检索结果-内蒙古大学图书馆

REFD:recurrent encoder and fusion decoder for temporal knowledge graph reasoning

APPLIED INTELLIGENCE 2025年第6期55卷 1-21页

作者： Liu, Qian Feng, Siling Huang, Mengxing Bhatti, Uzair Aslam Coll Informat & Commun Engn 58 Renmin Ave Haikou 570100 Hainan Peoples R China

Reasoning over Temporal Knowledge Graphs (TKGs) presents challenges in modeling the dynamic relationships and evolving behaviors of entities and relations over time. Traditional approaches often treat entities and relations separately, which limits their ability to capture their joint temporal evolution and interactions. To overcome these limitations, REFD (Recurrent encoder and Fusion Decoder) is proposed, a novel framework designed to improve TKG reasoning. The REFD framework consists of two primary components: a recurrent encoder and a fusion decoder. The recurrent encoder incorporates three key modules: (1) the full-domain multi-scale temporal recurrent encoder, which effectively captures temporal dependencies across varying time scales, (2) the entity-relation symbiotic temporal feature deep fusion engine, which integrates temporal features of both entities and relations, and (3) the intelligent temporal feature priority dynamic adjustment mechanism, which adaptively adjusts the importance of different features over time. The fusion decoder, particularly the entity-relation feature Fusion Decoder, combines the temporal features of entities and relations to model their joint evolution, overcoming the limitations of previous methods that model them separately. By jointly capturing the evolving dynamics of entities and relations over time, REFD significantly enhances the accuracy of temporal reasoning tasks. Experimental results show that REFD outperforms existing approaches, offering superior prediction accuracy and better handling of the complexities in TKGs.

关键词： Temporal knowledge graph Knowledge graph encoder Decoder

来源：评论

学校读者我要写书评

暂无评论

Abstractive Text Summarization for Legal Documents Using Optimization-Based Bi-LSTM with encoder-Decoder Model

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2025年

作者： Aggarwal, Deepti Sharma, Arun Indira Gandhi Delhi Tech Univ Women IT Dept New Delhi 110006 Delhi India

In recent years, the amount of textual data has grown quickly, creating a useful resource for information extraction and analysis. Due to the high complexity and unstructured nature of legal documents, automated text summarizing (ATS) is a necessary but difficult process. ATS is a technique that uses computer power to summarize lengthy paragraphs quickly. Summarizing the extensive materials manually is a highly difficult and time-consuming operation for people. As a result, an optimization-based deep learning (DL) model for abstract summarization is presented in the paper (AS). The proposed working procedure is broken down into three stages. They are text pre-processing, feature extraction, and abstractive summary categorization. The dataset is first placed through a pre-processing process, including stop word removal, tokenization, lemmatization, and stemming. The words and phrases are then represented in vector format throughout the feature extraction phase, which is handled by the NumberBatch (a combination of Enhanced GloVe Model (EGM), Enhanced FastText (EFT), and word2vector). To produce the abstractive text summary, the features obtained from the Numberbatch are fed into the DL model Bi-LSTM-based encoder-decoder with attention model. The metaheuristic optimization Honey Badger algorithm (HBA) is employed to optimize the network weights. This would increase the effectiveness of creating summaries based on ROUGE scores, and the proposed Bi-LSTM-HBA model performs better than currently used methods.

关键词： Feature extraction pre-processing encoder decoder abstractive summary optimization Bi-LSTM attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A tunable encoder with circular dichroism and polarization encoding function based on a layered metastructure in the GHz range

引用

MATERIALS & DESIGN 2025年 250卷

作者： Wu, Chuan-Qi Sui, Jun-Yang Chen, Qi Tang, Xing-Zhou Zhang, Hai-Feng Nanjing Univ Posts & Telecommun Coll Elect & Opt Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Flexible Elect Future Technol Nanjing 210023 Peoples R China

In this paper, based on a layered metastructure, a tunable encoder capable of circular dichroism (CD) and polarization conversion (PC) is researched, which contains one common medium, magnetized plasma, and yttrium iron garnet (YIG). The linear polarization waves (LPWs) are elected as incident waves. The incident angle and external magnetic field intensity are theta and H O . A modulable dielectric layer (MDL), composed of YIG, is optionally added to the preceding item of the given metastructure, which owns a certain thickness. By adjusting the proper theta , H O , and adding the MDL, the CD can be obtained at a certain frequency point, where the righthanded circular polarization waves (CPWs) and left-handed CPWs have different reflections. Meanwhile, the LPWs can be converted to CPWs or other polarization waves in a specific frequency band. Furthermore, the theta and addition of the MDL are considered as the first and second logic levels, respectively, to form four logic codes, which can realize the PC from LPWs to CPWs or LPWs within the same specific frequency band. Hence, the designed encoder has a promising potential in the precise control of PC in the special bandwidth, which can provide excellent support for the research of tunable and diverse polarization splitters and selectors.

关键词： Polarization conversion Circular dichroism encoder Yttrium iron garnet Magnetized plasma Layered metastructure

来源：评论

学校读者我要写书评

暂无评论

TBE-Net: A Deep Network Based on Tree-Like Branch encoder for Medical Image Segmentation

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第1期29卷 521-534页

作者： Yang, Shukai Zhang, Xiaoqian He, Youdong Chen, Yufeng Zhou, Ying Southwest Univ Sci & Technol Sch Informat Engn Mianyang 621010 Peoples R China Univ Elect Sci & Technol China Mianyang Cent Hosp Sch Med Mianyang 621000 Peoples R China MIANYANG Cent Hosp NHC Key Lab Nucl Technol Med Transformat Mianyang 621000 Peoples R China

In recent years, encoder-decoder-based network structures have been widely used in designing medical image segmentation models. However, these methods still face some limitations: 1) The network's feature extraction capability is limited, primarily due to insufficient attention to the encoder, resulting in a failure to extract rich and effective features. 2) Unidirectional stepwise decoding of smaller-sized feature maps restricts segmentation performance. To address the above limitations, we propose an innovative Tree-like Branch encoder Network (TBE-Net), which adopts a tree-like branch encoder to better perform feature extraction and preserve feature information. Additionally, we introduce the Depth and Width Expansion (DWE) module to expand the network depth and width at low parameter cost, thereby enhancing network performance. Furthermore, we design a Deep Aggregation Module (DAM) to better aggregate and process encoder features. Subsequently, we directly decode the aggregated features to generate the segmentation map. The experimental results show that, compared to other advanced algorithms, our method, with the lowest parameter cost, achieved improvements in the IoU metric on the TNBC, PH2, CHASE-DB1, STARE, and COVID-19-CT-Seg datasets by 1.6%, 0.46%, 0.81%, 1.96%, and 0.86%, respectively.

关键词： Decoding Feature extraction Image segmentation Medical diagnostic imaging Semantics Computer architecture Bioinformatics Transformers Focusing Accuracy Medical image segmentation encoder decoder tree-like branch deep aggregation

来源：评论

学校读者我要写书评

暂无评论

Numerical Investigation of 4 x 2 encoder and 2 x 4 Decoder Using Phononic Crystal Based Ring Resonator for Acoustic Applications

引用

JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES 2025年第1期13卷 1-11页

作者： Bin, Arka Roy Yakkala, Bhaskarrao Rakshit, Jayanta Kumar Nagaraju, V. Hossain, Manjur Kumar, Dhiraj Natl Inst Technol Agartala Dept Elect & Instrumentat Engn Agartala 799046 India Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Elect & Commun Engn Chennai 602105 India Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Comp Sci & Engn Chennai 602105 India

PurposeThis study aims to propose a novel design for a 4 x 2 encoder and its corresponding 2 x 4 decoder using two-dimensional phononic crystal ring resonator (PnC-RR).MethodsThe proposed encoder/decoder structure is based on acoustic waveguides and crystal ring resonator cavities, operating at a specific frequency of 45.1 kHz. The two-dimensional design employs a square lattice configuration comprising a rectangular mercury base and cylindrical water rods. The performance of the design is evaluated using key parameters such as Contrast Ratio, Extinction Ratio, and Insertion Loss. All simulations and analyses were conducted using COMSOL Multiphysics *** design demonstrates effective performance metrics, making it suitable for integration into phononic circuits. The encoder and decoder structures are optimized to enhance signal processing capabilities at the specified *** design has potential applications in phononic integrated circuits, particularly in underwater acoustic systems and medical *** proposed 4 x 2 encoder and 2 x 4 decoder based on PnC-RR offers a promising solution for efficient signal processing in specialized environments, supported by robust performance parameters and reliable simulation results.

关键词： Phononic crystal Phononic band gap Acoustic ring resonator encoder Decoder

来源：评论

学校读者我要写书评

暂无评论

Enhancing speaker identification in low-resource multilingual languages using hybrid MFCC-Chroma STFT and transformer encoder

引用

Multimedia Tools and Applications 2025年 1-35页

作者： Vajrobol, Vajratiya Aggarwal, Nitisha Saxena, Geetika Jain Singh, Sanjeev Pundir, Amit Institute of Informatics and Communication University of Delhi Delhi India Department of Electronics Maharaja Agrasen College University of Delhi Delhi India

Speaker identification is a critical need in various applications but remains underexplored, especially for low-resource languages like Khmer, Javanese, Sudanese, and Nepali. This study introduces a novel hybrid model that combines MFCC and Chroma Short-Time Fourier Transform (Chroma STFT) features with a Transformer encoder, targeting the unique challenges of speaker recognition in multilingual contexts. The paper demonstrates results using a carefully curated dataset with recordings from a diverse group of multilingual speakers. Our proposed model demonstrates excellent performance. An impressive accuracy of 99.04% is achieved. We obtain specifically for Khmer an overall accuracy of 98.16% with 98.19% for precision, 97.91% for recall, across all target languages with an F1 score of 97.95%. Chroma STFT is integrated with MFCC, with our approach, we also increase the ability to separate speakers, and add Transformer encoder in multilingual and low resource languages like Sudanese, Nepali, Khmer, and Javanese. The design and implementation of speaker’s voice found in this research is further improved with valuable insight. Then they contribute significantly to the advancement of identification systems designed for multilingual settings. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： encoder Javanese Khmer Nepali Transformer Speaker identification Speech Sudanese

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Single Layer Transformer Convolutional encoder for Accurate Price Prediction of Agriculture Commodities

引用

IEEE Access 2025年 13卷 82144-82159页

作者： Bundak, Caceja Elyca Rahman, Mohd Amiruddin Abd Haniff, Nurin Syazwina Mohd Afrizal, Nur Syaiful Yusof, Khairul Adib Karim, Muhammad Khalis Abdul Mamat, Md Shuhazlly Rahmat, Romi Fadillah Universiti Putra Malaysia Faculty of Science Department of Physics UPM Serdang 43400 Malaysia Universitas Sumatera Utara Faculty of Computer Science and Information Technology Department of Information Technology Medan 20155 Indonesia

Predicting the accurate future price of the agricultural crops is important to avoid overproduction or shortages in the food supply chain. To obtain accurate predictions, the process usually involves large and complex datasets, which would add to computational costs for developing a model with good performance. Therefore, this study introduces the single-layer Transformer Convolutional encoder algorithm (STCE), an improved version of the traditional transformer encoder. STCE is computationally efficient and does not compromise the accuracy of the prediction. In STCE, the fully connected Convolutional Neural Network (CNN) layer is used in the transformer to get the first temporal features and record long-range dependencies with Multi-Head Attention. To minimize complexity while maintaining performance, we use a single dense layer for the output instead of the Multi-Layer Perceptron (MLP) and omit positional encoding, which leverages the natural sequence order of the time series data. Additionally, since time-series price data normally comes with missing values, we introduce a sequence nearest neighbor imputation algorithm for anchoring that data to complement the STCE method. Our study focuses on various vegetable prices, such as tomatoes, long beans, and cucumbers, with empirical validation across various prediction prices, specifically 30-day, 60-day, and 90-day predictions. Predictions made with Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) show that the STCE algorithm is better than other deep learning algorithms, even the traditional transformer encoder. Our algorithm not only has better performance, but it also reduces the computational time in the training with 12% fewer seconds compared to the transformer encoder and 22% fewer seconds for LSTM. This study not only provides valuable insights for farmers and planners in the agriculture market but also highlights the robust potential of transformer encoder i

关键词： CNN Commodity price prediction Deep learning encoder Transformer

来源：评论

学校读者我要写书评

暂无评论

A Sentence-Level encoder-Decoder Architecture for Designing an Administrative Roman Urdu Chatbot

引用

APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING 2025年第1期2025卷

作者： Maqbool, Muhammad Nazam Saleem, Rana Muhammad Sarwar, Nadeem Ibrahim, Muhammad Hashmi, Muhammad Shadab Alam Univ Management & Technol Dept Artificial Intelligence Lahore Pakistan Univ Agr Faisalabad Dept Comp Sci Burewala Pakistan Bahria Univ Dept Comp Sci Lahore Campus Lahore Pakistan Islamia Univ Bahawalpur Dept Comp Sci Bahawalpur Pakistan Khwaja Fareed Univ Engn & Informat Technol Dept Comp Sci Rahim Yar Khan Pakistan

This research focuses on developing an intelligent administrative chatbot for Roman Urdu to overcome the language barrier that hinders individuals who are not fluent in English from utilizing existing chatbot frameworks. While chatbot architectures can be rule based or artificial intelligence (AI) based, the core objective of a chatbot is to effectively address user queries across diverse domains. AI-based chatbots have demonstrated higher interactivity, scalability, adaptability to human interests, and evolving knowledge compared with rule-based architectures. However, the majority of existing chatbot frameworks is in English, which poses a challenge in regions like Pakistan where only a small percentage of the population is proficient in English. In response to this challenge, this research introduces an intelligent administrative chatbot specifically developed for Roman Urdu. Roman Urdu is the practice of writing Urdu, the native language of Pakistan, using the English alphabet. The proposed chatbot allows students to post their questions in either English or Roman Urdu, enabling them to obtain conclusive answers. The chatbot system utilizes a sentence analysis approach to generate relevant and productive responses to user queries. The core building block of the proposed chatbot is the recurrent neural networks (RNNs) sequence-to-sequence (Seq2Seq) model with long short-term memory (LSTM) units. To train the model, a dataset was meticulously collected from various administrative offices at the University of Engineering and Technology (UET), Lahore, initially in English and subsequently translated into Roman Urdu using different writing styles. The effectiveness of the proposed system was evaluated through a human judgment approach, assessing the contextual relevance and productivity of the chatbot's responses to relevant questions. In conclusion, this research aims to bridge the language gap in chatbot frameworks, enhancing accessibility and usability.

关键词： chatbot evaluation decoder model education chatbot encoder natural language processing (NLP) Roman Urdu question answering chatbot Seq2Seq model

来源：评论

学校读者我要写书评

暂无评论

encoder-Based Optimization of CNFET-Based Ternary Logic Circuits

引用

IEEE TRANSACTIONS ON NANOTECHNOLOGY 2018年第2期17卷 299-310页

作者： Vudadha, Chetan Rajagopalan, Srinivasan Dusi, Aditya Phaneendra, P. Sai Srinivas, M. B. Birla Inst Technol & Sci Dept Elect & Elect Engn Hyderabad Campus Hyderabad 500078 Andhra Prades India BML Munjal Univ Sch Engn & Technol Gurgaon 122413 India

In existing CNFET-based design methodologies that are used to implement ternary logic circuits, ternary signals are first converted to binary signals, which are then passed through binary gates and an encoder to get the final ternary output. In a ternary circuit, encoder is used to convert intermediate binary signals to final ternary outputs. This paper presents improved encoder designs that are used in implementation of ternary logic circuits. A detailed analysis is carried out on encoders to understand the effect of using CNFETs with CNTs of different diameter on the overall propagation delay and power consumption of the encoder. Based on this analysis, algorithms, which choose appropriate encoders for different output stages of a ternary circuit while optimizing different design parameters, such as power consumption, propagation delay or power-delay product, are presented. These algorithms are used to map appropriate encoders for different outputs of a ternary adder resulting in adder designs that are optimized for delay, power or power-delay product. Simulation results indicate that the ternary adder designs, which use encoder mapping obtained from proposed algorithms, result in 54%-82% reduction in power consumption, 0%-75% in propagation delay and 54%-94% in power-delay product when compared with different existing ripple carry-based ternary adders.

关键词： CNFET ternary logic low power encoder

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-rate encoder of QC-LDPC Codes Based on FPGA for WIMAX Standard

引用

Chinese Journal of Electronics 2017年第2期26卷 250-255页

作者： WANG Xiumin GE Tingting LI Jun SU Chen HONG Fangfei College of Information Engineering China Jiliang University National Mobile Communications Research Laboratory Southeast University

An efficient multi-rate encoder for IEEE802.16e LDPC codes which outperforms current single rate encoders with acceptable hardware consumption and efficient memory consumption is *** design utilizes the common dual-diagonal structure in parity matrices to avoid the inverse matrix operation which requires extensive *** Matrix-vector multiplication(MVM) units,bidirectional operation and storage compression are applied to this multi-rate encoder to increase the encoding speed and significantly reduce the quantity of memory bits *** proposed encoding architecture also contributes to the design of multi-rate encoders whose parity matrices are dual-diagonally structured and have an Approximately lower triangular(ALT)form,such as in IEEE 802.11n and IEEE *** results verified that the proposed encoder can efficiently work for all code rates specified in WIMAX *** a maximum clock frequency of 117 MHz,the encoder achieves 3 to 10 times higher throughput than prior *** proposed encoder is capable to switch among six rates by adjusting the input parameter and it achieves the throughput up to 1Gbps.

关键词： encoder Multi-rate FPGA Dual Diagonal WIMAX

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：