检索结果-内蒙古大学图书馆

Blockchain-based cryptographic approach for privacy enabled data integrity model for IoT healthcare

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2025年第1期37卷 53-74页

作者： Chandol, Mohan Kumar Rao, M. Kameswara Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram Andhra Pradesh India Koneru Lakshmaiah Educ Fdn Dept ECM Vaddeswaram Andhra Pradesh India Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram 522302 Andhra Pradesh India

The development of Internet of Things (IoT) technologies allowed the rapid generation of massive amounts of data by people. Although moving data to a server is a useful solution for storage, the owner of the data loses control, which results in security lapses. An efficient method for cloud-based data models is data integrity. In order to protect data privacy in IoT healthcare, this paper develops a data integrity technique. The Data Owner, IoT server, Key Generator Center, and Auditor are the four entities that make up this model. Here, the ability to verify the accuracy of the outsourced data is present in the auditor, data owner, and IoT server. The setup, storage, and verification phase are the three stages that make up the data integrity model. Here, the proposed Taylor-based Border Collie Cat optimisation is used to generate integrity keys in the best possible way. Here, the Taylor series and Border Collie Cat optimisation (BCCO) are combined to derive the proposed Taylor-based BCCO. Python is used to carry out the proposed strategy's implementation. The proposed method offered enhanced performance with highest normalised variance of 0.710, highest conditional privacy of 2.880, and smallest computation time of 0.179 sec using heart disease dataset.

关键词： Blockchain Privacy IoT healthcare Cryptography Data integrity

来源：评论

学校读者我要写书评

暂无评论

Weighted Canonical Regressive Gradient Multilayer Perceptive Classifier for Identification of Coronary Artery Plaque and Stenosis with X-Ray Angiogram Images

引用

IETE JOURNAL OF RESEARCH 2025年

作者： Jayasree, M. Rao, L. Koteswara Koneru Lakshmaiah Educ Fdn Hyderabad 500043 Telangana India

Coronary artery disease (CAD) is a prevailing form of heart disease, which happens when atherosclerotic plaque, stenosis, or blood clots occur in the walls of coronary arteries. X-ray coronary angiogram holds significant value in computer-assisted diagnosis of CAD. Automatic detection demands a chore because of multifaceted vascular structures and the deprived quality of coronary angiogram images. X-ray angiogram images give detailed data regarding anatomy and blood flow in coronary arteries and play an essential task in diagnosing and treating CAD. Conventional detection methods are extremely time-consuming but accurate. Automated detection of CAD makes the issue challenging. To improve the accuracy of CAD, a novel technique called Weighted Canonical Regressive Gradient Multilayer Perceptive Classifier (WCRGMPC) has been introduced. The proposed WCRGMPC includes three major processes, namely image preprocessing, feature extraction and classification. Firstly, the X-ray angiogram images are collected from the dataset and used as input and get preprocessed using weighted adaptive generalized Kuwahara filtering technique which increases the overall region contrast by diminishing the issue of unwanted noise amplification. Secondly, an efficient feature extraction process is carried out on enhanced angiogram images to improve the performance of DL methods. Feature extraction procedure facilitates enhancing optimal accuracy of CAD in a minimum time. Finally, classification is done by using the Tversky Descent Deep Multilayer Perceptive Classifier for mapping the pixel with extracted features and identifying coronary plaque and stenosis in coronary angiogram images. In conclusion, our approach improves CAD identification accuracy and reduces loss. Experimental evaluation is carried out using the X-ray angiogram images dataset on various factors with numerous angiogram images and image sizes.

关键词： Coronary artery disease detection X-ray angiogram images Feature extraction Tversky descent deep multilayer perceptive classifier Weighted adaptive generalised Kuwahara filter-based preprocessing

来源：评论

学校读者我要写书评

暂无评论

IoT-based smart healthcare using efficient data gathering and data analysis

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2025年第1期18卷 15-24页

作者： Sahib, Raja Basha Adam Bhavani, R. Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram AP India

An IoT-based savvy medical service is the utilization of interconnected shrewd gadgets and sensors, similar to wearable, trackers, and portable applications, to gather and send continuous wellbeing information to attendants and specialists. This advancement focuses on remote checking and patient clinical issues, fortunate reflections, and restructured care. Using Internet of Things (IoT) devices, patients can remotely monitor their health conditions and send real-time data to healthcare providers. The next step is to use cutting-edge analytical tools to find patterns in the data and potential health issues. This encourages more proactive and preventative care, allowing providers of medical services to mediate earlier issues and possibly avoid more serious ones. Additionally, data analysis can provide insight into population health patterns, assisting health authorities in making more informed decisions regarding asset distribution and disease prevention efforts. Our paper introduces a novel framework for early disease diagnosis in IoT-based smart healthcare systems, employing efficient data collection and analysis methods. Specifically, we delve into the modified Influence Buddy Optimization (MIBO) algorithm for energy-efficient clustering during data collection and the Sparrow Search-based Self-Tuning (S3T) model for cluster head selection under design constraints. Additionally, we propose the Fractal Interpolation with Convolution Neural Network (FI-CNN) hybrid deep learning model for disease classification and detection. To assess the effectiveness of our framework, we conduct extensive validation experiments employing various performance metrics to evaluate both analytical and data collection models. Notably, our proposed MIBO-S3T scheme exhibits remarkably low energy consumption, achieving a 52.43% reduction compared to existing schemes. This work aims to succinctly present the background, problem statement, methodology, and key findings of our work, providing

关键词： Early diagnosis IoT network Smart healthcare Data gathering Data analysis

来源：评论

学校读者我要写书评

暂无评论

Speech2Dementia: A Novel Deep Learning Framework Integrating Enhanced CNN and Large Language Models for Automatic Detection of Alzheimer's Dementia

引用

COMPUTATIONAL INTELLIGENCE 2025年第2期41卷

作者： Chakravarthi, Bandaru A. Shivakanth, Gandla Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Hyderabad India

Early diagnosis of Alzheimer's disease (AD) is important for early intervention, but current diagnostic tools tend to use unimodal methods, processing either speech or text separately. Although models such as the ComParE Baseline for audio and BERT-based text classifiers have been successful, they do not take advantage of the complementary strengths of both modalities, which restricts their diagnostic power. To overcome this, we suggest SPID-AD (Speech-Based Intelligent Detection of Alzheimer's Dementia), a multimodal deep-learning approach that combines linguistic and acoustic features for the automated detection of Alzheimer's. Our approach uses a BERT-based architecture to mine semantic patterns from transcripts and an augmented Convolutional Neural Network (CNN) to process Mel-spectrogram representations of speech. By combining these features in dense layers, the model retains language-related as well as auditory biomarkers of cognitive impairment. Assessed on the DementiaBank Pitt Corpus, SPID-AD has 95.6% classification accuracy, surpassing state-of-the-art models in precision, recall, and F1-score. The findings demonstrate the strength of multimodal analysis in detecting dementia speech patterns, providing a non-invasive, AI-based diagnostic tool that may assist clinicians in the early detection of Alzheimer's.

关键词： Alzheimer's dementia detection enhanced CNN-BERT framework healthcare AI diagnostics multimodal deep learning speech and text analysis

来源：评论

学校读者我要写书评

暂无评论

Comprehensive approach to predictive analysis and anomaly detection for road crash fatalities

引用

AIP ADVANCES 2025年第1期15卷

作者： Gowthami, Chopparapu Kavitha, S. Koneru Lakshmaiah Educ Fdn Dept CSE Guntur Andhra Pradesh India

Since traffic accidents are a major global cause of injury and death, it is essential to comprehend and reduce their effects. Finding high-risk areas and creating focused interventions to increase road safety are made possible by the research's analysis of numerous variables that affect the number of fatalities in traffic crashes, including weather, road features, and geographic locations. To further contribute to the overall objective of building safer transportation networks for everyone, the application of predictive models and anomaly detection techniques enables proactive steps to avert collisions and lower the number of fatalities on our roadways. With the main objective of improving road safety, a thorough approach was put into place to evaluate data from traffic crashes, forecast deaths, and identify abnormalities. Using a multimodal method, the research first combines two datasets based on geographic coordinates: crash data and traffic count data. This integration makes it easier to grasp the various aspects that contribute to traffic accidents comprehensively. These factors include weather, road features, and geographic regions. A Random Forest Regression model is trained to estimate the number of deaths arising from traffic crashes after data preprocessing, which includes feature selection and encoding. The accuracy and predictive power of the model are assessed through the utilization of the Mean Squared Error measure. To determine the most important variables impacting traffic crashes, feature importance analysis is also carried out. To find anomalies or outliers in the data and take preventative action to reduce the impact of accidents, anomaly detection utilizing an Isolation Forest model is utilized. Through the possibility of highlighting regions with increased risk or problems with data quality, this part of the research improves our comprehension of unexpected events in accident data. For comparison analysis, other models such as Auto Regressive I

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Analysis of N plus Pocket-Doped Vertical DMDGDP TFET With T-Shape Channel for Sensitivity Improvement-As a Biosensor

引用

IEEE SENSORS JOURNAL 2025年第2期25卷 3444-3451页

作者： Kondavitee, Girija Sravani Kumar, Rapolu Anil Karumuri, Srinivasa Rao Koneru Lakshmaiah Educ Fdn Dept ECE Vaddeswaram 520002 Andhra Prades India

This paper presents and simulates N+ pocket-doped vertical dielectrically modulated double gate drain pocket tunnel field-effect transistor (V-DMDGDP TFET) a highly sensitive label-free biosensor. For the first time, a T-shaped channel is employed in a biosensor using a Triple Hetero junction. The proposed V-DMDGDP TFET device is composed of semiconductors such as Silicon (Si), Silicon Dioxide (SiO (2) ), Hafnium Oxide(HfO (2) ) and Titanium Oxide (TiO (2) ). Using a sacrificial etching approach two cavities are formed in the gate-source junction areas and two additional cavities are formed in the gate-drain junction regions for the detection of biomolecules such as SARS COV2 (Covid cells, K=4), Carbohydrates (K=5), RNA (K=8) and Amino acids (K=12). Two-dimensional (2D) calibrated simulations were used to examine how several device characteristics such as the height and length of the cavity affected different performance measures. Greater dielectric constants produce better drain current values, which enhance the device sensitivity. The biosensor sensitivity to both charged and neutral biological molecules can be significantly enhanced by optimizing the cavity length and height. For neutral, positive and negative charged biomolecules the proposed biosensor sensitivity has been greatly increased to 3.68x10 (5) , 2.13x10 (6) and 3.97x10 (3) respectively. Comparing it with other advanced biosensors, it has demonstrated improved sensitivity. Thus, the device is used in identifying SARS-COV2, Carbohydrates, RNA, Amino acids, etc.

关键词： Biosensors TFETs Tunneling Molecular biophysics Logic gates Sensitivity Biological system modeling Electric potential Electric fields Junctions Biosensor filling factor Ion/Ioff SARS-COV2 sensitivity subthreshold swing (SS) T-shape channel vertical tunnel FET (TFET)

来源：评论

学校读者我要写书评

暂无评论

Sustainable energy management in microgrids: a multi-objective approach for stochastic load and intermittent renewable energy resources

引用

ELECTRICAL ENGINEERING 2025年第1期107卷 285-299页

作者： Buchibabu, Prathikantham Somlal, Jarupula Koneru Lakshmaiah Educ Fdn Dept EEE Guntur 522502 Andhra Pradesh India

Integrating photovoltaic (PV) systems and wind energy resources (WERs) into microgrids presents challenges due to their inherent unpredictability. This paper proposes deterministic and probabilistic sustainable energy management (SEM) solutions for microgrids connected to the main power system. A prairie dog optimization (PDO) algorithm is utilized to optimize energy utilization, grid stability, and the integration of renewable energy resources (RERs). The algorithm addresses cost reduction, voltage profile improvement, and optimal sizing of RERs. Simulation results demonstrate that incorporating grid-connected PV units and wind turbines (WTs) strategically reduces total costs and enhances system performance. The PDO method outperforms other optimization algorithms, such as Equilibrium Optimizer (EO) and Whale Optimization Algorithm (WOA), in SEM for microgrids due to its consistent convergence properties. Under deterministic settings, optimal integration of RERs reduces overall costs by 52%, with a significant 7.49% improvement in voltage profile index. In probabilistic scenarios, a remarkable 63.68% reduction in overall costs and a 7.51% enhancement in voltage stability index are achieved. These findings demonstrate the effectiveness of PDO in addressing SEM challenges in microgrid environments, showcasing superior performance over existing optimization techniques.

关键词： Prairie dog optimization (PDO) Probabilistic scenarios Renewable energy resources (RERs) Voltage profiles

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis using osprey-optimized hybrid GoogleNet-ResNet with text and emoji data

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 277卷

作者： Anitha, Padigapati Krishna, A. V. Praveen Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram 522502 Andhra Prades India

Sentimental analysis (SA) plays a crucial role in understanding consumer opinions from mobile product reviews. While various Deep learning (DL) approaches, such as deep neural networks (DNN) and convolutional neural networks (CNN), have been developed for SA, they often suffer from limitations like low accuracy, high processing time and reliance on single data modality (text data). Upon considering these issues, a novel hybrid DL model is introduced in this research by integrating both text and emoji data for enhanced sentiment classification. Unlike the existing models that primarily rely on text-based features, the proposed approach utilizes both text and emoji representations to capture richer sentiment context. Initially, data pre-processing and sentiment annotation are performed. Text data is transformed into numerical feature vectors using advanced feature extraction techniques, including Word2Vec and Emoji2Vec models, as well as Continuous Bag of Words (CBOW) and Skip-gram (SG). To improve classification accuracy, a depthwise separable hybrid GoogleNet with ResNet convolutional model is employed, leveraging the strengths of both architectures in feature extraction and representation learning. Furthermore, the classifier's hyperparameters are fine-tuned using the osprey optimization mechanism, an advanced metaheuristic approach that enhances convergence speed and model performances. The proposed model is evaluated under the Flipkart product reviews sentiment dataset, demonstrating its efficacy through performance analysis. These findings confirm that incorporating multi-modal data (text and emoji) and leveraging optimized hybrid architectures significantly enhance sentiment analysis accuracy. From this analysis, the proposed model outperforms other classifiers. The experimental results prove that the proposed model achieves a high accuracy, precision, recall and f1-score of 98.3%, 96%, 97.6% and 96.82%, respectively.

关键词： Continuous Bag of Words Skip gram Depthwise separable layer Osprey optimization Emoji Lexicon and coarse-grained SA

来源：评论

学校读者我要写书评

暂无评论

Development of Sparse Time Frequency Distribution Reconstruction Using a Gradient Slime Mould Renyie Entropy Shrinkage Model

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2025年第4期44卷 2621-2646页

作者： Shareef, Shaik Mohammed Rao, M. Venu Gopala Koneru Lakshmaiah Educ Fdn Dept ECE Guntur 522302 Andhra Pradesh India

Time-frequency distributions (TFD) can provide a great set of tools for studying transient signals. Although TFD can overcome constraints on signal representation, the most widely used TFDs produce artifacts known as cross terms, which could pose a challenge when used on real-world signals. The paper proposes a sparse Time-Frequency Distribution (TFD) reconstruction method employing a gradient slime Renyi entropy shrinkage model. Each time-frequency slice within the TFD undergoes shrinkage utilizing distinct algorithms based on Renyi entropy, which accounts for both short-term and narrowband characteristics. Renyi entropy quantifies data presence in the time-frequency plane. By integrating the Renyi entropy-based shrinkage operator, the traditional hard threshold operator in the shrinkage process is replaced, enhancing TFD resolution. The reconstruction model parameters are fine-tuned using a gradient slime shape optimizer, employing a concentration minimization function and Mean Squared Error (MSE) metrics between initial and reconstructed TFD modules for optimization. The simulation results prove that the proposed method achieved a reduced MSE value of 1.95 as compared with other existing methods.

关键词： Time-frequency Sparse TFD reconstruction Time-frequency distribution Short-term and narrow band entropy Gradient slime mould Time-frequency slice shrinkage algorithm

来源：评论

学校读者我要写书评

暂无评论

Determining Potability Based on Heavy Metal Ion Analysis of Water using Machine Learning

引用

INTERNATIONAL JOURNAL OF ENGINEERING 2025年第1期38卷 108-119页

作者： Chandrika, K. B. Babu, T., V Reddy, M. V. Subhash Prasanna, J. L. Kumar, M. Ravi Parvez, M. M. Santhosh, C. Koneru Lakshmaiah Educ Fdn Dept Elect & Commun Engn Vaddeswaram AP India Koneru Lakshmaiah Educ Fdn Dept Artificial Intelligence & Data Sci Vaddeswaram AP India

In this study, a comprehensive methodology for assessing water quality that integrates heavy metal pollution indices with advanced machine learning techniques was proposed, which includes Support Vector Machine (SVM), Decision Trees (DT), Random Forest, and XGBoostHcritical indicators of contamination of heavy metals. In this approach, models achieved exceptional accuracy rates. SVM demonstrates 88.57% accuracy, DT achieves 91.96% and Random Forest further enhances predictive capabilities with an accuracy of 94.11%. Notably, with an accuracy of 93.28%, XGBoost also makes a substantial contribution. This innovative approach enables real-time monitoring and proactive management of water resources, offering a robust tool for addressing environmental difficulties brought on by heavy metal pollution. By integrating machine learning algorithms, we provide insights into water quality dynamics, aiding in early detection and mitigation of contamination risks. Moreover, the inclusion of Random Forest enhances model robustness and adaptability across diverse environmental settings. This work underscores the importance of leveraging data-driven methodologies to safeguard environmental health and ensure sustainable water management practices. By combining indices with advanced machine learning techniques, we offer a scalable and effective solution for addressing water contamination challenges, thereby contributing to Improved efforts to protect the environment and better outcomes for public health.

关键词： Heavy Metal Ion Contamination Heavy Metal Pollution Index Heavy Metal Evaluation Index Exploratory Data Analysis

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：