检索结果-内蒙古大学图书馆

Review Study on software risk factors

2019 Imam Al-Kadhum International Conference for Modern Applications of Information and Communication Technology, MAICT 2019

作者： Abbas, Ahmed Saleem Alabaichi, Ashwak Khodher, Maisa'a Abid Ali Software Department College of Information Technology University of Babylon Iraq Biomedical Engineering College of Engineering University of Kerbala Iraq Computer Sciences Department University of Technology Iraq

Risk management is an important aspect of any software project management. Risk management conditions are a position that prevents the software project from be a successful and within time or intervenes to make a project late. This is a critical aspect of software product development, where it is often ignored. From that, software project development schedules are negative influenced by managers themselves pressing their employees to overcome time losing problem when it was planned to be properly planned. Each software project faces risks of all types and seriousness. Design flaws nearly cause 50 percent of security problems, so the analysis of risk at the design stage is very important issue of the software security. Risk analysis is also a means of elicitation the required data to make a good decision depend on knowledge about sensitivity parts, threats and impacts. Most of the risk analysis methodologies share some common principles and limitations but also have advantages and disadvantages when implemented to recent software design. © Published under licence by IOP Publishing Ltd.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

HFANTrack: A Hierarchical Feature-Aware Network for Visual Tracking 30

HFANTrack: A Hierarchical Feature-Aware Network for Visual T...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Gu, Fengwei Li, Ao Liu, Tienan Shi, Tao Zhao, Ning Ju, Zhaojie Harbin University of Science and Technology School of Computer Science and Technology Harbin150080 China State Gird Harbin Electric Power Supply Company State Gird Harbin150023 China Shandong Baimeng Information Technology Co. Ltd. Weihai264200 China Bohai University College of Control Science and Engineering Jinzhou121013 China University of Portsmouth School of Computing PortsmouthPO1 3HE United Kingdom

ISBN: (纸本)9798350391916

In the field of visual tracking, it is a significant challenge to accurately capture the dynamic changes of targets in complex scenes. To address this issue, this paper proposes a novel Hierarchical Feature-Aware Network (HFAN) to improve tracking performance. The design of HFAN mainly includes two pivotal components: Feature-Enhanced Unit (FEU) and Hierarchical Feature-Aware Unit (HFAU). FEU enhances the richness and discriminative power of target representations by reinforcing features from the templates and search regions. HFAU establishes comprehensive dependencies among multi-level features to capture the changing characteristics of targets across different spatial hierarchies. Finally, a Siamese tracker called HFANTrack is proposed to improve tracking accuracy and robustness in complex scenarios. Extensive experimental results show that our method achieves competitive tracking performance with a real-time speed of 49.3fps compared to state-of-the-art methods. © 2024 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Evading Detection Actively: Toward Anti-Forensics against Forgery Localization

arXiv

引用

arXiv 2023年

作者： Zhuo, Long Luo, Shenghai Tan, Shunquan Chen, Han Li, Bin Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen Institute of Artificial Intelligence and Robotics for Society China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Anti-forensics seeks to eliminate or conceal traces of tampering artifacts. Typically, anti-forensic methods are designed to deceive binary detectors and persuade them to misjudge the authenticity of an image. However, to the best of our knowledge, no attempts have been made to deceive forgery detectors at the pixel level and mis-locate forged regions. Traditional adversarial attack methods cannot be directly used against forgery localization due to the following defects: 1) they tend to just naively induce the target forensic models to flip their pixel-level pristine or forged decisions;2) their anti-forensics performance tends to be severely degraded when faced with the unseen forensic models;3) they lose validity once the target forensic models are retrained with the anti-forensics images generated by them. To tackle the three defects, we propose SEAR (Self-supErvised Anti-foRensics), a novel self-supervised and adversarial training algorithm that effectively trains deep-learning anti-forensic models against forgery localization. SEAR sets a pretext task to reconstruct perturbation for self-supervised learning. In adversarial training, SEAR employs a forgery localization model as a supervisor to explore tampering features and constructs a deep-learning concealer to erase corresponding traces. We have conducted large-scale experiments across diverse datasets. The experimental results demonstrate that, through the combination of self-supervised learning and adversarial learning, SEAR successfully deceives the state-of-the-art forgery localization methods, as well as tackle the three defects regarding traditional adversarial attack methods mentioned above. Copyright © 2023, The Authors. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

3DS: An Efficient DPDK-based Data Distribution Service for Distributed Real-time Applications

3DS: An Efficient DPDK-based Data Distribution Service for D...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Tianyu Xu Xianzhang Chen Changze Wu Jiapin Wang Rongwei Zheng Duo Liu Yujuan Tan Ao Ren Jian Li College of Computer Science Chongqing University Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China School of Electrical Engineering Chongqing University Chongqing China

Data Distribution Service (DDS) is a widely-used middleware for data transmission in distributed real-time applications, such as autonomous vehicles and robotics. However, the communication of existing DDS middlewares generally relies on the network stacks of the operating system, which brings long latency to the real-time applications. In this paper, we propose a DPDK-based DDS, dubbed 3DS, to improve the performance of communication of DDS middlewares. First, 3DS reduces the latency of communication between distributed real-time applications by avoiding the latency of kernel. Second, 3DS reduces the overhead of dynamic memory allocation and deallocation by a reserved memory pool. Finally, 3DS adopts a thread-exclusive CPU model to reduce the resource contention between threads. We implement and evaluate 3DS on real systems running Linux. The experimental results show that 3DS reduces 44% of the communication latency over FastDDS, which is the state-of-the-art DDS middleware used by ROS2. Moreover, the throughput of data transfer in 3DS can be 1.51 times that of FastDDS.

关键词： Three-dimensional displays Smart cities Instruction sets Distributed databases Throughput Real-time systems Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired feedback for spatial frequency aware artificial networks

Brain-inspired feedback for spatial frequency aware artifici...

引用

Asilomar Conference on Signals, Systems & computers

作者： Ramin Toosi Mohammad Ali Akhaee Mohammad-Reza A. Dehaqani School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Cognitive Systems Laboratory Control and Intelligent Processing Center of Excellence (CIPCE) School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran School of Cognitive Sciences Institute for Research in Fundamental Sciences (IPM) Tehran Iran

Spatial frequency (SF) is a characteristic of an image that could dissociate course and fine shape information. Physiological and psychophysical studies widely investigated the role of various SF contents in image processing. Inspired by the primate brain structure, deep neural networks improved various computer vision tasks such as image classification. Physiological studies show that low SF (LSF) contents of an image could be processed faster to provide feedback to facilitate object recognition. However, this knowledge has not been considered in designing neural network structures. This study introduces SFNet, a new neural network structure that employs an LSF-based feedback mechanism. SFNet is a two-stream structure where one stream is used for LSF processing to provide feedback for image classification. The other stream combines the LSF-based feedback and the HSF processing to form the final decision. The role of the proposed LSF-based feedback in image classification is investigated utilizing the CIFAR100 dataset. The results show that SFNet improves the performance in the presence of SF filtering compared to the equivalent structures.

关键词： Band-pass filters Visualization Shape Filtering Streaming media Visual systems Physiology

来源：评论

学校读者我要写书评

暂无评论

Flexi-Compression: A Flexible Model Compression Method for Autonomous Driving 11

Flexi-Compression: A Flexible Model Compression Method for A...

引用

11th ACM Symposium on Design and Analysis of Intelligent Vehicular Networks and Applications, DIVANet 2021

作者： Liu, Hantao He, Ying Richard Yu, F. James, Jeremy School of Information Technology Carleton University OttawaON Canada College of Computer Science and Software Engineering Shenzhen University Shenzhen Guangzhou China Carleton University OttawaON Canada Four DRobotics Corp OttawaON Canada

ISBN: (纸本)9781450390811

Benefiting from the rapid development of convolutional neural networks, computer vision-based autonomous driving technologies are gradually being deployed in vehicles. However, these neural networks typically have a large number of parameters and extremely high computational cost, making them difficult to deploy in autonomous vehicles with limited storage and computational power. In this paper, we propose an innovative model compression approach to compress convolutional neural networks in autonomous driving algorithms, which we call Flexi-Compression. Flexi-Compression first modifies the model structure by replacing the traditional convolutional layers with our proposed Flexi-CP module, thus reducing the computation of the convolutional layers. Then, we leverage knowledge distillation to enable the compressed model to quickly acquire the knowledge of the original model. In addition, we use a Flexi-Batch Normalization layer to prune the model and finally further reduce the model size by model quantization. We compress the VGG-16 network using our proposed model compression algorithm, which is a commonly used backbone network in autonomous driving algorithms. On the CIFAR-10 dataset, our compression method can reduce the parameters of the VGG-16 network by 86% and the computation by 87% with 4% loss of accuracy. To verify the effectiveness of our compression algorithm in real-world applications, we also compress an autonomous driving algorithm and achieve excellent performance. © 2021 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Non-Contact Heart Rate Measurement from Face Video Based on Group Sparse Representation

SSRN

引用

SSRN 2022年

作者： Ou, Weihua Chen, Longbao Han, Jie Xiong, Jiahao Zeng, Wu Gou, Jianping School of Big Data and Computer Science Guizhou Normal University Guiyang550025 China School of Electrical and Electronic Engineering Wuhan Polytechnic University Wuhan430000 China College of Computer and Information Science College of Software Southwest University Chongqing400715 China

Non-contact heart rate measurement based on face video is rapidly developed due to its comfortable and wide application. However, it is diffificult to extract the pulse signals for non-contact heart rate measurement due to the various interference factors, such as illumination variation, head motion and face expression. In this paper, we propose group sparse representation to reconstruct the pulse signals, then estimate the heart rate. The motivation is that the real heart rate is the same although the color variation of different facial skin regions are *** on this fact, we formulate the reconstruction of pulse signals as a group sparse representation problem and require the raw signals of all the sub-regions to be the similar sparse representation. Specififically, we use the face detection algorithm to obtain the region of interest (ROI) and divide it into sub-regions, followed by the distortioncompensation of color signals from different sub-regions. Then we extract the sub-region chrominance signals and select the high-quality chrominance signals to construct the raw pulse matrix. After that, we construct a mixed pulse dictionary containing discrete cosine bases and wavelet bases considering the pulse signal periodicity andpulsatility. Finally, we conduct group sparse representation to reconstruct the pulse signal and estimate the heart rate via spectral analysis. Experimental results on two public datasets show that this method outperforms most existing heart rate measurement methods. © 2022, The Authors. All rights reserved.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning

arXiv

引用

arXiv 2023年

作者： Si, Lingyu Dong, Hongwei Qiang, Wenwen Yu, Junzhi Zhai, Wenlong Zheng, Changwen Xu, Fanjiang Sun, Fuchun Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China College of Engineering Peking University China Department of Computer Science and Technology Tsinghua University China

Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks. However, research on why transferred knowledge works has not been extensively explored. To address this issue, in this paper, we discover the correlation between feature discriminability and dimensional structure (DS) by analyzing and observing features extracted from simple and hard tasks. On this basis, we express DS using deep channel-wise correlation and intermediate spatial distribution, and propose a novel cross-modal knowledge distillation (CMKD) method for better supervised cross-modal learning (CML) performance. The proposed method enforces output features to be channel-wise independent and intermediate ones to be uniformly distributed, thereby learning semantically irrelevant features from the hard task to boost its accuracy. This is especially useful in specific applications where the performance gap between dual modalities is relatively large. Furthermore, we collect a real-world CML dataset to promote community development. The dataset contains more than 10, 000 paired optical and radar images and is continuously being updated. Experimental results on real-world and benchmark datasets validate the effectiveness of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Learning Reconstructability for Drone Aerial Path Planning

arXiv

引用

arXiv 2022年

作者： Liu, Yilin Lin, Liqiang Hu, Yue Xie, Ke Fu, Chi-Wing Zhang, Hao Huang, Hui Shenzhen University China The Chinese University of Hong Kong China Simon Fraser University Canada College of Computer Science & Software Engineering Shenzhen University China

We introduce the first learning-based reconstructability predictor to improve view and path planning for large-scale 3D urban scene acquisition using unmanned drones. In contrast to previous heuristic approaches, our method learns a model that explicitly predicts how well a 3D urban scene will be reconstructed from a set of viewpoints. To make such a model trainable and simultaneously applicable to drone path planning, we simulate the proxy-based 3D scene reconstruction during training to set up the prediction. Specifically, the neural network we design is trained to predict the scene reconstructability as a function of the proxy geometry, a set of viewpoints, and optionally a series of scene images acquired in flight. To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning. We demonstrate that our data-driven reconstructability predictions are more closely correlated to the true reconstruction quality than prior heuristic measures. Further, our learned predictor can be easily integrated into existing path planners to yield improvements. Finally, we devise a new iterative view planning framework, based on the learned reconstructability, and show superior performance of the new planner when reconstructing both synthetic and real scenes. Copyright © 2022, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

A High-Resolution Approach for Dynamic Traffic Police Gestures Recognition Based on Spatial Context and Temporal Features Fusion

A High-Resolution Approach for Dynamic Traffic Police Gestur...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Jian He Shengsheng Jiang Xin Wei Cheng Zhang Ruihai Dong Beijing Engineering Research Center for IOT Software and Systems Beijing University of Technology Beijing China Faculty of Information Technology Beijing University of Technology Beijing China School of Computer Science University College Dublin Dublin Ireland

According to the requirement of recognizing traffic police gestures for driver assistance systems and intelligent vehicles, a universal model for dynamic traffic police gesture recognition is firstly introduced, of which can accurately present the spatial context (such as the relative lengths of skeletons, the angles between each skeleton w. r. t. gravity, and part features) of the traffic police gestures. Secondly, an architecture which can respectively extract spatial context and temporal features of dynamic traffic police gesture is proposed. Meanwhile, deep neural network and LSTM are introduced to build a high-resolution traffic police gestures recognizer (namely HRTPGR). At last, the open Police Gesture Dataset is used to train and test TPGR, and the experimental results show that the TPGR achieves a state-of-the-art accuracy with 98.7% for dynamic traffic police gestures recognition, and has strong anti-interference ability to light, background and gesture shape changes.

关键词：

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：