Search

Background: Breast MRI has been recommended as supplemental screening tool to mammography and breast ultrasound of breast cancer by international guidelines, but its long examination time and use of contrast material remains concerning., Purpose: To develop an unenhanced radiomics model with using non-gadolinium based sequences for detecting breast cancer based on T2-weighted (T2W) and diffusion-weighted (DW) MRI., Study Type: Retrospective analysis followed by retrospective and prospective cohorts study., Population: 1760 patients: Of these, 1293 for model construction (n = 775 for training and 518 for validation). The remaining patients for model testing in internal retrospective (n = 167), internal prospective (n = 188), and external retrospective (n = 112) cohorts., Field Strength/sequence: 3.0T MR scanners from two institution. T2WI, DWI, and first contrast-enhanced T1-weighted sequence., Assessment: AUCs in distinguishing breast cancer were compared between combined model with gadolinium agent sequence and unenhanced model. Subsequently, the AUCs in testing cohorts of unenhanced model was compared with two radiologists' diagnosis for this research. Finally, patient subgroup analysis in testing cohorts was performed based on clinical subgroups and different types of malignancies., Statistical Tests: Mann-Whitney U test, Kruskal-Wallis H test, chi-square test, weighted kappa test, and DeLong's test., Results: The unenhanced radiomics model performed best under Gaussian process (GP) classifiers (AUC: training, 0.893; validation, 0.848) compared to support vector machine (SVM) and logistic, showing favorable prediction in testing cohorts (AUCs, 0.818-0.840). The AUCs for the unenhanced radiomics model were not statistically different in five cohorts from those of the combined radiomics model (P, 0.317-0.816), as well as the two radiologists (P, 0.181-0.918). The unenhanced radiomics model was least successful in identifying ductal carcinoma in situ, whereas did not show statistical significance in other subgroups., Data Conclusion: An unenhanced radiomics model based on T2WI and DWI has comparable diagnostic accuracy to the combined model using the gadolinium agent., Level of Evidence: 4 TECHNICAL EFFICACY: Stage 2., (© 2023 International Society for Magnetic Resonance in Medicine.)

Based on a study of the spatial distribution of coffee shops in the main urban area of Beijing, the main influencing factors were selected based on the multi-source space data. Subsequently, three regression models were compared, and the best site selection model was found. A comparison was performed between the prediction model functioning with a buffer and without one, and the accuracy of the location model was verified by comparing the actual change trend and the predicted trend in two years. The following conclusions were obtained: (1) coffee shops in the main urban area of Beijing are clustered in an area within 12 km of the main urban center, and also around the core commercial agglomeration area; (2) the random forest (RF) model is the best model in this study, and the accuracy values before and after buffer analysis were 0.915 and 0.929, respectively; and (3) after verifying the accuracy of the model through two years of data, we recommend the establishment of a main road buffer zone for site selection, and the success rate of site selection was found to reach 72.97%. This study provides crucial insight for coffee shop prediction model selection and potential store location selection, which is significant to improving the layout of leisure spaces and promoting economic development. [ABSTRACT FROM AUTHOR]

Incremental learning is one of the most important abilities of human beings. In the age of artificial intelligence, it is the key task to make neural network models as powerful as human beings, to achieve the ability to continuously acquire, fine-tune, and accumulate knowledge while simultaneously avoid catastrophic forgetting. In recent years, by virtue of deep neural networks, incremental learning has been attracting a great deal of attention in the field of computer vision. In this paper, we systematically review the current development of incremental learning and give the overall taxonomy of the incremental learning methods. Specifically, three kinds of mainstream methods, i.e., parameter regularization-based approaches, knowledge distillation-based approaches, and dynamic architecture-based approaches, are surveyed, summarized, and discussed in detail. Furthermore, we comprehensively analyze the performance of data-permuted incremental learning, class-incremental learning, and multi-modal incremental learning on widely used datasets, covering a broad of incremental learning scenarios for image classification and semantic segmentation. Lastly, we point out some possible research directions and inspiring suggestions for incremental learning in the field of computer vision. [ABSTRACT FROM AUTHOR]

Since automobile engine fault is the main factor leading to a vehicle breaking down, engine fault diagnosis has captured a lot of attention. Fault diagnosis identifies fault types to facilitate maintenance. However, the method of the warning before the fault occurs is more attractive to users and is more challenging. Therefore, this study would like to explore the feasibility of implementing automobile engine fault early warning based on the fault diagnosis model. First, the theoretical method of a fault domain is established, and the state of the engine is regarded as a point in n-dimensional space. The normal or fault of the engine will correspond to different state domains in this space. Second, to diagnose multiple fault types at the same time, an ensemble model based on multiple machine learning methods is established. The probability outputs by the ensemble model measure the distance between the point and each fault domain in the space. Finally, considering the temporal factor, an early warning threshold is established based on the probability, and a fault warning model is established by using the dual probability structure. Comparative experiments show that the proposed method can greatly reduce the calculation time based on ensuring the accuracy of early warning and is suitable for real-time early warning of multiple faults. [ABSTRACT FROM AUTHOR]

The Hengduan Mountains Region (HMR) is one of the areas that experience the most frequent geological hazards in China. However, few reports are available that address the geological hazard susceptibility of the region. This study developed six machine learning models to assess the geological hazard susceptibility. The results show that areas with medium and high susceptibility to geological hazards as a whole account for almost 21% of the total area, while both are 18% when it comes to the single hazard of landslide and rockfall respectively. Medium and high geological hazard susceptibility is found in three parts of the HMR with different characteristics: (1) the central and southern parts, where the population of the region concentrates; (2) the northern part, where higher geological hazard susceptibility is found along the mountain ranges; and (3) the junction of Tibet, Yunnan, and Sichuan in the eastern part, which is prone to larger-scale geological hazards. Of all the potential influencing factors, topographic features and climatic variables act as the major driving factors behind geological hazards and elevation, slope, and precipitation are crucial indicators for geological hazard susceptibility assessment. This study developed the geological hazard susceptibility maps of the HMR and provided information for the multi-hazard risk assessment and management of the region. [ABSTRACT FROM AUTHOR]

[Display omitted] • Infrared technology enables non-invasive temperature measurement. • Existing literature related to personal thermal comfort using infrared technology was reviewed. • Measurement equipment, experimental conditions, subject's information, and analytical methods were analyzed. • Accurate predictions should be translated into control commands for the equipment at different scales. • Diverse application scenarios including car cabin, sleep, and outdoor environments were discussed. Personal thermal comfort studies are crucial for balancing both human comfort and building energy savings. Thus, personal comfort models (PCMs) are expected to play a pivotal role in the development of smart buildings. Infrared technology has received significant attention from researchers because of its non-intrusive nature for collecting personal data. This systematic review examined 36 personal thermal comfort studies that employed infrared technology over the past decade. The review analyzed the (1) infrared devices, (2) experimental designs, (3) subjects, and (4) analysis methods and results. The review found that most studies were experimental and focused on exploring feasibility at a theoretical level, while the number of practical application studies was limited. The accuracy of infrared devices was identified as a primary concern for researchers, and some studies proposed methods to mitigate measurement errors. Most studies included young subjects and examined single clothing insulation and metabolic rates, limiting the generalizability of the corresponding PCMs, which were mainly constructed using machine learning. To facilitate data sharing and comparison of results and to overcome the limitations in terms of applicable populations and application scenarios, the review suggests that standardized data collection and processing should be used in future studies. Furthermore, the paper proposes the integration of PCMs and personal comfort systems, which are two hotspots in personal thermal comfort research, to achieve cooperative applications. Finally, the study discusses the future applications of infrared technology in scenarios such as vehicle cabins, sleep areas, and outdoor environments, considering their unique characteristics. [ABSTRACT FROM AUTHOR]

The receiver operating characteristic (ROC) and detection error tradeoff (DET) curves have been widely used in the machine learning community to analyze the performance of classifiers. The area (or volume) under the convex hull has been used as a scalar indicator for the performance of a set of classifiers in ROC and DET space. Recently, 3D convex-hull-based evolutionary multiobjective optimization algorithm (3DCH-EMOA) has been proposed to maximize the volume of convex hull for binary classification combined with parsimony and three-way classification problems. However, 3DCH-EMOA revealed high consumption of computational resources due to redundant convex hull calculations and a frequent execution of nondominated sorting. In this paper, we introduce incremental convex hull calculation and a fast replacement for non-dominated sorting. While achieving the same high quality results, the computational effort of 3DCH-EMOA can be reduced by orders of magnitude. The average time complexity of 3DCH-EMOA in each generation is reduced from O ( n 2 log n ) to O ( n log n ) per iteration, where n is the population size. Six test function problems are used to test the performance of the newly proposed method, and the algorithms are compared to several state-of-the-art algorithms, including NSGA-III, RVEA, etc., which were not compared to 3DCH-EMOA before. Experimental results show that the new version of the algorithm (3DFCH-EMOA) can speed up 3DCH-EMOA for about 30 times for a typical population size of 300 without reducing the performance of the method. Besides, the proposed algorithm is applied for neural networks pruning, and several UCI datasets are used to test the performance. [ABSTRACT FROM AUTHOR]

Recently, very high resolution (VHR) panchromatic and multispectral (MS) remote-sensing images can be acquired easily. However, it is still a challenging task to fuse and classify these VHR images. Generally, there are two ways for the fusion and classification of panchromatic and MS images. One way is to use a panchromatic image to sharpen an MS image, and then classify a pan-sharpened MS image. Another way is to extract features from panchromatic and MS images, respectively, and then combine these features for classification. In this paper, we propose a superpixel-based multiple local convolution neural network (SML-CNN) model for panchromatic and MS images classification. In order to reduce the amount of input data for the CNN, we extend simple linear iterative clustering algorithm for segmenting MS images and generating superpixels. Superpixels are taken as the basic analysis unit instead of pixels. To make full advantage of the spatial-spectral and environment information of superpixels, a superpixel-based multiple local regions joint representation method is proposed. Then, an SML-CNN model is established to extract an efficient joint feature representation. A softmax layer is used to classify these features learned by multiple local CNN into different categories. Finally, in order to eliminate the adverse effects on the classification results within and between superpixels, we propose a multi-information modification strategy that combines the detailed information and semantic information to improve the classification performance. Experiments on the classification of Vancouver and Xi’an panchromatic and MS image data sets have demonstrated the effectiveness of the proposed approach. [ABSTRACT FROM PUBLISHER]

Classifier performance optimization in machine learning can be stated as a multi-objective optimization problem. In this context, recent works have shown the utility of simple evolutionary multi-objective algorithms (NSGA-II, SPEA2) to conveniently optimize the global performance of different anti-spam filters. The present work extends existing contributions in the spam filtering domain by using three novel indicator-based (SMS-EMOA, CH-EMOA) and decomposition-based (MOEA/D) evolutionary multi-objective algorithms. The proposed approaches are used to optimize the performance of a heterogeneous ensemble of classifiers into two different but complementary scenarios: parsimony maximization and e-mail classification under low confidence level. Experimental results using a publicly available standard corpus allowed us to identify interesting conclusions regarding both the utility of rule-based classification filters and the appropriateness of a three-way classification system in the spam filtering domain. [ABSTRACT FROM AUTHOR]

With the popular use of high-resolution satellite images, remote sensing scene classification has always been a hot research topic in its related areas. However, limited to the issues of remote sensing datasets including the small scale of scene classes, the lack of rich label information and so on, it is quite challenging for deep learning methods to learn powerful feature representation. To overcome this problem, we propose a rotation-invariant feature learning and joint decision-making method based on Siamese convolutional neural networks with the combination of identification and verification models. Firstly, a novel data augmentation strategy is proposed specially for the Siamese model to learning rotation-invariant features. Secondly, a joint decision mechanism is introduced in our method, which is realized by the identification and verification model to better improve the classification performance. The proposed method can not only suppress problems caused by lack of rich label samples but also improve the robustness of Siamese convolutional neural networks. Experimental results demonstrate that the proposed method is effective and efficient for remote sensing scene classification. [ABSTRACT FROM AUTHOR]

It remains one of the most challenging tasks to distinguish different terrain materials from a single SAR image. With the increase of ground resolution, it allows us to model the SAR image directly by exploiting spatial structures and texture information that are extracted by several machine learning approaches. In this paper, a novel feature learning approach is proposed to capture discriminant features of high-resolution SAR images. In the first stage, a weighted discriminant filter bank is learned from some labeled SAR image patches to generate low-level features. Then, the locality constraint is introduced to produce the high-level features in both the encoding and the spatial pooling procedure. In this work, the superpixels are employed as the basic operational units instead of the pixels for terrain classification. With some learned domain patterns which are learned from all of the high-level features of each pixel, the superpixel is characterized by a hyper-feature. In the last stage, a linear-kernel support vector machine is utilized to classify all of these hyper-features which are generated for each superpixel. The experimental results show a better classification performance of the proposed approach than several available state-of-the-art approaches. [ABSTRACT FROM AUTHOR]