Stock forecasting has historically been a popular and lucrative field of study. It has been demonstrated that machine learning applications improve accuracy and return in the area of finance forecasting and prediction. This study chose data from the Yahoo Finance database that represented Apple's (AAPL) close price for research. This study categorized articles using a series of machine learning models, encompassing Linear Regression, Random Forest and so on. This paper also examines each article's dataset, variable, model, and findings. The survey in use showcases the findings using the most popular performance metrics. Recent models that combine LSTM with other techniques, For instance, RF has received a lot of study. Deep learning techniques like reinforcement learning and others produced excellent results. In conclusion, the use of deep learning-based techniques for financial modeling has become growing in popularity over the past few years.
Gestures from traffic police give the authorized information, especially in some urgent situation. Thus, understanding of traffic police instruction accurately and promptly is particularly crucial for the automated driving system. However, this task is a great challenge not only because of the dynamic and diversity characteristics of the human gesture, but also the high requirement for real-time performance in each frame. We propose an online activity recognition method based on pose estimation and Graph Convolutional Networks (GCN) to recognize the traffic police gesture in frame level. The main contribution in this work is the development of an online framework based on graph convolutional networks for traffic police recognition. Our approach obtained the state-of-the-art results on Traffic Police Gesture Recognition (TPGR) dataset.
Abstract Terahertz imaging technology has great potential applications in areas, such as remote sensing, navigation, security checks, and so on. However, terahertz images usually have the problems of heavy noises and low resolution. Previous terahertz image denoising methods are mainly based on traditional image processing methods, which have limited denoising effects on the terahertz noise. Existing deep learning‐based image denoising methods are mostly used in natural images and easily cause a large amount of detail loss when denoising terahertz images. Here, a residual‐learning‐based multiscale hybrid‐convolution residual network (MHRNet) is proposed for terahertz image denoising, which can remove noises while preserving detail features in terahertz images. Specifically, a multiscale hybrid‐convolution residual block (MHRB) is designed to extract rich detail features and local prediction residual noise from terahertz images. Specifically, MHRB is a residual structure composed of a multiscale dilated convolution block, a bottleneck layer, and a multiscale convolution block. MHRNet uses the MHRB and global residual learning to achieve terahertz image denoising. Ablation studies are performed to validate the effectiveness of MHRB. A series of experiments are conducted on the public terahertz image datasets. The experimental results demonstrate that MHRNet has an excellent denoising effect on synthetic and real noisy terahertz images. Compared with existing methods, MHRNet achieves comprehensive competitive results.
Triple-negative breast cancer (TNBC) is a subtype of breast cancer known for its high aggressiveness and poor prognosis. Conventional treatment of TNBC is challenging due to its heterogeneity and lack of clear targets. Recent advancements in immunotherapy have shown promise in treating TNBC, with immune checkpoint therapy playing a significant role in comprehensive treatment plans. The tumor microenvironment (TME), comprising immune cells, stromal cells, and various cytokines, plays a crucial role in TNBC progression and response to immunotherapy. The high presence of tumor-infiltrating lymphocytes and immune checkpoint proteins in TNBC indicates the potential of immunotherapeutic strategies. However, the complexity of the TME, while offering therapeutic targets, requires further exploration of its multiple roles in immunotherapy. In this review, we discuss the interaction mechanism between TME and TNBC immunotherapy based on the characteristics and composition of TME, and elaborate on and analyze the effect of TME on immunotherapy, the potential of TME as an immune target, and the ability of TME as a biomarker. Understanding these dynamics will offer new insights for enhancing therapeutic approaches and investigating stratification and prognostic markers for TNBC patients.
Finger vein image quality assessment is used to evaluate the quality of images, namely to evaluate the applicability of the finger vein images to the recognition system. The work of quality assessment will largely affects the performance of the finger vein recognition system. In previous work, people usually design quality indicators manually, construct quality functions or perform supervised learning based on visual inspection, which has limitations of subjectivity. In order to solve these problems, this paper proposes a finger vein image quality assessment algorithm based on Stochastic Embedding Robustness (SER), which is called SER algorithm in this paper. The algorithm generates random subnetworks from the deployed finger vein recognition system, and indirectly evaluates the image quality by calculating the variation of different subnetworks. The simulation results show that, SER algorithm can effectively filter out low-quality images and improve the performance of the recognition system. Compared with other methods, it is more efficient and stable.
Big data leads to a great success of deep learning in computer vision. Unfortunately, big datasets are often not balanced in all dimensions and rare cases are often underrepresented. On-board data collection by a moving vehicle can capture thousands of normal pedestrians and vehicles, but what about special persons like police officers, road workers, and school guards? Not only that those types of classes are hard to get, they are crucial to be recognized and classified as such for the task of automated driving. Future self-driving cars need to interact with their environment and need to also understand and follow the signals and instructions of those special persons. In this paper, we show how to classify special person types using Convolutional Neural Networks. The big data imbalance is handled by data augmentation using Generative Models, showing a clear advantage over classical data augmentation. The classification performance of special persons can be significantly improved using our Generative Model based Data Augmentation.
Few-shot image classification is a challenging topic in pattern recognition and computer vision. Few-shot fine-grained image classification is even more challenging, due to not only the few shots of labelled samples but also the subtle differences to distinguish subcategories in fine-grained images. A recent method called task discrepancy maximisation (TDM) can be embedded into the feature map reconstruction network (FRN) to generate discriminative features, by preserving the appearance details through reconstructing the query image and then assigning higher weights to more discriminative channels, producing the state-of-the-art performance for few-shot fine-grained image classification. However, due to the small inter-class discrepancy in finegrained images and the small training set in few-shot learning, the training of FRN+TDM can result in excessively flexible boundaries between subcategories and hence overfitting. To resolve this problem, we propose a simple scheme to amplify inter-class discrepancy and thus improve FRN+TDM. To achieve this aim, instead of developing new modules, our scheme only involves two simple amendments to FRN+TDM: relaxing the inter-class score in TDM, and adding a centre loss to FRN. Extensive experiments on five benchmark datasets showcase that, although embarrassingly simple, our scheme is quite effective to improve the performance of few-shot fine-grained image classification. The code is available at https://github.com/Airgods/AFRN.git
Abstract Background The impact of concurrent proton pump inhibitors (PPIs) use on the prognosis of patients with breast cancer undergoing cyclin-dependent kinase inhibitors (CDKIs) treatment is currently uncertain. Considerable divergence exists regarding the clinical studies. In this study, we aim to perform a comprehensive analysis to evaluate the influence of concomitant PPI use on the effectiveness and adverse effects of CDKIs in patients with breast cancer. Methods This study encompassed all pertinent clinical studies published up to the present, following the PRISMA guidelines. The study used hazard ratio (HR) or odds ratio (OR) as a summary statistic and used fixed or random effects models for pooled estimation. Results This study incorporated 10 research articles involving 2993 participants. Among patients with breast cancer undergoing treatment with CDKIs, the simultaneous administration of PPIs was associated with a notable reduction in overall survival (HR = 2.00; 95% CI, 1.35-2.96). Nevertheless, no substantial correlation was observed between the simultaneous utilization of PPIs and the progression-free survival (PFS) of patients (HR = 1.30; 95% CI, 0.98-1.74). PFS did not change significantly when considering different drugs, treatment lines, or regions alone. Furthermore, the simultaneous administration of PPIs was found to result in a notable decrease in the incidence of grades 3/4 risk factors (OR = 0.63, 95% CI, 0.46-0.85). Conclusion The concurrent administration of PPIs did not result in significant alterations in the risk of disease advancement among patients with breast cancer undergoing CDKIs treatment. The utilization of PPIs led to a decrease in the adverse effects linked to the administration of CDKIs.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
