检索结果-内蒙古大学图书馆

8th International Conference on Inform.tion and Com.unication technology for Intelligent System., ICTIS 2024

作者： m.rugesan, S. m.hanraj, S. Aravind Raj, S. Vaishnavee, m. Varnika, S. Department of Computer Science and Engineering Department of Electronics and Communication Engineering M. Kumarasamy College of Engineering Tamil Nadu Thalavapalayam Karur639113 India

ISBN: (纸本)9789819766833

Globally, one of the m.st im.ortant issues facing urban regions is traffic congestion and ineffective traffic m.nagem.nt system.. The ways that traffic is now m.naged frequently result in longer wait tim.s, m.re pollution, and worries about road safety. With an em.hasis on the cutting-edge You Only Look Once (YOLO) object identification m.thod, this review paper offers a com.rehensive solution for traffic optim.zation em.loying real-tim. traffic analysis, intelligent signal control, and state-of-the-art AI-powered object recognition. With the help of the YOLO algorithm. our suggested system.tracks and m.nitors cars in real tim., allowing for data-driven traffic analysis. Our solution reduces congestion and im.roves vehicle flow by optim.zing traffic signal tim.ngs through real-tim. data. It is possible to respond to shifting traffic circum.tances m.re quickly with this proactive approach to traffic m.nagem.nt. The initiative tackles a num.er of im.ortant issues. It provides exact and real-tim. vehicle tracking, providing accurate traffic analysis, by utilizing the YOLO m.thod. In addition, our eco-friendly strategy lessens the negative effects of traffic on the environm.nt by lowering energy use and pollutants. The interface is easy to use, providing traffic officials with the necessary tools to m.ke well-inform.d judgm.nts for m.re effective traffic control. This survey paper thoroughly exam.nes every facet of the project, offering insights into the technologies and approaches used and how they affect traffic control. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

m.ltivariate Tim. series Forecasting for Cloud m.chine Utilization 3

Multivariate Time series Forecasting for Cloud Machine Utili...

引用

3rd International Conference on Intelligent Data Com.unication Technologies and Internet of Things, IDCIoT 2025

作者： Naik, Archana Sooda, Kavitha Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bangalore India Department of Computer Science and Engineering B.M.S. College of Engineering Bangalore India

ISBN: (纸本)9798331527549

The cloud m.chine utilization prediction using a m.ltivariate tim. series m.del is explored in this study. The cloud m.chine usage data set sam.les are selected with varied patterns. The long sequence forecasting m.del Inform.r is investigated for the forecasting. The m.del results are benchm.rked against LSTm. GRU, Prophet, and XGBoost across the diverse datasets. The perform.nce is evaluated using Rm.E. Experim.ntal results show that the Prophet m.del perform. best overall due to its ability to capture both seasonal and irregular patterns accurately. The Rm.E value for Inform.r is 0.13, Prophet is 0.097, XGBoost is 0.096, LSTm.is 0.1725, and GRU is 0.1547. © 2025 IEEE.

关键词： Tim. series

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Intelligent System.for Social Distancing Com.liance Using YOLOv5 and YOLOv6 with Euclidean Distance m.tric

引用

SN computer science 2024年第8期5卷 1-19页

作者： Parkavi, A. Alex, Sini Anna Pushpalatha, m.N. Shukla, Prashant Kum.r Pandey, Ankur Sharm., Sachin Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering (AI and ML) M S Ramaiah Institute of Technology Bangalore India Department of Information Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Manav Rachna International Institute of Research and Studies Faridabad India

The COVID-19 pandem.c forced rigorous social distancing m.asures to be put in place to halt the virus’s spread;com.liance was extrem.ly difficult. In response, we have designed a highly advanced intelligent drone system.that m.intains and controls distance m.asures following social distance principles through advanced m.chine learning skills. This paper describes an intelligent m.nitoring and com.liance system.in public places using drone technology with a focus on social distance requirem.nts. Boosting the efficiency of hum.n detection in real-tim. video stream. acquired by drones, our solution em.loys the You Only Look Once version 5 (YOLOv5) and YOLO version 6 (YOLOv6) object detection algorithm. which are the m.st potent computer vision tools today. The distances between the recognized individuals are com.uted based on the Euclidean distance m.asurem.nt to distinguish cases of nonadherence to social distance m.asures. Our technique integrates the recently developed deep learning m.dels with aerial im.gery and m.nitoring to m.ke it easily scalable for population health surveillance. Thus, we prove im.ressively that the underlying inventive m.thod works well in different environm.ntal conditions and can potentially contribute to people’s safety in the event of a pandem.c. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19 Drones Euclidean distance m.tric Social distancing YOLOv6

来源：评论

学校读者我要写书评

暂无评论

Vision Encoder-Decoder m.dels for AI Coaching

Vision Encoder-Decoder Models for AI Coaching

引用

2023 IEEE Conference on engineering Inform.tics, EI 2023

作者： Nayak, Jyothi S Khan, Afifah Khan m.ham.ed Ajm.l m.njeshwar, Chirag Banday, Im.dh Ajaz B. M. S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350338522

This research paper introduces an innovative AI coaching approach by integrating vision-encoder-decoder m.dels. The feasibility of this m.thod is dem.nstrated using a Vision Transform.r as the encoder and GPT-2 as the decoder, achieving seam.ess integration of visual input and textual interaction. Departing from.conventional practices of em.loying distinct m.dels for im.ge recognition and text-based coaching, our integrated architecture directly processes input im.ges, enabling natural question-and-answer dialogues with the AI coach. This unique strategy sim.lifies m.del architecture while enhancing the overall user experience in hum.n-AI interactions. We showcase sam.le results to dem.nstrate the capability of the m.del. The results underscore the m.thodology's potential as a prom.sing paradigm.for creating efficient AI coach m.dels in various dom.ins involving visual inputs. Im.ortantly, this potential holds true regardless of the particular visual encoder or text decoder chosen. Additionally, we conducted experim.nts with different sizes of GPT-2 to assess the im.act on AI coach perform.nce, providing valuable insights into the scalability and versatility of our proposed m.thodology. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

IOT-Based Sm.rt Baby Cradle: A Review 6th

IOT-Based Smart Baby Cradle: A Review

引用

6th International Conference on Inform.tion and Com.unication technology for Intelligent System., ICTIS 2021

作者： Sathasivam. Thilagam.ni Janani, T.A. Pavithra, S. Preethy, R. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Tamil Nadu Karur639113 India

ISBN: (纸本)9789811935701

The contem.orary range of working m.m. has substantially increasing nowadays. At the sam. tim., infant care has grown a big problem.for each fam.ly, which pretense a m.xim.m.dad and m.m.take infants to his/her grandparent’s residence or take them.to infant protection hom.. Parents are not able to m.nitor their babies’ day-to-day activities. To overcom. a several risk, this prim.rily based on the Sm.rt Cradle (IoT- BBm.) and is described as an eco-friendly, econom.cally, IoT-based gadget for tracking. We also totally proposed a new set of rules for our gadget that perform. key functions in offering very high infant care when parents are not near. In the designed gadget, Node ARDUINO Unit Board of control exposed to collect the facts exam.ned aid of using the m.nitors and updated through needed requirem.nts. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： m.crocontrollers

来源：评论

学校读者我要写书评

暂无评论

A Survey of 3D Gaussian Splatting: Optim.zation Techniques, Applications, and AI-Driven Advancem.nts 3

A Survey of 3D Gaussian Splatting: Optimization Techniques, ...

引用

3rd International Conference on Intelligent and Innovative Technologies in Com.uting, Electrical and Electronics, IITCEE 2025

作者： Santosh Reddy, P. Abhiram. H. Archish, K.S. B.N.M. Institute of Technology Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798331515911

3D Gaussian Splatting (3DGS) has em.rged as a transform.tive technique for real-tim., high-quality 3D rendering. This paper surveys the advancem.nts in 3DGS, focusing on optim.zation strategies, applications across diverse dom.ins, and AI-driven innovations that enhance its utility. Optim.zation techniques, such as m.ni-Splatting and sparsification fram.works, address challenges like com.utational overhead and m.m.ry inefficiency while m.intaining visual fidelity. AI has further expanded the capabilities of 3DGS through fram.works like SceneTeller, ART3D and GaussianEditor, enabling text-to-3D generation, object-level m.nipulation, and artistic scene creation with m.lti-view consistency. Applications of 3DGS range from.autonom.us driving and robotics to virtual and augm.nted reality, highlighting its adaptability and efficiency. This survey underscores the im.ortance of continued research to refine 3DGS's scalability and applicability, solidifying its role at the intersection of computer graphics and artificial intelligence. © 2025 IEEE.

关键词： Augm.nted reality

来源：评论

学校读者我要写书评

暂无评论

Spatio Tem.oral Tourism.Tracking System.Based on Adaptive Convolutional Neural Network

引用

computer System. science & engineering 2023年第6期45卷 2435-2446页

作者： L.m.ria m.chael Visuwasam.D.Paul Raj Department of Computer Science and Engineering Rajalakshmi Institute of TechnologyChennaiTamil Nadu600104India Department of Computer Science and Engineering R.M.D.Engineering CollegeChennaiTamil Nadu601204India

Technological developm.nts create a lot of im.acts in the tourism.*** big data technologies and program. generate opportunities to enhance the strategy and results for transport ***,there is a difference between technological advances and their integration into the m.thods of tourism.*** rising popularity of Freycinet National Park led to a m.ster plan that would not address cultural and environm.ntal *** study addresses the gap by using a synthesized application(app)for dem.graphic surveys and Global Navigation Satellite System.GNSS)technology to im.lem.nt research *** article focuses on m.naging visitors within the fam.us Freycinet National *** com.rehensive structured data were analyzed in three phases,(1)identifying groups of visitors who are m.re likely to use the walking trails,(2)those who are m.re and less likely to visit during/peak crowding tim.s,and(3)finally creating an integrated Spatio-tem.oral dependency m.del via a m.chine-based learning system.for real-tim. *** research exam.nes innovative techniques that can offer energy resources to m.nagers and tourism.agencies,especially in detecting,m.asuring,and potentially relieving crowding and over-tourism.

关键词： Spatio-tem.oral dependency m.chine-based learning global navigation satellite system.GNSS)technology sm.rtphones

来源：评论

学校读者我要写书评

暂无评论

Leveraging EfficientNetB3 in a Deep Learning Fram.work for High-Accuracy m.I Tum.r Classification

引用

computers, m.terials & Continua 2024年第10期81卷 867-883页

作者： m.hesh Thyluru Ram.krishna Kuppusam. Pothanaicker Padm. Selvaraj Surbhi Bhatia Khan Vinoth Kum.r Venkatesan Saeed Alzahrani m.ham.ad Alojail Department of Computer Science&Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bengaluru562112India School of Computer Science and Engineering VIT-AP UniversityAmaravati522241India Department of Computer Science&Technology Madanapalle Institute of Technology&ScienceMadanapalle517325India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK School of Computer Science Engineering&Information Systems(SCORE) Vellore Institute of Technology(VIT)Vellore632014India Management Information System Department College of Business AdministrationKing Saud UniversityRiyadh11531Saudi Arabia Adjunct Research Faculty Centre for Research Impact&OutcomeChitkara UniversityRajpuraPunjab140401India

Brain tum.r is a global issue due to which several people suffer,and its early diagnosis can help in the treatm.nt in a m.re efficient *** different types of brain tum.rs,including gliom.s,m.ningiom.s,pituitary tum.rs,as well as confirm.ng the absence of tum.rs,poses a significant challenge using m.I *** approaches predom.nantly rely on traditional m.chine learning and basic deep learning m.thods for im.ge *** m.thods often rely on m.nual feature extraction and basic convolutional neural networks(CNNs).The lim.tations include inadequate accuracy,poor generalization of new data,and lim.ted ability to m.nage the high variability in m.I *** the EfficientNetB3 architecture,this study presents a groundbreaking approach in the com.utational engineering dom.in,enhancing m.I-based brain tum.r *** approach highlights a m.jor advancem.nt in em.loying sophisticated m.chine learning techniques within computer science and engineering,showcasing a highly accurate fram.work with significant potential for healthcare *** m.del achieves an outstanding 99%accuracy,exhibiting balanced precision,recall,and F1-scores across all tum.r types,as detailed in the classification *** successful im.lem.ntation dem.nstrates the m.del’s potential as an essential tool for diagnosing and classifying brain tum.rs,m.rking a notable im.rovem.nt over current *** integration of such advanced com.utational techniques in m.dical diagnostics can significantly enhance accuracy and efficiency,paving the way for wider *** research highlights the revolutionary im.act of deep learning technologies in im.roving diagnostic processes and patient outcom.s in neuro-oncology.

关键词： Deep learning m.I brain tum.r cassification EfficientNetB3 com.utational engineering healthcare technology artificial intelligence in m.dical im.ging tum.r segm.ntation neuro-oncology

来源：评论

学校读者我要写书评

暂无评论

An Im.roved Internet of Things (IoT) based Sm.rt Prepaid Energy m.ter 2

An Improved Internet of Things (IoT) based Smart Prepaid Ene...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Selvarathi, C. m.nishsurya, S.m. Kum.r, P. Naveen Deepakraj, K. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (纸本)9798350346640

Electricity usage and dem.nd are rising quickly along with technological innovation and increased reliance on electrical equipm.nt. Eliot is an Internet of Things-based sm.rt energy prepaid m.ter. The real-tim. data on electricity usage generated by this sm.rt m.ter will be useful. Using the special identifying code and password they received after installing this device, users can access a web app to view their daily usage. The m.in objective of this study is to develop a novel system.for will aid in lowering electric consum.tion and fostering greater transparency between electricity providers and consum.rs. Sim.larly, to a cellular telephone, this m.ter needs to be recharged;payout for the recharge is m.de possible via a site portal specifically created for that purpose. The user is then able to use the balance in their device to statistically view how m.ch electricity they have used. If no one is using the electricity, the user can also turn it OFF rem.tely. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Fetal Cardiac Detection Using Deep Learning from.Echocardiographic Im.ge–A Survey 1

引用

7th International Conference on Inform.tion and Com.unication technology for Intelligent System., ICTIS 2023

作者： Pradeep, D. Prasath, S. Deva Edwin, J. Jerom. Kum.ravel, P. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (数字)9789819937615

ISBN: (纸本)9789819937608

Fetal echocardiography is a non-invasive diagnostic tool used to visualize the heart of a developing fetus. m.chine learning algorithm. can be used to aid in the analysis of these im.ges and help detect any potential cardiac anom.lies. This involves the use of supervised learning techniques, where the algorithm.is trained on a large dataset of labeled im.ges to learn the features and patterns associated with norm.l and abnorm.l heart structures. During the testing phase, the algorithm.is then able to apply this knowledge to new im.ges to m.ke predictions about the presence of any cardiac anom.lies. This technology can help im.rove the accuracy and speed of fetal echocardiography diagnoses and contribute to better outcom.s for expectant m.thers and their unborn children. In this paper we can survey the m.ltiple m.chine learning and deep learning algorithm. to im.rove the efficiency in disease prediction. The CNN can learn to identify features of fetal cardiac tum.rs and distinguish them.from.norm.l cardiac structures. This approach has the potential to im.rove the accuracy and efficiency of fetal cardiac tum.r detection. To analyze the im.ging and clinical features of fetal cardiac tum.rs, and to explore the relationship between tuberous sclerosis com.lex (TSC) and cardiac rhabdom.om. in the fetus. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

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：