检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Gao, Yuan Ma, Shiwei Liu, Jingjing School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China State Key Laboratory of ASIC and System School of Microelectronics Fudan University Shanghai201203 China

This paper proposes a multi-modal medical image fusion method based on multi-scale feature fusion and global feature extraction to alleviate the loss of detailed features and long-distance dependency that are easy to appear in the existing methods. The proposed method designs new multi-scale fusion CNN (Convolutional Neural Networks): two trunks and three branches are used to extract and fuse features at different scales, thus reducing the loss of information in the fusion process. Meanwhile, the proposed method designs a global feature extraction module based on Transformer, which is introduced to extract global features at different scales. The global feature loss is constructed between the fused and the input images to enhance the long-distance dependence and ensure continuity. In addition to global feature loss, the proposed method also designs boundary loss and content loss in the training objectives to retain different kinds of information as much as possible from the source images, thus improving the quality of the fused image in all aspects. Experimental results in open datasets show that the proposed method has better qualitative and quantitative performance than other state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A K-Band Voltage-Controlled Oscillator with Gate-Drain Phase Shift Achieving 110 kHz 1/f3 Corner

A K-Band Voltage-Controlled Oscillator with Gate-Drain Phase...

引用

IEEE Symposium on Radio Frequency Integrated Circuits (RFIC)

作者： Zhenhua Jia Dawei Ye State Key Laboratory of ASIC and System Fudan University China School of Integrated Circuits Huazhong University of Science and Technology China

ISBN: (数字)9798350359473

ISBN: (纸本)9798350359480

This work presents a K-band low flicker phase noise (1/f 3 ) corner voltage-controlled oscillator (VCO) utilizing gate-drain phase shift. It incorporates two auxiliary LC tanks to shift the relative phase of the fundamental harmonic between the gate-drain and attenuate the second harmonic components at the output waveform. This design effectively suppresses phase noise caused by flicker noise upconversion without compromising the desired 1/f 2 phase noise (PN) performance. By utilizing gate-drain phase shift to symmetrize the effective impulse sensitivity function (ISF), the proposed VCO achieves a 1/f 3 PN corner of 110kHz while consuming only 4.18mW at 19.64GHz. The design is implemented in a 65nm technology process with an active area of 0.1mm 2 . The measured phase noise at a 1MHz offset frequency is -113.21dBc/Hz, yielding a peak Figure-of-Merit (FoM) of 186.84dBc/Hz at 19.64GHz.

关键词： Phase noise Sensitivity Voltage fluctuations Voltage-controlled oscillators K-band Logic gates Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Memristor-based in-situ convolutional strategy for accurate braille recognition

引用

Science China Materials 2024年第12期67卷 3986-3993页

作者： Xianghong Zhang Congyao Qin Wenhong Peng Ningpu Qin Enping Cheng Jianxin Wu Yuyang Fan Qian Yang Huipeng Chen Institute of Optoelectronic Display National&Local United Engineering Lab of Flat Panel Display TechnologyFuzhou UniversityFuzhou 350002China Zhicheng College Fuzhou UniversityFuzhou 350002China Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou 350100China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433China

Signal processing has entered the era of big data,and improving processing efficiency becomes *** computing architectures face computational efficiency limitations due to the separation of storage and *** circuits based on multi-conductor devices enable full hardware convolutional neural networks(CNNs),which hold great potential to improve computational ***,when processing large-scale convolutional computations,there is still a significant amount of device redundancy,resulting in low computational power consumption and high computational ***,we innovatively propose a memristor-based in-situ convolutional strategy,which uses the dynamic changes in the conductive wire,doping area,and polarization area of memristors as the process of convolutional operations,and uses the time required for conductance switching of a single device as the computation result,embodying convolutional computation through the unique spiked digital signal of the *** strategy reasonably encodes complex analog signals into simple digital signals through a memristor,completing the convolutional computation at the device level,which is essential for complex signal processing and computational efficiency *** on the implementation of device-level convolutional computing,we have achieved feature recognition and noise filtering for braille *** believe that our successful implementation of convolutional computing at the device level will promote the construction of complex CNNs with large-scale convolutional computing capabilities,bringing innovation and development to the field of neuromorphic computing.

关键词： convolutional computing multi-conductor memristor conductive filaments

来源：评论

学校读者我要写书评

暂无评论

Automated and Agile Design of Layout Hotspot Detector via Neural Architecture Search

Automated and Agile Design of Layout Hotspot Detector via Ne...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Zihao Chen Fan Yang Li Shang Xuan Zeng State Key Lab of ASIC & System School of Microelectronics Fudan University Shanghai China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

This paper presents a neural architecture search scheme for chip layout hotspot detection. In this work, hotspot detectors, in the form of neural networks, are modeled as weighted directed acyclic graphs. A variational autoencoder maps the discrete graph topological space into a continuous embedding space. Bayesian Optimization performs neural architecture search in this embedding space, where an architecture performance predictor is employed to accelerate the search process. Experimental studies on ICCAD 2012 and ICCAD 2019 Contest benchmarks demonstrate that, the proposed scheme significantly improves the agility of previous neural architecture search schemes, and generates hotspot detectors with competitive detection accuracy, false alarm rate, and inference time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TOTAL: Topology Optimization of Operational Amplifier via Reinforcement Learning

TOTAL: Topology Optimization of Operational Amplifier via Re...

引用

IEEE International Symposium on Quality Electronic Design

作者： Zihao Chen Songlei Meng Fan Yang Li Shang Xuan Zeng State Key Lab of ASIC & System School of Microelectronics Fudan University Shanghai China China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

With ever-increasing design complexity and stringent time-to-market pressure, automated topology synthesis tools for operational amplifiers are required to produce designs meeting different specifications. This paper proposes TOTAL, a reinforcement learning-based topology optimization method for operational amplifiers. We decompose the circuit topology design as a Markov decision process to solve the high dimensionality of the design space, with the three-stage cascode paradigm fixed to avoid meaningless structures. Therefore, starting from a basic behavior-level topology, an agent modifies the circuit step by step. Specifically, this agent mainly adopts a graph neural network to understand each design state, including specifications and the design history, and a convolutional neural network to modify the current topology. Every completed circuit is then simulated and evaluated by a customized reward function to guide the agent in finding qualified circuits, among which only the optimal one ever recorded is mapped to the transistor level for further evaluation. Experimental results show that the trained agent can not only generate high-performance circuits, but also be reusable by transferring to other specifications as a pre-trained model and achieving competitive results.

关键词： Operational amplifiers Circuit topology Network topology Optimization methods Reinforcement learning Markov processes Topology

来源：评论

学校读者我要写书评

暂无评论

Flexible EEG Electrodes with Embedded Pressure Sensors and Customized Interface Towards Comfortable Home EEG Monitoring

Flexible EEG Electrodes with Embedded Pressure Sensors and C...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Yizhou Jiang Jialong Zhang Hongjie Chen Chen Chen Jiaxin He Yajie Qin School of Information Science and Technology and State Key Laboratory of ASIC and System Fudan University Shanghai China

To realize stable and comfortable dry electroencephalography (EEG) recording for home healthcare, a flexible pressure-sensitive electrode (PSE) is proposed, and a dedicated multi-channel pressure sensor interface is developed. The PSE monitors the pressure on the electrode during continuous EEG recording. With the PSE, stable but comfortable electrode-skin contact can be achieved. The analog front-end of the sensor interface is fabricated in 180-nm CMOS, occupying an active area of 0.25 mm 2 . The flexible sensor exhibited a -2.5 kΩ/kPa sensitivity. The sensor interface enjoyed a large stimulus range of up to 2.65 mApp and showed a resolution of 0.047 – 8.0 mΩ/√Hz. It is digital-compatible, reconfigurable, and area-efficient, which can be migrated into various EEG acquisition integrated circuits and systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Latent space active learning with message passing neural network: The case of HfO2

引用

Physical Review Materials 2024年第10期8卷 103804页

作者： Xinjian Ouyang Zhilong Wang Xiao Jie Feng Zhang Yanxing Zhang Laijun Liu Dawei Wang School of Microelectronics and State Key Laboratory for Mechanical Behavior of Materials Key Lab of Micro-Nano Electronics and System Integration of Xi'an City School of Physics Key Laboratory of Nonferrous Materials and New Processing Technology Ministry of Education and College of Materials Science and Engineering

Due to their excellent abilities, machine learning potential models have shown significant promise in accurately constructing potential energy surfaces for various materials. As a data-driven approach, however, the training of these models necessitates carefully curated datasets to be effective. In this paper, we propose an active learning scheme for message passing neural networks (MPNNs). This method leverages the latent distance in the descriptor space, inherently generated by MPNNs, to quantify model uncertainty. Additionally, we employ CUR matrix decomposition for sample selection to reduce data redundancy. We demonstrate the application of this method on HfO2, a complex ferroelectric material with many phases, by investigating its static properties, phonon spectrum, and notably, structural phase transitions. We also demonstrate the reliability of latent distance as a model uncertainty metric. Utilizing latent space distance, the proposed method enriches active learning frameworks for machine learning potentials, providing an efficient alternative to traditional methods, such as the “query by committee” approach.

关键词： Potential energy surfaces Fluorite structure Density functional theory Machine learning

来源：评论

学校读者我要写书评

暂无评论

An integrated strategy towards the facile synthesis of core-shell SiC-derived carbon@N-doped carbon for high-performance supercapacitors

引用

Journal of Energy Chemistry 2021年第5期30卷 512-521页

作者： Zhongya Pang Guangshi Li Xingli Zou Chenteng Sun Conghui Hu Wei Tang Li Ji Hsien-Yi Hsu Qian Xu Xionggang Lu State Key Laboratory of Advanced Special Steel&Shanghai Key Laboratory of Advanced Ferrometallurgy&School of Materials Science and Engineering Shanghai UniversityShanghai 200444China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433China School of Energy and Environment&Department of Materials Science and Engineering City University of Hong KongKowloon Tong 999077Hong KongChina Shenzhen Research Institute of City University of Hong Kong Shenzhen 518057GuangdongChina

Porous active core-shell carbon material with excellent synergistic effect has been regarded as a prospective material for ***,we report an integrated method for the facile synthesis of carbide-derived carbon(CDC)encapsulated with porous N-doped carbon(CDC@NC)towards highperformance ***(PDA)as nitrogen and carbon sources was simply coated on SiC nanospheres to form SiC@PDA,which was then directly transformed into CDC@NC via a onestep molten salt electro-etching/in-situ doping *** synthesized CDC@NC with hierarchically porous structure has a high specific surface area of 1191 m^(2) g^(-1).The CDC core and NC shell are typical amorphous carbon and more ordered N-doped carbon,*** from its unique dual porous structures,the CDC@NC demonstrates high specific capacitances of 255 and 193 F g^(-1) at 0.5 and20 A g^(-1),*** reaction mechanism of the electro-etching/in-situ doping process has also been investigated through experimental characterizations and theoretical density functional theory *** is suggested that the molten salt electro-etching/in-situ doping strategy is promising for the synthesis of active core-shell porous carbon materials with synergistic properties for supercapacitors without the need for additional doping/activation processes.

关键词： Molten salt Electrochemical etching Core-shell structure Porous carbon In-situ nitrogen doping Supercapacitors

来源：评论

学校读者我要写书评

暂无评论

HierSyn: Fast Synthesis for Large Hierarchical Designs

HierSyn: Fast Synthesis for Large Hierarchical Designs

引用

International Conference on asic

作者： Yishan Zhang Zhiyong Zhang Chang Wu School of Microelectronics State-Key Lab of ASIC and System Fudan University Shanghai China Shanghai Fudan Microelectronics Group Co. Ltd Shanghai China

As design goes into multi-billion transistors, the synthesis runtime becomes an important issue, particularly for design verification and prototyping, as one may run the synthesis many times with design change. Module-by-module synthesis with multi-threading is a natural solution for fast synthesis, however, at the cost of quality of results (QoR) degradation. Besides, multi-thread speedup may not be so good due to very uneven sizes of the modules. In this paper, we propose a design hierarchy restructuring based multi-thread synthesis algorithm for large-scale designs. Small module flattening and large module partitioning are used to create moderate size design modules. Our experimental results show that our algorithm can produce results within 3% area increase and 21.3x speedup over the flat synthesis flow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Double Side Interfacial Optimization for Low-Temperature Stable CsPbI_(2)Br Perovskite Solar Cells with High Efficiency Beyond 16%

引用

Energy & Environmental Materials 2022年第2期5卷 637-644页

作者： Jing Ma Jie Su Zhenhua Lin Jian He Long Zhou Tao Li Jincheng Zhang Shengzhong Liu Jingjing Chang Yue Hao State Key Discipline Laboratory of Wide Band Gap Semiconductor Technology Shaanxi Joint Key Laboratory of GrapheneSchool of MicroelectronicsXidian UniversityXi’an 710071China Advanced Interdisciplinary Research Center for Flexible Electronics Xidian UniversityXi’an 710071China Centre for Spintronics and Quantum System State Key Laboratory for Mechanical Behavior of MaterialsSchool of Materials Science and EngineeringXi’an Jiaotong UniversityXi’an 710049China Key Laboratory of Applied Surface and Colloid Chemistry National Ministry of Education Shaanxi Engineering Lab for Advanced Energy TechnologySchool of Materials Science and EngineeringShaanxi Normal UniversityXi’an 710119China

CsPbI_(2)Br perovskite solar cells have achieved rapid development owing to their exceptional optoelectronic properties and relatively outstanding ***,open-circuit voltage(Voc)loss caused by band mismatch and charge recombination between perovskite and charge transporting layer is one of the crucial obstacles to further improve the device ***,we proposed a bilayer electron transport layer ZnO(bottom)/SnO_(2)(top)to reduce the Voc loss(Eloss)and promote device Voc by ZnO insert layer thickness modulation,which could improve the efficiency of charge carrier extraction/transfer and suppress the charge carrier *** addition,guanidinium iodide top surface treatment is used to further reduce the trap density,stabilize the perovskite film and align the energy levels,which promotes the fill factor,short-circuit current density(Jsc),and stability of the *** a result,the champion cell of double-side optimized CsPbI_(2)Br perovskite solar cells exhibits an extraordinary efficiency of 16.25%with the best Voc as high as 1.27 V and excellent thermal and storage stability.

关键词： CsPbI_(2)Br dual interfacial optimization high performance low temperature perovskite solar cells

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：