable to adversarial attacks. Adversarial examples generated by attack algorithms are not recognizable by the human eye and can easily deceive the state-of-the-art deep learning models, therefore they threaten security-critical learning applications. In this paper, the methodology, results and concerns of recent works on robustness of AI based COVID-19 systems are summarized and discussed. We explore important security concerns related to deep neural networks and review current state-of-the-art defense methods to prevent performance degradation.

Technical note: Impact of tissue section thickness on accuracy of cell classification with a deep learning network.

Deep Learning (DL) modeling has been a recent topic of interest. With the accelerating need to embed Deep Learning Networks (DLNs) to the Internet of Things (IoT) applications, many DL optimization techniques were developed to enable applying DL to IoTs. However, despite the plethora of DL optimization techniques, there is always a trade-off between accuracy, latency, and cost. Moreover, there are no specific criteria for selecting the best optimization model for a specific scenario. Therefore, this research aims at providing a DL optimization model that eases the selection and re-using DLNs on IoTs. In addition, the research presents an initial design for a DL optimization model management framework. This framework would help organizations choose the optimal DL optimization model that maximizes performance without sacrificing quality. The research would add to the IS design science knowledge as well as the industry by providing insights to many IT managers to apply DLNs to IoTs such as machines and robots.

Chronic liver disease (CLD) is currently one of the major causes of death worldwide. If not treated, it may lead to cirrhosis, hepatic carcinoma and death. Ultrasound (US) shear wave elastography (SWE) is a relatively new, popular, non-invasive technique among radiologists. Although many studies have been published validating the SWE technique either in a clinical setting, or by applying machine learning on SWE elastograms, minimal work has been done on comparing the performance of popular pre-trained deep learning networks on CLD assessment. Currently available literature reports suggest technical advancements on specific deep learning structures, with specific inputs and usually on a limited CLD fibrosis stage class group, with limited comparison on competitive deep learning schemes fed with different input types. The aim of the present study is to compare some popular deep learning pre-trained networks using temporally stable and full elastograms, with or without augmentation as well as propose suitable deep learning schemes for CLD diagnosis and progress assessment. 200 liver biopsy validated patients with CLD, underwent US SWE examination. Four images from the same liver area were saved to extract elastograms and processed to exclude areas that were temporally unstable. Then, full and temporally stable masked elastograms for each patient were separately fed into GoogLeNet, AlexNet, VGG16, ResNet50 and DenseNet201 with and without augmentation. The networks were tested for differentiation of CLD stages in seven classification schemes over 30 repetitions using liver biopsy as the reference. All networks achieved maximum mean accuracies ranging from 87.2%–97.4% and area under the receiver operating characteristic curves (AUCs) ranging from 0.979–0.990 while the radiologists had AUCs ranging from 0.800–0.870. ResNet50 and DenseNet201 had better average performance than the other networks. The use of the temporal stability mask led to improved performance on about 50% of inputs and network combinations while augmentation led to lower performance for all networks. These findings can provide potential networks with higher accuracy and better setting in the CLD diagnosis and progress assessment. A larger data set would help identify the best network and settings for CLD assessment in clinical practice.

MP43-02 LESSONS LEARNED IN APPLYING DEEP LEARNING TO FACILITATE PROSTATE MR-US FUSION BIOPSY WORKFLOW