检索结果-内蒙古大学图书馆

International Journal of Signal Processing, Image Processing and Pattern Recognition 2015年第9期8卷 229-238页

作者： Zhan, Tianming Gu, Shenghua Feng, Can Zhan, Yongzhao Wang, Jin School of Computer Science & communications Engineering Jiangsu University Zhenjiang China Jiangsu Key Laboratory of Big Data Analysis Technology Nanjing University of Information Science and Technology Nanjing China Center of software China North Industries Group Corporation Co. Ltd Nanjing China

Automatic brain tumor segmentation from multispectral magnetic resonance imaging (MRI) data is an important but a challenging task because of the high diversity in the appearance of tumor tissues among different patients and in many cases similarity with the normal tissues. In this paper, we propose a fully automatic technique for brain tumor segmentation from multispectral human brain MRIs. We first use the intensities of different patches in multispectral MRIs to represent the features of both normal and abnormal tissues and generate a dictionary for following tissue classification. Then, the sparse representation classification (SRC) is applied to classify the brain tumor and normal brain tissue in the whole image. At last, the Markov random field (MRF) regularization introduces spatial constraints to the SRC to take into account the pair-wise homogeneity in terms of classification labels and multispectral voxel intensities. Our method was evaluated on 20 multi-modality patient datasets with competitive segmentation results. ©, 2015 SERSC.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Intelligent multi-objective classifier for breast cancer diagnosis based on multilayer perceptron neural network and Differential Evolution

Intelligent multi-objective classifier for breast cancer dia...

引用

International Conference on Computing, Control, Networking, Electronics and Embedded Systems engineering (ICCNEEE)

作者： Ashraf Osman Ibrahim Siti Mariyam Shamsuddin Abdulrazak yahya Saleh Abdelzahir Abdelmaboud Awad Ali UTM Big Data Centre Universiti Teknologi Malaysia Skudai Johor Malaysia Facultv of computer and technology Alzaiem Alazhari University Khartoum Sudan Department of Software Engineering Universiti Teknologi Malaysia Skudai Johor Malaysia Faculty of computer science and information technology University of Kassala Sudan

Diagnosis of breast cancer disease depends on human experience. It is time consuming and has an element of human error in the results. This paper presents an intelligent multi-objective classifier to Diagnose breast cancer diseases using multilayer perceptron (MLP) neural network with Differential Evolution technique. The Differential Evolution (DE) algorithm is used to solve multi-objective optimization problems by tuning MLP neural network parameters. The proposed intelligent multi-objective classifier is used for diagnosis of breast cancer disease. In addition, it utilizes the advantages of multi-objective differential evolution to optimize the number of hidden nodes in the hidden layer of the MLP neural network and also to reduce network error rate. The results indicate that the proposed intelligent multi-objective classifier is viable in breast cancer diagnosis.

关键词： Diseases Medical diagnostic imaging Artificial neural networks Cities and towns Measurement uncertainty Sensitivity Training

来源：评论

学校读者我要写书评

暂无评论

Towards continuous and passive authentication via touch biometrics: an experimental study on smartphones 14

Towards continuous and passive authentication via touch biom...

引用

Proceedings of the Tenth USENIX Conference on Usable Privacy and Security

作者： Hui Xu Yangfan Zhou Michael R. Lyu Shenzhen Key Laboratory of Rich Media Big Data Analytics and Applications Shenzhen Research Institute The Chinese University of Hong Kong Shenzhen Key Laboratory of Rich Media Big Data Analytics and Applications Shenzhen Research Institute The Chinese University of Hong Kong and MoE Key Laboratory of High Confidence Software Technologies (CUHK Sub-Lab) Shenzhen Key Laboratory of Rich Media Big Data Analytics and Applications Shenzhen Research Institute The Chinese University of Hong Kong and Dept. of Computer Science & Engineering The Chinese University of Hong Kong

ISBN: (纸本)9781931971133

Current smartphones generally cannot continuously authenticate users during runtime. This poses severe security and privacy threats: A malicious user can manipulate the phone if bypassing the screen lock. To solve this problem, our work adopts a continuous and passive authentication mechanism based on a user's touch operations on the touchscreen. Such a mechanism is suitable for smartphones, as it requires no extra hardware or intrusive user interface. We study how to model multiple types of touch data and perform continuous authentication accordingly. As a first attempt, we also investigate the fundamentals of touch operations as biometrics by justifying their distinctiveness and permanence. A one-month experiment is conducted involving over 30 users. Our experiment results verify that touch biometrics can serve as a promising method for continuous and passive authentication.

关键词： smartphone touch biometrics continuous authentication

来源：评论

学校读者我要写书评

暂无评论

GPU accelerated item-based collaborative filtering for big-data applications

GPU accelerated item-based collaborative filtering for big-d...

引用

IEEE International Conference on big data

作者： Chandima Hewa Nadungodage Yuni Xia John Jaehwan Lee Myungcheol Lee Choon Seo Park Department of Computer & Information Science Purdue School of Science Indianapolis USA Department of Electrical & Computer Engineering Purdue School of Engineering & Technology Indianapolis USA Big-Data Software Platform Research Department Software Research Laboratory Electronics & Telecommunications Research Institute Korea

Recommendation systems are a popular marketing strategy for online service providers. These systems predict a customer's future preferences from the past behaviors of that customer and the other customers. Most of the popular online stores process millions of transactions per day; therefore, providing quick and quality recommendations using the large amount of data collected from past transactions can be challenging. Parallel processing power of GPUs can be used to accelerate the recommendation process. However, the amount of memory available on a GPU card is limited; thus, a number of passes may be required to completely process a large-scale dataset. This paper proposes two parallel, item-based recommendation algorithms implemented using the CUDA platform. Considering the high sparsity of the user-item data, we utilize two compression techniques to reduce the required number of passes and increase the speedup. The experimental results on synthetic and real-world datasets show that our algorithms outperform the respective CPU implementations and also the naïve GPU implementation which does not use compression.

关键词： Graphics processing units Runtime Kernel Instruction sets Indexes Memory management Acceleration

来源：评论

学校读者我要写书评

暂无评论

Reversible Fragile Watermarking based on Difference Expansion Using Manhattan Distances for 2D Vector Map

引用

Procedia Technology 2013年 11卷 614-620页

作者： Shelvie Nidya Neyman Benhard Sitohang Sobar Sutisna Department of Computer Science– Faculty of Mathematics and Natural Sciences (FMIPA) Institut Pertanian Bogor (IPB) Gedung FMIPA Kampus IPB Dramaga Jl. Meranti Dramaga Bogor 16680 Indonesia Software Engineering & Data – Research Group School of Electrical Engineering and Informatics (STEI) nstitut Teknologi Bandung(ITB) Achmad Bakrie Building 2nd Floor Jl. Ganesha No 10 Bandung 40132 Indonesia Peneliti Utama Badan Informasi Geospasial (BIG) Jl.Raya Jakarta-Bogor Km.46 Cibinong 16911 Indonesia

The need for publishing maps in secure digital format, especially guarantees data integrity which motivated us to propose a scheme that detects and locates modification data with high accuracy while ensuring exact recovery of the original content. In particular, using fragile watermarking algorithm based on reversible manner to embed hidden data in 2D vector map for each spatial features. In this paper, a reversible data-hiding scheme is explored based on the idea of difference expansion with Manhattan distances. A set of invertible integer mappings is defined to extract Manhattan distances from coordinates and the hidden data are embedded by modifying the differences between the adjacent distances. Experiments results show that the proposed scheme has good performance in term invisibility and tamper modification ability. The scheme could detect modification data such addition and deletion some features, and exactly recovery the original content of the 2D vector map.

关键词： Reversible Watermarking Fragile Watermarking Difference Expansion Manhattan Distances Vector Map

来源：评论

学校读者我要写书评

暂无评论

Characterizing Smart Contract Evolution

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Xiangping Chen Ziang Qian Peiyong Liao Yuan Huang Changlin Yang Zibin Zheng Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Journalism and Communication Sun Yat-sen University China School of Software Engineering Sun Yat-sen University China School of Computer Science and Engineering Sun Yat-sen University China

Smart contracts are programs that permanently store and automatically execute on the blockchain system such as Ethereum. Due to the non-tamperable nature of the underlying blockchain, smart contracts are difficult to update once deployed, which requires redeploying the contracts and migrating the data. It means that the observation of smart contract evolution in the real world makes more sense. Hence, in this paper, we conducted the first large-scale empirical study to characterize the evolution of smart contracts in Ethereum. For evolution identification, we presented a contract similarity-based search algorithm, digEvolution, and evaluated its effectiveness with five different search strategies. Then we applied this algorithm to 80,152 on-chain contracts we collected from Ethereum, to dig out the evolution among these contracts. We then explored three research questions. We first studied whether the evolution of smart contracts is common (RQ1), then we studied how do the Gas consumption (RQ2) and the vulnerability (RQ3) of smart contracts vary during the evolution. Our research results show that the evolution of smart contracts is not very common. There are some contract components that have vulnerability but still be called by users. The Gas consumption of most smart contracts doesn’t vary during the evolution, contract is Gas-efficient before and after the evolution. The vulnerability of most smart contracts doesn’t vary during the evolution, both are secure before and after the evolution.

关键词： Smart Contract software Evolution Code Clone

来源：评论

学校读者我要写书评

暂无评论

CROSS: Feedback-Oriented Multi-Modal Dynamic Alignment in Recommendation Systems

ACM Transactions on Recommender Systems

引用

ACM Transactions on Recommender Systems 1000年

作者： Yang Li Junpeng Du Chenzhan Wang Zunlong Liu Xiaomin Zhu Chen Lin Institute of Artificial Intelligence Xiamen University Xiamen China School of Informatics Xiamen University Xiamen China School of Big Data & Software Engineering Chongqing University Chongqing China School of Information Science and Engineering Shandong Normal University Jinan China Strategic Assessments and Consultation Institute Academy of Military Science Beijing China School of Informatics Xiamen University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University Xiamen China

Aligning the multi-modal content and ID embeddings is crucial in multi-modal recommendation systems. Existing solutions typically adopt a bidirectional alignment paradigm. Our prior work, FETTLE, challenges this paradigm by proposing a one-way directional alignment at the item level, thus reducing the negative impact of low-quality modalities. However, FETTLE leaves two open questions: (1) when is one-way directional alignment optimal, and (2) how to incorporate collaborative signals to enhance alignment? We present CROSS (feedbaCk-oRiented multi-mOdal alignment in recommendation SyStem), a plug-and-play framework that extends FETTLE by introducing three major advancements. First, we introduce Dynamic Item-Level Alignment, which dynamically calibrates the ’strength’ of each modality via a variance-based compensation mechanism, mitigating the risk of overshadowing weaker modalities in the early stages of training. Second, we develop Multi-grained Collaborative Alignment, which introduces a medium-granularity alignment strategy based on neighboring items that share similar user feedback profiles. This neighbor-level alignment effectively balances noisy user interactions and excessive smoothing across items. Third, we conduct extensive experiments on more real-world datasets and show that CROSS significantly boosts the performance of both collaborative filtering (CF) models and multi-modal recommendation (MRS) approaches, achieving 21.52%–70.78% average improvement on CF backbones and 8.70%–20.73% on MRS backbones. Compared with FETTLE, CROSS achieves additional improvements of 3.82%–5.24%.

关键词： Recommender Systems Multi-modal Recommendation Multi-Modality Alignment

来源：评论

学校读者我要写书评

暂无评论

Multi-view Intent Learning and Alignment with Large Langue Models for Session-based Recommendation

引用

ACM Transactions on Information Systems 1000年

作者： Shutong Qiao Wei Zhou Junhao Wen Chen Gao Qun Luo Peixuan Chen Yong Li School of Big Data & Software Chongqing University China School of Big Data & Software Chongqing University China Beijing National Research Center for Information Science and Technology Tsinghua University China Tencent China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University China

Session-based recommendation (SBR) methods often rely on user behavior data, which can struggle with the sparsity of session data, limiting performance. Researchers have identified that beyond behavioral signals, rich semantic information in item descriptions is crucial for capturing hidden user intent. While large language models (LLMs) offer new ways to leverage this semantic data, the challenges of session anonymity, short-sequence nature, and high LLM training costs have hindered the development of a lightweight, efficient LLM framework for *** address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views. This two-stage framework leverages the strengths of both LLMs and traditional SBR models while minimizing training costs. In the first stage, we use multi-view prompts to infer latent user intentions at the session semantic level, supported by an intent localization module to alleviate LLM hallucinations. In the second stage, we align and unify these semantic inferences with behavioral representations, effectively merging insights from both large and small models. Extensive experiments on two real datasets demonstrate that the LLM4SBR framework can effectively improve model performance. We release our codes along with the baselines at https://***/tsinghua-fib-lab/LLM4SBR.

关键词： Recommender System Session-based Recommendation Large Language Models data Augmentation

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Early Detection and Diagnosis of Cervical Cancer 1

引用

丛书名： Signals and Communication Technology

1000年

作者： Sejal Shah Rohit M. Thanki Anjali Diwan

来源：评论

学校读者我要写书评

暂无评论

Interpreting Deep Forest through Feature Contribution and MDI Feature Importance

引用

ACM Transactions on Knowledge Discovery from data 1000年

作者： Yi-Xiao He Shen-Huan Lyu Yuan Jiang National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources and College of Computer Science and Software Engineering Hohai University China

Deep forest is a non-differentiable deep model that has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide a local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explaining tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real-world data verify the effectiveness of our methods.

关键词： deep forest feature importance interpretability

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：