检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Sushma, K.S.N. Sarkar, Argha Sanyal, Gautam School Of Computer Science And Engineering Reva University Bengaluru India National Institute Of Technology Department Of Computer Science And Engineering Durgapur India

ISBN: (纸本)9798350371567

Addressing the challenge of manually analyzing nanoparticle characteristics, such as size and shape, researchers have increasingly turned to deep learning methodologies. This research paper introduces a novel approach, a synergistic combination of CNN-GA architecture, to efficiently analyze the physical properties of nanoparticles. The integration of CNN for feature extraction from image data and GA for fine-tuning hyperparameters and attributes proves to be a powerful tool. Unlike the traditional manual design of CNN architectures, this semi-automatic approach allows researchers to design robust architectures without necessitating in-depth CNN expertise, facilitating the achievement of benchmark results in nanoparticle characterization. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Presentation Dynamics with Real-time Hand Gesture Recognition: A Review

Enhancing Presentation Dynamics with Real-time Hand Gesture ...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Upadhyay, Divya Sati, Pankaj Jain, Naman Computer Science And Engineering Abes Engineering College Uttar Pradesh Ghaziabad India

ISBN: (纸本)9798350366846

Consider conducting talks where the presenter uses only hand gestures no buttons or mouse to interact with the audience and control the slides. An in-depth discussion of enhancing presentation dynamics through real-time hand gesture recognition will be covered in this research paper. A presentation's importance in the digital age is underscored by the need to make it more dynamic and engaging. The paper investigates how real-time hand gesture recognition technologies might significantly improve the quality of presentations. In this paper, the instruments and techniques that people are now using are examined closely. Consider cameras like the Microsoft Kinect that can detect hand movements. These enable presenters to transition between slides seamlessly, emphasise key points, and engage with images or videos without uncomfortable pauses. Furthermore, they examine wearable technology with unique sensors that enable presenters to control their presentations without bulky equipment. Presenters now have greater freedom to engage with their audience thanks to wearables that use tiny sensors to interpret hand movements and convert them into actions. Not only that, but this study will go even more deeply into the scientific aspect. This paper will focus on advanced artificial intelligence-based computer programs and devices that can detect hand movements in real time. Teaching a computer to recognize when a user points, swipes, or waves their hand to interact with an audience is analogous to teaching it to do the same. When users combine verbal and hand movements, it gets incredibly lively. This article explores the possibilities of integrating spoken words and hand gestures to provide highly interactive presentations. With the help of this fusion, presenters can more easily convey their message by using their hands to give instructions or add explanations. © 2024 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Bouke, Mohamed Aly El Atigh, Hayate Abdullah, Azizol Department of Communication Technology and Network Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia Departement of Computer Engineering Faculty of Computer Engineering Bandirma Onyedi Eylul University Balikesir10200 Turkey

The Internet of Medical Things (IoMT) brings advanced patient monitoring and predictive analytics to healthcare but also raises cybersecurity and data privacy issues. This paper introduces a deep-learning model for IoMT intrusion detection, utilizing the WUSTL EHMS 2020 dataset, which focuses on cyber threats like man-in-the-middle attacks and data injection. Our sequential model, trained with TensorFlow, surpasses traditional predictive accuracy and efficiency methods. It achieves 99% accuracy with reduced loss and excels in precision, recall, F1 Score, and ROC AUC. The model uses 25 key features from 45, preventing overfitting and addressing data leakage in preprocessing. These steps ensure the model's reliability for IoMT cybersecurity, demonstrating its effectiveness in real-world scenarios. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Species Density Analysis Using Deep Learning

Species Density Analysis Using Deep Learning

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Rekha, K.S. Shamlin, A Harini Saveetha Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350309140

The primary objective of this project is to develop a machine learning model, specifically Convolutional Neural Network (CNN), to count the density of several particular species in an audio clip. The model is trained on a dataset containing calls of the specified species and other species. This innovation has significant implications for wildlife monitoring and ecological research, as it can help researchers track and understand the behavior of organisms in forest regions more efficiently. Manual effort in audio analysis can be reduced by machine learning, thereby saving time. By improving and broadening techniques, algorithms, and training methodologies, researchers can uncover more about animal behavior and contribute to our collective understanding of ecosystems. The application of this technology can be useful for analyzing the total number of species in a certain rainforest region, eventually reducing the burden on researchers and streamlining the entire process. Overall, this project has immense potential to pave the way for more efficient and accurate wildlife monitoring and ecological research that can ultimately benefit our planet's biodiversity. © 2024 IEEE.

关键词： Forest ecology

来源：评论

学校读者我要写书评

暂无评论

Automated Brain Tumor Detection and Classification Through Deep Learning Analysis of MRI Scans

Automated Brain Tumor Detection and Classification Through D...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Mary, Anne Khanna, Bobby Malarvel, Muthukumaran Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

Deep learning, a prominent facet of AI, has rapidly reshaped the healthcare landscape by offering swift and accurate data analysis techniques. These methodologies aid medical professionals and caregivers worldwide in achieving precise diagnoses and administering follow-up treatments. The brain, serving as the central control unit of the human body is accountable for making decisions. and overseeing the functionality of all other organs and systems, both voluntary and involuntary. Brain tumors, characterized by abnormal cell growth in the brain, can lead to severe conditions like Cancer. Examination through Magnetic Resonance Imaging (MRI) scans are the primary the technique employed by medical professionals to identify brain tumors offers detailed insights into any atypical tissue growth within the brain. By applying machine learning (ML) and deep learning (DL) algorithms to MRI images accelerates and enhances the identification and prediction of brain tumors, empowering radiologists to make quick and well-informed decisions. Our proposed methodology entails training a Deep Neural Network (DNN) model on a dataset of MRI images to pinpoint tumor segments within them for further analysis. We utilize the Flask web framework to detect tumor presence. Convolutional Neural Networks (CNNs) are harnessed in our model to detect and classify brain tumors using advanced deep learning techniques. We evaluate our system's performance by comparing it with traditional methods, validating its effectiveness and accuracy through diverse performance metrics. The results exhibit promising potential for future healthcare applications, enabling more precise and timely diagnoses. © 2024 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Resourceful Energy Management and Improved Security in Wireless Sensor Networks by Optimized Energy-Based Security Prototype

引用

SN computer science 2025年第3期6卷 1-13页

作者： Arya, Nancy Deore, Shailesh Shivaji Sharma, Mahendra Verma, Amit Patibandla, R. S. M. Lakshmi Krishna, K. Murali Pareek, Piyush Kumar Department of Computer Science and Engineering School of Engineering & Sciences GD Goenka University Sohna Gurugram India Department of Computer Engineering SSVPS B S DEORE College of Engineering Maharashtra Dhule India DoIT IMT College of Engineering UP Greater Noida India Department of Computer Science University Centre for Research and Development Chandigarh University Gharuan Punjab Mohali India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Department of Electronics Communication Engineering Rajalakshmi Engineering College TN Chennai India Department of AIML and IPR Cell Nitte Meenakshi Institute of Technology Bengaluru India

One must admit that while using a number of remote sensing points with limited nodes, it is crucial to optimize resource usage as intensely as possible and have a secure network with the least compromises, even though WSNs are applied in increasing numbers of industries. When deploying WSN, power utilization and ability to withstand a number of threats and attacks are important factors to be considered. This work presents a technique for a routing protocol that determines the shortest path between two nodes in a network while at the same time trying to conserve energy. Lifetime and energy consumption of the networks are two important factors when designing new protocols for WSN. An important problem of finding a load-sharing routing method with less energy consumption is difficult. TBEBR routing protocol optimizes the parameters that lead to minimal energy dissipation to enhance the lifetime of the network by identifying the path with the least energy consumption possible. Throughput, overhead, packet loss and end to end delay were used as performance parameters to assess the routing protocol. The analysis of the overall efficiency of the routing concept as well as the method of its application was described. As far as the performance of network and nodes is concerned, it is clear that TBEBR outperforms both DSR and AODV. For WSNs, the proposed routing protocol aims at minimizing the energy issue, which is a disadvantage of the technology. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： DoS attack EWMA Unit energy requirement WSN

来源：评论

学校读者我要写书评

暂无评论

Deep bed filtration model for cake filtration and erosion

引用

Applied Mathematics and Mechanics(English Edition) 2024年第2期45卷 355-372页

作者： L.I.KUZMINA Y.V.OSIPOV A.R.PESTEREV Department of Applied Mathematics HSE UniversityMoscow 101000Russia Department of Computer Science and Applied Mathematics Moscow State University of Civil EngineeringMoscow 129337Russia

Many phenomena in nature and technology are associated with the filtration of suspensions and colloids in porous media. Two main types of particle deposition,namely, cake filtration at the inlet and deep bed filtration throughout the entire porous medium, are studied by different models. A unified approach for the transport and deposition of particles based on the deep bed filtration model is proposed. A variable suspension flow rate, proportional to the number of free pores at the inlet of the porous medium, is considered. To model cake filtration, this flow rate is introduced into the mass balance equation of deep bed filtration. For the cake filtration without deposit erosion,the suspension flow rate decreases to zero, and the suspension does not penetrate deep into the porous medium. In the case of the cake filtration with erosion, the suspension flow rate is nonzero, and the deposit is distributed throughout the entire porous medium. An exact solution is obtained for a constant filtration function. The method of characteristics is used to construct the asymptotics of the concentration front of suspended and retained particles for a filtration function in a general form. Explicit formulae are obtained for a linear filtration function. The properties of these solutions are studied in detail.

关键词： deep bed filtration cake filtration porous medium particle deposition and erosion analytical solution concentration front

来源：评论

学校读者我要写书评

暂无评论

Enhanced Genomic Prediction for Maize Breeding Using Deep Learning and K-mer-based Sequence Encoding 5

Enhanced Genomic Prediction for Maize Breeding Using Deep Le...

引用

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

作者： Kudiyarasudevi, C. Suresh, S. SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram India

ISBN: (纸本)9798331518097

Maize (Zea mays L.) plays a pivotal role in global food security due to its substantial economic and nutritional value. With advancements in agricultural technologies, crop yields have surged, but challenges remain in optimizing maize breeding for even higher productivity. This research explores cutting-edge approaches in maize breeding, focusing on novel genomic prediction tools that enhance crop yield. While numerous studies have demonstrated the potential of genomic prediction in accelerating maize yields, current models often suffer from suboptimal data quality and lengthy processing times due to the use of raw data for genotype prediction. To address these challenges, this study introduces a deep learning- based model that leverages polymorphism data, employs k-mer methods to shorten sequences, and applies one-hot encoding for preprocessing. This data is then processed by a convolutional neural network (CNN) to predict genotypes efficiently. The proposed model aims to achieve a 98% accuracy in genomic prediction, outperforming existing models in both speed and accuracy, thereby contributing to the generation of superior maize traits. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Histopathology Breast Cancer Detection and Classification using Optimized Superpixel Clustering Algorithm and Support Vector Machine

引用

Journal of The Institution of Engineers (India): Series B 2022年第5期103卷 1589-1603页

作者： Saturi, Rajesh Chand Parvataneni, Prem Department of Computer Science Engineering University College of Engineering Osmania University Hyderabad India

In recent decades, nuclei cell classification in histology has played a significant role in early diagnosis of breast cancer. However, it is a challenging task, due to the presence of small variant sizes of cells and heavy noise in histology images. To overcome these problems, an optimization-based superpixel-clustering algorithm is introduced to segment non-nuclei and nuclei cell separately. Initially, the histopathology breast images are collected from BreaKHis database. Then, image pre-processing is accomplished by applying normalization technique that increases the quality of image. After normalization, segmentation is performed using superpixel with Particle Swarm Optimizer (PSO) and Grey Wolf Optimizer (GWO) to segment nuclei, and non-nuclei cells. The proposed segmentation algorithm has the advantages of parallel computing and global optimization search, which helps to find a superior result of the superpixel-clustering algorithm. Later, feature extraction is carried out using Local Direction Ternary Pattern (LDTP), perimeter, solidity, circularity, Grey Level Co-Occurrence Matrix (GLCM), eccentricity, and colour autocorrelogram. Finally, Support Vector Machine (SVM) classifier is utilized to grade the histology breast images as malignant or benign images. In the experimental section, the proposed model obtained better performance in breast cancer detection compared to the existing research works and showed 7–8% improvement in classification accuracy. © 2022, The Institution of Engineers (India).

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Smart CIoT with Secure Healthcare Framework Using Optimized Deep Recuperator Neural Network Long Short-Term Memory

引用

IEEE Internet of Things Journal 2024年第6期11卷 10551-10562页

作者： Narmatha, C. Manimurugan, S. Karthikeyan, P. University of Tabuk Faculty of Computers and Information Technology Tabuk71491 Saudi Arabia Oakland University Department of Electrical and Computer Engineering RochesterMI112345 United States National Chung Cheng University Department of Computer Science and Information Engineering Chiayi62102 Taiwan RV University School of Computer Science and Engineering Bengaluru560059 India

The healthcare system currently relies on the facility to store and process large amounts of health data, supported by efficient management. The Internet of Things (IoT) has driven the growth of Adroit Healthcare, which has vast data processing capabilities and extensive data collection. The consumer IoT (CIoT), also known as the IoT in the context of individual use cases, is dominated by personal healthcare applications. The remarkable expansion of the CIoT can be attributed to the extensive embrace of wearable technology, facilitating everyday monitoring of vital health indicators like blood pressure, heart rate, and respiration rate. However, the CIoT raises concerns about data security, confidentiality, and customer trust. This study proposes an integrating blockchain and deep learning (DL) approach to promote responsible use of CIoT. The study develops an Intelligent IoT (IIoT) and healthcare diagnostic model, named BT-PWO-DRNN-LSTM, using blockchain technology and Prairie Wolf optimization-based deep recuperator neural network (DRNN) and long short-term memory (LSTM). The BT-PWO-DRNN-LSTM approach includes three key processes: 1) encrypted transactions;2) cryptographic hash feature;and 3) medical diagnosis. The PWO technique is used for secure communication of medical images, the neighborhood catalogue disposition (NCD) technique is used in the cryptographic hash feature operation (CHFO), and the DL approach is employed as a classification algorithm for diagnosing disorders. The use of PWO methodology for secure healthcare communication and optimal parameter fine-tuning highlights the originality of the study. The BT-PWO-DRNN-LSTM prototype showed positive results with high sensitivity, specificity, and accuracy during the diagnostic process. © 2014 IEEE.

关键词： Blockchain

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

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

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：