检索结果-内蒙古大学图书馆

TaxDiff: taxonomic-guided diffusion model for protein sequence generation

Science China(Information Sciences) 2025年第4期68卷 385-386页

作者： Zongying LIN Hao LI Liuzhenghao LV Yu WANG Bin LIN Junwu ZHANG Zijun CHEN Calvin Yu-Chian CHEN Li YUAN Yonghong TIAN School of Electronic and Computer Engineering Peking University AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Peng Cheng Laboratory School of Chemical Biology and Biotechnology Peking University

Protein design aims to generate protein variants with targeted biological functions, which is significant in multiple biological areas, including enzyme reaction catalysis, vaccine design, and fluorescence intensity. Protein design contains two paradigms: sequence generation and structure generation. Recently, EvoDiff [1] proposed a universal designing paradigm, combining structure and sequence generation using the diffusion framework, which improves the protein design efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synonym Replacement Augmentation for Handling Data Imbalance in Personality Classification 8

Synonym Replacement Augmentation for Handling Data Imbalance...

引用

8th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2024

作者： Pradana, Rilo Chandra Suhartono, Derwin Bina Nusantara University Binus Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368970

The Myers-Briggs Type Indicator (MBTI) classification is a widely utilized instrument for personality assessment. However, it frequently encounters challenges due to imbalanced data distributions across personality dimensions. It is paramount to address this issue to enhance the accuracy and reliability of personality predictions. Most current research in this field is focused on data balancing techniques, such as oversampling and undersampling, which have been demonstrated to enhance model performance. Nevertheless, there is a dearth of research exploring text augmentation methods, particularly synonym replacement, for this purpose. This study examines the efficacy of synonym replacement as a data augmentation technique for MBTI classification. Experiments are conducted with varying levels of synonym replacement (10%, 30%, 50%, 70%, and 90%) to assess its impact on model accuracy and F1 scores across the four MBTI dimensions. Our findings indicate that low levels of synonym replacement, particularly at 10% to 50%, can enhance the performance of the model in predicting MBTI dimensions. On the other hand, a higher number of replaced words in the synonym replacement augmentation can harm the model's performance. These observations suggest that synonym replacement can effectively address data imbalance in MBTI classification, although its application must be tailored to specific personality dimensions. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Vigenère Encryption Algorithm using 6S-Substitution and 2S-Transposition Technique

An Enhanced Vigenère Encryption Algorithm using 6S-Substitu...

引用

2024 IEEE International Conference on Data and Software Engineering, ICoDSE 2024

作者： Galeza, Sugar Mae T. Sison, Ariel M. Medina, Ruji P. Graduate Program Technological Institute of the Philippines Quezon City Philippines School of Computer Studies Emilio Aguinaldo College Manila Philippines

ISBN: (纸本)9798331506407

Vigenère encryption algorithm is a classical cryptographic algorithm featuring a polyalphabetic stream cipher, which as numerous limitations pertaining to finding the size and length of the encryption key. This study presents the process of enhancing the Vigenère algorithm using 6S-substitution and 2S-transposition techniques with the novelty of accommodating a 103-character set based on the selected ASCII and Unicode characters. It adopts the three-security metrics such as the degree of diffusion, degree of confusion, and integrity check for measuring the security level. Experiment results showed that the enhanced Vigenère algorithm produced more secure ciphertexts. Using PHP, the proponents tested and simulated ten (10) data sets to ensure the consistency of the results at each security level. The results exhibited a vigorous outcome starting the degree of diffusion output, the original Vigenère yields 1.8% while the enhanced Vigenère obtains 68.75% with an increase of 66.95%. Secondly, the result in the degree of confusion test, the former algorithm results in 1.88%, on the other hand, the latter obtains 53.39% with an increase of 51.51%. In the integrity check, the former gets 2.42% while the latter advances to 57.11%, increasing 54.69%. Thus, it is evident that the test result for the Enhanced Vigenère has a higher percentage than the original Vigenère in providing better security in the ciphertext and improving the overall encryption and decryption processes. © 2024 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Negation Handling on XLNet Using Dependency Parser for Sentiment Analysis 4

Negation Handling on XLNet Using Dependency Parser for Senti...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Winaya, Ferdinand Girsang, Abba Suganda Binus Graduate Program Bina Nusantara University Jakarta Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331506490

Negation handling is often overlooked in Indonesian sentiment analysis, making it difficult to automatically and accurately determine the polarity of sentences containing negation words. Negation is a challenging issue in natural language processing, as it can drastically alter the meaning of a sentence. For example, common Indonesian negation words such as 'tidak' (no/not), 'belum' (not yet), or 'jangan' (do not) can reverse the sentiment polarity in a text. Previous studies have proposed rule-based approaches, relying on linguistic rules or dependency parse trees to handle negation. However, negation is a complex problem that cannot be effectively addressed by simple rules alone, as they often lack flexibility in handling diverse sentence structures and negation complexities. Therefore, a more dynamic approach is needed, such as combining a dependency parser with an embedding layer, which can map syntactic relationships between words and learn vector representations of negation. This allows the model to flexibly determine the scope of negation words, enabling more accurate sentiment analysis even in complex sentences. This study evaluates the impact of negation handling on a transformer-based model, specifically XLNet, in Indonesian sentiment analysis. Using the proposed method, the model's F1 score increased by 2.13%, from 71.42% to 73.55%, compared to the baseline model. This demonstrates that the proposed negation handling strategy enhances sentiment prediction accuracy, making the model more effective at handling texts with negation. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Visualization and Simulation of Any MPU Architecture Design with Meta-Instruction 23

Visualization and Simulation of Any MPU Architecture Design ...

引用

23rd International Symposium on Communications and Information Technologies, ISCIT 2024

作者： Morimoto, Tomoyuki Wang, Ziming Luo, Jiahui Ogawa, Sota Tsutsumi, Toshiyuki Meiji University Department of Computer Science School of Science and Technology Kanagawa Japan Graduate School of Science and Technology Meiji University Computer Science Program Kanagawa Japan

ISBN: (纸本)9798350353952

Our conventional architecture design tool converted instructions of microprocessor (MPU) into meta-instructions with both semantic and functional expressions, and it displayed a circuit diagram of the meta-instruction. The tool was able to perform dynamic simulation only on an educational processor called COMET. However, the meta-instruction must be able to express the arbitrary instruction of at least different significant existing MPUs in order to design arbitrary MPUs. Furthermore, it should be possible to visualize all instructions and then execute them. Therefore, we have improved the meta-instruction so that the architecture design tool applies to major MPUs: MIPS, ARM, and RISC-V in addition to COMET. The improved architecture design tool visualizes and simulates the circuit diagram of the improved meta-instruction. The result shows the possibility of the meta-instruction-based architecture design tool being able to design any MPU. © 2024 IEEE.

关键词： Microprocessor chips

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-step ahead wind power forecasting based on N-BEATS model

Multi-step ahead wind power forecasting based on N-BEATS mod...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Agottani, Luis Fernando Rodrigues Girardi, Matheus Melara De Souza Chaves, Wendel Rafael De Azevedo Takara, Lucas Dos Santos Coelho, Leandro Mariani, Viviana Cocco Federal University of Parana Graduate Program in Mechanical Eng. Curitiba Brazil Pontifical Catholic University of Parana Department of Computer Science Curitiba Brazil Federal University of Parana Graduate Program in Electrical Eng. Curitiba Brazil

ISBN: (纸本)9789531842976

For wind power systems to operate successfully and efficiently, accurate forecasting is critical. The integration of large wind farms with smart grid technology mainly depend on accurate models for wind power output prediction. This study introduces a neural basis expansion approach named N-BEATS (neural basis expansion analysis for interpretable time series forecasting) for time series multi-step wind power forecasting. N-BEATS is a deep neural network architecture composed of multiple fully connected layers, arranged with both forward and backward residual connections. The performance of N-BEATS was benchmarked using classical approaches including AutoRegressive Integrated Moving Average (ARIMA), Seasonal AutoRegressive Integrated Moving Average (SARIMA), Holt-Winters, and the recurrent neural network named Long Short-Term Memory (LSTM). All models hyperparameters were tuned by Bayesian optimization. The N-BEATS model demonstrated superior forecasting scores and outperformed traditional methods in metrics such as mean absolute error and root mean square error for different forecasting horizons. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Compact Model Build Upon Dynamic Weighting Artificial Neural Network Approach for Complementary Field Effect Transistors

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 246-253页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation The Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program The Institute of Communications Engineering the Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

In this work, a dynamic weighting-artificial neural network (DW-ANN) methodology is presented for quick and automated compact model (CM) generation. It takes advantage of both TCAD simulations for high accuracy and SPICE simulations for cost-effectiveness. This methodology is developed for gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field effect transistor (CFET), a potential candidate for future CMOS technology due to its innate properties. The critical process variation (PV) sources that severely degrade the CFET performance are estimated using DW-ANN. It reduces the computation cost and predicts the effects of PV sources with less than 1% error. Furthermore, a compact DW-ANN-based Verilog-A model has been developed that captures the dc as well as transient behavior accurately for circuit-level analysis. CFET-based circuits such as inverter, 6T-static random access memory (SRAM), and ring oscillator (RO) are characterized and implemented using DW-ANN-based CM. The overall average error of the model is reported as less than 2%. Therefore, the proposed device and circuit modeling approach provides a feasible solution for the rapid compact modeling of new emerging devices with good convergence and high accuracy. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis and Remediation of Insecure Direct Object References (IDOR) Vulnerabilities in Android APIs 1

Comprehensive Analysis and Remediation of Insecure Direct Ob...

引用

1st IEEE International Conference on Cryptography, Informatics, and Cybersecurity, ICoCICs 2023

作者： Yulianto, Semi Abdullah, Roni Reza Soewito, Benfano Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia National Institute of Science and Technology Faculty of Informatics Engineering Jakarta12630 Indonesia Bina Nusantara University Binus Graduate Program. Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350339437

The escalating visibility of secure direct object reference (IDOR) vulnerabilities in API security, as indicated in the compilation of OWASP Top 10 API Security Risks, highlights a noteworthy peril to sensitive data. This study explores IDOR vulnerabilities found within Android APIs, intending to clarify their inception while evaluating their implications for application security. This study combined the qualitative and quantitative approaches. Insights were obtained from an actual penetration test on an Android app into the primary reasons for IDOR vulnerabilities, underscoring insufficient input validation and weak authorization methods. We stress the frequent occurrence of IDOR vulnerabilities in the OWASP Top 10 API vulnerability list, highlighting the necessity to prioritize them in security evaluations. There are mitigation recommendations available for developers, which recognize its limitations involving a possibly small and homogeneous selection of tested Android applications, the testing environment that could cause some inaccuracies, and the impact of time constraints. Additionally, the study noted insufficient threat modeling and root cause analysis, affecting its generalizability and real-world relevance. However, comprehending and controlling IDOR dangers can enhance Android API security, protect user data, and bolster application resilience. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

An Augmented Reality Game's User Experience and Its Effect on Immersion Leading to Intention 11

An Augmented Reality Game's User Experience and Its Effect o...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Oktavia, Tanty Utomo, Kawang Gaol, Ford Lumban Hosoda, Takaaki Bina Nusantara University Binus Graduate Program - Information System Management Information Systems Management Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan

ISBN: (纸本)9798350389654

Since the emergence of Pokémon Go in 2016, the world has been introduced to Augmented Reality (AR) games. Many IT companies have begun developing augmented reality (AR) games due to the great commercial potential in this industry. Certain products may have managed to remain viable in the market, while others were forced to close due to one or two factors. Since the emergence of Pokémon Go, no other game has managed to surpass its unprecedented success. The company responsible for developing Pokémon Go has decided to shut down one of their games due to a lack of consumer interest. The technology of augmented reality (AR) is consistently associated with the concept of immersion. Immersion is a key aspect of the game that allows users to deeply engage and feel fully involved in the experience. This study will employ a quantitative methodology, utilising a questionnaire that will be distributed to and completed by those who have engaged in augmented reality (AR) games. The data will be analysed using Smart PLS to examine the impact of user experience on immersion, which in turn influences intention. After gathering over 200 participants by spreading google form questionnaires and doing data analysis, the findings indicate that only a few aspects of user experience, namely Brand Experience and User Need Experience, have an impact on reasons. Niantic, the developer of Pokémon Go, was unable to replicate their success with a similar augmented reality game called Harry Potter: Wizards Unite. The initial release occurred on June 21, 2019, and the shutdown took place on December 21, 2021. In the beginning, they shown a profound enthusiasm for the game but were unable to sustain it, much as Pokémon Go. According to Niantic CEO John Hanke, the primary reason for the game's shutdown was its immersion. Immersion has a notable impact on User Confirmation, which in turn has a notable impact on Satisfaction, and Satisfaction has a notable impact on Intention. Moreover, there have be

关键词： Plant shutdowns

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：