检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Recent Advances in Science and engineering technology, ICRASET 2024

作者： Dheemanth, G. Shashikala, S.V. Apoorva, I.S. Bgs Institute of Technology Adichunchanagiri University Department of Computer Science and Engineering BG Nagara Mandya India

ISBN: (纸本)9798350388602

The meal type, calorie count, and weight are all estimated using a smartphone app. The created software classifies the user as underweight, normal weight, overweight, or obese based on many medical criteria like BMI, etc. The software also sorts foods according to their GI. The software estimates the user's weight and caloric intake using cloud-based ML. Eating recommendations for optimal nutritional management is another area the app will expand its utility for. The recommendations will take into account a number of underreported dietary characteristics, such as body mass index (BMI), age, sex, food type, eating habits, etc. This study will not only help medical experts make correct diagnoses, but the technology will also be able to supply individuals with self-eating instructions. In areas where healthcare equipment is lacking and expertise is few, this breakthrough will provide a significant answer for the pharmaceutical and wellness sectors. Dietary management programs will also find this product useful for demonstrations and lessons. Reliable scientific tracking of intake categorisation systems by food chews event identification in the portable context is a medically important aspect of this work. The suggested AdaBoost with Random Forest approach achieves much higher accuracy than the other methods when compared to their respective performances. J48-DT delivers good results, KNN improves accuracy, and Naive Bayes performs adequately. The suggested strategy, on the other hand, has an astounding 94.1% accuracy. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Image Based Plant Disease Detection Using computer Vision 4

Image Based Plant Disease Detection Using Computer Vision

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Gali, Bhavya Jaina, Tejashwi Katpally, Gourav Kankipati, Gowtham Rajyalakshmi, Ch. B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Medak502313 India

ISBN: (纸本)9798350343670

Despite fast population growth, agriculture supplies food for all people. Early detection of plant diseases is advocated as it is essential to making certain the entire population has an abundance of food. However, it is inconvenient to foresee diseases when crops are young due to a lack of necessary infrastructure. The purpose of the paper is to inform farmers about innovative technology that can help to prevent plant diseases. To detect plant conditions, an accurate algorithm for machine learning and imaging sensors is identified. Optical techniques, such as RGB imaging, multi- and hyperspectral sensors, thermography, and chlorophyll fluorescence, have proven effective in computerized, unbiased, repeatable detection systems for locating and measuring plant diseases during the initial phases of outbreaks. The extracts of diseased leaves are taken into account in this investigation. Farmers can quickly identify diseases based on early symptoms by using these disordered leaf samples. By applying machine learning techniques like Support Vector Machine (SVM), Convolutional Neural Network (CNN), and K-Nearest Neighbour (K-NN), the generated characteristics are finally classified. High-end and cutting-edge data processing techniques that produce fresh insights from sensor data for intricate plant-pathogen systems help with the accurate and reliable diagnosis of illnesses. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MPEG-DASH Multi-View Video and Audio Transmission QoE Over HTTP/2 Stream

MPEG-DASH Multi-View Video and Audio Transmission QoE Over H...

引用

2024 International Conference on Advanced Technologies for Communications, ATC 2024

作者： Wakayama, Yamato Nunome, Toshiro Graduate School of Engineering Nagoya Institute of Technology Computer Science Program Department of Engineering Nagoya466-8555 Japan

ISBN: (纸本)9798350353983

In this paper, we consider multi-view video and audio streaming using MPEG-DASH, which enables to transmit video tailored to the network conditions over HTTP communication. This paper uses HTTP/2 instead of HTTP/1.1, which the authors previously used. HTTP/2 manages a series of request-response exchanges called a stream, which is assigned a unique stream ID. We perform a subjective experiment under various network conditions to evaluate application-level QoS and QoE. From the evaluation results, we investigate the effect of the HTTP/2 stream on the video and audio quality of the users in the multi-view video transmission scenario. © 2024 IEEE.

关键词： Audio streaming

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Diabetic Retinopathy Using Pretrained Models: A Focus on Initial Stages 1

Early Detection of Diabetic Retinopathy Using Pretrained Mod...

引用

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Raza, Md Aasif Dua, Mohit Berwal, Krishan National Institute of Technology Kurukshetra Department of Computer Engineering Kurukshetra India Military College of Telecommunication Engineering Department of Communication Engineering Mhow India

ISBN: (纸本)9798350367720

Early detection of diabetic retinopathy is crucial because this disease currently has no cure. Identifying the condition at an early stage can significantly help in halting its progression and preventing severe vision loss. Numerous studies have focused on the detection and classification of diabetic retinopathy using various machine learning and deep learning techniques. In this work, we aim to detect the disease in its initial stages using a pre-trained VGG16 model, which is proved to be efficient in many image recognition tasks by recent researchers. Our initial approach achieved an accuracy of 79%, indicating a promising potential for early detection. To further improve the detection accuracy, we incorporated Ben Graham's preprocessing method, which enhances the finer details of the retinal images. This enhancement led to a 5% increase in accuracy, resulting in a final accuracy of 84.40%. These results underscore the effectiveness of advanced preprocessing techniques combined with deep learning models in the early detection of diabetic retinopathy. © 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

Custom ANN: An Approach for Efficient Modulation Classification

Custom ANN: An Approach for Efficient Modulation Classificat...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Kumar, Varun Gupta, Deepika Indian Institute of Information Technology Vadodara Department of Computer Science and Engineering International Campus Diu India

ISBN: (纸本)9798350350821

Modulation is a fundamental technique for transmitting signals between a transmitter and receiver in wired and wireless scenarios. In a non-cooperative communication scenario, the receiver should be capable of classifying the modulation type efficiently. Automatic Modulation Classification (AMC) is designed to monitor the radio-frequency spectrum and for making effective transmission decisions. Earlier AMC methods relied on feature extraction and likelihood-based approaches. However, with the rise of Deep Learning (DL), AMC has gained momentum due to its superior predictive capabilities. In this work, we propose a custom artificial neural network (ANN) for modulation classification. We analyze the impact of a deep learning model on AMC and how different modulation techniques influence its accuracy. © 2024 IEEE.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

Recognition of Deep Fake Voice Acoustic using Ensemble Bagging Model 5

Recognition of Deep Fake Voice Acoustic using Ensemble Baggi...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Basha, Shaik Abdul Yunus Priya, K.Ulaga Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350379945

As artificial speech generates technological evolution;fake voice information has become an increasingly prevalent avenue for fraud. Numerous investigations have been carried out into machine learning techniques, signal processing techniques, and the Automatic Speaker Verification System to address such issues. Since there are increasing methods to create fake information, techniques must be developed to determine when audio recordings employed as electronic proof are corrupted. Such recordings contain the potential to be manipulated. Hence, this research work identified the data regarding audio systems as either fake or real by i) extracting features from audio file metadata using oversampling techniques and ii) Developing an Ensemble Bagging Model appropriate for analyzing input audio signal followed by classification of fake (fraudulent) and real (authentic) audio. Our experimental results reveal that the ensemble bagging model attained an accuracy of 99.5%, precision of 99%, 99.6% recall, and 99.9% Fl-measure in the prediction of the audio system compared with traditional approaches. © 2024 IEEE.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

Optimized Biometric Key Management System for Enhanced Security 11th

Optimized Biometric Key Management System for Enhanced Secu...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Kaur, Prabhjot Kumar, Nitin School of Computing DIT University Uttarakhand India Department of Computer Science and Engineering National Institute of Technology Uttarakhand India Department of Computer Science and Engineering PEC Deemed to be University Chandigarh India

ISBN: (纸本)9789819717231

Biometric cryptosystems are security tools that use an individual’s distinctive physical or behavioral characteristics to secure sensitive data. Any biometric cryptosystem’s effectiveness is dependent on how well the features are extracted. The suggested solution uses an evolutionary algorithm to first optimize the retrieved attributes. Second, fuzzy vault is used to safeguard these optimized features. The fuzzy vault system is a well-known biometric cryptography device that creates a vault by using a polynomial equation, protecting the biometric information. However, if an attacker has access to the polynomial equation, the security of the fuzzy vault scheme may be jeopardized. The shuffled frog leaping algorithm (SFLA) method has been suggested as a way to improve the security of the fuzzy vault technique in order to overcome this drawback. The SFLA is a meta-heuristic optimization method that resolves challenging optimization issues by simulating the social behavior of frogs. This meta-heuristic technique is used in this paper’s suggested strategy to produce and secure optimized points. The experiments are performed onn AMI and MMU2 databases. The results achieve higher levels of performance compared to the traditional schemes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

TuringQ: Benchmarking AI Comprehension in Theory of Computation

TuringQ: Benchmarking AI Comprehension in Theory of Computat...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zahraei, Pardis Sadat Asgari, Ehsaneddin Computer Engineering Department Sharif University of Technology Iran Qatar Computing Research Institute - QCRI Qatar

ISBN: (纸本)9798891761681

We present TuringQ, the first benchmark designed to evaluate the reasoning capabilities of large language models (LLMs) in the theory of computation. TuringQ consists of 4,006 undergraduate and graduate-level question-answer pairs, categorized into four difficulty levels and covering seven core theoretical areas. We evaluate several open-source LLMs, as well as GPT-4, using Chain of Thought prompting and expert human assessment. Additionally, we propose an automated LLM-based evaluation system that demonstrates competitive accuracy when compared to human evaluation. Fine-tuning a Llama3-8B model on TuringQ shows measurable improvements in reasoning ability and out-of-domain tasks such as algebra. TuringQ serves as both a benchmark and a resource for enhancing LLM performance in complex computational reasoning tasks. Our analysis offers insights into LLM capabilities and advances in AI comprehension of theoretical computer science. © 2024 Association for Computational Linguistics.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Comparison between experimental and numerical results for piezoelectric signals generated in water-saturated cancellous bone by ultrasound irradiation

Comparison between experimental and numerical results for pi...

引用

2023 International Congress on Ultrasonics, ICU Beijing 2023

作者： Hosokawa, A. Department of Electrical and Computer Engineering National Institute of Technology Akashi College Akashi674-8501 Japan

The bone formation is considered to be accompanied by the piezoelectric effects in bone. Therefore, the piezoelectric effect under ultrasound irradiation should be elucidated to realize the effective healing. Then, the piezoelectric properties in cancellous bone have been attempted to clarify by complementing experiments and simulations with each other. In this paper, the piezoelectric signals generated in water-saturated cancellous bone by ultrasound irradiation were experimentally and numerically observed, and the effect of the trabecular orientation was investigated. The experimental observation was performed by the piezoelectric cell (PE-cell), which corresponds to an ultrasound receiver using the cancellous bone specimen as a piezoelectric element. The numerical observation was performed by the piezoelectric finite-difference time-domain (PE-FDTD) method, which is an elastic FDTD method with piezoelectric constitutive equations. In both the experimental and simulated results, the piezoelectric signal amplitude increased with the mean intercept lengths (MILs) of the trabecular elements and the pore spaces or the strength of the trabecular orientation. From the fact that the ultrasound propagation in water-saturated cancellous bone can depend on the trabecular orientation, it was considered that the ultrasound properties could be largely associated with the piezoelectric properties. © 2024 institute of Physics Publishing. All rights reserved.

关键词： Piezoelectricity

来源：评论

学校读者我要写书评

暂无评论

Facial recognition using grey wolf optimization

引用

Materials Today: Proceedings 2022年 58卷 273-285页

作者： Barman, Bhaswati Dewang, Rupesh Kumar Mewada, Arvind Computer Science and Engineering Department Motilal Nehru Institute of Technology Allahabad Prayagraj India

Nowadays, multimedia data on social media platforms of the Internet, especially images, are proliferating, due to which image retrieval systems based on content are one of the major research areas. Despite the introduction of various content-based images retrieval approaches, face recognition remains a problematic task. Consequently, this paper developed a face recognition framework using modifying the bag-of-features (BOF) from a grey wolf optimisation (GWO) algorithm in which a variable weight is used. Variable weight proposes a sine cos function to find the best score. The convergence behaviour of the variable weight GWO algorithm is performed over some benchmark functions. Furthermore, it has been used to get the histograms fed into training and testing function to get the model accuracy using the Yale face database. © 2022

关键词： Face recognition

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：