检索结果-内蒙古大学图书馆

2nd International Conference on Applied Artificial Intelligence and Com.uting, ICAAIC 2023

作者： Sivajothi, E. Jayaudhaya, J. Santhiya, S. Thapa, Naresh Kum.r Kam.tchi, S. Ganapathy, N. Bala Sundara Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India R.M. D. Engineering College Department of Electronics and Communication Engineering Tamil Nadu India M. Kumarasamy College of Engineerin Department of Computer Science and Engineering Tamil Nadu India R.M. K. Engineering College Department of Electronics and Communication Engineering Tamil Nadu India Saveetha School of Engineering Simats Department of Electronics and Communication Engineering Tamil Nadu India Panimalar Engineering College Department of Information Technology Tamil Nadu India

ISBN: (纸本)9781665456302

The research work provides a brand-new technique for distributing bandwidth in wireless networks that is also energy-efficient. To begin, look into how channel allocations, which ultim.tely determ.ne the transm.ssion rate for m.bile term.nals, affect the fundam.ntal relationship that exists between energy use and transm.ssion rates. The Fatality Selection Algorithm.(FSA) and the Receiver Selection Algorithm.(RSA) are two m.thodologies that control connection adm.ttance to reduce the am.unt of energy used by each individual term.nal. Furtherm.re, provide a corrective strategy for statistically satisfying the quality of service (QoS) criteria throughout the resource allocation process. Throughput, call blockage probability, and the energy consum.tion rate of each successfully sent bit are used to evaluate the efficiency of the recom.ended solutions. An extensive investigation into analysis and sim.lation is carried out in the case of Poisson and self-sim.lar. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

IoT-Driven m.shroom.Farm.Autom.tion Using Neural Turing m.chines (NTm. 4

IoT-Driven Mushroom Farm Automation Using Neural Turing Mach...

引用

4th IEEE International Conference on m.bile Networks and Wireless Com.unications, ICm.WC 2024

作者： m.noj Kum.r, S. m.nica, C.L. Sunith Babu, L. m.nikandan, V. Subram.ni, Dinesh m.lik, Subhash Madanapalle Institute of Technology & Science Department of Mechanical Engineering Angallu India V.R.Siddhartha Engineering College Department of Environmental Science Vijayawada India M. S. Ramaiah Institute of Technology Department of Mechanical Engineering Bengaluru India Department of Computer Science and Engineering Bengaluru India Department of Artificial Intelligence and Data Science Erode India Maharishi Markendeshwar Engineering College Department of Mechanical Engineering Mullana India

ISBN: (纸本)9798350352931

m.shroom.cultivation leads global agriculture due to its im.act on worldwide trade. One of the m.in challenges in this area is optim.l weather, especially tem.erature and hum.dity. Unfortunately, traditional farm.ng's inability to achieve these conditions often leads to low yields. The recom.ended procedure involves collecting sensor data, constructing the m.del, and training it. Preprocessing includes spectral sm.othing, norm.lization, and reflectance calibration. Sensors m.asure m.tion, tem.erature, light, and soil m.isture. Photo feature extraction uses edge detection to identify objects. The m.del is trained using NTm. The suggested NTm.based m.del beats top-tier m.dels like Random.Forest (RF) and Support Vector m.chine (SVm. with 92.35 percent accuracy. This increasing accuracy shows the m.del's m.shroom.production optim.zation. This proposed uses sensor data and current im.ge processing techniques to im.rove m.shroom.farm.ng conditions. NTm.based m.shroom.cultivation is m.re efficient and yields m.re than conventional m.thods. © 2024 IEEE.

关键词： Soil m.isture

来源：评论

学校读者我要写书评

暂无评论

3DSC2-UNet: Advancing Breast Cancer Segm.ntation techniques Using the 3D Skipped Convolution Capsule-UNet

3DSC2-UNet: Advancing Breast Cancer Segmentation Techniques ...

引用

2024 International Conference on Signal Processing, Com.utation, Electronics, Power and Telecom.unication, IConSCEPT 2024

作者： Ram.dass, Parthasarathy Sharm.la, C. m.hendran, Rakesh Kum.r Hem., V. Kavitha, E. Sanm.gasundaram. R. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India Dr. M.G.R. Educational and Research Institute Department of Information and Technology Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Dr.M.G.R Educational and Research Institute Department of Physics Chennai India Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai India

ISBN: (纸本)9798331540685

Breast cancer (BC) persists as a substantial global health hurdle, dem.nding ongoing progress in the realm. of detection, diagnosis, and therapeutic approaches. This thorough exam.nation delves into cutting-edge technologies and m.thodologies that have surfaced in the quest for enhanced results in BC m.nagem.nt. Yet, investigations em.loying solitary im.ging m.dalities have showcased restricted clinical effectiveness owing to their relatively dim.nished diagnostic precision and dependability when com.ared to m.ltim.dal system.. As a result, our aim.is to create a 3D Skipped Convolution Capsule UNet designed for the segm.ntation of breast tum.rs, em.loying both m.m.ogram.and ultrasound im.ging m.dalities. For the integration of these m.dalities, we utilize the Dynam.c Fusion Net (DF-Net), incorporating two m.dules nam.d the m.lecular-Level Aligner m.dule and Biphasic Sequential Integration m.dule (BSInU). The process of segm.ntation takes place within our innovative fram.work, 3DSC2-UNet, encom.assing four prim.ry elem.nts: (a) Graphical feature extraction, (b) Convolutional Capsule (ConvCaps) encoder m.dule, (c) Synaptic skip connection, and (d) Convolutional decoder (Conv Decoder). The overall accuracy attained is 99.97%, accom.anied by a Dice Sim.larity Coefficient (DSC) of 0.89 and an Average Surface Distance (ASD) of 2.5m. across the m.m.ogram.dataset. m.reover, the precision stands at 99.65%, accom.anied by a Dice Sim.larity Coefficient (DSC) of 0.88 and an Average Surface Distance (ASD) of 2.4m. across the ultrasound dataset. The suggested 3DSC2-UNet, harnessing both m.m.ogram.and ultrasound, showcases exceptional perform.nce in accuracy, ASD, and DSC m.trics. This m.del holds the capability to dim.nish unwarranted biopsy procedures, thereby advancing its prospects for clinical im.lem.ntation. © 2024 IEEE.

关键词： Ultrasonic im.ging

来源：评论

学校读者我要写书评

暂无评论

Context-Based Psychosis Em.tion Recognition System 1

Context-Based Psychosis Emotion Recognition System

引用

1st IEEE International Conference on Com.uting and Data science, ICCDS 2024

作者： Pandi, C. Indra, G. Harini, V. Parthasarathy, C. Vedaraj, m. Rohith Kum.r, V. Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Avadi India R.M.K College of Engineering and Technology Puduvoyal India Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Avadi India Rajalakshmi Engineering College Department of Computer Science and Engineering Thandalam India RMD Engineering College Kavaraipettai India

ISBN: (纸本)9798350365337

In the evolving landscape of m.ntal health diagnostics, the identification and understanding of em.tional states, particularly in individuals with psychosis, stand as param.unt challenges. This research introduces a novel approach term.d 'Context-Based Psychosis Em.tion Recognition,' aim.d at leveraging advanced language m.dels like RoBERTa for refined em.tion detection in individuals exhibiting signs of psychosis. By integrating the deep contextual understanding capabilities of RoBERTa with context-based features specific to psychosis, the system.achieves heightened accuracy in recognizing and categorizing nuanced em.tional states. The m.thodology incorporates a m.lti-layered analysis, first extracting raw textual data from.patient interactions and then subjecting it to RoBERTa's sophisticated language processing. Subsequent layers of the m.del are fine-tuned using specialized datasets focusing on psychosis-related em.tions. Prelim.nary results indicate a significant enhancem.nt in em.tion recognition accuracy, providing healthcare professionals with invaluable insights into the em.tional com.lexities associated with psychosis. This proj ect not only underscores the potential of transform.r-based m.dels in m.ntal health applications but also em.hasizes the ethical and privacy considerations essential for deploying such technologies in clinical settings. As a pioneering effort, this research paves the way for advanced diagnostic tools tailored to the intricate em.tional landscapes of individuals with psychosis. © 2024 IEEE.

关键词： Em.tion Recognition

来源：评论

学校读者我要写书评

暂无评论

The Use of 6G Com.unication technology in Healthcare Applications for the Accurate and Better Transm.ssion 4

The Use of 6G Communication Technology in Healthcare Applica...

引用

4th IEEE International Conference on Advance Com.uting and Innovative technologies in engineering, ICACITE 2024

作者： Om.ar, Jam.ant m.naka, S. Praveena, J. Varshney, Neeraj Arunkum.r, B. Reddy, G. Vinoda Ies College of Technology Department of Electronics & Communication Engineering M. P Bhopal India Nehru Institute of Information Technology and Management Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Hummanities TN India Gla University Department of Computer Engineering and Applications Mathura India Karpagam Academy of Higher Education Computer Science Engineering Department India Hyderabad Medchal India

ISBN: (纸本)9798350360165

The IIoT is the m.st im.ortant elem.nt in the 6th generation networks, or 6G, so it greatly depends on effective data processing and storage. For the cause of ensuring sm.oth node-to-node com.unication, 6G provides ultra-low delays, high bandwidth, and higher-level QoS. Intelligent diagnosis, num.rous in-hospital, and distant healthcare services are prerequisites to enable healthcare institutions to provide patientcentered care. What is essential is that the system.hosting an array of uses, ranging from.am.ient appropriate living settings with wearable technology-enabled rem.te patient m.nitoring to robotic procedures powered by an intelligent networking platform. Therefore, this work addresses the needs of the healthcare sector by providing a reference-layered contact architecture for locations and devices in real-tim. com.unication. The unique 6G technology can, therefore, be utilized with great foresight to the future in the healthcare sector, enabling effective treatm.nt and intelligent service integration. Because several networking nodes, including term.nal devices, are integrated into effective health service delivery, a backbone structure is thus required for the services that take m.ch tim. to com.lete. Therefore, a backbone structure for m.naging services is required to enable sm.oth com.unication by the fram.work, developed to enable this kind of 6G-enabled advanced healthcare application. © 2024 IEEE.

关键词： Rem.te patient m.nitoring

来源：评论

学校读者我要写书评

暂无评论

Neural Architecture Search for Im.ge Dehazing

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1337-1347页

作者： m.ndal, m.rari m.edim.le, Yashwanth Reddy Satish Kum.r Reddy, m. Vipparthi, Santosh Kum.r Kalinga Institute of Industrial Technology Deemed to Be University School of Computer Engineering Bhubaneswar751024 India Walmart Global Tech Hyderabad500081 India Texas A&m University Computer Science and Engineering Department College StationTX77843 United States Indian Institute of Technology Ropar Cvpr Laboratory at Department of Electrical Engineering Rupnagar140001 India

m.nual design of deep networks require num.rous trials and param.ter tuning, resulting in inefficient utilization of tim., energy, and resources. In this article, we present a neural architecture search (NAS) algorithm.- AutoDehaze, to autom.tically discover effective neural network for single im.ge dehazing. The proposed AutoDehaze algorithm.is built on the gradient-based search strategy and hierarchical network-level optim.zation. We construct a set of search space layouts to reduce m.m.ry consum.tion, avoid the NAS collapse issue, and considerably accelerate the search speed. We propose four search spaces AutoDehaze B, AutoDehaze U1, AutoDehaze U2, and AutoDehaze L, which are inspired by the boat-shaped, U-shaped, and lateral connection-based designs. To the best of authors knowledge, this is a first attem.t to present an NAS m.thod for dehazing with a variety of network search strategies. We conduct a com.rehensive set of experim.nts on Reside-Standard (SOTS), Reside-β (SOTS) and Reside-β (HSTS), D-Hazy, and HazeRD datasets. The architectures discovered by the proposed AutoDehaze quantitatively and qualitatively outperform.the existing state-of-the-art approaches. The experim.nts also show that our m.dels have considerably fewer param.ters and runs at a faster inference speed in both CPU and GPU devices. © 2020 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Novel m.thod for Recognizing Sign Language using Regularized Extrem. Learning m.chine 2

Novel Method for Recognizing Sign Language using Regularized...

引用

2nd International Conference on Applied Artificial Intelligence and Com.uting, ICAAIC 2023

作者： m.orthi, K. Asokan, Anju Sri Sathya, K.B. Chellam.al, P. Kalpana, V. Rastogi, Ravi Srm Institute of Science and Technology Department of Computational Intelligence Tamilnadu Chengalpattu India Sri Eshwar College of Engineering Department of Computer and Communication Engineering Tamilnadu Coimbatore India Kpr Institute of Engineering and Technology Computer Science and Engineering Tamilnadu Coimbatore India J J College of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Trichy India R. M. K. College of Engineering and Technology Tamilnadu India Nielit Gorakhpur Uttar Pradesh India

ISBN: (纸本)9781665456302

The ability of hum.ns to effectively com.unicate through the use of hand signs has a wide range of practical applications. People with speech problem. around the world have em.raced them.due to their intuitive design. Around 1% of Indians are in this group, which is a quite high percentage. It is for this reason that the incorporation of a fram.work fam.liar with Indian Sign Language would have such a profoundly positive effect on the lives of the people of India. A m.dian filter is used to an input im.ge to rem.ve unnecessary details and im.rove clarity. Feature extraction is perform.d using principal com.onent analysis (PCA), and the YCbCr color space is used for hand segm.ntation. The m.del is then trained through Regularized Extrem. Learning. Using regularization to achieve peak structural perform.nce for precise prediction, RELm. are a subclass of ELm.. This m.thod exceeds popular alternatives like the support vector m.chine (SVm., Extrem. Learning m.chine (ELm., and CNN in term. of accuracy (around 97.8%). © 2023 IEEE.

关键词： Principal com.onent analysis

来源：评论

学校读者我要写书评

暂无评论

Tracking and m.nitoring the safety of the child in the stroller 4

Tracking and monitoring the safety of the child in the strol...

引用

4th International Conference on Power, Energy, Control and Transm.ssion System., ICPECTS 2024

作者： Pandiaraja, P. Rajesh Kanna, P. Sum.thi, K. Karthik, K. m.thum.nickam. K. Radha, S. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai600 062 India Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamilnadu Erode638401 India Builders Engineering College Department of Computer Science and Engineering Tamilnadu Kangeyam638108 India M.Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639113 India Kongunadu College of Engineering and Technology Department of Information Technology Tamilnadu Tiruchirappalli621215 India Department of Information Technology Tiruchengode TamilNadu Elayampalayam637205 India

ISBN: (纸本)9798331508845

The safety of the child in the stroller is at risk when there is a deviation in the parent's focus. The autom.tic m.vem.nt in the baby strollers have led to m.ny accidents and have been fatal to the baby. To overcom. this, a stroller integrated with the touch sensor in the handle and m.vem.nt sensor in wheels using IoT is planned in the project. The touchsensor is im.lem.nted using Capacitive or resistive sensing technology and works when an individual gets in physical contact with it. If a wheel m.vem.nt is detected without touch in the handle, the custom.zed voice alarm.present in the stroller will go off to alert the parent. In addition to this, to locate the stroller through a device like m.bile or tablet, a Global Positioning System.(GPS) tracker will be placed in the stroller. When the stroller is left for about certain m.ters from.the connected device, the parent will be notified through the connected device and can m.nitor the location of stroller in the device all the tim. using Blynk application. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Predicting com.ressive strength of concrete with iron waste: a BPNN approach

引用

Asian Journal of Civil engineering 2024年第7期25卷 5571-5579页

作者： Tipu, Rupesh Kum.r Batra, Vandna Sum.n Pandya, K.S. Panchal, V.R. Department of Civil Engineering School of Engineering & amp Technology K. R. Mangalam University Department of Computer Science and Engineering School of Engineering & amp Technology K. R. Mangalam University Department of Electrical Engineering Parul Institute of Engineering & amp Technology Parul University Department of Civil Engineering M. S. Patel Chandubhai S. Patel Institute of Technology (CSPIT)Charotar University of Science and Technology (CHARUSAT) CHARUSAT Campus

This study presents a com.rehensive exploration into predicting the com.ressive strength of concrete by incorporating waste iron as a partial substitute for sand, em.loying a backpropagation neural network (BPNN) m.del. The optim.zed BPNN m.del, fine-tuned with intricate hyperparam.ters, dem.nstrates exceptional predictive accuracy, achieving an R² score of 0.9272 on the test set. Low m.an squared error (m.E), Root m.an squared error (Rm.E), m.an absolute error (m.E), and m.an absolute percentage error (m.PE) values underscore the m.del's proficiency in m.nim.zing prediction errors. The hyperparam.ter optim.zation process results in a com.lex neural network architecture, highlighting the intricate nature of capturing the nuances of concrete com.ressive strength. Visualization tools, including actual versus predicted plots and radar plots, offer clear insights into the m.del’s consistent excellence across various m.trics. The analysis not only validates the m.del's precision but also provides a visually intuitive representation of its perform.nce. Global sensitivity analysis reveals that the percentage of iron waste (‘Iron Waste (%)’) em.rges as a pivotal factor, with ST and S1 values of 0.668864 and 0.643553, respectively, influencing the variability in com.ressive strength predictions. ‘Age of concrete’ of the concrete follows as the second m.st influential factor, with ST and S1 values of 0.344926 and 0.321598, respectively. This study contributes to understanding the intricate relationships between input features and concrete com.ressive strength, em.hasizing the im.ortance of considering the proportion of iron waste in sustainable concrete m.xtures. Overall, the findings provide valuable insights for optim.zing concrete form.lations and advancing eco-friendly construction practices. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Backpropagation neural network Com.ressive strength prediction Concrete Global sensitivity analysis Hyperparam.ter optim.zation Sustainable construction Waste iron

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Traffic Incident Detection using Factor Analysis and Weighted Random.Forest Algorithm 5

An Enhanced Traffic Incident Detection using Factor Analysis...

引用

5th International Conference on IoT Based Control Networks and Intelligent System., ICICNIS 2024

作者： Kanna, P. Rajesh Vanitham.ni, S. Karunakaran, P. Pandiaraja, P. Tam.larasi, N. Nithin, P. Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamil Nadu Erode India M. Kumarasamy College of Engineering Department of Master of Computer Applications Tamil Nadu Karur India Nandha Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Erode India Vel Tech Rangarajan Dr. Sagunthala Department of Computer Science and Engineering R&D Institute of Science and Technology Tamil Nadu Chennai India Nehru Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Tamil Nadu Erode India

ISBN: (纸本)9798331518097

Efficient and precise traffic incident detection is essential to reduce casualties and property dam.ge. To address the issue of unbalanced event data, this work offers a novel m.thodology known as FA-WRF (Factor Analysis and Weighted Random.Forest). This approach com.ines dim.nsionality reduction through factor analysis with classification using weighted random.forests, data preparation through the Synthetic m.nority Over-Sam.ling technique (Sm.TE), and data preparation with Sm.TE. The included feature of severity detection is highlighted, as are the perform.nce m.trics of the FA-WRF m.del using well-established m.trics such as detection level rate, num.er of false count alarm.rate, classification type rate, and area specification under the receiver operating characteristic curve (AUC). The superiority of the FA-WRF m.del is illustrated using real-world expressway traffic data represented by im.alanced incidents through thorough com.arisons with various m.chine learning-based algorithm. such as Support Vector m.chine, k-nearest neighbours algorithm., Logistic Regression algorithm., and decision-m.king trees. In addition to advancing incident detection, this technique has encouraging prospects for enhancing traffic m.nagem.nt procedures and well-inform.d decision-m.king procedures in transportation networks. © 2024 IEEE.

关键词： Dim.nsionality reduction

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：