检索结果-内蒙古大学图书馆

Multi-Agent systems for Collaborative Intelligence (ICMsCI), International Conference on

作者： bulla sujitha Anitha Ponraj Chakkarapani v sriram Parabrahmachari T. v. Hyma Lakshmi T. Annamani Department of ECE V. R. Siddhartha Engineering College Vijayawada AP India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Kalasalingam University Krishnankoil Tamil Nadu India School of Electrical and Electronics Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Department of CSE Guru Nanak institutions Technical Campus Ibrahimpatnam Telangana India Department of ECE S.R.K.R. Engineering College Bhimavaram A.P India Department of ECE Anurag University Hyderabad Telangana India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Each day, countless individuals around the globe are affected by the extensive and complex problem of traffic congestion. This raising challenge is becoming increasingly substantial across the country, driven by factors such as rising population numbers, speedy urban development, insufficient infrastructure, and changing socioeconomic requirements. This paper depicts a novel global video-based parking approach designed to boost the supervising and management of parking spaces using real-time aerial statistics. Utilizing advanced image processing and computer vision procedures, the system essentially detects and examines the occupancy position of parking slots. In our realization, we assessed a total of 48 parking spaces, positively identifying 7 as unused while 41 were occupied. The application of Python, OpenCv, and machine learning assisted real-time monitoring, allowing precise counting and expose of parking availability. The procedure contained critical procedures, including Gaussian blur filtering to minimize noise and improve edge detection, followed by binary thresholding to describe vehicles and parking spots from the background. Furthermore, a median filter was utilized to boost the clarity of vehicle contours. These image enhancement methods significantly expanded detection accuracy and facilitated precise recognition of the Region of Interest (ROI). The results show the system's ability to provide reliable, real-time data for dynamic parking administration, thereby focusing the challenges of urban parking.

关键词： computer vision Thresholding (Imaging) Accuracy Filtering streaming media Real-time systems Car parking vehicle dynamics Monitoring Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

synthesis, Characterization, Electrochemical sensing, DFT Analysis, Molecular Docking and Anticancer Activity of a Novel Thiadiazole-based Azo Dye Incorporating a barbituric Acid scaffold

引用

Journal of Molecular structure 2025年 1341卷

作者： s, Harisha Nagaraj, Kalyan Reddy R, Mohan sridhar, Amulyashree Kumar, s.R. Kiran surendranaik, Y. Centre for Nanosciences Department of Chemistry K.S. Institute of Technology Karnataka Bengaluru560 109 India B.M.S. College of Engineering Karnataka Bengaluru560019 India Department of Chemistry B.M.S. College of Engineering Karnataka Bengaluru560019 India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Karnataka Bengaluru560035 India Department of P.G. Studies and Research in Chemistry Kuvempu University Jnanasahyadri Shankaraghatta Karnataka 577451 India

We report the synthesis of a heterocyclic azo dye, (E)-6-hydroxy-5-((5-mercapto-1,3,4-thiadiazol-2-yl)diazenyl)-1,3-dimethylpyrimidine-2,4(1H,3H)-dione (DsTDPT). The structure of DsTDPT was characterized using Uv-v.s.ble, FTIR, 1HNMR, and LCMs analyses. Its electrochemical properties were examined in a 0.2 M phosphate buffer (pH=7.2) with a carbon paste electrode (CPE). The electrodes sensitivity and selectivity toward paracetamol detection were enhanced by incorporating surfactants such as CTAb, sDs, and Triton X-100. The nonlinear optical metrics and electronic structure of DsTDPT were explored through density functional theory (DFT) computations using 6-31G (d, p)/b3LYP basis set. The enol form of DsTDPT demonstrated promising optical characteristics, including a first-order hyperpolarizability values approximately 19 times greater than that of urea. Molecular docking studies revealed favourable binding energies of DsTDPT towards b-cell lymphoma-extra-large (bcl-xL) protein. To further investigate the stability and dynamics of the bcl-xL protein and bcl-xL-DsTDPT complex, molecular dynamics (MD) simulations were conducted. These studies confirmed that DsTDPT is a promising lead molecule with potent anti-cancer property. Finally, in vitro cytotoxic activity was evaluated against HCT-116 (human colon cancer) cell lines using MTT assay. The compound exhibited concentration-dependant cytotoxicity with IC50 values ranging from 22 µM - 36 µM, as compared to known cytotoxic agent cisplatin. © 2025 Elsevier b.v.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Autonomous Robots for search and Rescue Operations in Disaster Zones

AI-Driven Autonomous Robots for Search and Rescue Operations...

引用

Data science, Agents & Artificial Intelligence (ICDsAAI), International Conference on

作者： Meenakshi s. Pavaimalar Rama Prabha K. P s. Ravi N. Kumaran s. b. Priya Department of Artificial Intelligence & Data Science Nitte Meenakshi Institute of Technology Nitte University Bangalore India Department of Information Technology V. S. B. Engineering College Karur Tamilnadu India School of Computer Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Tamil Nadu India Department of Mathematics Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science St Joseph's Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

search and rescue (sAR) operations designed to save lives in disaster zones face difficulties executing effectively because of dangerous surroundings and challenging terrain features. An AI-controlled robotic system exists to deal with existing challenges. The system combines a reinforcement learning-based navigation system that integrates multiple sensors including LiDAR with thermal cameras and RGb sensors for detecting victims to work with decentralized task distribution frameworks. Real-time simulations tested disaster navigation datasets showing an overall detection accuracy rate of 95.6%, navigation accuracy at 92.8%, while obstacle avoidance performed at 97.2%. This deployed system achieved 3.2-minute average response times and processed requests with 85.4% resource efficiency. The system proves superior performance over existing sAR methods while demonstrating speed enhancement, accuracy improvement, and autonomous operational value in sAR operations. Future disaster response will change thanks to AI-powered robotics because this technology enables scalable efficient reliable solutions for future deployments.

关键词： Accuracy Navigation Disasters Transforms Thermal sensors sensor systems Time factors Collision avoidance Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Metallurgical test on 20mncr5 steel: To suggest as a suitable crankshaft material 1st

引用

1st International Conference on Emerging Trends in science, engineering and Technology, INCOsET 2012

作者： Umashankaran, M. vignesh, J. Hari Kumar, A. saravana shyamaprasad, R. Prabhu, R. saravana V.S.B Engineering college Karur Tamilnadu India

ISBN: (纸本)9788132210061

The crankshaft is the part of an engine which translates reciprocating linear piston motion into rotation. In converting the linear motion of the piston into rotational motion;crankshafts operate under high loads and require high strength and stiffness to withstand the high loads in modern engines, and to offer opportunities for downsizing and weight reduction. We have come with an idea of suggesting a new crank shaft material 20MnCr5 steel, which has high strength and stiffness and satisfies all the requirements of the crank shaft materials. We did the various important testing like hardness test (Rockwell Hardness), impact test, torsion test, fatigue test, metallography test on this 20MnCr5. Our chapter deals with our experimental works on this 20MnCr5. The objective of this testing is to suggest that 20MnCr5 alloy steel is one of the suitable material for making crankshafts for the modern engines. © springer India 2012.

关键词： 20MnCr5 Crankshaft stiffness strength Weight alloy steel reduction

来源：评论

学校读者我要写书评

暂无评论

super-resolution Radial Fluctuations Enables Polarization-resolved Nonlinear Optical Nanoscopy

arXiv

引用

arXiv 2025年

作者： Harvey, MacAulay Cisek, Richard Al-Turk, sarry Ruda, Harry E. Kreplak, Laurent Tokarz, Danielle Department of Chemistry Saint Mary’s University 923 Robie Street HalifaxNSB3H 3C3 Canada Centre for Advanced Nanotechnology University of Toronto 170 College Street TorontoONM5S 3E4 Canada Department of Materials Science and Engineering University of Toronto 184 College Street TorontoONM5S 3E4 Canada Department of Electrical and Computer Engineering University of Toronto 10 Kings College Road TorontoONM5S 3G4 Canada Department of Physics and Atmospheric Science School of Biomedical Engineering Dalhousie University HalifaxNSB3H 4J5 Canada

second harmonic generation microscopy (sHG) is a powerful imaging modality which has found applications in investigating both biological and synthetic nanostructures. Like all optical microscopy techniques, the resolution of sHG is limited to approximately half the wavelength of the excitation light. because of this several groups have proposed techniques to enable super-resolution sHG imaging. However, these techniques often involve quite complicated optical setups compared to standard sHG microscopes, a major impediment towards more widespread utilization. Here we apply super-resolution radial fluctuations (sRRF), a commonly used technique for super-resolution fluorescence imaging, to enable super-resolution sHG microscopy. by imaging individual nanostructures, we demonstrate that sRRF can provide resolution enhancement of up to 3× compared to a laser scanning sHG microscope, which is comparable to the best resolution enhancement reported in the literature. Additionally, we show that sRRF maintains the polarization dependence of sHG, therefore enabling super-resolution polarization sHG imaging. Finally, we perform sRRF processing on third harmonic generation images to demonstrate the significant potential of sRRF for other super-resolution nonlinear optical microscopy. Importantly, since sRRF can achieve super-resolution purely through image processing, the technique demonstrated here could be used to enhance the resolution of images obtained using a wide variety of nonlinear optical microscopy setups including both laser scanning and widefield configurations. Copyright © 2025, The Authors. All rights reserved.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Performance optimization of hybrid nano-engineered geopolymer binders-based ultra-high-performance concrete

引用

Nano-structures and Nano-Objects 2025年 42卷

作者： Raut, Jayant M. Pande, Prashant b. Madurwar, Kamlesh v. bahoria, boskey v. bhagat, Rajesh M. Kakade, Niteen T. Karmore, Pravin Y. Pinjarkar, Latika Muley, Manjushree Department of Civil Engineering Yeshwantrao Chavan College of Engineering Maharashtra Nagpur 441110 India Department of Civil Engineering Priyadarshini Bhagwati College of Engineering Maharashtra Nagpur 440024 India Department of Mechanical Engineering Tulsiramji Gaikwad Patil College of Engineering and Technology Maharashtra Nagpur 441108 India Department of Computer Science and Applications Ramdeobaba University Maharashtra Nagpur 440013 India Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed) University Maharashtra Pune 440008 India Department of Mathematics S. B. Jain Institute of Technology Management and Research Maharashtra Nagpur 441501 India

Ultra-high-performance and sustainable construction materials have given the thrust to the development of geopolymer technology. This work presents a nano-engineered geopolymer binder incorporating hybrid nano-reinforcements of nano-silica and graphene oxide at optimized ultrasonication and mechanical milling for improved dispersion and prevention of agglomeration. The resulting specimen exhibits a compressive strength exceeding 120 MPa at 24 h and a water absorption below 3 %. A microwave-assisted novel curing method accelerates geopolymerization, achieving this strength in less than 1 h and a reduction of the curing duration by 70 %. Further employing doped CNTs for structural health sensing has even greater potential, creating a self-sensing system with a gauge factor of over 25. synchrotron XRD analysis supplies information about phase evolution, thus ensuring a crystallinity index greater than 50 %. Molecular dynamics simulations predict robust interactions with bond energies beyond 320 KJ/mol, whereas kinetic modeling optimizes reaction rates of up to 80 % polymerization within 8 h. ballistic Impact testing shows over 50 percent enhancement in impact resistance, proving to be very robust under a severe loading condition. The overall picture created by inter alia superior mechanical properties, durability, self-sensing ability, and environmental benefits (20 % energy saving) should be considered as a paradigm shift for constructions with high performance and sustainability, stretching its applications to aerospace and defenses. © 2025 Elsevier b.v.

关键词： ballistic impact resistances microwave-assisted curing Nano-geopolymer self-sensing materials ultra-high-performance concrete

来源：评论

学校读者我要写书评

暂无评论

Towards Refining Developer Questions using LLM-based Named Entity Recognition for Developer Chatroom Conversations

arXiv

引用

arXiv 2025年

作者： Fathollahzadeh, Pouya Mezouar, Mariam El Li, Hao Zou, Ying Hassan, Ahmed E. Department of Electrical and Computer Engineering Queen’s University KingstonONK7L 3N6 Canada School of Computing Queen’s University KingstonONK7L 3N6 Canada Department of Mathematics and Computer Science Royal Military College of Canada KingstonONK7K 7B4 Canada

In software engineering chatrooms, communication is often hindered by imprecise questions that cannot be answered. Recognizing key entities (e.g., programming languages and libraries) and user intent (e.g., learning or requesting a review) can be essential for improving question clarity and facilitating better exchange. However, existing research using natural language processing techniques often overlooks these software-specific nuances. In this paper, we introduce softwarE-specific Named entity recognition, Intent detection, and Resolution classification (sENIR), a labelling approach that leverages a Large Language Model to annotate entities, intents, and resolution status in developer chatroom conversations. To offer quantitative guidance for improving question clarity and resolvability, we build a resolution prediction model that leverages sENIR’s entity and intent labels along with additional predictive features. We evaluate sENIR on the DIsCO dataset using a subset of annotated chatroom dialogues. sENIR achieves an 86% F-score for entity recognition, a 71% F-score for intent detection, and an 89% F-score for resolution status classification. Furthermore, our resolution prediction model, tested with various sampling strategies (random undersampling and oversampling with sMOTE) and evaluation methods (5-fold cross-validation, 10-fold cross-validation, and bootstrapping), demonstrates AUC values ranging from 0.7 to 0.8. Key factors influencing resolution include positive sentiment and entities such as Programming Language and User variable across multiple intents, while diagnostic entities (e.g., Error Name) are more relevant in error-related questions. Moreover, resolution rates vary significantly by intent: questions about API Usage and API Change achieve higher resolution rates, whereas Discrepancy and Review have lower resolution rates. A Chi-square analysis confirms the statistical significance of these differences. © 2025, CC bY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Prediction of stock Price Using XG boost Integrated bi-Channel LsTM

Prediction of Stock Price Using XG Boost Integrated Bi-Chann...

引用

Advances in computer science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Amey Adinath Choudhari Rajeswaran Ayyadurai Jayant Maruti Hudar v.K. Arthi Tasriqul Islam G Jayashree Hareesh JSPM's Rajashi Shahu College of Engineering Pune India IL Health & Beauty Natural Oils Co Inc California USA DBA BHS University Switzerland DBA in Data Science and AI PGDBM B.E. Electronics. Diploma in Computer Technology Navi Mumbai India Department of Management Studies Sri Ramakrishna Engineering College Coimbatore India Harvard University Cambridge Massachusetts USA Fahad Bin Sultan University Tabuk Saudi Arabia

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Investors' biggest problem is determining the appropriate stock price by studying financial information, which is a difficult process due to enormous and related inefficiencies. so, among the biggest challenges for investors is identifying a stock. Currently, it's very challenging to carry out research in the forecasts for the finance industry, including the stock market, currency value, and stock price. Due to its critical importance in financial consumers' decision-making, the prediction and examination of the stock price is yet another important research subject. A novel Xgboost Integrated bichannel Long/short-Term Memory (X-bLsTM) technique is implemented in this article to provide a sophisticated and perfect framework for the share market's price prediction The share value dataset is the first thing we collect to assess the way the suggested X-bLsTM strategy performs. Due to the existence of noisy data, min-max normalization is performed to preprocess the raw dataset. The efficiency of the proposed approach is assessed using several measures, and comparative between the proposed and current methods is also provided. The studies' findings show that the recommended approach outperforms alternative techniques for share value prediction.

关键词： Training Industries Electric potential Current measurement Decision making Noise measurement stock markets Forecasting Long short term memory Currencies

来源：评论

学校读者我要写书评

暂无评论

Explainable deep stacking ensemble model for accurate and transparent brain tumor diagnosis

引用

computers in biology and Medicine 2025年 191卷 110166-110166页

作者： Haque, Rezaul Khan, Mahbub Alam Rahman, Hamdadur Khan, shakil siddiqui, Md Ismail Hossain Limon, Zishad Hossain swapno, s M Masfequier Rahman Appaji, Abhishek Department of Computer Science and Engineering East West University A 2 Jahurul Islam Ave Dhaka1212 Bangladesh Department of Management Information System Pacific State University 3424 Wilshire Blvd. 12th Floor Los Angeles CA90010 United States Department of Management of Information System International American University 3440 Wilshire Blvd STE 1000 Los AngelesCA90010 United States Department of Business Analytics International American University 3440 Wilshire Blvd STE 1000 Los AngelesCA90010 United States Department of Engineering/Industrial Management Westcliff University IrvineCA92614 United States Department of Computer Science Westcliff University IrvineCA92614 United States Department Of Computer Science and Engineering Bangladesh University of Business and Technology Mirpur-2 Dhaka1216 Bangladesh Department of Medical Electronics Engineering B.M.S. College of Engineering Bangalore560019 India Maastricht University University Eye Clinic Maastricht Maastricht Netherlands

Early detection of brain tumors in MRI images is vital for improving treatment results. However, deep learning models face challenges like limited dataset diversity, class imbalance, and insufficient interpretability. Most studies rely on small, single-source datasets and do not combine different feature extraction techniques for better classification. To address these challenges, we propose a robust and explainable stacking ensemble model for multiclass brain tumor classification. To address these challenges, we propose a stacking ensemble model that combines EfficientNetb0, MobileNetv2, GoogleNet, and Multi-level CapsuleNet, using Catboost as the meta-learner for improved feature aggregation and classification accuracy. This ensemble approach captures complex tumor characteristics while enhancing robustness and interpretability. The proposed model integrates EfficientNetb0, MobileNetv2, GoogleNet, and a Multi-level CapsuleNet within a stacking framework, utilizing Catboost as the meta-learner to improve feature aggregation and classification accuracy. We created two large MRI datasets by merging data from four sources: braTs, Msoud, br35H, and sARTAJ. To tackle class imbalance, we applied borderline-sMOTE and data augmentation. We also utilized feature extraction methods, along with PCA and Gray Wolf Optimization (GWO). Our model was validated through confidence interval analysis and statistical tests, demonstrating superior performance. Error analysis revealed misclassification trends, and we assessed computational efficiency regarding inference speed and resource usage. The proposed ensemble achieved 97.81% F1 score and 98.75% PR AUC on M1, and 98.32% F1 score with 99.34% PR AUC on M2. Moreover, the model consistently surpassed state-of-the-art CNNs, vision Transformers, and other ensemble methods in classifying brain tumors across individual four datasets. Finally, we developed a web-based diagnostic tool that enables clinicians to interact with the proposed mo

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A transformer based real-time photo captioning framework for visually impaired people with visual attention

引用

Multimedia Tools and Applications 2024年第41期83卷 88859-88878页

作者： Muhammed Kunju, Abubeker Kiliyanal baskar, s. Zafar, sherin A R, bushara s, Rinesh A, shafeena Karim Kerala Kanjirapally India Faculty of Engineering Department of Electronics and Communication Engineering Karpagam Academy of Higher Education Coimbatore India Department of Computer and Electronics Engineering SEST- Jamia Hamdard New Delhi India Department of Electronics and Communication Engineering KMEA College of Engineering Kerala Cochin India Department of Computer Science and Engineering V.S.B College of Engineering Technical Campus Coimbatore India

In recent years, transformer-based photo captioning frameworks plays a crucial role in improving individuals’ overall well-being, self-reliance, and inclusivity by giving them access to visual content via written and voiced explanations. This research investigates a two-layer transformer architecture to capture extensive relationships in visual data effectively. Using a two-layer transformer design, visual attention mechanism enables the model to autonomously identify relevant regions within a picture while generating a particular word within the anticipated caption. To get the features from the images, a pre-trained Inception v3 model is used, and the feature maps are extracted from the final convolutional block. The dataset used in this research was Flick8k, Flick30k, among bespoke datasets. The model was trained on a TPU platform and implemented on a Raspberry Pi 4b graphics processing unit. To assess the efficacy of the two-layer transformer model for photo captioning, a series of experiments were undertaken using benchmark datasets and with state-of-the-art models. The quality of the generated captions was evaluated using quantitative criteria such as bLEU, bLEUR, ROUGE and F1 score. Furthermore, a series of qualitative assessments were conducted, employing human evaluators, to measure the overall coherence, and fluency of the captions. © The Author(s), under exclusive licence to springer science+business Media, LLC, part of springer Nature 2024.

关键词： computer vision

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：