检索结果-内蒙古大学图书馆

3rd International Conference on Machine Learning, Internet of Things and Big data, ICMIB 2023

作者： Anoop, R. Anand, Impana Rehan, Mohammed Yashvanth, R. Kodipalli, Ashwini Rao, Trupthi Kamal, Shoaib Department of Artificial Intelligence and Data Science Global Academy of Technology Bangalore India

ISBN: (纸本)9789819939312

Schizophrenia is a chronic illness that most frequently affects people between the ages of 16 and 30. There are many elements that lead to a patient receiving a diagnosis of the illness, but since the origin of the illness is unknown, fuzzy analysis can be an important tool in identifying the factors. The purpose of this study report is to inform readers of the factors that have the greatest influence on an individual. Fuzzy logic is a powerful tool for tackling a wide range of problems in research. It can be used to model complex systems, analyze decision-making processes, and develop systems that can recognize patterns in data. In addition, fuzzy logic can be used to model complex systems such as financial markets and natural phenomena. As fuzzy logic is able to deal with uncertainty and imprecise data, it is particularly well-suited to a wide range of research. Fuzzy TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) is a method used to determine the best of the options under consideration with respect to the weights and influence of each of the attributes associated with every option. Fuzzy AHP (Analytic Hierarchy Process) is a multi-criteria decision-making method that uses fuzzy set theory to evaluate alternatives. This method seeks to identify the best option from a set of alternatives based on the relative importance of the criteria. The goal of this study is to emphasize a through and in-depth literature evaluation of multi criteria decision making challenges in addition to pinpointing the aspects that contribute most significantly. We have implemented MCDM techniques to propose an effective approach towards decision making of various factors at multiple levels in patients suffering from schizophrenia and observed that the highest ranked Person (P4) with 0.8097 CCi can be inferred to most likely be affected by Schizophrenia, while the person at the bottom of the rank hierarchy (P1) with 0.2813 CCi is least likely to be affected. © The A

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Anemia Detection And Severity Prediction Using Classification Algorithms With Optimized Hyperparameters, Boosting Techniques And XAI 5

Anemia Detection And Severity Prediction Using Classificatio...

引用

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Kumar, Ashwin Chirag, Y. Kodipalli, Ashwini Rao, Trupthi Department of Artificial Intelligence and Data Science Global Academy of Technology Bangalore India

ISBN: (纸本)9798350361155

Anemia is a blood disorder where there's a shortage of blood cells or haemoglobin. If not detected or treated promptly it can pose health risks. Detecting anemia accurately and, on time is crucial for managing and preventing complications. In this study we analyzed a sample of 364 individuals to explore how different classification algorithms perform in detecting anemia and predicting its severity. We considered Logistic regression, K-Neighbours-Classifier (KNN) Support-Vector-Machine (SVM), decision-tree and Random-forest algorithms. We fine-tuned the hyperparameters using grid and random search validation techniques to optimize their performance. Additionally, we used boosting techniques like AdaBoost, Gradient Boosting, CatBoost and XGBoost to improve accuracy. To understand the model's predictions better we employed Local Interpretable Model Explanations (LIME) and SHAP (SHapley Additive exPlanations). Among the models evaluated the random forest model's with optimized hyperparameters showed the best accuracy, in detecting anemia followed by CatBoost. In the severity prediction again random-forest turned out to give the most accurate results. This research emphasizes the significance of using classification algorithms and interpretability techniques to achieve detection of anemia and predict its severity. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Fractal Image Encoding:A Comparative Study of Compression Techniques 10

Fractal Image Encoding:A Comparative Study of Compression Te...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Kulkarni, Milind Khedkar, Sanskruti Kumbhar, Sanket Mohod, Khushi Mandalpure, Shantanu Meshram, Yashashri Vishwakarma Institute of Technology Intelligence and Data Science Department of Artificial Pune India

ISBN: (纸本)9798350363104

Fractal image compression is a promising technique in the field of image compression. It is based on Affine contractive transforms and utilizes various methods such as fractal DCT, fractal wavelet compression, Huffman encoding, and decoding. This innovative approach involves feature extraction and a unique method of image comparison, making it a block-based image compression technique. The encoding time for fractal image compression is relatively high, while the decoding time is very short. Researchers have also explored the use of artificial intelligence techniques, such as neural networks, to reduce the search spaceand encoding time for fractal image compression, leading to significant advancements in this area. The technique has been lauded for its ability to detect and decode similarities between different regions in an image. Despite its advantages, the intensive computation required for fractal image compression can limit its practical use. Overall, fractal image compression holds great potential for achieving high compression ratios, butits computational demands remain a key consideration in its application. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Partial Label Learning with Noisy Labels

引用

Annals of data science 2025年第1期12卷 199-212页

作者： Zhao, Pan Tang, Long Pan, Zhigeng School of Artificial Intelligence Nanjing University of Information Science & Technology Nanjing210044 China Research Institute of Talent Big Data Nanjing University of Information Science & Technology Nanjing210044 China

Partial label learning (PLL) is a particular problem setting within weakly supervised learning. In PLL, each sample corresponds to a candidate label set in which only one label is true. However, in some practical application scenarios, the emergence of label noise can make some candidate sets lose their true labels, leading to a decline in model performance. In this work, a robust training strategy for PLL, derived from the joint training with co-regularization (JoCoR), is proposed to address this issue in PLL. Specifically, the proposed approach constructs two separate PLL models and a joint loss. The joint loss consists of not only two PLL losses but also a co-regularization term measuring the disagreement of the two models. By automatically selecting samples with small joint loss and using them to update the two models, our proposed approach is able to filter more and more suspected samples with noise candidate label sets. Gradually, the robustness of the PLL models to label noise strengthens due to the reduced disagreement of the two models. Experiments are conducted on two state-of-the-art PLL models using benchmark datasets under various noise levels. The results show that the proposed method can effectively stabilize the training process and reduce the model's overfitting to noisy candidate label sets. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

HL-YOLOv8s: A High-Performance and Lightweight Network for Fall Detection 5

HL-YOLOv8s: A High-Performance and Lightweight Network for F...

引用

5th International Seminar on artificial intelligence, Networking and Information technology, AINIT 2024

作者： Wu, Jianfei Dong, Meiqi Zhang, Yan Peng, Haojie Wang, Zhixiang Hebei University of Technology College of Artificial Intelligence and Data Science Tianjin China

ISBN: (纸本)9798350385557

AYOLOv8s-based fall detection method, termed HL-YOLOv8s, is presented in this paper. It achieves high-performance and lightweight prediction on edge devices via two steps: architectural design and model pruning. In the first step, three key components - the spatial collaborative perception fusion module (SCPFM), spatial channel dual attention network (SCDAN), and the dynamic decoupled head (DDH) - are designed to ensure considerable performance. SCPFM enhances global information perception via expanding receptive fields, while SCDAN aims to learn the relationship between different positions and channels with an attention mechanism. DDH, motivated by the recently popular Dynamic Head method, alleviates the negative effect caused by multiple down samplings of features. In the second step, random channel pruning is adopted to reduce the dependency on computing resources. Experimental results on the Fall Detection Image dataset (FDID) indicate that HL-YOLOv8s obtains a mean average precision (mAP@0.5:0.95) improvement of 3.0% compared to YOLOv8-s, while the number of parameters, floating point operations per second (FLOPS), and model size are reduced by up to 45.10%, 52.82%, and 43.93%, respectively. Additionally, the final model deployed on the Jetson Xavier NX satisfies the requirement of real-time detection. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

CogniVisio: Fusion Image Classifier 2

CogniVisio: Fusion Image Classifier

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Mundargi, Zarinabegam Shinde, Aryan Bahirat, Shravani Das, Shreya Deokar, Om Shetiya, Dipasha Vishwakarma Institute of Technology BTech- Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798350360523

CogniVisio is an innovative project that leverages state-of-the-art technologies such as Google Colab, Python, TensorFlow, Convolutional Neural Network (CNN) Inception for developing a robust image classification system. The project addresses the challenge of enhancing image classification accuracy by employing a fusion approach that combines the strengths of image generation and the powerful feature extraction capabilities of CNN Inception. With a dataset comprising 8732 images, our methodology achieves an impressive accuracy of 86.86%, showcasing the effectiveness of the proposed fusion image classifier. The utilization of cloud-based computing through Google Colab provides scalability and accessibility, making CogniVisio a versatile solution for image classification task. © 2024 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing Consumer Insights: Predicting Customer Purchase Behavior by using artificial Neural Networks Approach 2

Optimizing Consumer Insights: Predicting Customer Purchase B...

引用

2nd IEEE International Conference on Integrated intelligence and Communication Systems, ICIICS 2024

作者： Reddy, Vonteddu Adharsh Dilish, M. Kodipalli, Ashwini Harish, L. Soma, Bhavani Rohini, B.R. Department of Artificial Intelligence & Data Science Global Academy of Technology Bangalore India

ISBN: (纸本)9798331504960

This study investigates the use of artificial neural networks (ANN) to predict consumer purchase behavior based on behavioral and demographic characteristics. The proposed ANN model comprises input, hidden, and output layers, optimized through hyperparameter tuning for improved prediction accuracy. The model employs non-linear activation functions, including ReLU, Sigmoid, and Tanh, alongside both Stochastic Gradient Descent (SGD) and Adam optimizers to enhance learning efficiency. Results indicate that Adam and RMSprop optimizers achieve the best balance, with Adam providing the highest accuracy (0.88) and RMSprop showing the lowest loss (0.2614) with strong accuracy (0.87), making these optimizers well-suited for capturing complex consumer behavior patterns. Further accuracy, loss, confusion matrix, ROC curve, and area under the curve (AUC)-demonstrate the model's capacity to capture intricate patterns. The confusion matrix highlights high precision in classification, with an overall accuracy of correctly predicting 262 out of 300 cases. The ROC curve further supports the model’s classification strength, achieving an AUC of 0.92, which confirms its high discriminatory ability. These findings suggest the ANN model is effective for deriving consumer insights, capable of delivering accurate forecasts for data-driven marketing strategies and customer behavior optimization in practical business settings. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Cascaded Network for Airway Tree Segmentation Incorporating Multiple Attention Mechanisms 7

A Cascaded Network for Airway Tree Segmentation Incorporatin...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Yang, Hong Wei Wang, Yuan Zhu, Haixing Zhang, Jiaqi Deng, Xinyue Liu, Weipeng Hebei University of Technology The School of Artificial Intelligence and Data Science Tianjin China

ISBN: (纸本)9798350363173

Airway tree segmentation is crucial for diagnosing and treating lung diseases. A three-dimensional representation of the patient's airway tree serves as the foundation for bronchoscopic navigation, instrumental for preoperative planning and intraoperative visualization during intervention procedures. However, certain inherent characteristics such as complex structure, scale variation, and class imbalance often result in inadequate segmentation. To mitigate these limitations, we propose a cascaded airway tree segmentation network named Spatial-Channel-Deformable Cascade Network (SCD-CascadeNet). It consists of two main stages: coarse segmentation and fine segmentation. The coarse segmentation network swiftly localizes the major airways, while the fine segmentation network offers more precise segmentation of the peripheral minor airways. Specifically, the Spatial-Channel-Deformable Attention module (SCDA) is designed to capture crucial spatial regions and significant channel features within the skip connection of the fine segmentation network, thereby enhancing the network's ability to recognize tubular structures and peripheral airways. We evaluate our method using the challenging dataset named Airway Tree Modeling (ATM). Both qualitative and quantitative experimental results demonstrate that our method achieves competitive performance and holds promise for further clinical applications. © 2024 IEEE.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Exemplar-Based Continual Learning via Contrastive Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第7期5卷 3313-3324页

作者： Chen, Shuai Zhang, Mingyi Zhang, Junge Huang, Kaiqi School of Artificial Intelligence Beijing100049 China Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

Despite the impressive performance of deep learning models, they suffer from catastrophic forgetting, which refers to a significant decline in overall performance when trained with new classes added incrementally. The primary reason for this phenomenon is the overlapping or confusion between the feature space representations of old and new classes. In this study, we examine this issue and propose a model that can mitigate the problem by learning more transferable features. We employ contrastive learning, a recent breakthrough in deep learning, which can learn visual representations better than the task-specific supervision method. Specifically, we introduce an exemplar-based continual learning (CL) method using contrastive learning to learn a task-agnostic and continuously improved feature expression. However, the class imbalance between old and new samples in CL can affect the final learned features. To address this issue, we propose two approaches. First, we use a novel exemplar-based method, called determinantal point processes experience replay (DPPER), to improve buffer diversity during memory update. Second, we propose an old sample compensation weight (CW) to resist the corruption of the old model caused by new task learning during memory retrieval. Our experimental results on benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in terms of comparable performance. © 2020 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning based garbage recognition system 4

Deep learning based garbage recognition system

引用

4th International Conference on Machine Learning and Computer Application, ICMLCA 2023

作者： Song, Zelong School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China

ISBN: (数字)9781510680265

ISBN: (纸本)9781510680258

The rapid increase in the amount of rubbish and the diversity of the substances in people's daily rubbish are two major problems of rubbish disposal at present, and the rubbish problem brings a serious burden to the environment as well as a waste of resources. At present, the main approach to deal with the waste problem is through waste separation. However, today’s traditional manual classification method is still used to screen the rubbish, which is labour-intensive with low sorting efficiency. This paper proposes a deep learning-based intelligent rubbish classification system, which can quickly achieve the positioning and recognition of rubbish in complex backgrounds for classification by incoming pictures and effectively improve the efficiency of rubbish classification. The system uses TensorFlow as the deep learning platform, and the combination of a convolutional neural network and a fully connected neural network is used to achieve the construction of the deep learning model. Meanwhile, Some nodes of the fully connected layer are discarded with a given probability in the training phase to avoid the overfitting of the system to optimise the system, and the system is also optimised by collecting various types of rubbish pictures and building inspection datasets, using data augmentation to improve the robustness of the model, the fast and accurate identification of different types of rubbish is achieved. The experimental results demonstrate that the intelligent rubbish classification system proposed in this paper has a high performance in terms of both accuracy and efficiency. © 2024 SPIE.

关键词： Efficiency

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：