检索结果-内蒙古大学图书馆

18th International Conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2024

作者： Chaurasia, Anushka Kumar, Deepak Yogita, Yogita Department of Computer Science and Engineering National Institute of Technology Meghalaya Shillong India Department of Computer Engineering National Institute of Technology Kurukshetra Kurukshetra India

ISBN: (纸本)9783031878725

In the context of modern medicine, where polypharmacy is prevalent, particularly among older adults, the potential for hazardous drug-drug interactions (DDIs) is a significant concern. These interactions can lead to severe adverse reactions, with consequences ranging from debilitating health complications to fatality. Previously, distinct machine learning and deep learning algorithms were used to predict DDIs using gold-standard datasets. These methods demonstrate remarkable accuracy but lack precision due to a high false positive rate. Therefore, there is a crucial need to enhance the models’ ability to reduce the false positive rate. This paper introduces a deep learning-based framework named InteractNet to enhance precision in DDI predictions. This framework employs 1D convolutional neural networks with streamlined parameterization in the convolutional layer for multi-scale feature extraction, bidirectional long short-term memory to capture drug feature interactions, and an attention mechanism to concentrate on key data features for precise predictions. The efficacy of InteractNet is thoroughly examined through five performance metrics, namely accuracy, precision, true positive rate, harmonic mean, and ROC-AUC score. Results indicate that InteractNet achieves the highest testing accuracy of 94.29 ± .0088, a precision of 94.23 ± .0023, a true positive rate of 94.49 ± .0037, a harmonic mean of 94.21 ± .0029, and a ROC-AUC score of 96.24 ± .0032. These outcomes surpass those of existing state-of-the-art methods, underscoring the profound potential of deep learning to enhance medical safety. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Drug interactions

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection: Exploring the Efficiency of Soft and Hard Voting Ensemble 4

Fake News Detection: Exploring the Efficiency of Soft and Ha...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Rahman, Arifur Zaman, Sakib Parvej, Shahriar Shill, Pintu Chandra Salim, Md. Shahidul Das, Dola Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna9203 Bangladesh

Fake news dissemination is a critical problem, jeopardizing the reliability of information and eroding public confidence. Machine learning provides a solution by distinguishing between real and misleading news. In this study, we utilized various classifiers such as KNN, Logistic Regression, Decision Tree, LightGBM, XGBoost, Gradient Boosting, Random Forest, and Naive Bayes on an open-source dataset. Tf-idf (Term frequency-inverse document frequency) and Count vectorization were used for text preprocessing, and soft and hard voting ensembles were applied to the best three and five models to boost performance. Additionally, we employed BERT (Bidirectional Encoder Representations from Transformers) and CNN (Convolutional Neural Network) models with various optimizers (adam, rmsprop, SGD, adadelta, and adagrad) to further improve classification. The BERT model, optimized with adam, achieved the highest accuracy of 99.93%, with perfect precision (100%) and high recall (99.84%). Furthermore, using Count vectorization for feature extraction, the soft voting ensemble of the top five models (LGBM, XGB, RF, DT, LR) achieved peak performance among all ensemble models, achieving 99.87% accuracy, with precision, recall, f1-score, MAE, MSE, RMSE, RAE, and RRSE of 99.83%, 99.88%, 99.86%, 0.13%, 0.13%, 3.66%, 0.27%, and 7.80%, respectively. The exhaustive experimentation confirms the applicability and efficiency of the recommended models in identifying fake news. © 2025 The Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bridging the Bandwidth Gap: A Mixed Band Telephonic Urdu ASR Approach with Domain Adaptation for Banking Applications 1

Bridging the Bandwidth Gap: A Mixed Band Telephonic Urdu ASR...

引用

1st Workshop on Challenges in Processing South Asian Languages, CHiPSAL 2025, co-located with the 31st International Conference on Computational Linguistics, COLING 2025

作者： Khalid, Ayesha Adeeba, Farah Sehar, Najm Ul Hussain, Sarmad Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan Department of Computer Science University of Engineering and Technology New Campus Pakistan

ISBN: (纸本)9798891762015

The accuracy of Automatic Speech Recognition (ASR) systems is influenced by the quality and context of speech signals, particularly in telephonic environments prone to errors like channel drops and noise, leading to higher Word Error Rates (WER). This paper presents the development of a large vocabulary Urdu ASR system for telephonic speech, based on a corpus of 445 speakers from diverse domains. The corpus, annotated at the sentence level, is used to train and evaluate GMM-HMM and chain Time-Delay Neural Network (TDNN) models on a 10-hour test set. Results show that the TDNN model outperforms GMM-HMM. Mixing narrowband and wideband speech further reduces WER. The test sets are also evaluated for the pre-trained model Whisper for performance comparison. Additionally, system adaptation for the banking domain with a specialized lexicon and language model demonstrates the system’s potential for domain-specific applications. © 2025 International Committee on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

LeukoDeepNet: A Novel Approach in Automated Identification of Leukemia Diseases in Microscopic Human Blood Cells

LeukoDeepNet: A Novel Approach in Automated Identification o...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Hossain, Md. Monwar Sakib, Najmus Milu, Insan Ara Jennifer, Sanjeda Sara Morshed, Md. Adnan Wasif Reza, Ahmed Arefin, Mohammad Shamsul East West University Department of Computer Science and Engineering Dhaka Bangladesh Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798331529765

Leukemia, a critical hematologic malignancy, demands early and accurate diagnosis for effective treatment. In this research, we present a comprehensive approach to the detection of leukemia based on microscopic human blood cell images. Our research is dedicated to the early detection of leukemia by leveraging deep learning techniques on microscopic blood cell images. The study introduces a new modified VGG16 model, LeukoDeepNet, and compares it with conventional Convolutional Neural Network (CNN) and Inception (GoogLeNet) models. LeukoDeepNet stands out with remarkable training and validation accuracies of 99.96% and 92.63%, along with low training and validation losses of 0.0013 and 0.6295, respectively. These findings underscore the success of the approach and its potential to enhance both leukemia diagnosis and treatment. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

引用

computer Modeling in engineering & sciences 2025年第1期142卷 209-229页

作者： Jiawei Tian Yu Zhou Xiaobing Chen Salman A.AlQahtani Hongrong Chen Bo Yang Siyu Lu Wenfeng Zheng Department of Computer Science and Engineering Major in Bio Artificial IntelligenceHanyang UniversityAnsan-si15577Republic of Korea School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11574Saudi Arabia School of Automation University of Electronic Science and Technology of ChinaChengdu610054China

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical *** study proposes a novel end-to-end disparity estimation model to address these *** approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting *** study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and *** model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video *** results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing ***,the model exhibited faster convergence during training,contributing to overall performance *** study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

关键词： Parallax estimation parallax regression model self-supervised learning Pseudo-Siamese neural network pyramid dilated convolution binocular disparity estimation

来源：评论

学校读者我要写书评

暂无评论

Hybrid approach for the detection of epileptic seizure using electroencephalography input

引用

International Journal of Information technology (Singapore) 2024年第1期16卷 569-575页

作者： Basha, Niha Kamal Surendiran, B. Benzikar, Amutha Joyal, S. School of Computer Science and Engineering Vellore Institute of Technology (VIT) Vellore India Department of Computer Science and Engineering National Institute of Technology (NIT) Puducherry Karaikal India School of Computer Science and Engineering Vellore Institute of Technology (VIT) Chennai India Saveetha Engineering College Chennai India

In the early days, it was difficult to study bio-electric signals, but now a days these problems have been solved by many hardware devices which are available at low cost. Even then there is a need for technical improvements to process bio-electric signals. Enormous effort has been taken for the detection of epileptic seizure from EEG signal. Considerable evidence available on Bonn university EEG dataset for epileptic seizure detection. However, deep learning algorithms have not applied often on Bonn university data like other machine learning algorithms for the detection of epileptic seizure due to the less availability of data. This work adopted machine learning and deep learning models for the detection of epileptic seizure. The data consists of a hundred subjects with sampling rate as 173.61 Hz of ‘S’ (ictal) and ‘Z’ (normal) dataset. The results show how the choice of healthy and ictic subjects through high order functional math decision like variance (STD), Power, Skewness, and Kurtosis values are analyzed to extract epileptic features. The performance of classifiers has been evaluated based on the evaluation metrics within which CGRU-SVM outperforms all other models with 97.54% accuracy. The features are extracted based on the statistical measures to detect epileptic seizure. Further, the proposed work provides more evidence on the epileptic seizure features, and it shows the new possibility for using deep learning models for epileptic seizure detection. In future, an analysis must be performed with dynamic sets of input and different analysis techniques. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Confusion matrix Deep learning model Electroencephalography Epilepsy Ictal subject Rhythmic frequency Statistical feature

来源：评论

学校读者我要写书评

暂无评论

Forensic Eye: Convolutional Neural Network-based Crime Scene Object Detection System 2

Forensic Eye: Convolutional Neural Network-based Crime Scene...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Sudha, I. Vadivel, M. Lakshmiramana, P. Kalpana, N. Kumar, Nellore Manoj Vinoth, R. Saveethe University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science Tamilnadu Chennai India Excel Engineering College Department of Information Technology Komarapalayam Namakkal India Madanapalle Institute of Technology & Science Department of Computer Science & Technology Andhra Pradesh India Psna College of Engineering and Technology Department of Computer Science and Engineering India Saveetha School of Engineering Department of Mathematics Tamilnadu Chennai India Rmk College of Engineering and Technology Department of Computer Science and Engineering Puduvoyal India

ISBN: (纸本)9798350364699

Forensic investigations rely heavily on the accurate detection and analysis of crime related objects present at crime scenes. Traditional methods of object detection often involve manual labor and are error prone process to human error. In recent years, Convolutional Neural Networks (CNNs) have shown remarkable success in various computer vision tasks, including in object detection. In this article, we introduce ForensicEye, a novel CNN-based crime scene object detection system designed to assist forensic investigators in identifying the objects related to the crime. It utilizes a state-of-the-art CNN architecture trained on a large dataset of crime scene images, enabling robust detection even in challenging lighting and environmental conditions. We evaluated the performance of the ForensicEye on benchmark datasets with various preprocessing techniques, demonstrating its superior accuracy and efficiency compared to traditional methods. Our proposed model achieved the accuracy of 96.2%, precision of 97.9%, Recall of 96.9%, F1-score of 97.4%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing skin lesion diagnosis with data augmentation techniques: a review of the state-of-the-art

引用

Multimedia Tools and Applications 2024年 1-40页

作者： Patil, Aniket Mehto, Anjula Nalband, Saif Maharashtra Pune411048 India Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Bhadson Road Punjab Patiala147004 India

Even if more and more high-quality public datasets are available, one of the biggest problems with deep learning for skin lesion diagnosis is the scarcity of training samples. Deep Convolutional Neural Networks (CNNs) have exhibited remarkable performance across multiple computer Vision tasks. Despite their tendency to surpass conventional machine learning methods, the models produced by these algorithms require larger datasets to be accessible during training. An increasingly popular method to deal with this problem is data augmentation, especially in domains like medical imaging where big datasets are hard to come by. Experiments on independent, unknown datasets have demonstrated improved performance using data augmentation, which creates more data to train the model. This survey devotes a lot of time to using augmentation techniques based on basic data augmentation algorithms and the pros and cons of Test Time Augmentation (TTA), Generative Adversarial Networks (GANs), Variational Auto-Encoders (VAEs), and Synthetic Minority Oversampling Techniques (SMOTE). The main focus of this survey is data augmentation, which addresses the problem of limited data by providing a solution within the data space. When these approaches are incorporated into clinical practice, our research attempts to clarify them and increase trust in the reliability of AI models created from augmented data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of Insurance Claims for Health Sector using Machine Learning Techniques 3

Prediction of Insurance Claims for Health Sector using Machi...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Pragatheeswari, E. Kavitha, M.N. Saranya, S.S. Dhanushree, D. Jasmitha, S. Abiradhie, P.V. Department of Computer Technology Kongu Engineering College Perundurai Erode India Department of Computer Science and Design Kongu Engineering College Perundurai Erode India Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

Nowadays, health issues play a tremendous role in day-to-day life and the medical expenditure to get treatment becomes more difficult for the ordinary people. Health insurance has become a vital aspect of people's lives. In this massive community, to access healthcare services such as insurance policies, LIC, ICICI, HDFC ERGO, Star Healthcare are benefits for claiming an amount for their medical expenses. The dataset encompasses three categories, such as generalized data, hospitalized data and claim data. Each record in the dataset represents an individual’s health insurance charges along with corresponding demographic and health-related characteristics. In this paper, Machine Learning techniques are used to group the claim amount that has been adopted by the individuals based on the hospitalized expenditure and insurance charges paid by the individuals. In the health sector, machine learning techniques are used to forecast insurance claims by building predictive models from historical data on claims, patient demographics, treatment types, and results. By predicting future claims based on trends seen in the data, these models help insurance firms better manage risk and allocate resources. In case of a fresher to this concept, it feels challenging to understand whereas generating as a pattern can be more flexible to acquire knowledge about how much amount has been claimed. © 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

Novel Double Modular Redundancy Based Fault-Tolerant FIR Filter for Image Denoising

引用

computer Systems science & engineering 2023年第7期46卷 181-193页

作者： V.S.Vaisakhi D.Surendran Department of Electronics and Communication Engineering Nehru Institute of Engineering and TechnologyCoimbatore641105India Department of Computer Science and Engineering KPR Institute of Engineering and TechnologyCoimbatore641105India

In signal processing and communication systems,digital filters are widely *** some circumstances,the reliability of those systems is crucial,necessitating the use of fault tolerant filter *** strategies have been presented throughout the years to achieve fault tolerance by utilising the structure and properties of the *** technology advances,more complicated systems with several filters become *** of the filters in those complicated systems frequently function in parallel,for example,by applying the same filter to various input ***,a simple strategy for achieving fault tolerance that takes advantage of the availability of parallel filters was *** fault-tolerant ways that take advantage of the filter’s structure and properties have been proposed throughout the *** primary idea is to use structured authentication scan chains to study the internal states of finite impulse response(FIR)components in order to detect and recover the exact state of faulty modules through the state of non-faulty ***,a simple solution of Double modular redundancy(DMR)based fault tolerance was developed that takes advantage of the availability of parallel filters for image *** approach is expanded in this short to display how parallel filters can be protected using error correction codes(ECCs)in which each filter is comparable to a bit in a standard ECC.“Advanced error recovery for parallel systems,”the suggested technique,can find and eliminate hidden defects in FIR modules,and also restore the system from multiple failures impacting two FIR *** the implementation,Xilinx ISE 14.7 was found to have given significant error reduction capability in the fault calculations and reduction in the area which reduces the cost of *** were introduced in all the outputs of the functional filters and found that the fault in every output is corrected.

关键词： Fault tolerance filters efficiency redundancy image denoising error correction codes double modular redundancy

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：