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

Movie Recommendation System Using Hybrid Based Method 3

Movie Recommendation System Using Hybrid Based Method

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Kamble, Khushi Bhadarge, Pradnyanand Bhakte, Shreejit Kulkarni, Omkaresh Kadam, Rutuja Pinjarkar, Latika Vishwakarma Institute of Information Technology Computer Science and Engineering - Artificial Intelligence and Machine Learning Department Pune India Maharashtra Pune India Nagpur Campus Pune India

ISBN: (纸本)9798331542375

The rise of digital platforms has increased user engagement and satisfaction through personalized recommendation systems. The research paper presents a hybrid approach to movie recommendation, which uses content-based filtering and collaborative filtering techniques to mitigate the cold start problem, data sparsity, and scalability issues. The proposed system will utilize methodologies from machine learning, such as cosine similarity and vectorization, and the K-Nearest Neighbors (KNN) algorithm, for recommending movies based on their precise and personalized values. The dataset TMDB5000 will then be used for two datasets involving movie features, cast, and crew information while preprocessing techniques in cleaning, feature extraction, and merging are undertaken to ensure robust foundation for the model building. The hybrid model uses the bag-of-words technique to vectorize and compute cosine similarity to determine movies' relationships in a multidimensional space. The KNN algorithm then refines the collaborative filtering process by the clustering of user preferences and makes recommendations using nearest-neighbor analysis. Our current approach overcomes these weaknesses by combining both content-based and collaborative methods, resulting in a system which handles diverse user preferences while maintaining high recommendation accuracy. As the evaluation of precision, recall, F1-score, and mean squared errors further validates that this system performance is good and also scalable and efficient for processing large datasets for which it explains some practical aspects related to implementation in real time. The future work includes deep learning models like neural collaborative filtering to further improve semantic understanding and recommendation accuracy. This paper addresses the current system's limitations by proposing a novel, efficient, and user-centric hybrid approach, which can be extended to other domains, such as e-commerce, music, and book recommendati

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Non-Destructive Detection of Fillet Fish Quality Using MQ135 Gas Sensor and Neutrosophic Logic-Enhanced System

引用

Neutrosophic Sets and Systems 2025年 80卷 540-563页

作者： Shams, M.Y. Darwesh, M.R. Bhatnagar, Roheet Al-Sattary, N.S.A. Salama, A.A. Ghoname, M.S. Deptartment of Machine Learning Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheihk33516 Egypt Department of Agriculture Engineering Faculty of Agriculture Tanta University Tanta31527 Egypt Department of Food Processing Faculty of Industry and Energy Samannoud Technological University Egypt Department of Computer Science and Engineering Manipal University Rajasthan Jaipur India Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt

This paper demonstrates the feasibility of using an electronic nose to assess fish quality by analyzing air quality and examining volatile organic compounds (VOCs) alongside physical variables, with pH, protein content, and VOCs serving as chemical reference points. artificial intelligence algorithms were employed to predict quality and calculate regression coefficients. Using the reference neural network algorithm based on chemical and physical compounds, regression coefficients (R values) achieved were 0.99, 0.98, and 0.97, respectively. Additionally, ANFIS (Adaptive Neuro-Fuzzy Inference System) produced R values of 0.99, 0.85, and 0.98. Both fuzzy logic and ANFIS proved effective for predicting fish quality. Image processing techniques, including histogram analysis, color mapping, and edge detection, were also applied to assess fish quality. To enhance the inference process, Neutrosophic Logic-Enhanced Fuzzy Logic Systems were utilized, addressing uncertainty and imprecision in fish quality assessment. Neutrosophic logic combines fuzzy logic's partial truth with indeterminacy, represented by three membership functions: truth, indeterminacy, and falsity. Neutrosophic fuzzy inference integrates steps like neutrosophication, rule evaluation, aggregation, and defuzzification, ensuring improved expressiveness and fidelity. For instance, neutrosophic fuzzy rules evaluated fish freshness and appearance to determine quality ratings such as poor, good, or excellent. This integration enhances decision-making by accurately modeling complex real-world uncertainties. These methods, combining electronic nose technology, artificial intelligence, and neutrosophic inference, provide a robust, non-destructive, and cost-effective approach to detecting spoilage in fillet fish. © 2025, University of New Mexico. All rights reserved.

关键词： Volatile organic compounds

来源：评论

学校读者我要写书评

暂无评论

Touchless Mouse Control Via Hand Gestures Using Resnet and Mediapipe

Touchless Mouse Control Via Hand Gestures Using Resnet and M...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Jagadeeswara Rao Palisetti Digumarthi Srilikhitha Karna Bhargava Basa Bhavana Devi Mettu Bharath Kumar Computer Science and Engineering(Artificial Intelligence and Machine Learning) Lakireddy Bali Reddy College of Engineering Mylavaram India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Touchless control of systems using hand gestures is a trending technology in the field of Human-computer Interaction (HCI). One of the most common ways to interact with systems is through the mouse. In this paper, a touchless mouse is focus on, which can perform the same operations as a physical mouse using finger and hand gestures. All of these operations are carry out by the system without requiring any external devices. In the physical mouse, we hold and operate it using the index and middle fingers. Similarly, we use the same hand pose to control the touchless mouse system. Nowadays, every system has an inbuilt webcam. This system uses a low-resolution webcam as input to capture hand gestures with 21 landmarks using OpenCV and MediaPipe. Based on the movements of the landmarks in the hand, the cursor can navigate, and various actions such as right-click, left-click, double-click, zoom in and zoom out, drag and drop files, multiselect files, increase, and decrease volume, adjusting the brightness, are easily performed, ResNet18 is used to stop the cursor movement. Using different finger and hand gestures. The system has the potential to replace traditional HCI tools in the future and help optimize hu-man-computer communication.

关键词： Hands Human computer interaction Performance evaluation Webcams Tracking Navigation Hospitals Brightness Gesture recognition Indexes

来源：评论

学校读者我要写书评

暂无评论

AI -Driven Detection of Gastrointestinal Disease based on Advanced Deep learning Techniques 4

AI -Driven Detection of Gastrointestinal Disease based on Ad...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Izankar, Sakshi V. Puri, Chetan Burle, Rushikesh Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India

ISBN: (纸本)9798331523923

Esophageal, gastric, and colorectal cancers (CRC) are some of the gastrointestinal (GI) cancers threatening global health with CRC being particularly concerning due to its high fatality rate. While early diagnosis is crucial in improving treatment efficiency, barriers such as image noise and visual subjective assessments during diagnostics such as colonoscopies often render it inconceivable. For better diagnostic accuracy in detecting gastrointestinal disease via endoscopic images, the research explores whether highly advanced artificial intelligence (AI) models such as Vision Transformers (ViTs) and pre-trained DenseNet201 can be effective. We compare these models to popular deep learning techniques such as Support Vector machines (SVM), ResNet50, VGG19, and GoogleNet. At a training accuracy of 99.9% and a validation accuracy of 98.8%, experiments on the KVASIR dataset indicate that Vision Transformer is superior to other models since it can learn long-range dependencies. The robustness of deep learning models for identifying GI disease is exemplified by the superior performance of DenseNet201, ResNet50, and InceptionV3, all of which possess high accuracy, precision, and recall values. The paper illustrates the potential of Vision Transformers, when combined with transfer learning and pre-trained CNN models, to revolutionize endoscopic diagnoses and provide a valuable resource to help physicians manage gastrointestinal conditions more effectively. © 2025 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

A Survey of Advanced Algorithms and Experimental Approaches for Kidney Abnormality Detection in Ultrasound Imaging 3

A Survey of Advanced Algorithms and Experimental Approaches ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chitra, N. Thulasi Gogula, Sreenivasulu Satapathy, Sukla Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Telangana Hyderabad500075 India Telangana Hyderabad501218 India Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence and Machine Learning Telangana Hyderabad500075 India

ISBN: (纸本)9798331509675

Kidney abnormalities, such as cysts, tumors, and stones, are critical health concerns requiring early and precise detection. This study reviews advanced algorithms and experimental approaches for kidney abnormality detection in ultrasound imaging, emphasizing deep learning (DL) methodologies and explainable AI (XAI) techniques. Contributions include exploring CNN-based segmentation frameworks like SDFNet and U-Net, multi-scale feature fusion, and transfer learning to enhance diagnostic accuracy. Data augmentation and adversarial training are employed to address dataset bias, while Grad-CAM and CAManim provide interpretability, fostering clinician trust. Results demonstrate significant improvements in diagnostic performance, with sensitivity and specificity exceeding 95% and Dice coefficients surpassing 95% on diverse clinical datasets. The findings highlight the transformative potential of DL to automate kidney abnormality detection, reducing dependency on operator expertise while improving accuracy and efficiency. Challenges such as dataset scarcity and computational complexity persist, but future research on multimodal imaging, CNN optimization, and emerging technologies like quantum machine learning presents promising opportunities. This study serves as a guide for advancing diagnostic tools, paving the way for next-generation solutions in clinical applications. © 2025 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

A Performance Analysis of Supervised machine learning Models for Thyroid Disease Detection 4

A Performance Analysis of Supervised Machine Learning Models...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Gaurkhede, Sanskruti Burle, Rushikesh Puri, Chetan Datta Meghe Institute of Higher Education and Research Computer Science and Design Faculty of Engineering and Technology Mahartashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Mahartashtra Wardha442001 India

ISBN: (纸本)9798331523923

Thyroid disease is a major causes of the main reasons for medical diagnosis and prediction is thyroid illness, whose growth is a interesting topic in medicinal study. One of our body's utmost dynamic body part is the thyroid secreter. Thyroid hormone issues are in control for adaptable metabolism. Two predominant thyroid disorders that issue thyroid hormones to controller the body's breakdown are thyrotoxicosis and hypothyroidism. Thyrotoxicosis and hypothyroidism are two mutual thyroid situations that impair the thyroid's capacity to generate thyroid hormones and regulate the build's absorption. Data cleaning actions remained utilised to kind the data simple sufficient for analytics to demonstration the likelihood of affected role having thyroid illness. Thirteen clinicopathologic features from the dataset occupied from UCI machine learning source are employed In order to prediction the reappearance of well-differentiated thyroid cancer, this article analyses and classifies thyroid disease models. machine learning is a key component in the sickness prediction process. For complex knowledge activities, like medical diagnostic and prediction jobs, it is crucial to take a tough information base that can be combined and used as a cross model. We too optional a quantity of machine learning methods for thyroid preventative diagnosis in this work. machine learning methods such decision trees, logistic regression, random forest, and gradient boosting remained used to evaluate the likelihood that a patient will acquire thyroid disease. © 2025 IEEE.

关键词： Endocrinology

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM for Enhanced Accuracy

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM fo...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Saini, Aradhna Attiuttama Naaz, Sheenam Shivhare, Anushka Dhuriya, Gaurav Yadav, Neha G L Bajaj Institute of Technology and Management Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Artificial Intelligence and Machine Learning Greater Noida India Sharda University Computer Science and Engineering Greater Noida India Netaji Subhas University of Technology Computer Science and Engineering Delhi India

ISBN: (纸本)9798331508685

The antique adage "seeing is believing"is simply no longer actual, which has profound implications for a ramification of sides of our lives. Deepfakes are becoming less complicated and simpler to create as technology advances. In fact, with the right software program, you can do a part of it right out of your palm. it is challenging to pick out deepfakes. The capability of the human eye to differentiate among deepfakes has reduced. however, a few academics have tried to identify deepfake. Deepfakes are media that can be generated by synthetic intelligence (AI) using algorithms. artificial intelligence algorithms are designed to understand the traits of both the supply and the target photo. Subsequently, the target image is positioned on the pinnacle of the supply photograph. Our goal is to pick out video deepfakes by way of utilizing deep getting-to-know neural networks which include InceptionResNetV2 and LSTM. With the usage of transfer learning and the pre-trained InceptionResNetV2 CNN for characteristic extraction and vector production, we were able to efficaciously assemble a deepfake detection version. The capabilities had been used to train the LSTM layer, and the confusion matrix that was produced offers us the accuracy of testing and validation. The corresponding version's accuracy for 20 and 40 epochs was 84.75% and 91.48%, respectively. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Review on Applications of IoT in Healthcare 3

A Review on Applications of IoT in Healthcare

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Thakare, Vedant Verma, Prateek Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

This article examines how the Internet of Things (IoT) is rapidly transforming the medical field. IoT technologies are revolutionizing patient care, increasing productivity, and boosting results in a variety of ways, from wearable technology and telemedicine to smart hospitals and personalized medicine. Predictive analytics, remote patient monitoring, and the use of AI and machine learning for more precise diagnosis and treatment regimens are important applications. The future of IoT in healthcare is extremely bright, with developments in 5G, AI, and other cutting-edge technologies set to further transform the sector and enhance human health, even while issues like data security and privacy still need to be resolved. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture: A Comprehensive Approach to Crop Disease Diagnosis using Offline Multilingual Technologies

Smart Agriculture: A Comprehensive Approach to Crop Disease ...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Ashok K Jimsha K Mattew Chandana K S Maharathi G N Abhilash GM Nithish Somani Computer Science and Engineering New Horizon College of Engineering Bengaluru Artificial Intelligence and Machine Learning New Horizon College of Engineering Bengaluru

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

This research study presents a comprehensive multilingual approach to crop disease diagnosis aimed at transforming agricultural practices. The proposed system leverages advanced deep learning models such as ResNet, EfficientNet, and MobileNet to automate plant phenotyping using high-resolution images. Beyond disease identification, it provides intelligent plant parenting recommendations to enhance crop breeding strategies. The system is equipped with multilingual support and offline capabilities, ensuring global accessibility, especially in areas with limited internet access. Additionally, the model delivers outputs by detecting diseases and offering diagnosis in the user's native language, facilitating better decision-making for farmers. Experimental results from real-world scenarios demonstrate the system's high accuracy and potential to drive sustainable agriculture, accelerate genetic progress, and improve crop prediction.

关键词： Smart agriculture Deep learning Decision making Crops Genetics Multilingual Medical diagnosis Informatics Mobile computing Diseases

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：