检索结果-内蒙古大学图书馆

Customizing Tablets Using machine Learning Through Rapid Prototyping 7

Customizing Tablets Using Machine Learning Through Rapid Pro...

7th IEEE International Conference on Computational Systems and Information technology for Sustainable Solutions, CSITSS 2023

作者： Shashank, K.T. Gururaja, H.S. Nagaraj, Seema B.M.S. College of Engineering Department of Me Bangalore India B.M.S. College of Engineering Department of Ise Bangalore India Bangalore Institute of Technology Mca Department Bangalore India

ISBN: (纸本)9798350343144

The use of cutting-edge technology like rapid prototyping and machine learning may change future tablet designs. The time it takes to make a tablet is drastically reduced thanks to these technologies, which could speed up the quality assurance process. Create novel and original dosage forms and hasten the production of new pharmaceuticals, integration of human learning, 3D printing, and machine learning can be used. This study analyzes and extracts data from a specific person using a natural language Processing methodology, then Processing Double Layer blowing Agent using a 3D printing technique called fused deposition of filaments. The result is that the release profile is influenced by the 3D printing process's Fill factor of the process. 3D printing fused, according to study, may present a fresh way to produce unit dosage forms or drugs with unique dosages and controlled-release characteristics. © 2023 IEEE.

关键词： Deposition

来源：评论

学校读者我要写书评

暂无评论

Early Detection of benign Ovarian Tumor Classification Using U-NET+ with Hybrid Deep Learning Techniques

引用

SN Computer Science 2024年第7期5卷 966页

作者： Kamala, C. Shivaram, Joshi manisha Department of Medical Electronics Dr. Ambedkar Institute of Technology Karnataka Bengaluru India Department of Medical Electronics B.M.S. College of Engineering Karnataka Bengaluru India

Ovarian cysts are common gynecological ailments that, if undiagnosed or ignored, can lead to substantial medical issues. Recognizing and categorizing ovarian cysts is critical for optimal treatment planning and patient care. Screening for ovarian cysts on time is critical for efficient treatment and better patient outcomes. Despite the fact that cysts often damage female follicles, a large ovarian cyst can induce torsion and infertility. As a result, it is critical to obtain a diagnosis as quickly as feasible. An ovarian cyst is diagnosed with an ultrasound (US) screening. most cysts have been detected at an early stage due to the enhancement of these concepts and technologies in medical imaging. As a consequence, with this study, US images from several women's ovaries were collected to find out the kinds of ovarian cysts that would be identified. Existing attempts, however, have flaws such as slow convergence and prolonged training time. This study attempts to further develop deep learning-based segmentation of ovarian US cyst images using an active database to address this issue. The present investigation examines five types of ovarian cysts: serous tumor (ST), mucinous tumor (mT), endometrioid tumor (ET), clear cell tumor (CCT), and No tumor (NT). The input image was first pre-processed using the Diagonal bilinear interpolation (DbI) preprocessing approach, designed to enhance borders and reduce noise while retaining crucial image attributes. It's extremely helpful for medical images like USs. The pre-processed image is then segmented using U-NET +, which offers a new “deep supervision” technique in which intermediate segmentations are created at each level of the hierarchy and combined to form the final segmentation. The deep features are then extracted using the VGG19 model, which is fine-tuned on a dataset to attain high accuracy with minimal training data. A hybrid Equilibrium and Jarratt butterfly optimization algorithm (EJbOA) is then employed for feature s

关键词： benign Classification Deep learning Jarratt-butterfly algorithm Ovarian tumor U-NET plus

来源：评论

学校读者我要写书评

暂无评论

message from the Program Chair TIACOmP 2024

Proceedings - 2024 1st International Conference on Technolog...

引用

Proceedings - 2024 1st International Conference on Technological Innovations and Advance Computing, TIACOmP 2024 2024年 XVIII页

作者： mittal, Harish Kumar B M Institute of Engineering and Technology Sonepat India

来源：评论

学校读者我要写书评

暂无评论

An overview of biomass solid fuels:biomass sources,processing methods,and morphological and microstructural properties

引用

Journal of bioresources and bioproducts 2023年第4期8卷 333-360页

作者： Segun E.Ibitoye Rasheedat m.mahamood Tien-Chien Jen Chanchal Loha Esther T.Akinlabi Department of Mechanical Engineering Science Faculty of Engineering and the Built EnvironmentUniversity of JohannesburgAuckland Park2006524South Africa Department of Mechanical Engineering Faculty of Engineering and TechnologyUniversity of IlorinIlorin P.M.B.1515Nigeria Energy Research and Technology Group CSIR-Central Mechanical Engineering Research InstituteWest BengalDurgapur-713209India Department of Mechanical and Construction Engineering Faculty of Engineering and EnvironmentNorthumbria UniversityNewcastle NE18STUnited Kingdom

biomass solid fuel(bSF)has emerged as a promising renewable energy source,but its morphological and microstructural properties are crucial in determining their physical,mechanical,and chemical *** paper provides an overview of recent research on *** focus is on biomass sources,bSF processing methods,and morphological and microstructural properties,with a special emphasis on energy-related *** inclusion and exclusion criteria were established for the study to ensure *** inclusion criteria encompassed studies about bSFs and studies investigating the influence of biomass sources and processing methods on the morphological and microstructural properties of solid fuels within the past five *** technologies for converting biomass into usable energy were discussed,including gasification,torrefaction,carbonization,hydrothermal carbonization(HTC),and *** has advantages and disadvantages in energy performance,techno-economics,and climate *** is efficient but requires high *** produces bio-oil,char,and gases based on feedstock *** generates low-cost biochar for solid fuels and carbon sequestration *** increases energy density for co-firing with *** processes wet biomass efficiently with lower energy *** treatment affects bSF durability and strength,often leading to less durability due to voids and gaps between *** carbonization alters surface morphology,creating cavities,pores,and distinctive *** pyrolysis generates biochar with better morphological properties,while fast pyrolysis yields biochar with lower porosity and surface *** constitutes 67%of the biomass sources utilized for bioenergy generation,followed by wood residues(5%),agro-residues(4%),municipal solid wastes(3%),energy crops(3%),livestock wastes(3%),and forest residues(1%).Each source has advantages and drawbacks,such as avail

关键词： biomass feedstock microstructural property morphological property Renewable energy Thermal treatment

来源：评论

学校读者我要写书评

暂无评论

Trajectory correction for lunar flyby transfers to libration point orbits using continuous thrust

引用

Astrodynamics 2022年第3期6卷 285-300页

作者： Yi Qi Anton de Ruiter School of Aerospace Engineering Beijing Institute of TechnologyBeijing 100081China Department of Aerospace Engineering Ryerson UniversityTorontoON M5B 2K3Canada

Trajectory corrections for lunar flyby transfers to Sun–Earth/moon libration point orbits(LPOs)with continuous thrusts are investigated using an ephemeris *** lunar flyby transfer has special geometrical and dynamical structures;therefore,its trajectory correction strategy is considerably different from that of previous studies and should be specifically *** this paper,we first propose a control strategy based on the backstepping technique with a dead-band scheme using an ephemeris *** initial error caused by the launch time error is *** the perturbed transfers significantly diverge from the reference transfers after the spacecraft passes by the moon,we adopt two sets of control parameters in two portions before and after the lunar flyby,***,practical constraints owing to the navigation and propellant systems are introduced in the dynamical model of the trajectory *** a prograde type 2 orbit as an example,numerical simulations show that our control strategy can efficiently address trajectory corrections for lunar flyby transfers with different practical *** addition,we analyze the effects of the navigation intervals and dead-band scheme on trajectory ***,trajectory corrections for different lunar flyby transfers are depicted and compared.

关键词： libration point orbit trajectory correction Earth-moon system continuous thrust backstepping technique

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Sensor Fusion Technique for Indigenous Intelligent Vision System for Theft Detection

Deep Learning and Sensor Fusion Technique for Indigenous Int...

引用

2023 IEEE World Conference on Applied Intelligence and Computing, AIC 2023

作者： Pranav, m. Hegde, Veena N. Raju, Rachana S. Roopa, S. B.M.S College of Engineering Department of Electronics and Instrumentation Engineering Bangalore India Engineering Siddaganga Institute of Technology Department of Electronics and Communication Tumkur India

ISBN: (纸本)9798350310061

This paper proposes an indigenous system with modified architecture to classify different kinds of objects used in burglary and certain suspicious activities identified in thievery. The classifier used is a part of the security system to detect the images/ movements pertaining to theft or unusual acts while shoplifting valuable objects from jewellery stores. A sequence of integrated real-time computer vision algorithms and sensor fusion technology are implemented. The system adopts the transfer learning method (has 68 layers, 75 connections) as a pre-trained neural network to identify the unusual objects. Here, a person can take suitable action to aid the situation. The classifier algorithm was trained on a dataset of 144 cases of images and augmented appropriately belonging to seven different classes. It provides an accuracy of 97.73% during the validation phase and the confusion matrix resulted in an accuracy close to 95% and an F1-score of 84%. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Design and Control of Four Legged Spyder Robot 8

Design and Control of Four Legged Spyder Robot

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： bhardwaj, Anjali Hyder, mohammad muzaffar Pragna, b. Anche, Laieeqa Hegde, Veena N. Roopa, S. B.M.S College of Engineering Department of Electronics and Instrumentation Engineering Bangalore India Siddaganga Institute of Technology Department of Electronics and Communication Engineering Tumakuru India

ISBN: (纸本)9798350396638

In the realm of robotics, the design, development, and motion planning of a mobile robot are now being explored as research fields. mobile robots can be used in space exploration, military applications, and industrial applications. As a result, designing and developing a mobile robot is an important aspect of the aforementioned applications. In this paper, a quadruped robot (spy-der), which is a four-legged robot that outperforms wheeled and tracked robots by being able to explore in all terrains, like human and animal is developed. This research work focuses on different quadruped robot design, development, and control methodologies. The robot is controlled by two methods: bluetooth and web control, along with live video streaming, motion detection, and location tracking features. © 2023 IEEE.

关键词： bluetooth

来源：评论

学校读者我要写书评

暂无评论

machine Learning models for Sentiment Analysis 10

Machine Learning Models for Sentiment Analysis

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： muralidhar, Amrutha Lakkanna, Yathindra B. M. S College of Engineering Department of Computer Science and Engineering Bengaluru India National Institute of Fashion Technology Department of Fashion and Lifestyle Accessory Design Bengaluru India

ISBN: (纸本)9798350384369

In the competitive landscape of online fashion retail, understanding and responding to customer sentiments is crucial for success. Our study addresses the challenge faced by retailers in effectively analyzing diverse customer feedback data to enhance their understanding of customer sentiments. We evaluate the performance of five machine learning models using techniques like word cloud examination, sentiment distribution assessment, and Latent Dirichlet Allocation. Our findings indicate that SVm and Logistic Regression emerge as the top-performing models, with SVm demonstrating superior accuracy and overall performance compared to the others. by using these methods, online stores may improve consumer satisfaction and obtain a competitive advantage in the market. This research contributes to broader industry advancements by providing clear guidance on leveraging machine learning for sentiment analysis in the online fashion retail sector. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Performance Towards Torque and Flux Control through a Hybrid Approach of Intelligent and DTC for SRm Drives

引用

IEEE Access 2025年 13卷 92168-92179页

作者： Deepak, m. Umavathi Chokkalingam, bharatiraja Verma, Rajesh mihet-Popa, Lucian of Technology Department of Electrical and Electronics Engineering Coimbatore India B.M.S College of Engineering Department of Electrical and Electronics Engineering Bangalore India SRM Institute of Science and Technology Kattankulathur Centre for Electric Obility Department of Electrical and Electronics Engineering Tamil Nadu Chengalpattu603203 India King Khalid University College of Engineering Electrical Engineering Department Asir Abha61411 Saudi Arabia Ostfold University College Faculty of Information Technology Engineering and Economics Halden1757 Norway

Switched Reluctance motors (SRms) are considered the preferred choice for next-generation electric vehicle (EV) traction motor applications due to their simple rotor structure and favorable power and torque characteristics. However, SRm drives suffer from high torque ripples, which can cause severe vibrations and acoustic noise. moreover, the highly nonlinear characteristics of SRms complicate their control and modeling, making it a significant challenge to achieve optimal performance. Therefore, this paper proposes a Direct Torque Control (DTC) strategy for SRms, which incorporates a modified dynamic precise model and an Adaptive Neuro-Fuzzy Inference System (ANFIS). First, a DTC technique based on a two-level hysteresis controller with an appropriate switching scheme is introduced for instantaneous torque control, ensuring proper torque tracking with a smooth torque profile. Second, a novel hybrid intelligent ANFIS model is developed for accurate flux and torque estimation and optimal selection of switching angles. The proposed method employs a multi-objective function to fully exploit the torque production capability of the SRm, minimize torque ripple, and enhance operational efficiency. The proposed solutions are compared with conventional DTC schemes, and experimental evaluations demonstrate significant reductions in torque ripple, flux ripple, and current distortion. © 2013 IEEE.

关键词： Fuzzy models

来源：评论

学校读者我要写书评

暂无评论

Design and Numerical Investigation of FTO/TiO2/FA0.85Cs0.15Pb(I0.85br0.15)3/moO3/Au Perovskite Solar Cell

Design and Numerical Investigation of FTO/TiO2/FA0.85Cs0.15P...

引用

2023 IEEE International Conference on modelling, Simulation and Intelligent Computing, moSICom 2023

作者： Sarkar, Paramita Srivastava, Ashutosh Narmada, G. Nithin, E.N. Naidu, J. B.M.S. Institute of Technology and Management Department of ECE Bangalore560064 India Bennett University School of Computer Science Engineering and Technology Greater Noida India B v Raju Institute of Technology Department of ECE Narsapur India

ISBN: (纸本)9798350393415

The primary aim of the present work is to design a perovskite photovoltaic cell with higher efficacy that is suitable for practical applications. Therefore, a mixed perovskite layer composed of FA0.85Cs0.15Pb(I0.85br0.15)3 was used as the active layer. Along with this perovskite, TiO2 and moO3 have been used as electron and hole transport layer, respectively. The cell was optimized by varying the working temperature between 280K to 325K, absorber layer thickness between 100nm to 700nm, and bulk defect density between 1011/Cm-3 to 1016/Cm-3. The final Optimized cell shows 1.53V open circuit voltage, 23.67mA/Cm2 short circuit current, 85.63% of fill factor and 30.84% of efficiency at optimized temperature of 280K, optimized perovskite layer thickness of 700nm and bulk defect density of 1011 Cm3. The present modeling technique is compared with the reported theoretical as well as experimental data that confirm the accuracy of the conclusions we have obtained for the proposed cell. © 2023 IEEE.

关键词： Perovskite

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：