检索结果-内蒙古大学图书馆

Boundary-Guided Learning for Gene Expression Prediction in Spatial Transcriptomics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qu, Mingcheng Wu, Yuncong Di, Donglin Su, Anyang Su, Tonghua Song, Yang Fan, Lei Faculty of Computing Harbin Institute of Technology Harbin China School of Astronautics Harbin Institute of Technology Harbin China Space AI Li Auto Beijing China College of Software Jilin University Changchun China Computer Science and Engineering UNSW Sydney Australia

Spatial transcriptomics (ST) has emerged as an advanced technology that provides spatial context to gene expression. Recently, deep learning-based methods have shown the capability to predict gene expression from WSI data using ST data. Existing approaches typically extract features from images and the neighboring regions using pretrained models, and then develop methods to fuse this information to generate the final output. However, these methods often fail to account for the cellular structure similarity, cellular density and the interactions within the microenvironment. In this paper, we propose a framework named BG-TRIPLEX, which leverages boundary information extracted from pathological images as guiding features to enhance gene expression prediction from WSIs. Specifically, our model consists of three branches: the spot, in-context and global branches. In the spot and in-context branches, boundary information, including edge and nuclei characteristics, is extracted using pretrained models. These boundary features guide the learning of cellular morphology and the characteristics of microenvironment through Multi-head Cross-Attention. Finally, these features are integrated with global features to predict the final output. Extensive experiments were conducted on three public ST datasets and the Visium dataset. The results demonstrate that our BG-TRIPLEX consistently outperforms existing methods in terms of Pearson Correlation Coefficient (PCC). This method highlights the crucial role of boundary features in understanding the complex interactions between WSI and gene expression, offering a promising direction for future research. Codes are available at: https://***/WcloudC0416/BG-TRIPLEX. Copyright © 2024, The Authors. All rights reserved.

关键词： Gene expression

A Comprehensive Approach to Identify Stroke based on Real-time Medical Data

学校读者我要写书评

暂无评论

A Comprehensive Approach to Identify Stroke based on Real-ti...

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： M. Maragatharajan Shanmugapriya S M. B. Sudhan Deeptha R. Sankar Muthu Paramasivam School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Srivilliputhur Tamilnadu India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai Tamilnadu Department of Information Technology SRM Institute of Science and Technology Ramapuram Chennai Tamilnadu India Distinguished Software Engineer Palo Alto Networks Inc Santa Clara California USA

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

Strokes or cardiovascular disorders continue to be a major global health concern. Proactive intervention and timely detection greatly reduce the morbidity and death related to strokes. The goal of this research is to build a prediction model using machine learning techniques to assess a person’s risk of stroke based on a variety of sociodemographic and health characteristics. The dataset used in this study consists of a large collection of medical records. It contains important details including age, gender, BMI, smoking habits, heart disease, hypertension, and the type of residential property. Using this information, a Decision Tree Classifier is trained to predict the likelihood of strokes, enabling early detection and customized treatment plans. A Decision Tree Classifier with a predetermined maximum depth is used in the proposed methodology’s rigorous data preprocessing, which includes handling missing values, encoding categorical features, and developing models. Both the training and testing datasets are used to evaluate the model’s performance using evaluation measures including accuracy, precision, and recall. The model’s insights provide important characteristics that influence the prediction of stroke risk, assisting medical professionals in focused risk assessment and preventive intervention. The proposed method has the potential to improve healthcare practices by facilitating prompt interventions and personalized treatment for stroke risk individuals. The proposed model has resulted in 86.78% accuracy for this dataset by using the traditional machine learning algorithms. This work highlights the value of predictive modelling in the healthcare industry by demonstrating how it may improve early detection techniques and lessen the impact of strokes on public health.

关键词： Training Machine learning algorithms Machine learning Predictive models Stroke (medical condition) Real-time systems Risk management

Assessing the Robustness of LLM-based NLP software via Automated Testing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiao, Mingxuan Xiao, Yan Ji, Shunhui Cai, Hanbo Xue, Lei Zhang, Pengcheng Key Laboratory of Water Big Data Technology Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing211100 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China

Benefiting from the advancements in LLMs, NLP software has undergone rapid development. Such software is widely employed in various safety-critical tasks, such as financial sentiment analysis, toxic content moderation, and log generation. Unlike traditional software, LLM-based NLP software relies on prompts and examples as inputs. Given the complexity of LLMs and the unpredictability of real-world inputs, quantitatively assessing the robustness of such software is crucial. However, to the best of our knowledge, no automated robustness testing methods have been specifically designed to evaluate the overall inputs of LLM-based NLP software. To this end, this paper introduces the first AutOmated Robustness Testing frAmework, AORTA, which reconceptualizes the testing process into a combinatorial optimization problem. Existing testing methods designed for DNN-based software can be applied to LLM-based software by AORTA, but their effectiveness is limited. To address this, we propose a novel testing method for LLM-based software within AORTA called Adaptive Beam Search. ABS is tailored for the expansive feature space of LLMs and improves testing effectiveness through an adaptive beam width and the capability for backtracking. We successfully embed 18 test methods in the designed framework AORTA and compared the test validity of ABS with three datasets and five threat models. ABS facilitates a more comprehensive and accurate robustness assessment before software deployment, with an average test success rate of 86.138%. Compared to the currently best-performing baseline PWWS, ABS significantly reduces the computational overhead by up to 3441.895 seconds per successful test case and decreases the number of queries by 218.762 times on average. Furthermore, test cases generated by ABS exhibit greater naturalness and transferability. © 2024, CC BY-NC-ND.

关键词： software testing

Robust and digital hyper-polarization protocol of nuclear spins via magic sequential sequence

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Haiyang Liao, Hao Wang, Ping Faculty of Arts and Sciences Beijing Normal University Zhuhai519087 China National Engineering Laboratory on Big Data System Computing Technology Guangdong Province Engineering Center of China-made High Performance Data Computing System College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Hyper-polarization of nuclear spins is crucial for advancing nuclear magnetic resonance (NMR) and quantum information technologies, as nuclear spins typically exhibit extremely low polarization at room temperature due to their small gyro-magnetic ratios. A promising approach to achieving high nuclear spin polarization is transferring the polarization of electron to nuclear spin. The nitrogen-vacancy (NV) center in diamond has emerged as a highly effective medium for this purpose, and various hyper-polarization protocols have been developed. Among these, the pulsed polarization (PulsePol) method has been extensively studied due to its robustness against static energy shifts of the electron spin. In this study, we introduce a sequential polarization protocol and identify a series of magic and digital sequences for hyper-polarizing nuclear spins. Notably, we demonstrate that some of these magic sequences exhibit significantly greater robustness compared to the PulsePol protocol in the presence of finite half π pulse duration of the protocol. This enhanced robustness positions our protocol as a more suitable candidate for hyper-polarizing nuclear spins species with large gyromagnetic ratios and also ensures better compatibility with high-efficiency readout techniques at high magnetic fields. Additionally, the generality of our protocol allows for its direct application to other solid-state quantum systems beyond the NV center. © 2025, CC BY.

关键词： Chemical shift

A Multi-objective Salp Swarm Algorithm for Multi-product Two-sided Disassembly Line Balancing Problem with Special Workers

学校读者我要写书评

暂无评论

A Multi-objective Salp Swarm Algorithm for Multi-product Two...

Chinese Control and Decision Conference, CCDC

作者： Xinyu Zhu Shujin Qin XiWang Guo Jiacun Wang Qi Zhang Jiawei Li School of Economics and Management Shangqiu Normal University Shangqiu China Liaoning Petrochemical University Monmouth University West Long Branch USA Computer Science and Software Engineering Monmouth University West Long Branch USA Information Science and Engineering Shenyang University of Chemical Technology Shenyang China Computer and Communication Engineering Liaoning Petrochemical University Fushun China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The escalating volume of discarded large-scale electronic products has triggered significant attention within the research community toward the TDLBP (Two-sided Disassembly Line Balancing Problem. In response, this study presents a biobjective optimization problem for TDLBP, incorporating the considerations of hiring special WGB (Workers with Government Benefits) workers. The objectives are two-fold: one is to maximize disassembly profit, and the other is to concurrently enhance the WGB index. The resulting problem is named a Bi-objective Multi-product Two-sided Disassembly-line-balancingproblem considering Workers-with-government-benefits. MSSA (Multi-objective Salp Swarm Algorithm) is proposed to tackle the problem. The effectiveness of the proposed algorithm is validated through comparison with NSGA-III and MOEA/DCRA.

关键词： Heuristic algorithms Government Mathematical models Encoding Decoding Indexes Optimization

An Improved Semantic Place Retrieval Method by Learning-based Clustering

学校读者我要写书评

暂无评论

An Improved Semantic Place Retrieval Method by Learning-base...

Data Science and Information technology (DSIT), International Conference on

作者： Jiamin Lu Jiahao Liu Zhendong Fan Zhenyu Zhou Xu Kong Jun Feng Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer and Software Hohai University Nanjing China PowerChina Huadong Engineering Corporation Limited Hangzhou China

ISBN: (数字)9798350384093

ISBN: (纸本)9798350384109

Traditional sorting-based semantic place retrieval methods may face the problem of a large retrieval space. An improved method is proposed in this paper, based on Learning-based Clustering. It has three components: encoding, clustering and retrieval. Specifically, we craft a spatial entity encoder that integrates both spatial and semantic dimensions to embed spatial entities. Then, we utilize a cascaded Siamese network architecture for deep clustering, thereby minimizing the retrieval space for downstream tasks. Finally, we employ the SSPR method to assess the impact of our approach on retrieval efficiency.

关键词： Clustering methods Semantics Focusing Network architecture Data science Vectors Resource description framework Encoding Information technology Faces

Collaborative Segmentation Model for Colonoscopy Ulcers based on Fuzzy Labeling*

学校读者我要写书评

暂无评论

Collaborative Segmentation Model for Colonoscopy Ulcers base...

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Yanning Lin Jie Chen Ziqian Ding Linxu Chen Le Li Zhongsheng Zhu Zhaoxia Wang Jianqiang Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Children’s Hospital Shenzhen China Gastroenterology Shenzhen Children’s Hospital China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Inflammatory Bowel Disease (IBD) is a global chronic intestinal inflammatory disease, and its incidence rate increases year by year with the progress of economic globalization. Currently, the diagnosis of IBD in children mainly relies on endoscopic examination, but scoring endoscopic images is a challenging issue, especially in distinguishing different types of ulcers. To address this issue, this article designs a mobile application to accelerate data annotation processing and may provide reference for other unlabeled datasets. In the context of image segmentation, blurring labels has become an important issue. Deep learning methods are widely used in medical image segmentation, but their accuracy depends on high-quality annotated data. However, there are low-quality noise areas in the annotated data, and obtaining accurate and high-quality annotations becomes more time-consuming with limited annotation budgets. This article proposes a collaborative training framework to improve learning of noisy pixels. This framework determines the label confidence of an image by calculating the similarity between image pixels and surrounding pixels. Then, two parallel deep networks were constructed for semantic prediction, which aimed to guide each other on pixels that may have noise. By applying consistency in dual network prediction, the semantic information of uncertain pixels is corrected as much as possible. Experimental results have shown that this framework is slightly superior to models trained with pixel level precise labels, thus more effectively utilizing existing annotated data in the case of fuzzy labels.

关键词： Training Image segmentation Accuracy Annotations Biological system modeling Semantics Noise Collaboration Colonoscopy Medical diagnostic imaging

Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liang, Hanzhe Zhou, Jie Chen, Xuanxin Dai, Tao Wang, Jinbao Gao, Can College of Computer Science and Software Engineering Shenzhen University China Shenzhen Audencia Financial Technology Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Faculty of Education Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgements to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Semantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem’s causal logic. Copyright © 2025, The Authors. All rights reserved.

关键词： Fences

Deep Learning-based Classification of Lung CT Scan for Accurate Cancer Diagnosis

学校读者我要写书评

暂无评论

Deep Learning-based Classification of Lung CT Scan for Accur...

International Conference on Inventive Computation Technologies (ICICT)

作者： D.Christy Sujatha T.R. Vijaya Lakshmi Surya G U. Surendar Rajendiran M Ramya Maranan Department of Software Engineering Periyar Maniammai Institute of Science and Technology Thanjavur Tamail Nadu India Department of Electronics and Communication Engineering Mahatma Gandhi Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering K. Ramakrishnan College of Engineering Tiruchirappalli Tamil Nadu India Department of Electronics and Communication Engineering SRM Institute of Science and Technology - Ramapuram Campus Chennai Tamil Nadu India Department of Computer Science And Engineering Panimalar Engineering College Poonamallee Chennai Tamil Nadu India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

This paper investigates the suitability of advanced deep learning models for precise diagnosis of lung cancer from MRI images. Recurrent neural networks (RNN), K-Nearest Neighbors (KNN), ResNet50, and convolutional neural networks (CNN) were all carefully evaluated to determine their unique contributions. The CNN showed off its good performance and capacity to recognize intricate patterns in lung images, achieving an accuracy of 92.3%. KNN demonstrated competitive results, demonstrating the adaptability of non-parametric methods for medical image classification. Remarkably, ResNet50 fared extremely well, exhibiting a remarkable accuracy of 94.8% and verifying the value of deep residual networks in differentiating between intricate features. RNNs gave the analysis a temporal dimension and contributed to its 89.5% accuracy. Information from confusion matrices containing comprehensive classification results was useful in refining the model. Spatial representations of expected cancer cell locations showed the effectiveness of the models by giving doctors visual cues for targeted interventions. Comparisons with the literature show that the results are in line with recent developments in deep learning for medical image analysis. Because of its comprehensive assessment of different deep learning architectures, which provides fresh perspectives that advance the field of lung cancer detection technologies, this work is an invaluable resource for future research.

关键词： Deep learning Visualization Recurrent neural networks Magnetic resonance imaging Lung cancer Lung Convolutional neural networks