检索结果-内蒙古大学图书馆

IEEE NW Russia Young Researchers in Electrical and Electronic engineering Conference (EIConRusNW)

作者： Hein Htet Zaw Khant Zin Win Evgeniy M. Portnov Institute of System and Software Engineering and Information Technologies National Research University of Electronic Technology Zelenograd Moscow Russia

The article substantiates the need to use neural network algorithms to search for mature crops and optimize harvesting equipment routes based on the data obtained. A technique for detecting fruit maturity based on the use of neural network technologies has been developed. The experiments have shown that the accuracy of the neural network algorithm developed in this dissertation work significantly exceeds the standard YOLOv4 neural networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Autoregressive Sign Language Translation: A Transformer Encoder-only Approach for Enhanced Multimodal Integration 24

Non-Autoregressive Sign Language Translation: A Transformer ...

引用

2024 International Conference on Advanced Robotics, Automation engineering and Machine Learning, ARAEML 2024

作者： Du, Yao Xie, Pan Peng, Taiying Hu, Xiaohui School of Automation Science and Electrical Engineering Beihang University Beijing China Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400717116

Sign language translation aims to transform continuous sign language videos into text, thereby mapping sign language actions onto natural language. Current research primarily focuses on the Transformer's encoder-decoder architecture, employing an autoregressive (AR) approach for SLT. This one-by-one token generation method has a slow speed to translate. We design a Non-Autoregressive Sign Language Translation (NA-SLT) model based on Transformer Encoder. The proposed model consists of three components: The text-encoder, sign-encoder, and sign-Text-encoder. Both the text-encoder and sign-encoder utilize the Encoder to model single-modality data. The sign-Text-encoder effectively engages with multi-modal data, producing high-quality corresponding text after minimal refinement iterations. Moreover, during model training, we devise a double-mask strategy. In addition to traditional random masking, the schedule allocates mask probabilities based on each word's frequency, ensuring long-Tail tokens have an increased chance of being masked and receiving extensive training. We evaluate the model on PHOENIX-2014T, and the results indicate that NA-SLT approaches the performance of AR models on BLEU (21.06) and ROUGE(49.59) metrics while significantly improving translation speed (5.4x-7.9x). © 2024 ACM.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Quadrature Demodulation as a Technique to Measure Signal Parameters with Increased Accuracy 34

Quadrature Demodulation as a Technique to Measure Signal Par...

引用

34th International Scientific Symposium Metrology and Metrology Assurance, MMA 2024

作者： Krylovich, Anna A. Podobuev, Sergey A. Loginov, Vadim A. Zolkin, Dmitry S. Serov, Nikolay A. Serov, Andrey N. National Research University 'Moscow Power Engineering Institute' Diagnostic Information Technologies Department Moscow Russia National Research University 'Moscow Power Engeneering Institute' Computer Engineering Department Moscow Russia Division for Design of Information Retrieval System Moscow Russia

ISBN: (纸本)9798350352832

To solve modern problems related to spectrum measurement, the most common use of discrete Fourier transform algorithms. The main problem of using these algorithms is associated with the so-called 'spectrum leakage' effect, the occurrence of which limits the maximum achievable accuracy from the point of view of the methodological component of the error. An alternative solution to the spectrum measurement problem is to use a quadrature demodulator. The approach itself has great potential in terms of the final accuracy achieved. The use of additional modifications discussed in the paper can further improve it. The paper discusses the advantages and disadvantages of all the considered modifications, and obtains analytical expressions that allow us to estimate the final achievable error. An assessment of possible influencing quantities was carried out and their influence on the measurement errors of amplitude, initial phase and frequency was assessed. Considerations are given for developing a simulation model of such a demodulator and its modifications under consideration. A ready-made model which is performed in Simulink environment is presented. The correctness of the obtained analytical relationships was checked by comparing the results of simulation modeling and analytical calculations. © 2024 IEEE.

关键词： Demodulators

来源：评论

学校读者我要写书评

暂无评论

Optimizing piezoelectric performance of complex perovskite through increasing diversity of B-site cations

引用

Journal of Materials Science & Technology 2024年第3期170卷 78-86页

作者： Mengdi Cheng Dongyan Zhang Yangxi Yan Zhimin Li Pangpang Wang Ri-ichi Murakami School of Advanced Materials and Nanotechnology Xidian UniversityXi’an 710126China Nanomaterials Group Institute of SystemInformation Technologies and Nanotechnologies(ISIT)Fukuoka Industry-Academia Symphonicity(FiaS)4-1 KyudaishinmachiNishi-kuFukuoka 819-0388Japan School of Mechanical Engineering Chengdu UniversityChengdu 610106China

Piezoelectric materials with unique properties are hugely appealing for high sensitivity sensors and ultrasonic ***,Pb(Ni_(1/3)Nb_(2/3))O_(3)-Pb(Yb_(1/2)Nb_(1/2))O_(3)-PbTiO_(3)piezoelectric system was designed and investigated in *** optimized piezoelectric response(d_(33)=826 pC/N,d_(33)∗=1017 pm/V)together with good temperature stability and negligible performance degradation up to 10^(6) cycles was achieved in 0.58PNN-0.10PYN-0.32PT *** analysis revealed the amplification of intrinsic and extrinsic contributions in MPB region due to more spontaneous polarization orientations and an increase in chemical disorder of system after the introduction of *** origin of high piezoelectric response was investigated through the combination of scanning electron microscopy and piezoresponse force *** diversity of B-site cations was shown to enhance local structural heterogeneity,weaken long-range ferroelectric ordered domains,and lower free energy barrier via the formation of nanodomain configuration that promoted polarization rotation,thereby improving piezoelectric properties of the ***,it is suggested that increasing the diversity of B-site cations is an effective strategy for achieving outstanding piezoelectric performance.

关键词： PNN-PYN-PT ceramics Piezoelectricity enhancement Relaxation behavior Domain structure

来源：评论

学校读者我要写书评

暂无评论

Empowering Deaf Children with Sinhala Sign Language, Emotion Detection, and Sound Recognition 5

Empowering Deaf Children with Sinhala Sign Language, Emotion...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Fernando, W.H.K. Perera, P.L.D.N. Fernando, M.I.N. Gunasekara, P.T.E.W. Fernando, Harinda De Zoysa, Rivoni Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This study describes a broad endeavor to use cutting-edge technologies to empower deaf primary school students in Sri Lanka. Three key elements make up the study: a sound recognition and classification system, an Android software for translating gestures in Sinhala Sign Language (SSL), and a mobile app for emotion recognition and text-tospeech in Sinhala. By promptly alerting caregivers to potential dangers, the sound recognition technology secures the security of deaf children at home, providing an invaluable layer of security. The Android software bridges the communication gap and improves family interactions by translating SSL gestures captured by the device's camera into textual representations. This promotes successful communication between deaf children and their parents. Convolutional Neural Networks (CNNs) are used in the mobile application to detect and understand emotions based on facial expressions. This enables non-verbal youngsters to communicate successfully through Sinhala textto-speech output with adaptive tone modulation. This research aims to build a caring and inclusive atmosphere, enabling increased independence and enhanced communication skills in deaf children by combining these advances. The suggested solutions could significantly improve the lives of deaf kids, providing them with opportunities for better learning, social interaction, and emotional health. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Establishing Pattern Sequences Using Artificial Neural Networks with an Application to Organizational Patterns 10

Establishing Pattern Sequences Using Artificial Neural Netwo...

引用

10th Workshop on software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Matovič, Viktor Vranić, Valentino Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava Ilkovičova 2 Bratislava84216 4 Slovakia

Explicit relationships included in textual description of patterns are insufficient to establish pattern sequences. This article brings a new method of establishing pattern sequences using artificial neural networks. The method is based on extracting implicit relationships between organizational patterns using the softmax regression model by Zhang et al., which are learned by the artificial neural network and encoded in its weights. The implementation of the method is based on the mini-batch stochastic gradient descent method by Zhang et al. and the Keras application programming interface of the TensorFlow framework. To evaluate the method, we conducted four experiments on selected organizational patterns documented by Coplien and Harrison. Two pattern sequences were established in each experiment. For each pattern sequence, a pattern story was created in order to check its meaningfulness. © 2023 Copyright for this paper by its authors.

关键词： artificial neural networks organizational pattern pattern relationships pattern sequence softmax regression

来源：评论

学校读者我要写书评

暂无评论

Half space object classification via incident angle based fusion of radar and infrared sensors

引用

Journal of systems engineering and Electronics 2022年第5期33卷 1025-1031页

作者： HE Zhenyu ZHUGE Xiaodong WANG Junxiang YU Shihao XIE Yongjun ZHAO Yuxiong School of Electronic Information and Engineering Beihang UniversityBeijing 100191China Beijing Institute of Electronic System Engineering Beijing 100854China Beijing Institute of Astronautical Systems Engineering Beijing 100076China Shenzhen Institute of Beihang University Shenzhen 518038China School of Software Beihang UniversityBeijing 100191China

In this paper,we introduce an incident angle based fusion method for radar and infrared sensors to improve the recognition rate of complex targets under half space scenarios,e.g.,vehicles on the ground in this *** radar sensors,convolutional operation is introduced into the autoencoder,a“winner-take-all(WTA)”convolutional autoencoder(CAE)is used to improve the recognition rate of the radar high resolution range profile(HRRP).Moreover,different from the free space,the HRRP in half space is more *** order to get closer to the real situation,the half space HRRP is simulated as the *** recognition rate has a growth more than 7%com-pared with the traditional CAE or denoised sparse autoencoder(DSAE).For infrared sensor,a convolutional neural network(CNN)is used for infrared image ***,we com-bine the two results with the Dempster-Shafer(D-S)evidence theory,and the discounting operation is introduced in the fusion to improve the recognition *** recognition rate after fusion has a growth more than 7%compared with a single *** the discounting operation,the accuracy rate has been improved by 1.5%,which validates the effectiveness of the proposed method.

关键词： convolutional autoencoder(CAE) half space high-resolution range profile(HRRP) incident angle based fusion tar-get recognition

来源：评论

学校读者我要写书评

暂无评论

Code Based Selected Object-Oriented Mechanisms Identification 10

Code Based Selected Object-Oriented Mechanisms Identificatio...

引用

10th Workshop on software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Jablonický, Kristián Lang, Ján Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava Ilkovičova 2 Bratislava842 16 4 Slovakia

This article deals with select mechanisms that are provided by the object-oriented programming language Java. Using these mechanisms is crucial for a proper approach to object-oriented programming. However, this is often difficult for many programmers that are new to writing code in the said language. This paper looks at these mechanisms, defines them by quoting various sources, and proposes a solution that spots these described mechanisms in code. It does so by reading source code from .java files inputted by its user, gathering information about the defined and used classes, interfaces, methods, etc. With this information gained it outputs data which would often require a larger context of the code and good knowledge of the files’ contents. Thanks to the strict definitions and rules, that will be stated later in this paper, the application can consistently spot these mechanisms in code and inform its user about the fact. As a result, the application can help programmers that are new to object-oriented programming languages by ensuring them, that they implemented these mechanisms correctly, or by informing them about their absence. The core mechanisms described in this paper are inheritance, encapsulation, class association, and polymorphism. © 2023 Copyright for this paper by its authors.

关键词： class association encapsulation inheritance Java object-oriented polymorphism programming refactoring

来源：评论

学校读者我要写书评

暂无评论

DRDnet22: Advanced convolutional techniques for early diabetic retinopathy detection in retinal images 15

DRDnet22: Advanced convolutional techniques for early diabet...

引用

15th International Conference on Computing Communication and Networking technologies, ICCCNT 2024

作者： Mazumder, Md. Sakib Ali Shamrat, F M Javed Mehedi Mahmud, Imran Sharmin, Sharmin Hossain, Tanzim Biplab, Ekramul Kabir Daffodil International University Department of Software Engineering Dhaka Bangladesh Universiti Malaya Department of Computer System and Technology Kuala Lumpur Malaysia Institute of Information Technology University of Dhaka Dhaka Bangladesh

ISBN: (纸本)9798350370249

Diabetic Retinopathy (DR) is a prevalent eye complication among individuals with diabetes. Early detection of DR can prevent vision loss and lower associated problems. Manual diagnosis via retinal fundus images requires the expertise of medical professionals to assess several complex characteristics, including visual acuity tests, pupil dilation, and optical consistency tomography. The process is challenging, time-consuming, and prone to errors. This paper proposes a deep learning (DL) technique, DRDnet22, to detect and categorize DR into five distinct stages. The APTOS 2019 dataset is utilized in this study, which contains 3662 images. The study employs dense block and transition layer with global average pooling (GAP) techniques, and the combination of distinct Convolutional Networks (ConvNets) results in an enhanced representation beyond the utilization of features from a single ConvNet alone. To conduct an ablation analysis, the conventional pre-trained model's performance was compared. The performance evaluation points out that the proposed model achieved 81.6% accuracy, which is an advantage over other DCNN models. Despite facing a few inaccuracies, the model's competence in spotting vital features underscores its diagnostic potential. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Matrix Based Approach to Structural and Semantic Analysis Supporting software Product Line Evolution 10

Matrix Based Approach to Structural and Semantic Analysis Su...

引用

10th Workshop on software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Perdek, Jakub Vranić, Valentino Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava Ilkovičova 2 Bratislava842 16 4 Slovakia

The evolution of product families is complex due to the exponential growth of new products with a modified codebase. It is caused by the introduction of new such important or restrictive features that allow transforming an existing solution into a new product as the basis for another one. Specifically, both the structure of resulting components and semantic information need to be taken into account to provide in-depth supporting materials by capturing feature interactions and their capabilities. Additionally, data from heterogeneous applications usually differ and their handling needs account for different scoring. We tackled these problems by creating various supporting views based on structural and semantic information. Related applications are modeled as graphs, also instances of their components are optionally included, and various matrix based algorithms based on similarity metrics are integrated. The final integrated and automated approach is efficient because it runs in polynomial time, is extensively focused on dependencies/connections between nodes, can be adapted to big data, and is extendable and enhanced to support different metrics. Its capability to organize analyzed parts into hierarchies by applying hierarchic clustering helps to specify the context to support comprehension or find a related position of features based on their interaction, especially their coupling. With regards to possible design issues, each updated product should be checked by an expert or more autonomously against performed predictions, especially its complexity and coupling between components. Additionally, extendability can be measured from the chosen sequence of such updates. An approach including an automated matrix based feature recognition process is presented in the analysis of modular Angular applications. Our future work will be more focused on semantic enhancements, and its applications on big data by generating and analyzing various types of fractals including extracte

关键词： feature modeling feature trees graph comparison hierarchical clustering matrix clustering

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：