检索结果-内蒙古大学图书馆

14th International Conference on Cloud Computing, Data science and Engineering, Confluence 2024

作者： Apoorva Shankar, Anushka Bondia, Anushree Rani, Ritu Jaiswal, Garima Sharma, Arun Computer Science Engineering-Artificial Intelligence Indira Gandhi Delhi Technical University for Women Delhi India Artificial Intelligence and Machine Learning Indira Gandhi Delhi Technical University for Women Delhi India Centre of Excellence-Artificial Intelligence Indira Gandhi Delhi Technical University for Women Delhi India Artificial Intelligence and Machine Learning Bennett University Noida India

ISBN: (纸本)9798350344837

The convergence of innovative strategies to human-computer interaction is evidently supported by two underlying research. One experiment involves controlling objects using hand motions, while the other involves identifying the symbols we write in the air. In the first, a ground-breaking method for manipulating the mouse cursor is introduced: gesture recognition. By fusing motion modelling, pattern recognition, and machine learning, this technique perfectly supports a range of mouse movements. The system, which was created in Python, effectively separates finger motions in order to accurately mimic mouse events. It is improved with coloured finger caps to guarantee the best contrast. The second research explores air-writing recognition, a novel technique that involves drawing letters and numbers by hand, in conjunction with the first. This is when individuals draw letters and numbers in the air with their hands. An approved CNN model is the result of extensive testing and sets new standards for recognising characters created in the air. It is quite effective at identifying the letters or numbers that someone is forming in the air. These research, which cover gesture-based control and progressive air-writing recognition and push the frontiers of technical interface development, collectively represent the evolution of human-computer interaction paradigms. Making computers and people interact in novel and fascinating ways is the main goal! © 2024 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Ultrasound Images based and Convolutional Neural Network 6

Breast Cancer Detection using Ultrasound Images based and Co...

引用

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

作者： Langote, Meher Hiwase, Kunal Wande, Radha Tale, Abhay Kalekar, Harsh Gundewar, Swapnil Artificial Intelligence and Data Science Faculty of Engineering and Technology Maharashtra Sawangi India Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Maharashtra Sawangi India

ISBN: (纸本)9798331522667

Breast cancer forms one of the most common types of cancer among women worldwide;therefore, it highlights the importance of having rapid and timely diagnosis methods. Here, we will survey the use of convolutional neural networks (CNNs) for mutually exclusive cancer detection in ultrasound images using detectors. A dataset of benign and malignant breast tumors visualized via ultrasound is taken as the base for the training and testing of the CNN model. The CNN architecture is arranged to select valuable features from the ultrasound pictures only, but not malignant lesions. The performance and the evaluation of the CNN model are done through metrics like accuracy, precision, recall, and F1 score. The findings confirm the efficiency of using the CNN here, as it shows the extent and solidity of reading textures with excellent precision and quick performance in breast cancer screening. This investigation is the advancement of computer-aided diagnostic tools for breast cancer screening. As medical practice sees these benefits, the efficiency of healthcare delivery and patient outcomes are bound to be optimized. © 2025 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

SpikingMiniLM: energy-efficient spiking transformer for natural language understanding

引用

science China(Information sciences) 2024年第10期67卷 115-128页

作者： Jiayu ZHANG Jiangrong SHEN Zeke WANG Qinghai GUO Rui YAN Gang PAN Huajin TANG College of Computer Science and Technology Zhejiang University The State Key Lab of Brain-Machine Intelligence Zhejiang University Collaborative Innovation Center of Artificial Intelligence Zhejiang University Advanced Computing and Storage Laboratory Huawei Technologies Co. Ltd. College of Computer Science and Technology Zhejiang University of Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University

In the era of large-scale pretrained models, artificial neural networks（ANNs） have excelled in natural language understanding（NLU） tasks. However, their success often necessitates substantial computational resources and energy consumption. To address this, we explore the potential of spiking neural networks（SNNs） in NLU——a promising avenue with demonstrated advantages, including reduced power consumption and improved efficiency due to their event-driven characteristics. We propose the SpikingMiniLM,a novel spiking Transformer model tailored for natural language understanding. We first introduce a multi-step encoding method to convert text embeddings into spike trains. Subsequently, we redesign the attention mechanism and residual connections to make our model operate on the pure spike-based paradigm without any normalization technique. To facilitate stable and fast convergence, we propose a general parameter initialization method grounded in the stable firing rate principle. Furthermore, we apply an ANN-to-SNN knowledge distillation to overcome the challenges of pretraining SNNs. Our approach achieves a macro-average score of 75.5 on the dev sets of the GLUE benchmark, retaining 98% of the performance exhibited by the teacher model MiniLMv2. Our smaller model also achieves similar performance to BERTMINIwith fewer parameters and much lower energy consumption, underscoring its competitiveness and resource efficiency in NLU tasks.

关键词： spiking neural networks natural language understanding spiking Transformer spike-based attention multi-step encoding ANN-to-SNN distillation

来源：评论

学校读者我要写书评

暂无评论

Identification of Infectious Disease Like COVID-19 Gene Biomarkers Using a Clear artificial intelligence Approach

引用

SN computer science 2025年第4期6卷 1-13页

作者： Dubey, Shivendra Verma, Dinesh Kumar Kumar, Mahesh Department of Artificial Intelligence and Machine Learning Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science and Engineering Jaypee University of Engineering and Technology MP Guna India

This study offers an approach that uses SARS-COV-2 mNGS (meta-genomic next-generation sequencing) samples to apply XAI (explainable artificial intelligence) methodologies derived from the use of machine learning methods. The research's data set contains 15,979 expressions of genes from 234 infected persons, of whom 39.68% (93) had SARS-COV-2 that was positive and 60.29% (141) had SARS-COV-2 that was negatives. The SARS-COV-2 related gene was chosen using the LASSO (least absolute shrinkage and selection operator) technique. The class imbalanced issue has been resolved using the SVM-SMOTE (Support Vector machine - Synthetic Minority Oversampling Technique) approach. To identify SARS-COV-2 related biomarkers possibilities and increase the comprehensibility of the final approach, an explainable strategy that utilized SHAP (SHAPley Additive exPlanations) as well as LIME (local interpretable model-agnostic explanations) approaches were used. The XGBoost (92.98% accuracy) approach performs better for the identification of infectious diseases like COVID-19 than the LR (91.17% accuracy), SVM (87.68% accuracy), and RF (91.18% accuracy) models. The three most significant genes connected to COVID-19 by the SHAP method were FAM83A, LGR6, and IFI27. The LIME findings demonstrated that the likelihood of a positive class was particularly influenced by the elevated degree of IFI27 expression of genes. Infectious diseases like COVID-19 could be accurately predicted using the suggested framework (XGBoost). The findings demonstrate that SHAP and LIME, along with the exploit of ML methods, it could be clarify the biological marker prognosis for infectious disease and give health center a clear knowledge about how potential risk factors affect the forecasts made by the model. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biomarker Gene LIME SARS SHAP

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 6

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

引用

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

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

ISBN: (纸本)9798331522667

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. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A Survey on Graph Neural Networks and its Applications in Various Domains

引用

SN computer science 2025年第1期6卷 1-12页

作者： Murgod, Tejaswini R. Reddy, P. Srihith Gaddam, Shamitha Sundaram, S. Meenakshi Anitha, C. Department of Artificial Intelligence & Machine Learning BNM Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering NITTE Meenakshi Institute of Technology Karnataka Bengaluru India

Graph Neural Networks (GNNs) are neural models that use message transmission between graph nodes to represent the dependency of graphs. Variants of Graph Neural Networks (GNNs), such as graph recurrent networks (GRN), graph attention networks (GAT), and graph convolutional networks (GCN), have shown remarkable results on a variety of deep learning tasks in recent years. In this study, we offer a generic design pipeline for GNN models, go over the variations of each part, classify the applications in an organized manner, and suggest four outstanding research issues. Dealing with graph data, which provides extensive connection information among pieces, is necessary for many learning tasks. A model that learns from graph inputs is required for modelling physics systems, learning molecular fingerprints, predicting protein interfaces, and identifying illnesses. Reasoning on extracted structures (such as the dependency trees of sentences and the scene graphs of photos) is an important research issue that also requires graph reasoning models in other domains, such as learning from non-structural data like texts and images. Graph Neural Networks (GNNs) are primarily designed for dealing with graph-structured data, where relationships between entities are modeled as edges in a graph. While GNNs are not traditionally applied to image classification problems, researchers have explored ways to leverage graph-based structures to enhance the performance of Convolutional Neural Networks (CNNs) in certain scenario. GNN have been increasingly applied to Natural Language Processing (NLP) tasks, leveraging their ability to model structured data and capture relationships between elements in a graph. GNN are also applied for traffic related problems particularly in modeling and optimizing traffic flow, analyzing transportation networks, and addressing congestion issues. GNN can be used for traffic flow prediction, dynamic routing & navigation, Anomaly detection, public transport network

关键词： computer vision Graph neural networks Intrusion detection Natural language processing Neural networks Traffic control

来源：评论

学校读者我要写书评

暂无评论

Kontho: An AI-Driven Smart Glove for Enhanced Sign Language Communication 2nd

Kontho: An AI-Driven Smart Glove for Enhanced Sign Language...

引用

2nd International Conference on Applied Algorithms, ICAA 2025

作者： Dasgupta, Dyuti Datta, Soumyajit Pramanik, Sagnik Dey, Rohit Kumar Nandigrami, Jeet Ghosh, Debaditya Department of Artificial Intelligence and Machine Learning Heritage Institute of Technology Kolkata India Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India

ISBN: (纸本)9783031845420

In India, over 63 million individuals are affected by hearing loss, yet less than 350 certified sign language interpreters are available, thus leading to communication barriers and significant social and economic exclusion. This paper introduces Kontho, an ergonomic, AI-driven, multi-sensor glove integrated with a mobile app for real-time sign language communication via American Sign Language (ASL). Utilizing flex sensors, accelerometers, gyroscopes and EMG sensors, Kontho captures gestures and muscle activity which is processed through a combination of ensemble models and Large Language Models (LLMs) to enhance communication by predicting and completing incomplete gestures. Evaluated on a dataset of 23 ASL gestures at over 3867 data points with an accuracy of 99.61%, Kontho offers a scalable solution to foster social inclusion and address the economic isolation of hearing and speech-impaired individuals, enabling their active participation in the society. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Sustainable Urban Street Lighting through Predictive Maintenance using IoT and AI 2

Sustainable Urban Street Lighting through Predictive Mainten...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Sudharson, D. Jananiksha, P. Mukilarasu, R. Sushmita, V. Vaishali, V. Rini Vaishnavi, S.R. Kumaraguru College of Technology Artificial Intelligence and Data Science Coimbatore India Vellore Institute of Technology CSE - Artificial Intelligence and Machine Learning Vellore India

ISBN: (纸本)9798331534950

The potential for transformative urban management is enhanced through the integration of IoT and AI, creating smart ecosystems that revolutionize intelligent lighting systems. This paper explores predictive maintenance solutions for urban street lighting, leveraging advanced machine learning models such as Temporal Fusion Transformer (TFT), Temporal Aggregation and Decomposition-based Attention (TADA), and Graph Neural Networks (GNNs). By analyzing historical operational data, these models detect subtle fault patterns and predict failures, improving system reliability, reducing maintenance costs, and optimizing energy use. The work contributes to United Nations SDGs 11 and 9 by promoting sustainable urban infrastructure and smart city development, fostering a future where IoT and AI systems enhance sustainability and resilience. © 2024 IEEE.

关键词： Sustainable city

来源：评论

学校读者我要写书评

暂无评论

Precision Land Use and Land Cover Mapping with a High-Accuracy Time Series LSTM Model

Precision Land Use and Land Cover Mapping with a High-Accura...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Aryan, Adla Rv, Prakash Aluvala, Srinivas Chowdary, Venigalla Shashank Ardhaman College of Engineering Department of Artificial Intelligence & Machine Learning Telangana Hyderabad501218 India Sr University Department of Computer Science & Artificial Intelligence Telangana Warangal506371 India Nandyal518501 India

ISBN: (纸本)9798331529833

This paper introduces a machine-learning-based LULC classifying model developed with a time series data set, trained on a diverse set of agriculture and non-agricultural classes. It used a strong generalization capability employing an LSTM architecture;that is, it achieved accuracy of 90.04% in training and also validation accuracy of 90.55%. The ultimate accuracy was obtained at the minimal loss of 0.1909 at the accuracy of 95.58%, thereby validating its usability for LULC pattern classification. This model has a wide-range of potential application in environmental monitoring and resource management. Future work involves introducing more variables into the dataset, the inclusion of other environmental factors, and fine-tuning of the model towards more general applications in geospatial applications. Thus, this work advances the current state of remote sensing and LULC classification to present an effective tool in sustainable land management. © 2025 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Revisiting face detection: Supercharging Viola-Jones with particle swarm optimization for enhanced performance

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10727-10741页

作者： Mohana, M. Subashini, P. Shukla, Diksha Centre for Machine Learning and Intelligence Department of Computer Science Avinashilingam Institute Tamil Nadu Coimbatore India Department of Electrical Engineering and Computer Science University of Wyoming LaramieWY United States

In recent years, face detection has emerged as a prominent research field within computer Vision (CV) and Deep learning. Detecting faces in images and video sequences remains a challenging task due to various factors such as pose variation, varying illumination, occlusion, and scale differences. Despite the development of numerous face detection algorithms in deep learning, the Viola-Jones algorithm, with its simple yet effective approach, continues to be widely used in real-time camera applications. The conventional Viola-Jones algorithm employs AdaBoost for classifying faces in images and videos. The challenge lies in working with cluttered real-time facial images. AdaBoost needs to search through all possible thresholds for all samples to find the minimum training error when receiving features from Haar-like detectors. Therefore, this exhaustive search consumes significant time to discover the best threshold values and optimize feature selection to build an efficient classifier for face detection. In this paper, we propose enhancing the conventional Viola-Jones algorithm by incorporating Particle Swarm Optimization (PSO) to improve its predictive accuracy, particularly in complex face images. We leverage PSO in two key areas within the Viola-Jones framework. Firstly, PSO is employed to dynamically select optimal threshold values for feature selection, thereby improving computational efficiency. Secondly, we adapt the feature selection process using AdaBoost within the Viola-Jones algorithm, integrating PSO to identify the most discriminative features for constructing a robust classifier. Our approach significantly reduces the feature selection process time and search complexity compared to the traditional algorithm, particularly in challenging environments. We evaluated our proposed method on a comprehensive face detection benchmark dataset, achieving impressive results, including an average true positive rate of 98.73% and a 2.1% higher average prediction accura

关键词： Face recognition

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：