检索结果-内蒙古大学图书馆

DBNLP: detecting bias in natural language processing system for India-centric languages

International Journal of Information Technology (Singapore) 2025年 1-16页

作者： T. G, Keerthan Kumar Mendke, Saish Parihar, Rohit Mayya, Samarth Venkatesh, Spoorthy Koolagudi, Shashidhar G. Department of Information Science and Engineering Siddaganga Institute of Technology Karnataka Tumkur 572102 India Department of Computer Science and Engineering National Institute of Technology Karnataka Surathkal Karnataka Mangalore 575025 India Department of Artificial Intelligence and Machine Learning CSPIT CHARUSAT Gujarat Anand 388421 India

Natural language processing (NLP) is gaining widespread interest and seeing advancements rapidly due to its attractive and exhilarating applications. NLP models are being developed in search engines for real-world scenarios such as language translation, sentiment analysis, chat-bots such as ChatGPT, and auto-completion. These models are trained on a vast corpus of online data, exposing them to harmful biases and stereotypes towards various communities. The models learn these biases, making harmful and undesirable predictions about particular genders, religions, races, and professions. Biases in NLP systems can perpetuate societal biases and discrimination, leading to unfair and unequal treatment of individuals or groups. It is crucial to identify these biases, which will help mitigate them. Most of the literary works in this area have been primarily Western-centric, focusing on the English language, making it tough to use them for Indian models and languages. In this work, we propose a model called Detecting Bias in Natural Language Processing System for India-Centric Languages (DBNLP), which aims to identify the biases relevant to the Indian context present in the text-based language models, particularly for the English and Hindi languages. The DBNLP presents three techniques for bias identification based on (1) a Context Association Test (CAT), (2) a template-based perturbation technique for various co-domain associations, and (3) a co-occurrence count-based corpus analysis technique. Further, this work showcases how India-centric models such as IndicBERT, MuRIL, and datasets such as IndicCorp are biased toward various demographic categories. Detecting bias in natural language processing systems for India-centric languages is essential to creating fair, diverse, and inclusive models that benefit society. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Diverse and Inclusive models Harmful biases and stereotypes India-centric models Indian context Natural language processing

来源：评论

学校读者我要写书评

暂无评论

TransUAAE-CapGen: Caption Generation from Histopathological Patches through Transformer and UNet-Based Adversarial Autoencoder

TransUAAE-CapGen: Caption Generation from Histopathological ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Taslim Uddin Raju, S.M. Mohammad, Abdul Raqeeb Islam, Md. Milon Karray, Fakhri University of Waterloo Department of Electrical and Computer Engineering Ontario Canada University of Waterloo Centre for Pattern Analysis and Machine Intelligence Department of Electrical and Computer Engineering Ontario Canada Mohamed Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9781665410205

Captioning Whole Slide Images (WSIs) for pathological analysis is an essential but not extensively explored aspect of computer-aided pathological diagnosis. Challenges arise from insufficient datasets and the effectiveness of model training. Generating automatic caption reports for various gastric adenocarcinoma images is another challenge. In this paper, we introduce a hybrid method referred to as TransUAAE-CapGen to generate histopathological captions from WSI patches. The TransUAAE-CapGen architecture consists of a hybrid UNet-based Advereasrial Autoencoder (AAE) for feature extraction and a transformer for caption generation. The hybrid UNet-based AAE extracted complex tissue properties from histopathological patches, transforming them into low-dimensional embeddings. The embeddings are then fed into the transformer to generate concise captions. Our proposed method is validated using the PatchGastricADC22 dataset. The TransUAAE-CapGen model provides the best estimated accuracy of BLEU-4 = 86.8%, METEOR = 59.6%, a ROUGE = 89.3%, and CIDEr = 7.72%. Experimental analysis indicates that the TransUAAE-CapGen architecture outperforms the traditional LSTM-based model for the caption generation task. Our findings reveal that the proposed architecture can effectively generate accurate and precise reports for medical image analysis. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

引用

Journal of machine learning Research 2023年第1期24卷 1-11页

作者： Hedström, Anna Weber, Leander Bareeva, Dilyara Krakowczyk, Daniel Motzkus, Franz Samek, Wojciech Lapuschkin, Sebastian Höhne, Marina M.-C. Understandable Machine Intelligence Lab TU Berlin Berlin10587 Germany Department of Electrical Engineering and Computer Science TU Berlin Berlin10587 Germany Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin10587 Germany Department of Computer Science University of Potsdam Potsdam14476 Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. Until now, no tool with focus on XAI evaluation exists that exhaustively and speedily allows researchers to evaluate the performance of explanations of neural network predictions. To increase transparency and reproducibility in the field, we therefore built Quantus—a comprehensive, evaluation toolkit in Python that includes a growing, wellorganised collection of evaluation metrics and tutorials for evaluating explainable methods. The toolkit has been thoroughly tested and is available under an open-source license on PyPi (or on https://***/understandable-machine-intelligence-lab/Quantus/). © 2023 Anna Hedström, Leander Weber, Dilyara Bareeva, Daniel Krakowczyk, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, and Marina M.-C. Höhne.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

De-Styling Bias in #Climatical Tweets: A Neural Language Style Transfer Approach 3

De-Styling Bias in #Climatical Tweets: A Neural Language Sty...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： George, Elizabeth Leah Parthasarathy, Subashini Avinashilingam Institute for Home Science and Higher Education for Women Department of Computer Science Coimbatore India Centre for Machine Learning and Intelligence Avinashilingam Institute for Home Science and Higher Education for Women Department of Computer Science Coimbatore India

ISBN: (纸本)9798331515911

The spread of biased and misleading opinions on social media regarding climate change necessitates robust solutions to counteract misinformation and promote balanced discourse. In this study, we introduce the Semantic Neural Style Transfer Bias (SNLT) Framework, an AI-driven solution designed to identify and mitigate bias in climate-related tweets. Leveraging a curated dataset of climate change tweets collected from Twitter, we employ the all-MiniLM-L6-v2 sentence transformer for feature extraction and BERT-based embeddings to capture semantic nuances. Our methodology integrates semantic clustering models to evaluate clustering performance using silhouette scores, including KMeans, Gaussian KMeans, keyNMF clustering, and an Autoencoder-based model. DistilBERT is further employed to classify tweets as biased or unbiased, while a Named Entity Recognition (NER) model trained on RobERTa transformers identifies word-level bias indicators. The fundamental basis of our framework is a transformer-based style transfer model, such as GPT-2, which adjusts the stylistic tone of biased text while preserving its semantic meaning. This approach employs a style-specific decoder to ensure grammatical accuracy and contextual relevance, producing text with a neutral tone through refined phrasing and word choice. Evaluation results demonstrate a substantial reduction in bias without compromising fluency or naturalness, validated through statistical metrics and human assessments. Additionally, Explainable AI techniques are integrated to enhance the transparency of model decisions, offering insights into bias mitigation processes. Our findings highlight the framework's efficacy in addressing climate misinformation and fostering constructive conversations on social media, underscoring its potential as a responsible AI tool for digital discourse. © 2025 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

OP-FedELM: One-Pass Privacy-Preserving Federated Classification via Evolving Clustering Method and Extreme learning machine Hybrid 1

引用

23rd International Conference on Intelligent Systems Design and Applications, ISDA 2023

作者： Prasad, Polaki Durga Vivek, Yelleti Ravi, Vadlamani Center for Artificial Intelligence and Machine Learning Institute for Development and Research in Banking Technology Hyderabad500076 India School of Computer and Information Sciences University of Hyderabad Hyderabad500046 India

ISBN: (数字)9783031648366

ISBN: (纸本)9783031648359

The need to protect data privacy is critical in industries like healthcare, finance, and banking. Federated learning (FL) has attracted widespread attention due to its decentralized, distributed training and the potential to protect privacy. However, FL presents challenges like privacy concerns, network, and data heterogeneity. This motivated us to propose a two-phase, one-pass FL algorithm, where (I) In the first phase, the differentially private dataset is generated by incorporating the Laplacian mechanism, and (ii) during the second phase, we employed one-pass privacy-preserving federated extreme learning machine (OP-FedELM) for generating globally shared training dataset and build the global model. ELM generally tends to overfit training data at a client. Therefore, we employed a modified version of the Evolving clustering algorithm (ECM), an online one-pass clustering algorithm, to cluster training datasets at the clients. Further, it will reduce the computational training time of ELM and communication overhead. At the server, we employed a meta-clustering algorithm to cluster the updates from the clients. We also proposed another one-shot FL algorithm called privacy-preserving federated ELM based on minimum least square solution (FedELM-LS). The experimental analysis concludes that OP-FedELM is computationally less expensive yet achieves higher AUC in three of four datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

SightAid: empowering the visually impaired in the Kingdom of Saudi Arabia (KSA) with deep learning-based intelligent wearable vision system

引用

Neural Computing and Applications 2024年第19期36卷 11075-11095页

作者： Talaat, Fatma M. Farsi, Mohammed Badawy, Mahmoud Elhosseini, Mostafa Machine Learning Department Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh Egypt Faculty of Computer Science & amp Engineering New Mansoura University Gamasa35712 Egypt College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Computer Science and Information Department Applied College Taibah University Madinah46537 Saudi Arabia

In the Kingdom of Saudi Arabia, visual impairment poses significant challenges for approximately 17.5% of school-aged children, mainly due to refractive errors. These challenges extend to everyday navigation, environmental interaction, and overall life quality. Motivated by the desire to empower visually impaired individuals, who face navigational limitations, difficulties in object recognition, and inadequate assistance from traditional technologies, we propose SightAid. This innovative wearable vision system utilizes a deep learning-based framework, addressing the gaps left by current assistive solutions. Traditional methods, such as canes and GPS devices, often fail to meet the nuanced and dynamic needs of the visually impaired, especially in accurately identifying objects, understanding complex environments, and providing essential real-time feedback for independent navigation. SightAid comprises a seven-phase framework involving data collection, preprocessing, and training of a sophisticated deep neural network with multiple convolutional and fully connected layers. This system is integrated into smart glasses with augmented reality displays, enabling real-time object detection and recognition. Interaction with users is facilitated through audio or haptic feedback, informing them about the location and type of objects detected. A continuous learning mechanism, incorporating user feedback and new data, ensures the system's ongoing refinement and adaptability. For performance assessment, we utilized the MNIST dataset, and an Indoor Objects Detection dataset tailored for the visually impaired, featuring images of everyday objects crucial for safe indoor navigation. SightAid demonstrates remarkable performance with accuracy up to 0.9874, recall values between 0.98 and 0.99, F1-scores ranging from 0.98 to 0.99, and AUC-ROC values reaching as high as 0.9999. These metrics significantly surpass those of traditional methods, highlighting SightAid's potential to substan

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

The Impact of AI-Powered Personalization on Academic Performance in Students 5

The Impact of AI-Powered Personalization on Academic Perform...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Shete, Shweta G. Koshti, Priyanka Pujari, Vinayak I. Sanjay Ghodawat University Department of Artificial Intelligence and Machine Learning Kolhapur India Sanjay Ghodawat University Department of Computer Science Kolhapur India D.Y. Patil School of Engineering and Management Department of Computer Application Kolhapur India

ISBN: (纸本)9798350351378

This study investigates how learners' performance is affected by AI-driven personalization. This goal compares students' academic performance in AI-driven personalized learning environments to that of students in conventional learning environments. This study shows the rapid development and application of artificial intelligence (AI) in education has led to the emergence of personalized learning platforms that utilize AI to provide tailored learning experiences for individual students. The study shows a beneficial relationship between enhanced academic accomplishment, engagement, and satisfaction with individualized AI-based adaptive learning through quantitative and qualitative analysis. The results demonstrate how AI-driven customization can improve student achievement and change the way that education is delivered. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Energy Aware Routing Mechanism Using AODV Protocol For Low Energy Consumption in WSN 5

Energy Aware Routing Mechanism Using AODV Protocol For Low E...

引用

5th IEEE International Conference on Cybernetics, Cognition and machine learning Applications, ICCCMLA 2023

作者： Shanmugavalli, R. Krishnaveni, M. Dhivyaprabha, T.T. Subashini, P. Center for Machine Learning Intelligence Avinashilingam Institute for Home Science and Higher Education for Women Department of Computer Science Coimbatore India

ISBN: (纸本)9798350338287

Wireless Sensor Network (WSN) is a self-configured and infrastructure-less network that is used to monitor the environmental conditions and transfer sensor data to the desired destination in a particular region. Energy consumption is the most important concern in WSN, which is considered as an active research area. Routing selection is one method that is used to optimize energy in WSN. There are many protocols for discovering a route between two nodes. However, the performance of the Ad hoc On-Demand Distance Vector (AODV) routing protocol is a more suitable one. It is a generic reactive protocol for routing mostly used in MANET (Mobile Ad Hoc Networks) and WSNs (Wireless Sensor Networks). This protocol supports unicasting and multicasting and will also identify the shortest path. In this paper, energy-aware routing is implemented in the AODV protocol which is derived from nodes remaining energy. The remaining energy of node is computed by Max-Min energy algorithm in order to extend the network's life span and facilitates to keep the network lively. The performance of AODV is compared with Modified AODV protocols. The comparison is done by various performance metrics such as PDR (Packet Delivery Ratio), throughput, delay time, loss rate, and energy consumption. Analysis on the experimental results showed that MAODV protocol gives better results than traditional AODV protocol and it is also inferred that MAODV avoids too much energy consumption of nodes in the network. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

An Efficient Biometric Authentication Based on Face Image using Deep Generative Adversarial Network 2

An Efficient Biometric Authentication Based on Face Image us...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Aswini, K.R.N. Al-Fatlawy, Ramy Riad Jagadish, Sripelli Ramaswamy, Palanivel Deepak Kumar, B.P. KNS Institute of Technology Department of Artificial Intelligence and Machine Learning Bangalore India The Islamic University Najaf Iraq SR University School of Computer Science & Artificial Intelligence Warangal India Nitte Meenakshi Institute of Technology Department of AI and DS Bengaluru India CMR Technical Campus Hyderabad India

ISBN: (纸本)9798350317558

face authentication is one of the technique to prevent the loss of personal data, however the process is challenging due to variations in the patterns of the mouth, nose, eyes, and angles. A face authentication system that leverages an enhanced Deep Generative Adversarial Network (DGAN) is being developed as a solution to the problem. The process begins with preprocessing Histogram Equalization method to enhance the image quality for generator input. GAN generator to create synthetic image using data augmentation method to identify the true face, which is helpful for identifying fake one. Then AlexNet called discriminator to extract the feature of input image and compare the real and fake images to authenticate the person. The implemented DGAN model demonstrates superior performance, achieving Precision of (97.12%), recall of (97.31%) and F1-Score of (97.01%). When compared to previous models like AutoRegressive Biometric Authentication-Oriented Face Detection (ARBAOFD), deep steganography with Celebes (DSC) and Convolutional Neural Network (CNN) © 2024 IEEE.

关键词： AutoRegressive Celebes Convolutional Neural Network Generative Adversarial Network Steganography

来源：评论

学校读者我要写书评

暂无评论

Addressing Data Imbalance in machine learning: Challenges and Approaches 6

Addressing Data Imbalance in Machine Learning: Challenges an...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Langote, Meher Zade, Nikita Gundewar, Swapnil Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Sawangi India

ISBN: (纸本)9798331522667

A key difficulty of dealing with imbalanced datasets is that machine learning models are trained to favor the majority class and therefore perform poorly when it comes to a minority class classification. In this paper, we consider the following methods of tackling the issue of the over-representation of a class;random oversampling, undersampling, SMOTE, cost-sensitive learning, and ensemble methods. Comparing them, we assess the performance of each of these techniques within different classifiers. Techniques including SMOTE together with combined methods including Random Forests also show higher capacity in minority class predictions. However, problems such as overfitting and the increase in the computational load are not escapable yet. We briefly recap the strengths and weaknesses of each approach and propose potential refinements including a combination of both methods and dynamic resampling methods to serve as the next steps toward improving the model. Thereby, our results draw attention to the necessity of accurate methods for handling the class imbalance, which will further yield more accurate and fair machine learning solutions across a variety of applications. © 2025 IEEE.

关键词： Adversarial machine learning

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：