检索结果-内蒙古大学图书馆

Identifying Fake Reviews in Relation with Property and Political Data Using Deep Learning

Procedia computer science 2023年 218卷 1742-1751页

作者： Ashwin Valliappan S G R Ramya Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham India

Modern deep learning algorithms have achieved tremendous success in many visual applications by training a model with all relevant task-specific data. In this module fake reviews evolving in online political and property data will be discussed. Regarding political information there are many differences while switching from offline to online mode. The views and comments of the politicians in social media act as a question mark “whether it is true or not?”. In some cases, it appears to be real and sometimes it may be a false/fake statement. All because, the online information is often considered as the most important source of info for the users these kinds of reviews and comments affects the trust factors of social media. Now days in social media, more of toxic contents and unwanted information were present rather than the useful information. These toxic comments acts as a threat for users using the application. Hence users do not come forward to post their thoughts and actions or to share the information. This module is used to distinguish reviews, identify the factor in online mode of political and property comments in social media. The LSTM and BERT (Bidirectional Encoder Representations from Transformers) algorithms are used in the first module because they offer a wide variety of parameters such as learning rates, input and output biases, and text categorization. Additionally, GPT2 (Generative Pre-Trained Transformer 2) is implemented which helps in text generation, increasing the size of dataset for training in different classification models. Thus it is important to understand for us that ultimately the model will be getting trained in such a way that it is able to give accurate results while we are undergoing classification of text and also while we are undergoing the identification of fake/authentic comments that are there in the source of our data.

关键词： Doc2Vec Fasttext cold-start issue hybrid model LSTM RNN BERT

来源：评论

学校读者我要写书评

暂无评论

Image Denoising Method Based on Channel Compression and Split-Attention Mechanism 5

Image Denoising Method Based on Channel Compression and Spli...

引用

5th International Conference on computer engineering and Intelligent Control, ICCEIC 2024

作者： Sun, Hao Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Technology and Evaluation Shandong Engineering Research Center Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Shandong Yantai China

ISBN: (纸本)9798331507992

In the image restoration task, how to make full use of spatial and channel feature information to improve the reconstruction quality of the model without significantly increasing the computational complexity is an important research issue. To address this challenge, this paper proposes a CS module (Channel Compression and Split-Attention) specifically for optimizing image denoising tasks. The module first compresses the features through a preliminary convolution operation, then introduces the split attention convolution mechanism to split the features by channel and dynamically weight them, thereby enhancing the model's adaptive attention to different feature channels and improving feature expression capabilities. Through experiments on multiple image denoising datasets, the results show that the CS module significantly improves the image reconstruction quality, especially in terms of peak signal-to-noise ratio (PSNR). At the same time, the introduction of the CS module does not lead to a significant increase in computational complexity, maintaining a high computational efficiency, which verifies the practicality and superiority of the module in image denoising tasks. © 2024 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep Learning with XAI for Transparent and Accurate Doctor Prescription Recognition

Multimodal Deep Learning with XAI for Transparent and Accura...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Sunil Reddy J Tenzin Sungrab Norbu Pavan Kumar Praveen Vitthal Ajjanakatt Reddyam Harsha U Ananthanagu Department of Computer Science and Engineering Alliance School of Advanced Computing Alliance University India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

This paper presents a deep learning framework to automate recognition of medical prescriptions by using handwritten content, feature extraction from CNNs like VGG16, Alex Net, and MobileNetV2, and sequential data utilizing LSTMs. A multi-modal approach captures even the spatial and temporal details in a prescription, which assists in an accurate interpretation of complex handwriting. Specifically, key pre- processing like grayscale conversion, normalization and edge detection improving the quality of the image, reducing noise and bringing forth the prominent features that aid in the improvement of recognition accuracy and also implementation of XAI concepts to further enhance the interpretation. This model reduces transcriptions, making it easier for the patients as well as the practitioners to understand the handwriting through the computer screen. The method therefore assists in safer patient-centered healthcare by automating prescription processing thus triggering clearer communication towards more informed healthcare decisions.

关键词： Deep learning Handwriting recognition Accuracy Text recognition Computational modeling Medical services Predictive models Feature extraction Transformers Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Compressive Sensing Based Image Compression-Encryption Scheme Using Triangular Series and Novel Chaotic Map

Compressive Sensing Based Image Compression-Encryption Schem...

引用

Delhi Section Conference (DELCON), IEEE

作者： Kolagani Yeshwanth Sai K Ashwini Vadde Karthik Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

In recent years communication through image has evolved so much that we must make sure that secret message stages should not be leaked. Hence the use of compression-encryption algorithms is of utmost necessity. In this paper, we present a unique chaotic map and encryption algorithm that can provide a robust yet efficient method for securing digital images against unauthorized access. The proposed encryption scheme begins by employing the triangular series to rearrange the pixel values of the input image. For the encryption process to offer a high level of security, a chaotic map is designed to display desirable qualities like ergodicity, unpredictability, and sensitivity to the initial key values. image compression through the Compressive sensing approach because of its lightweight implementation and suitability for resource-constrained environments like real-time image processing applications and Internet of Things devices. To prove the robustness of the chaotic map and encryption algorithm, many quantitative evaluation metrics such as entropy, correlation, bifurcation etc are used.

关键词： Image coding Sensitivity Machine learning algorithms Chaotic communication Digital images Real-time systems Encryption Sensors Internet of Things Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Data Fusion Architecture Empowered with Deep Learning for Breast Cancer Classification

引用

computers, Materials & Continua 2023年第12期77卷 2813-2831页

作者： Sahar Arooj Muhammad Farhan Khan Tariq Shahzad Muhammad Adnan Khan Muhammad Umar Nasir Muhammad Zubair Atta-ur-Rahman Khmaies Ouahada Faculty of Computing Riphah International UniversityIslamabad45000Pakistan Department of Forensic Sciences University of Health SciencesLahore54000Pakistan Department of Electrical and Electronic Engineering Science University of JohannesburgP.O.Box 524Johannesburg2006South Africa School of Computing Skyline University CollegeUniversity City SharjahSharjah1797United Arab Emirates Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department of Software Faculty of Artificial Intelligence&SoftwareGachon UniversitySeongnamGyeonggido13120Korea Department of Computer Science Bahria UniversityLahore CampusLahore54000Pakistan Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia

Breast cancer(BC)is the most widespread tumor in females worldwide and is a severe public health *** is the leading reason of death affecting females between the ages of 20 to 59 around the *** detection and therapy can help women receive effective treatment and,as a result,decrease the rate of breast cancer *** cancer tumor develops when cells grow improperly and attack the healthy tissue in the human *** are classified as benign or malignant,and the absence of cancer in the breast is considered *** learning,machine learning,and transfer learning models are applied to detect and identify cancerous tissue like *** research assists in the identification and classification of *** implemented the pre-trained model AlexNet and proposed model Breast cancer identification and classification(BCIC),which are machine learning-based models,by evaluating them in the form of comparative *** used 3 datasets,A,B,and *** fuzzed these datasets and got 2 datasets,A2C and *** A2C is the fusion of A,B,and C with 2 classes categorized as benign and *** B3C is the fusion of datasets A,B,and C with 3 classes classified as benign,malignant,and *** used customized AlexNet according to our datasets and BCIC in our proposed *** achieved an accuracy of 86.5%on Dataset B3C and 76.8%on Dataset A2C by using AlexNet,and we achieved the optimum accuracy of 94.5%on Dataset B3C and 94.9%on Dataset A2C by using proposed model BCIC at 40 epochs with 0.00008 learning *** proposed fuzzed dataset model using transfer *** fuzzed three datasets to get more accurate results and the proposed model achieved the highest prediction accuracy using fuzzed dataset transfer learning technique.

关键词： Breast cancer classification deep learning machine learning transfer learning learning rate

来源：评论

学校读者我要写书评

暂无评论

Enhancing Migraine Diagnosis and Classification with TabNet: A Data-Driven Approach

Enhancing Migraine Diagnosis and Classification with TabNet:...

引用

International Conference on Confluence The Next Generation Information Technology Summit (Confluence)

作者： Shaik Nawab Mudassir Ravichandran M Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

In recent years, significant advancements in health-care analytics have shown immense potential in enhancing patient care and clinical decision-making. This research delves into innovative methods for precise migraine classification using TabNet, a state-of-the-art deep learning model specifically designed for tabular data. Migraine, a debilitating neurological condition, poses challenges in accurate categorization and effective management. Our method utilizes the capabilities of TabNet to establish a robust system for classifying various migraine subtypes. We leverage a rich array of clinical and patient-reported data to enable accurate, automated diagnosis. This research underscores the impact of advanced analytical techniques in healthcare, offering a more personalized, data-centric approach to diagnosing and treating migraines. Our findings reveal an impressive 98% accuracy in overall migraine classification, outperforming other methods, and an exceptional approximate 99% accuracy in identifying specific migraine subtypes. Through TabNet, we aim to advance healthcare analytics, providing healthcare professionals with enhanced tools for patient care and contributing to the broader field of precision medicine.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Modelling of Diabetes Complications: Insights from Binary Classifier on Chronic Diabetic Mellitus

Predictive Modelling of Diabetes Complications: Insights fro...

引用

Communication, computer sciences and engineering (IC3SE), International Conference on

作者： Smita Panigrahy Sachikanta Dash Sasmita Padhy Naween Kumar Yajnaseni Dash Computer Science and Engineering GIET University Gunupur Odisha School of Computing Science and Engineering VIT Bhopal University Bhopal MP School of Computer Science Engineering and Technology Bennett University Greater Noida Uttar Pradesh India School of Computer Science Engineering and Technology Bennett University Uttar Pradesh India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

Chronic diabetes Mellitus (DM) leads to severe consequences such as nephropathy, neuropathy, and retinopathy. Various learning algorithms are employed to forecast and categorize eight issues, encompassing metabolic syndrome and dyslipidemia. Machine learning is revolutionizing various domains by enabling algorithms to extract models from data. The main objective of this proposed study is to utilize binary classifiers to predict and categorize eight problems associated with DM. For this study we have used the dataset obtained from the Jeevandeep Hospital and Research Centre (JHRC) in Baripada, Mayurbhanj, Odisha, India. It includes 1296 records and has nine input variables and eight output categories that indicate different issues. Multiple models were constructed to address problems like Nephropathy, neuropathy, dyslipidemia, diabetic foot, metabolic syndrome, retinopathy, hypertension, and obesity. Different preprocessing operations on missing data, unbalanced data, and feature selection are employed. Binary classifiers were developed for each type of complication, with the number of records varied for each. Subsequently, an evaluation was conducted. The models achieved a maximum of 95.7% accuracy and 97.9% F1 score. The study demonstrates the effectiveness of using selected features to build accurate classifiers for predicting diabetes complications.

关键词： Hypertension Machine learning algorithms Retinopathy Predictive models Prediction algorithms Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Secure Protocol With Mutual Authentication For Telecare Medical Information System Using ECC For IOT Enabled WBAN Devices

Secure Protocol With Mutual Authentication For Telecare Medi...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： Ss Anushaa S Naundhini Dharminder Chaudhary Department of Computer Science and Engineering (Amrita School of Computing) Amrita Vishwa Vidyapeetham Chennai

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

Telecare Medical Information System (TMIS) is a technology that has been on rise in the recent times with the onset of the COVID-19 pandemic. TMIS can be implemented in wireless body area networks (WBAN) in the form of devices worn by the patient and is convenient and time saving for both patients and doctors. The data that is generated is transferred through an insecure channel and thus, there is a need to protect confidential patient data. There is a necessity to provide secure authentication and access control to ensure only authorized users can access the data even in a device with limited storage and computational power. In this paper, Elliptic Curve Cryptography and the three-factor authentication method are combined to propose an enhanced protocol that is immune to the flaws in previously proposed ones. It uses a trusted party that helps in the registration process, ensuring that only authorized parties can read the data. A cloud-assisted TMIS is implemented by using the cloud as a storage medium and securing it, as well as the transfer of data. The Automated Validation of Internet Security Protocols and Applications (AVISPA) tool is used to validate the proposed protocol and prove its security.

关键词： Wireless communication Cloud computing Protocols Pandemics Authentication Medical services Medical information systems Body area networks Elliptic curve cryptography Secure storage

来源：评论

学校读者我要写书评

暂无评论

Travel Destination Recommendation System based on Machine Learning by Analyzing Instagram Review Comments and Hashtags

Travel Destination Recommendation System based on Machine Le...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Sruthi.M.S Arathy Krishna Anu Prabha.R.S Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

This project aims to develop an advanced hybrid travel recommendation system that leverages emotion extraction from user comments and visual recognition from images to provide personalized travel suggestions. The system integrates three distinct datasets an image dataset, a custom dataset containing location details, sublocation information, user comments, and hashtags, and a user interaction dataset comprising user IDs, locations, and ratings. Emotion extraction is performed exclusively on user comments to capture sentiments, while visual recognition is applied to images to identify and classify visual *** recommendation system employs a hybrid approach, combining collaborative filtering and content-based filtering techniques. Collaborative filtering utilizes user interaction data to identify similarities between users and recommend locations based on their ratings. Content-based filtering, on the other hand, analyzes user posts, comments, and hashtags to recommend locations and sublocations that match the user’s preferences and *** enhance user engagement and accessibility, a user interface is developed, allowing users to input their posts (images and captions) and receive personalized travel recommendations. This interface not only makes the system user-friendly but also facilitates seamless interaction, providing users with insightful travel suggestions based on their unique ***, this project demonstrates the effectiveness of integrating emotion extraction and visual recognition into a hybrid recommendation system, offering a sophisticated solution for personalized travel planning and exploration.

关键词： Visualization Emotion recognition Image recognition Filtering Reviews Collaborative filtering Machine learning Market research Planning Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Strategic Applications of Deep Belief Networks in Anomaly Detection and Generative Modeling for Business Intelligence 5th

Strategic Applications of Deep Belief Networks in Anomaly De...

引用

5th International Conference on Electrical and Electronics engineering, ICEEE 2024

作者： Bansal, Abhay Singh, Jagendra Mathur, Anubhav Alghamdi, Mohammed. I. Anant, B.C. Agnihotri, Kuldeep Kaliyar, Rohit Kumar School of Computer Science Engineering & Technology Bennett University Greater Noida India School of Media Bennett University Greater Noida India Computer Science Department Faculty of Computing and Information Al-Baha University Al-Baha65779 Saudi Arabia School of Management Studies Sandip University Madhubani India Director ISBA Group of Institutes Indore Madhya Pradesh Indore India

ISBN: (纸本)9789819791118

This study examines the strategic deployment of Deep Belief Networks in detecting anomalies and performing generative modeling in business intelligence efforts. Three kinds of DBN models, such as Temporal-DBN, Variational-DBN, and Sparse-DBN, were reviewed and assessed for their performance, especially in conducting anomaly detection in a diverse range of data acquired from the online domain and real-time banking transactions. Evaluation measures, including accuracy, precision, recall, and F1 scoring, indicate that the Temporal-DBN model is significantly superior to others, showing an accuracy percentage of 97.67% relative to Variational-DBN and Sparse-DBN, which were rated at 93.45% and 90.23%, respectively. Examining the receiver operating curves further reinforced the efficacy of the Temporal-DBN model at a higher percentage rate of 0.978 against Variational-DBN and Sparse-DBN, which were rated at 0.953 and 0.922, respectively, indicating higher discrimination ability between normal and anomalous instances. Theoretical data analysis, particularly through confusion matrices, demonstrated that Temporal-DBN provides a balanced performance of the minimized number of misclassified cases, with higher true positive rates and true negative rates compared to Variational-DBN and Sparse-DBN. Overall, these measures and outcomes imply that Deep Belief Networks, especially the Temporal-DBN model, have the potential to maximize anomaly detections and the generative modeling efforts of business intelligence solutions. They also suggest increased theoretical and methodological innovation for wider applications in conducting analysis and data-driven decision-making in a broad range of business fields using deep learning methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

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：