检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiangru Lin Shenghua Zhong Yan Liu Gong Chen College of Computer Science Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China College of Computer Science Shenzhen University Shenzhen China Department of Computer Science The Hong Kong Polytechnic University HK China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

The existing text-to-image generation methods based on stable diffusion yield better results in low-semantic prompt but often neglect the generation quality of high-semantic prompt such as emotional vocabulary, resulting in poor emotional image generation. In order to address this issue, we propose a novel approach called Sal-Guide Diffusion, which leverages saliency maps to guide emotional image generation with the goal of producing superior emotionally expressive images. In order to let the saliency maps guide the diffusion process, we introduce a lightweight adapter to extract emotional information from saliency maps and incorporate it into the diffusion process. Experimental results demonstrate that our proposed method generates higher-quality images across eight emotional dimensions, excelling in both generalization, emotional congruence, and subjective preference compared to stable diffusion or similar methods.

关键词： Vocabulary Image synthesis Buildings Diffusion processes Text to image data mining

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Skin Cancer by Using a Parallel Deconvolutional Network Model 1

Detection and Classification of Skin Cancer by Using a Paral...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Sangeetha, M. Karthikeyini, C. Vasundhara, S. Saravanan, D. Arunkumar, G. School of Computing SRMIST Department of Data Science and Business Systems Kattankulathur C India Excel Engineering College Department of ECE Tamil Nadu Komarapalayam India G.Narayanamma Institute of Technology &science Department of Humanities & Mathematics JNTUH Hyderabad India IFET College of Engineering Department of CSE Tamil Nadu Villupuram India Madanapalle Institute of Technology & Science Department of CSE Andhra Pradesh Madanapalle India

ISBN: (纸本)9781665456876

Skin Cancer is one of the most common cancer forms in many countries, it is considered to be one of the dangerous types in the sense that it is lethal and its occurrence over time has been dramatically high. It is one of the deadliest cancers among all diseases and has a large rate of mortality. The efficiency of the earlier approaches to assess one of the most hazardous melanoma diagnosis in dermoscopic criteria are not up to the mark. Therefore, in this research, the work has been carried out in three stages in order to detect melanoma in an efficient manner. In the first stage, prior to the implementation of the image segmentation technique, noise elimination and pre-processing steps are carried out to remove the noise and to achieve better execution results. This segmentation model focuses on the separation of the interesting portions from the background and collects the necessary information from the neighboring pixels of the same category. Gaussian analytical patterns are used to handle the heterogeneous regions/sections of dermoscopy images whose mean and variance can be dynamic. In addition, the third stage of work is based on the texture classification, which is proposed as the CSTC-Mel Identification Model. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Conditional Handover for 5g Networks with Dynamic Obstacles

SSRN

引用

SSRN 2024年

作者： Deb, Souvik Rathod, Megh Balamurugan, Rishi Singh, Rajeev Kumar Sanyal, Samriddha Ghosh, Shankar K. Advanced Computing & Microelectronics Unit Indian Statistical Institute West Bengal Kolkata700108 India Department of Computer Science and Engineering Shiv Nadar Institution of Eminence Delhi201314 India School of Computing and Data Science FLAME University Maharashtra Pune412115 India Shiv Nadar University India

To enhance seamless connectivity in millimetre wave New radio networks, Conditional handover has evolved as a promising solution. Unlike A3 handover where handover execution is certain after receiving handover command from the serving access network, in conditional handover, handover execution is conditional on the Reference signal received power measurements from both current and target access networks, as well as on mobility parameters such as preparation and execution offsets. Presence of dynamic obstacles may block the signal from serving and (or) target access networks, which results in violation of the conditions for the handover preparation/execution. Moreover, signal blockage by dynamic obstacles may cause radio link failure, which may cause handover failure as well. Analytic evaluations of conditional handover performance in the presence of dynamic obstacles are quite limited in the preceding literature. In this work, handover performance of conditional handover has been carried out in terms of handover latency, handover packet loss and handover failure probability. A Markov model accounting the effect of dynamic obstacles, different mobility parameters (e.g., execution offset, preparation offset, time-to-preparation and time-to-execution), user velocity and channel fading characteristics has been proposed to characterize handover failure. Results obtained from the analytic model has been validated against extensive simulation results. Our study reveal that optimal configuration of the mobility parameters is actually conditional on the presence of dynamic obstacles, user velocity and fading characteristics. This study will be helpful for the mobile operators to configure the mobility parameters for New radio systems where dynamic obstacles are present. © 2024, The Authors. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm for Software Reliability Prediction via Harris Hawks Optimization 2nd

An Efficient Algorithm for Software Reliability Prediction v...

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： Kong, Li Sheng Jasser, Muhammed Basheer Issa, Bayan Ajibade, Samuel-Soma M. Majeed, Anwar P. P. Abdul Luo, Yang Department of Smart Computing and Cyber Resilience School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia Department of Data Science and Artificial Intelligence School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Bandar Sunway Selangor Petaling Jaya47500 Malaysia Faculty of Informatics Engineering University of Aleppo Aleppo Syria School of Intelligent Manufacturing Ecosystem Xi’an Jiaotong-Liverpool University Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

Software reliability has become an increasingly important characteristic as software systems continue to be integrated into all parts of our lives. While the occurrence of failure after a period of time is within the nature of all software systems, the ability to estimate and predict failure is greatly beneficial to software development and maintenance. Hence, Software Reliability Growth Models (SRGMs) were developed to fulfill this requirement. Conventional parameter estimation methods of SRGM functions were complex and left more to be desired. Consequently, metaheuristics such as Swarm Intelligence algorithms were introduced to estimate and optimize the parameters of SRGM functions. Likewise, Swarm Intelligence algorithms were found to be exceptionally effective in estimating and optimizing the parameters of SRGM functions. This paper presents a novel approach to parameter estimation on three different SRGM functions through Harris’ Hawks Optimization (HHO). The proposed HHO design is compared against numerous different variants of Swarm Intelligence algorithms and is shown to be significantly more efficient than the majority of the compared designs. Moreover, as the proposed design is a base variant of Swarm Intelligence algorithms, various avenues of future improvements have also been presented to improve its overall prediction accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Harris’ Hawks Optimization Parameter Estimation Software Reliability Growth Models Software Reliability Prediction Swarm Intelligence

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of UAV-Carried IRS for Urban Low Altitude mmWave Communications with Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Xie, Wenwen Sun, Geng Liu, Bei Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit Kim, Dong In The College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The University of Hong Kong 999077 Hong Kong The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Emerging technologies in sixth generation (6G) of wireless communications, such as terahertz communication and ultra-massive multiple-input multiple-output, present promising prospects. Despite the high data rate potential of millimeter wave communications, millimeter wave (mmWave) communications in urban low altitude economy (LAE) environments are constrained by challenges such as signal attenuation and multipath interference. Specially, in urban environments, mmWave communication experiences significant attenuation due to buildings, owing to its short wavelength, which necessitates developing innovative approaches to improve the robustness of such communications in LAE networking. In this paper, we explore the use of an unmanned aerial vehicle (UAV)-carried intelligent reflecting surface (IRS) to support low altitude mmWave communication. Specifically, we consider a typical urban low altitude communication scenario where a UAV-carried IRS establishes a line-of-sight (LoS) channel between the mobile users and a source user (SU) despite the presence of obstacles. Subsequently, we formulate an optimization problem aimed at maximizing the transmission rates and minimizing the energy consumption of the UAV by jointly optimizing phase shifts of the IRS and UAV trajectory. Given the non-convex nature of the problem and its high dynamics, we propose a deep reinforcement learning-based approach incorporating neural episodic control, long short-term memory, and an IRS phase shift control method to enhance the stability and accelerate the convergence. Simulation results show that the proposed algorithm effectively resolves the problem and surpasses other benchmark algorithms in various performances. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Superpixel Segmentation: From Theory to Applications*

Superpixel Segmentation: From Theory to Applications*

引用

Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI)

作者： Isabela Borlido Felipe Belém Leonardo Melo Taylla M. Theodoro Ilan F. Silva Zenilton K. G. do Patrocínio Alexandre X. Falcão Silvio Jamil F. Guimarães Computer Science Department (DCC) Image and Multimedia Data Science Laboratory (IMScience) Pontifical Catholic University of Minas Gerais (PUC Minas) Belo Horizonte Brazil Laboratory of Image Data Science (LIDS) Institute of Computing (IC) University of Campinas (UNICAMP) Campinas Brazil

Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications since it allows for reducing the workload, removing redundant information, and preserving regions with meaningful features. Due to the rapid progress in this area, the literature fails to catch up on more recent works among the compared ones and to categorize the methods according to all existing strategies. We revisit the recent and popular literature according to our taxonomy and evaluate 20 strategies based on nine criteria: connectivity, compactness, delineation, control over the number of superpixels, color homogeneity, robustness, running time, stability, and visual quality. Thus, this document presents a proposal for a tutorial to be presented at SIBGRAPI 2023.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Smoke and Fire Detection Algorithm Based on YOLOv11

Research on Smoke and Fire Detection Algorithm Based on YOLO...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Sisi Cai Junqing Lin Zhongxi Chen Congshen Zheng Youyu Zhou Department of Data Science Beijing Institute of Technology Zhuhai Zhuhai China School of Computing Beijing Institute of Technology Zhuhai Zhuhai China Law school Beijing Institute of Technology Zhuhai Zhuhai China

ISBN: (数字)9798331522285

ISBN: (纸本)9798331522292

Currently, the fire rescue field is still facing many technical challenges, in which the accurate detection of fire source smoke and real-time response in complex environments is the core problem to be solved. Traditional detection methods mainly rely on sensor technology or threshold segmentation algorithms, which are susceptible to interference by environmental factors, and it is difficult to achieve an effective balance between detection speed and accuracy. Although deep learning techniques have made significant progress in the field of fire detection, there are still obvious limitations in areas such as detection in complex backgrounds and multi-target scenes. Aiming at the above technical bottlenecks, this study uses a YOLOv11-based fire-smoke target detection algorithm. By using the YOLOv11 model, the feature extraction ability of irregular targets such as smoke and flame is significantly enhanced; meanwhile, the detection robustness in complex scenes is effectively improved due to the loss function and multi-scale detection architecture. The experimental results show that the algorithm achieves 77.7 % mean average precision (mAP) and 82.9% accuracy on the complex fire source smoke dataset, which provides a reliable technical support for fire warning and rescue command.

关键词： Seminars Accuracy Fires Object detection Interference Feature extraction Robustness Real-time systems Environmental factors Information technology

来源：评论

学校读者我要写书评

暂无评论

Beyond the Known: Novel Class Discovery for Open-world Graph Learning

arXiv

引用

arXiv 2024年

作者： Jin, Yucheng Xiong, Yun Fang, Juncheng Wu, Xixi He, Dongxiao Xing, Jia Zhao, Bingchen Yu, Philip Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China College of Intelligence and Computing Tianjin University China School of Informatics University of Edinburgh United Kingdom Department of Computer Science University of Illinois Chicago United States

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has been paid to novel class discovery on graphs. Discovering novel classes is challenging as novel and known class nodes are correlated by edges, which makes their representations indistinguishable when applying message passing GNNs. Furthermore, the novel classes lack labeling information to guide the learning process. In this paper, we propose a novel method Open-world gRAph neuraL network (ORAL) to tackle these challenges. ORAL first detects correlations between classes through semi-supervised prototypical learning. Inter-class correlations are subsequently eliminated by the prototypical attention network, leading to distinctive representations for different classes. Furthermore, to fully explore multi-scale graph features for alleviating label deficiencies, ORAL generates pseudo-labels by aligning and ensembling label estimations from multiple stacked prototypical attention networks. Extensive experiments on several benchmark datasets show the effectiveness of our proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Bag of Tricks of Hybrid Network for Covid-19 Detection of CT Scans

Bag of Tricks of Hybrid Network for Covid-19 Detection of CT...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Chih-Chung Hsu Chih-Yu Jian Chia-Ming Lee Chi-Han Tsai Shen-Chieh Tai Center of Data Science Miin Wu School of Computing National Cheng Kung University No.1 University Rd Tainan City Taiwan Department of Statistics Institute of Data Science No.1 University Rd Tainan City Taiwan

This paper presents a study using deep learning models to analyze lung Computed Tomography (CT) images. Traditionally used for this task, deep learning frameworks face compatibility issues due to the variances in CT image slice numbers and resolutions caused by the use of different machines. Typically, individual slices are predicted and combined to obtain the final result, but this approach lacks slice-wise feature learning and ultimately leads to decreased performance. To address this limitation, we propose a novel slice selection method for each CT dataset, effectively filtering out uncertain slices and enhancing the model’s performance. Moreover, we introduce a spatial-slice feature learning technique that uses a conventional and efficient backbone model for slice feature training. We then extract one-dimensional data from the trained COVID and non-COVID classification models by employing a dedicated classification model. Leveraging these experimental steps, we integrate one-dimensional features with multiple slices for channel merging and employ a 2D convolutional neural network for classification. In addition to the aforementioned methods, we explore various high-performance classification models, ultimately achieving promising results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Learning-Based Machine Fault Diagnosis Using EMD-Gammatone Spectrogram with Limited Labeled Audio dataset

Few-Shot Learning-Based Machine Fault Diagnosis Using EMD-Ga...

引用

2025 IEEE International Conference on Big data and Smart computing, BigComp 2025

作者： Zabin, Mahe Ayon, Syed Tasnimul Karim Siraj, Farhan Md Shuvo, Mehedi Hasan Choi, Ho-Jin Uddin, Jia Korea Advanced Institute of Science and Technology School of Computing Daejeon Korea Republic of BRAC University Department of Computer Science and Engineering Dhaka Bangladesh Dhaka University of Engineering & Technology Department of Computer Science and Engineering Dhaka Gazipur Bangladesh Woosong University AI and Big Data Department Endicott College Daejeon Korea Republic of

The deep learning models are computationally burdensome, and their accuracy depends on the number of labeled datasets used in training. The scarcity of the labeled dataset in industrial machine diagnosis is a significant concern as it is pretty impossible to collect data from faulty machines in industrial environments. To address this issue, in this paper, we presented a few-shot learning-based machine fault diagnosis model on a lightweight SqueezeNet architecture using generated texture images from audio sensor data. Subsets of two public audio datasets, MIMII and ToyADMOS, containing limited data- 10 images per class were used to validate the model. The experimental results demonstrate that the model has exhibited 89.6% and 98.3% accuracy for MIMII and ToyADMOS, respectively, with only ten labeled images of each fault class. As the model has only 73 thousand trainable parameters and requires only 300 KB of memory, it is expected to be deployable in a portal device for machine fault diagnosis. © 2025 IEEE.

关键词： Deep learning

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：