检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Sanjay, S.J. Akash, J. Rajan, Sreehari Shajahan, Dimple A Sharma, Charu Iiit Hyderabad Machine Learning Lab India Tkm College of Engineering Department of Computer Science Kollam India

ISBN: (纸本)9798331510831

The significant improvements in point cloud representation learning have increased its applicability in many real-life applications, resulting in the need for lightweight, better-performing models. One widely proposed efficient method is knowledge distillation, where a lightweight model uses knowledge from large models. Very few works exist on distilling the knowledge for point clouds. Most of the work focuses on cross-modal-based approaches that make the method expensive to train. This paper proposes PointKAD, an adversarial knowledge distillation framework for point cloud-based tasks. PointKAD includes adversarial feature distillation and response distillation with the help of discriminators to extract and distill the representation of feature maps and logits. We conduct extensive experimental studies on both synthetic (ModelNet40) and real (ScanObjectNN) datasets to show that PointKAD achieves state-of-the-art results compared to the existing knowledge distillation methods for point cloud classification. Additionally, we present results on the part segmentation task, highlighting the efficacy of the PointKAD framework. Our experiments further reveal that PointKAD is capable of transferring knowledge across different tasks and datasets, show-casing its versatility. Furthermore, we demonstrate that PointKAD can be applied to a cross-modal training setup, achieving competitive performance with cross-modal-based point cloud methods for classification. © 2025 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency in IoT Networks Through Fuzzy Clustering and Optimization

引用

Mobile Networks and Applications 2024年第5期29卷 1594-1617页

作者： Javadpour, Amir Sangaiah, Arun Kumar Zaviyeh, Hadi Ja’fari, Forough Department of Computer Science and Technology Harbin Institute of Technology Shenzhen China ADiT-Lab Electrotechnics and Telecommunications Department Instituto Politécnico de Viana do Castelo Porto4900-347 Portugal International Graduate School Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon School of Economics and Statistics Guangzhou University Guangzhou510006 China Department of Computer Engineering Sharif University of Technology Tehran Iran

Wireless Sensor and Internet of Things (WSIoT) networks are characterized by nodes scattered throughout the environment, posing a significant challenge when it comes to battery replacement. The task of developing an algorithm that effectively reduces energy consumption in IoT networks through the utilization of artificial intelligence and fuzzy logic is a formidable one. Heuristic algorithms emerge as valuable tools in this context, capable of swiftly addressing non-deterministic polynomial problems or approximating optimal solutions with remarkable accuracy. Conversely, mathematical optimization approaches often falter due to their sluggishness or inefficiency, rendering them less suited for the dynamic demands of IoT networks. This study embarks on a novel approach, leveraging the synergy of fuzzy clustering to intricately connect sensors to the network and particle optimization to approximate the initial values of head clusters within the realm of WSIoT. A comprehensive evaluation of our proposed strategy is meticulously conducted through extensive simulations utilizing the NS2 simulator. In this evaluation, we distinguish our algorithm from existing methods, including IoTbWSN and REcsIoT. The results of this comparative analysis are illuminating. In contrast to other methodologies, our proposed approach demonstrates a notable 9.57% improvement in network throughput and a substantial 8.47% reduction in energy consumption. This signifies a remarkable leap forward in the quest to address the challenges posed by energy consumption and battery replacement within the complex landscape of IoT networks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Dual Interspersion and Flexible Deployment for Few-Shot Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2732-2744页

作者： Cheng, Ziming Wang, Shidong Long, Yang Zhou, Tao Zhang, Haofeng Shao, Ling Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Newcastle University School of Engineering Newcastle upon TyneNE1 7RU United Kingdom Durham University Department of Computer Science DurhamDH1 3LE United Kingdom University of Chinese Academy of Sciences UCAS-Terminus Ai Lab Beijing100049 China

Acquiring a large volume of annotated medical data is impractical due to time, financial, and legal constraints. Consequently, few-shot medical image segmentation is increasingly emerging as a prominent research direction. Nowadays, Medical scenarios pose two major challenges: (1) intra-class variation caused by diversity among support and query sets;(2) inter-class extreme imbalance resulting from background heterogeneity. However, existing prototypical networks struggle to tackle these obstacles effectively. To this end, we propose a Dual Interspersion and Flexible Deployment (DIFD) model. Drawing inspiration from military interspersion tactics, we design the dual Interspersion module to generate representative basis prototypes from support features. These basis prototypes are then deeply interacted with query features. Furthermore, we introduce a fusion factor to fuse and refine the basis prototypes. Ultimately, we seamlessly integrate and flexibly deploy the basis prototypes to facilitate correct matching between the query features and basis prototypes, thus conducive to improving the segmentation accuracy of the model. Extensive experiments on three publicly available medical image datasets demonstrate that our model significantly outshines other SoTAs (2.78% higher dice score on average across all datasets), achieving a new level of performance. The code is available at: https://***/zmcheng9/DIFD. © 2025 IEEE.

关键词： Prototypes Medical diagnostic imaging Predictive models Training Mathematical models Visualization Semantic segmentation Lesions Law Electronic mail

来源：评论

学校读者我要写书评

暂无评论

MARRS: Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation

MARRS: Modern Backbones Assisted Co-training for Rapid and R...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Jain, Saurabh Kumar Das, Sukhendu Indian Institute of Technology Visualization and Perception Lab Department of Computer Science Engineering Madras India

ISBN: (纸本)9798350302493

Semi-Supervised Domain Adaptation (SSDA) aims to develop domain invariant models from scarcely labeled target domain in addition to the fully labeled source domain. Current SSDA works are often applied in conjunction with ResNet34 backbone, which makes them overlook the advantages of utilizing other backbones. Hence, in this paper, we investigate the impact of employing different modern backbones in SSDA and propose a novel solution named Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation (MARRS), that uses discriminative features of two modern backbones for training linear classifiers using the well established co-training framework. To induce diversity among classifiers for effective co-training, we propose a novel module that produces diversity at three levels, namely image, backbone, and feature distribution levels. Experiments reveal that MARRS not only achieves state-of-the-art performance across all popular SSDA datasets, but also drastically cuts the computation time compared to other SSDA approaches, making MARRS a rapid and robust solution for SSDA. We also provide extensive ablation experiments to verify our framework's vitality and primary design choices. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Square tessellation for stochastic connected k- coverage in planar wireless sensor networks 28

Square tessellation for stochastic connected k- coverage in ...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Nakka, Kalyan Ammari, Habib M. Research Lab Department of Electrical Engineering and Computer Science KingsvilleTX78363 United States

ISBN: (纸本)9798350300482

In this paper, we focus on the problem of connected k-coverage in planar wireless sensor networks (PWSNs), where every point in a field of interest (FoI) is covered by at least k sensors simultaneously, while all the participating sensors are mutually connected, where k > 1. To this end, we develop a global framework using a square tessellation that considers both deterministic and stochastic sensing models. Initially, we tessellate a planar FoI into adjacent and congruent square tiles. In each tile of this tessellation, we construct a cusp-square area for sensor placement to achieve k-coverage. Based on this cusp-squared square tile configuration, we compute the minimum sensor density that is required for deterministic and stochastic k-coverage in PWSNs. Then, we establish the necessary relationship that should exist between the sensing and communication ranges of the sensors to maintain network connectivity in k-covered PWSNs. Finally, we propose our stochastic k-coverage protocol for sensor scheduling and substantiate our theoretical analysis with simulation results. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

RL with Balanced Reward and Masking Mechanism for Multi-NUMA Virtual Machine Scheduling 19

RL with Balanced Reward and Masking Mechanism for Multi-NUMA...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Gao, Yucen Cheng, Yunlong Ping, Chan Tin Gao, Xiaofeng Chen, Guihai MoE Key Lab of Artificial Intelligence Department of Computer Science and Engineering Shanghai China Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798331507817

With the rapid development of data center and cloud computing, the importance of resource management is increasing in recent years. In this paper, we focus on the virtual machine scheduling problem in resource management, that is, how to allocate the limited virtual machine resources when a request arrives. Existing works usually model the virtual machine scheduling problem as a bin-packing problem, but they do not consider the multi-NUMA architecture servers that have been widely used in recent years. Compared with the traditional symmetric multiprocessing architecture, the multi-NUMA architecture has the advantages of faster access time and higher energy efficiency, which is more suitable for dealing with today’s scenarios with a large number of computing requirements. In this paper, we first formalize the multi-NUMA virtual machine scheduling problem as a combinatorial optimization problem and explain why it is suitable to be solved by reinforcement learning. A reinforcement learning model called BM-DQN is then proposed, which designs a balanced reward function suitable for the multi-NUMA architecture and adopts a masking mechanism to screen out the optional servers in each step of reinforcement learning, so as to improve the solution performance. Experimental results on the open-source real-world virtual machine scheduling dataset of Huawei Cloud show that BM-DQN is superior to the existing methods in terms of the number of completed requests. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Automated Rice Leaf Disease Diagnosis Using CNNs

Automated Rice Leaf Disease Diagnosis Using CNNs

引用

IEEE Region 10 Symposium

作者： Amit Kumar Biswajit Bhowmik Department of Computer Science and Engineering Maharshi Patanjali CPS Lab BRICS Lab National Institute of Technology Karnataka Mangalore Bharat

Rice is a staple food in Bharat (India) and many other parts of the world. However, the increasing demand for rice due to population growth forces various challenges, including degraded crop quality and quantity due to rice plant diseases. Diseases such as brown spots, bacterial blight, and hispa can significantly reduce farming output, thereby impacting the productivity of the agriculture sector. To address this challenge, various solutions such as Agricultural cyber-physical systems (ACPS) and precision agriculture have been proposed, along with the application of deep learning techniques. This paper presents a rice leaf disease detection method using deep transfer learning. The proposed approach explores well-known pre-trained deep Convolutional Neural Network (CNN) models - VGG19, DenseNet201, InceptionV3, ResNet50, EfficientNetB3, EfficientNetB7, and XceptionNet, for image-based rice disease classification. Experimental results show that the DenseNet model by the proposed method achieved the highest classification accuracy of 98.75% when fine-tuned properly. The proposed scheme outperforms many existing approaches, delivering a superior disease control solution for rice leaf diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Paradigm Shift From Monolithic to Microservices

Paradigm Shift From Monolithic to Microservices

引用

Recent Advances in Systems science and engineering (RASSE), IEEE International Conference on

作者： Divarshana Saxena Biswajit Bhowmik Department of Computer Science and Engineering Swami Vivekananda NoC Lab BRICS Lab National Institute of Technology Karnataka Mangalore Bharat

Microservices have been making waves among forward-thinking application development organizations. In the realm of software development, software architecture holds paramount importance because it serves as a guiding force to shape the entire life cycle of a software system. Software architecture is a foundation for complex digital components built upon a software system. Within this domain, two prevalent paradigms, monolithic and service-oriented architecture (SOA), stand distinct. While monolithic simplifies development using its integrated structure, SOA reduces complexity through modular services. However, both paradigms suffer severe scalability, development cycle, and flexibility challenges. Subsequently, microservice architecture as a modern paradigm emerges to overcome these challenges. This paper presents an in-depth analysis of the paradigm shift from monolithic to microservice architecture. It begins with exploring the monolithic and SOA conceptual landscape and their pros and cons. After that, we delve into the microservice platform, including its basic architecture and implementation stages. Furthermore, we provide the trend of the paradigm shift that highlights the recent developments in the field and identifies the research challenges associated with it. Thus, the paper brings multiple research dimensions for the researchers and lets the software and application development teams improve resilience and expedite their time to market.

关键词：

来源：评论

学校读者我要写书评

暂无评论

State Modeling and Verification of Solar Energy Harvesting System for IoT Applications

State Modeling and Verification of Solar Energy Harvesting S...

引用

International Conference on Signal Processing and Communication (ICSC)

作者： M R Prathyusha Biswajit Bhowmik Department of Computer Science and Engineering Maharshi Vasistha IoT Lab BRICS Lab National Institute of Technology Karnataka Surathkal Mangalore Bharat

The increasing popularity of using renewable energy emerges as a leading sustainable solution in the energy domain. Recently, energy harvesting, as a promising technology, uses ambient energy sources from nature to power IoT devices. For example, solar energy holds immense potential from the energy sources as it is abundantly available in the Earth’s atmosphere. While practical applications of energy harvesting systems in real-life scenarios exist, it is essential to verify these systems formally. This paper presents a comprehensive model followed by verifying a solar energy harvester system. Each proposed solar energy harvesting system component is transformed into respective finite state models. The details are then formally verified using model checking, a powerful formal verification technique. The specifications that ascertain desired properties serve as a foundation for evaluating the performance of the designed solar energy harvesting system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MARIE:One-Stage Object Detection Mechanism for Real-Time Identifying of Firearms

引用

computer Modeling in engineering & sciences 2025年第1期142卷 279-298页

作者： Diana Abi-Nader Hassan Harb Ali Jaber Ali Mansour Christophe Osswald Nour Mostafa Chamseddine Zaki Computer Science Department Faculty of SciencesLebanese UniversityBeirut146404Lebanon College of Engineering and Technology American University of the Middle EastEgaila54200Kuwait Lab-STICC CNRS UMR 6285ENSTA-BretagneBrest29200France

Security and safety remain paramount concerns for both governments and individuals *** today’s context,the frequency of crimes and terrorist attacks is alarmingly increasing,becoming increasingly intolerable to ***,there is a pressing need for swift identification of potential threats to preemptively alert law enforcement and security forces,thereby preventing potential attacks or violent *** advancements in big data analytics and deep learning have significantly enhanced the capabilities of computer vision in object detection,particularly in identifying *** paper introduces a novel automatic firearm detection surveillance system,utilizing a one-stage detection approach named MARIE(Mechanism for Realtime Identification of Firearms).MARIE incorporates the Single Shot Multibox Detector(SSD)model,which has been specifically optimized to balance the speed-accuracy trade-off critical in firearm detection *** SSD model was further refined by integrating MobileNetV2 and InceptionV2 architectures for superior feature extraction *** experimental results demonstrate that this modified SSD configuration provides highly satisfactory performance,surpassing existing methods trained on the same dataset in terms of the critical speedaccuracy *** these innovations,MARIE sets a new standard in surveillance technology,offering a robust solution to enhance public safety effectively.

关键词： Firearm and gun detection single shot multi-box detector deep learning one-stage detector MobileNet inception convolutional neural network

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：