检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Signal, information and Data Processing, ICSIDP 2024

作者： Liu, Meiding Zhou, Zhengchun Shi, Qiao Li, Guyue Liu, Zilong Fan, Pingzhi Lee, Inkyu Southwest Jiaotong University School of Information Science and Technology Chengdu China Southeast University School of Cyber Science and Engineering Nanjing China University of Essex School of Computer Science and Electronics Engineering Colchester United Kingdom Southwest Jiaotong University Key Lab of Information Coding and Transmission Chengdu China Korea University School of Electrical Engineering Seoul Korea Republic of

ISBN: (纸本)9798331515669

In this paper, we consider the joint beamforming design in secure integrated sensing and communication (ISAC) systems, where the active eavesdropper intercepts the transmitted confidential information with an external passive eavesdropper. To improve the sensing performance while preventing the potential eavesdropping, the base station transmits a signal consisting of information symbols and sensing waveform, in which the sensing waveform is also used as artificial noise to interfere with eavesdroppers. Under this setup, we formulate the communication and sensing beamforming design problem, which aims to enhance the transmit beampattern performance, while ensuring the quality of service (QoS) of communication transmission and the secure communication constraint. Furthermore, we propose the semi-definite relaxation (SDR) algorithm to solve the non-convex problem. Numerical results demonstrate the effectiveness of the proposed scheme in both sensing and secure communication. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Classification and Segmentation of Brain MRI Images

Deep Learning Classification and Segmentation of Brain MRI I...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Pooja Ahuja, S. Likhith, S.R. Shiva Balan, A. Navya, K. Bengaluru India Bio-intelligence Lab Presidency University Department of School of Computer Science and Engineering and Information Science Bengaluru India Nagarjuna College of Engineering and Technology Department of Ise Bengaluru India

ISBN: (纸本)9798350317060

Unique Clinical pictures have a basic impact on the specialist's capability to the right conclusion and in the treatment of the patient. Diagnostic imaging can quickly identify lesions thanks to sophisticated algorithms, and it is essential to glean characteristics from photographs. In a number of studies, a number of algorithms have been incorporated into imaging in medicine. Using convolutional neural network, CNN's fundamental architecture is constructed using picture component extraction. To be able to circumvent the limitations imposed by both machine vision and human vision, the study is extended to include CNN with multiple input channels for visual feature extraction. This study uses approximately 3300 MRI samples from Kaggle to investigate four classifications: tumors of the pituitary gland, meningioma, glioma, and none. The implemented BrainNet has a accuracy of 98.31 percent and a validation accuracy of 87.80 percent. In order to determine which strategy performed better, deep architectures like InceptionNet and ResNet were also put through tests with or without learning through transfer. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

AegonKV: a high bandwidth, low tail latency, and low storage cost KV-separated LSM store with SmartSSD-based GC offloading 25

AegonKV: a high bandwidth, low tail latency, and low storage...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Zhuohui Duan Hao Feng Haikun Liu Xiaofei Liao Hai Jin Bangyu Li National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world *** this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/ software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Elastic Collision Based-Interactive Path Planning system for Vascular Intervention Robots

Elastic Collision Based-Interactive Path Planning System for...

引用

International Conference on Biomimetic Intelligence and Robotics & Medical Robotics Forum, ICBIR+MRF 2024

作者： Cao, Sheng Guo, Shuxiang Guo, Jian Wang, Jian Wang, Bin Ding, Mingchao Aerospace Center Hospital The Key Laboratory of Convergence Medical Engineering System and Healthcare Technology School of Life Science Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China Shenzhen Institute of Advanced Biomedical Robot Company Limited Guangdong Province Shenzhen518000 China Department of Electronic and Electrical Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

As population aging intensifies, the incidence of cardiovascular and cerebrovascular diseases has continued to rise. Vascular interventional surgery, known for its minimal trauma, rapid recovery, and clear effectiveness, requires doctors to perform procedures in radiation environments while wearing lead aprons. The advent of vascular intervention robots has provided a system-level solution to protect doctors from radiation and enhance outcomes. Currently, preoperative path planning for these robots predominantly relies on automatically generated paths, calculated by setting constraints and minimizing costs. However, this method lacks incorporation of physicians' expertise and consideration of elastic collision. Therefore, this study has designed an interactive path planning system for vascular intervention robot based on elastic collision. By establishing a simulation environment, doctors can use a manipulator to control virtual catheters and guidewires. While considering deformations, they maneuver the guidewire to the target position and record the current motion trajectory to guide the procedure in actual surgeries. Experimental tests have been conducted, confirming the system's effectiveness and feasibility. © 2024 The Authors.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Experimental measurement of bipartite entanglement using parameterized quantum circuits

引用

science China(Physics,Mechanics & Astronomy) 2022年第8期65卷 73-84页

作者： Shunzhong Xue Yulei Huang Dafa Zhao Chao Wei Jun Li Ying Dong Jiancun Gao Dawei Lu Tao Xin Gui-Lu Long State Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics Tsinghua UniversityBeijing100084China Shenzhen Institute for Quantum Science and Engineering and Department of Physics Southern University of Science and TechnologyShenzhen518055China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen518055China Research Center for Quantum Sensing Zhejiang LabHangzhou311121China Frontier Science Center for Quantum Information Beijing100084China Beijing National Research Center for Information Science and Technology Beijing100084China Beijing Academy of Quantum Information Sciences Beijing100193China

Entanglement in quantum systems plays a crucial role in various quantum information tasks. Measuring entanglement has been an important issue in both experiments and theories. In this work, we use parameterized quantum circuits(PQCs) to diagonalize density matrices of quantum states and obtain entanglement by only measuring the diagonal elements. With this method, full quantum state tomography can be bypassed, greatly reducing the number of measurements. A comprehensive characterization of entanglement was performed by using Rényi entropy and partially transposed moments. Mutual information, calculated from entropy is also used to characterize dynamical quantum phase transitions. We experimentally demonstrated the method on a four-qubit nuclear magnetic resonance quantum simulator. Our results agree with the theoretical descriptions. The measurement complexity of our PQC-based method grows linearly with the number of diagonal elements in the density matrix, a square root reduction over the full quantum tomography. The proposed method can have great potential in quantum systems with a large number of particles.

关键词： quantum information entanglement characterization quantum tomography

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model Combined with SVM and CNN for Community Content Classification 23

A Hybrid Model Combined with SVM and CNN for Community Conte...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data science and systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Ye, Yukui Xie, Xia Jin, Hai Wang, Duoqiang National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and Technology Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Hainan University Haikou China

ISBN: (纸本)9781665494571

Community websites bring many conveniences to people, and the classification of community content is playing an important role in website management and information searching. As the carrier of community content, posts are difficult to classify manually. According to the characteristics of community content, a hybrid classification model for machine learning is proposed. This model consists of three steps. Firstly, aiming at the problem of fewer features of posts, a weighted word vector is proposed to enrich the features of posts. Secondly, since the single kernel function of SVM can not completely match all data distributions, a mixed kernel function is employed to improve the model. Finally, in order to fully utilize the powerful feature extraction ability of Convolutional Neural Network as well as the classification ability of SVM, a hybrid model is designed and implemented by replacing softmax layer with SVM classifier. The corresponding experiment results indicate that compared with traditional Convolutional Neural Network, the proposed hybrid model has better performance and stability with classification accuracy improved from 0.9% to 1.4% in general. © 2021 IEEE.

关键词： Support vector machines Smart cities Support vector machine classification Machine learning Feature extraction Stability analysis Data models

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attack Detection Based on Example Semantics and Model Activation Features 5

Adversarial Attack Detection Based on Example Semantics and ...

引用

5th International Conference on Data science and information technology, DSIT 2022

作者： Chen, Jinyin Yu, Tianle Wu, Changan Zheng, Haibin Zhao, Wenhong Pang, Ling Li, Hu Institute of Cyberspace Security Zhejiang University of Technology Hangzhou China College of Information Engineering Zhejiang University of Technology Hangzhou China College of Information Engineering Jiaxing Nanhu University Zhejiang Jiaxing China Chinese National Key Laboratory of Science and Technology on Information System Security Shijiazhuang China Chinese National Key Laboratory of Science and Technology on Information System Security Gansu Dingxi China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

With the widespread application of deep learning technology, its security issue is also gradually paid attention to. To improve the security and reliability of deep learning technology in practical applications, we focus on the vulnerability of deep neural networks against adversarial attacks and address the problems of existing adversarial example detection algorithms that rely on pre-known attack types, and low detection efficiency, and high detection costs. In this paper, we propose an adversarial attack detection method based on sample semantics and model activation features to provide an effective solution sample semantics for the problems of attack dependence and uninterpretable detection results of detection methods. Firstly, normal examples are input into the deep model to obtain the semantic features and model activation features. Secondly, binary classification datasets are constructed separately to train the binary classifier and then divides by the binary classification detector for we construct the adversarial samples in two parts based on relevance features and model activation features to achieve the detection of adversarial samples. Finally, in the experiments, the detection rate against different attacks under different datasets reached higher than 93.00%. At the same time, the detection algorithm in this paper still maintains high performance in the case of the attacker's known detection algorithm, the average detection rate decreases by no more than 5%. © 2022 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

A Non-Calibration Nonlinear Errors Correction Method for Phase-Shifting Patterns

A Non-Calibration Nonlinear Errors Correction Method for Pha...

引用

Chinese Automation Congress (CAC)

作者： Yujie Zheng Bin Chen Shiqian Wu Institute of Robotics and Intelligent System School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

To reduce phase errors caused by nonlinear responses in the measurement system, we propose a non-calibration correction method for nonlinear errors in phase-shifting patterns. First, the captured grating fringes are transformed using a Fourier transform to convert the images from the gray scale to the frequency domain. The first harmonic frequency is then determined using an appropriate method. Second, the appropriate filter cutoff frequency is calculated by combining the phase-shift algorithm's sensitivity to different harmonics with frequency response curves. Low-pass filtering is then performed on the phase-shift patterns to suppress high frequencies caused by nonlinear responses, thus reducing phase errors in the actual measurement process. Finally, the standard plane and other irregularly shaped objects were reconstructed using the proposed method and other techniques. Measurement errors under different conditions were then compared. Experimental results show that the proposed method significantly suppresses gamma nonlinear responses and achieves high measurement accuracy and efficiency.

关键词： Optical filters Measurement errors Phase measurement Nonlinear distortion Measurement uncertainty Low-pass filters Optical distortion Harmonic analysis Distortion measurement Power harmonic filters

来源：评论

学校读者我要写书评

暂无评论

Two-color emissive AIEgens with anti-Kasha property for dual-organelle imaging and phototherapy

引用

science China Chemistry 2024年第5期67卷 1740-1752页

作者： Pu Chen Guogang Shan Qingli Nie Yuting Yan Pengfei Zhang Zujin Zhao Hai-Tao Feng Ben Zhong Tang AIE Research Center Shaanxi Key Laboratory of PhytochemistryCollege of Chemistry and Chemical EngineeringBaoji University of Arts and SciencesBaoji 721013China Institute of Functional Material Chemistry and National&Local United Engineering Lab for Power Battery Faculty of ChemistryNortheast Normal UniversityChangchun 130024China College of Chemistry&Materials Science Northwest UniversityXi’an 710127China Guangdong Key Laboratory of Nanomedicine CAS-HK Joint Lab of BiomaterialsCAS Key Laboratory of Biomedical Imaging Science and SystemShenzhen Engineering Laboratory of Nanomedicine and NanoformulationsCAS Key Lab for Health InformaticsShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China State Key Laboratory of Luminescent Materials and Devices Key Laboratory of Luminescence from Molecular Aggregates of Guangdong ProvinceSouth China University of TechnologyGuangzhou 510640China School of Science and Engineering Shenzhen Institute of Aggregate Science and TechnologyThe Chinese University of Hong KongShenzhen(CUHK-Shenzhen)Shenzhen 518172China

Despite the rapid development of probes for targeting single organelle, the construction of robust dual-organelle targeting probes with multicolor emission was rarely reported. Herein, two dual-emissive aggregation-induced emission luminogens(AIEgens)with donor-π-acceptor structures were designed and synthesized, namely QT-1 and QF-2. Both two AIEgens exhibited excitation wavelength-dependence defying the Kasha's rule, and could stain lipid droplets(LDs) and mitochondria in blue and red fluorescence, respectively. Moreover, thanks to the near-infrared emission and abundant reactive oxygen species(ROS) generation efficiency of QT-1, it was chosen as a photodynamic therapy agent to selectively kill cancer cells from normal cells. Upon light irradiation, an obvious decrease of mitochondrial membrane potential(MMP) and serious change of mitochondrial shape in cells were observed, which corresponded to the efficient inhibition of tumor growth in vivo. This work afforded a promising strategy for the construction of multicolor emission by tuning anti-Kasha behaviors and expanding their application in dualorganelle targeting-based phototheranostics.

关键词： aggregation-induced emission anti-Kasha luminescence fluorescent probe bioimaging photodynamic therapy

来源：评论

学校读者我要写书评

暂无评论

Number of Road Accidents Predicting Using Deep Learning-Based LSTM Development Models 11

Number of Road Accidents Predicting Using Deep Learning-Base...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Siswanto, Joko Hendry Rahardja, Untung Sembiring, Irwan Hartomo, Kristoko Dwi Purnomo, Hindriyanto Dwi Iriani, Ade Road Transportation System Engineering Politeknik Keselamatan Transportasi Jalan Tegal Indonesia Satya Wacana Christian University Faculty of Information Technology Salatiga Indonesia University of Raharja Faculty of Science and Technology Tangerang Indonesia

ISBN: (纸本)9798350305968

Road accidents cause chaos and state financial losses every year. Road accidents cannot be stopped but can be controlled with predictions. The existing road accident prediction model accuracy for the medium and long term still has many discrepancies, and it is rarely done. A comparison of the deep learning algorithms of the LSTM, Bi-LSTM, ConvLSTM, and Att-LSTM models with hidden layer variations is used to select the suitable model to make predictions. Use data from the road accident dataset in Thailand in 2011-2022, which can be accessed freely on Kaggle. The results show that the BiLSTM model with 4 hidden layers can predict the number of road accidents in the medium and long term with the highest accuracy. MSLE is used to measure the accuracy of the model with variations without hidden layers, 2 hidden layers, and 4 hidden layers to find the best model for predicting the number of road accidents for the medium and long term. © 2023 IEEE.

关键词： Forecasting

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：