检索结果-内蒙古大学图书馆

30th IEEE International Conference on Telecommunications, ICT 2024

作者： Al-Khateeb, Shahed N Yarmouk University Faculty of Information Technology Computer Science Dept Irbid Jordan

ISBN: (纸本)9798350356694

Plant diseases pose a hazard to world food security. According to data from the Jordanian department of Statistics, the olive crop was Jordan's greatest agricultural crop in terms of planted area and quantity produced in 2022. This study intends to use deep learning and machine learning approaches to identify olive crop illnesses. Image data was acquired from several sources and integrated into a single dataset. The data was split among 70% training and 30% testing. Deep learning SqueezeNet methods were used to extract features. Data training was conducted using both Artificial Neural Networks and Support Vector Machines models. In terms of accuracy, the Artificial Neural Network provided 92.9%, surpassing the Support Vector Machines model score of 85.5%. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Thailand Food Price Forecasting: Comparative Analysis of Machine Learning Models 6

Thailand Food Price Forecasting: Comparative Analysis of Mac...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Watthananon, Julaluk Thongrak, Prapas Thwe, Yamin Saekhow, Navarat Computer Science Department Faculty of Science and Technology RMUTT Pathum Thani Thailand

ISBN: (纸本)9798331539603

This study aims to address food price fraud and predict pricing trends for key commodities—Cassava flour, Maize, Meat (chicken), and Rice—in Thailand, using advanced machine learning techniques to enhance forecasting accuracy and detect anomalies. We utilized historical food price data from 2000 to 2020 and incorporated USD exchange rate fluctuations to build and evaluate several regression models, including Linear Regression, Decision Tree Regressor, Random Forest Regressor, Gradient Boosting Regressor, and Support Vector Regressor. The Decision Tree and Random Forest models demonstrated superior performance with the lowest mean squared error (MSE) and root mean squared error (RMSE), effectively capturing price trends and fluctuations. In contrast, Linear Regression and Support Vector Regressor showed higher errors and less effectiveness in handling nonlinear patterns. This study highlights the efficacy of machine learning in improving price prediction accuracy and detecting potential fraud, offering a robust framework for analyzing commodity pricing dynamics. The findings provide actionable insights for policymakers and stakeholders to implement proactive strategies, promoting greater market stability and fairness in Thailand's agricultural sector. © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

MLIDS22- IDS Design by Applying Hybrid CNN-LSTM Model on Mixed-Datasets

引用

Informatica (Slovenia) 2022年第8期46卷 121-134页

作者： Abdulmajeed, Inam Abdullah Husien, Idress Mohammed Department of Computer Science College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq

The intrusion detection system (IDS) is an essential part of cyber security which captures and investigates traffic to distinguish between legitimate and malicious activities and determines the type of attack. The selection of the dataset used in training the machine learning-based IDS is crucial in ensuring that IDS performs accurately in cyber-attack classification. When utilizing multiple datasets in the training process, the metrics will relate numerically between the ML algorithm and a particular dataset. Previous research concluded a major decline in metrics when using inter-datasets evaluation. This research thoroughly investigates the use of the most modern and comprehensive IDS datasets, CIC-IDS2017 and CSE-CIC-IDS2018, to design and evaluate machine learning-based IDS systems using hybrid CNN-LSTM architecture. The new approach followed is to generate a new dataset which is the output of mixing both datasets. The experimental testing showed superior metrics values yielded when training with the mixture dataset against the use of individual datasets, especially when performing the inter-datasets evaluation, which overcomes the generalization problem. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Data Aggregation Approach to Enhance Energy-Efficient Routing Protocol for HWSNs

引用

Informatica (Slovenia) 2022年第7期46卷 47-54页

作者： Alhijaj, Asaad A. Qader Khudor, Baida'a Abdul Alshawi, Imad S. Department of Computer Science College of Computer Science and Information Technology University of Basrah Basrah Iraq

The sensor nodes' computing capability, communication capabilities, and power supply are severely constrained in WSNs, making sensor battery replacement or recharging difficult or even impossible. Therefore, energy is an important challenge to consider while creating WSNs. In hazardous circumstances, accurate data aggregation and routing are crucial, and the energy consumption of sensors must be closely controlled. Due to environmental conditions and short-distance sensors, however, there is a high possibility of duplicating data. Large datasets include a range of data, some of which are helpful while others are entirely unnecessary. This redundancy reduces performance in terms of redundant transmission and computation expense. Data aggregation, on the other hand, may reduce duplicate data in a network, hence reducing the volume of data sent and increasing the network's lifespan. In this context, two novel energy-conscious approaches called Fuzzy Data Aggregation with Spider monkey optimization (FDA-SMORP) for data aggregation in the cluster head and routing to the sink are presented. These strategies attempt to offset the energy consumption among all nodes in a wireless network such that these nodes exhaust all of their energy and die almost simultaneously. To demonstrate the efficacy of the suggested approaches in terms of minimizing delay caused by route planning, balancing energy usage, and extending network lifetime, the proposed methods are compared to some of the most well-known WSN systems. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Remote Inter-beat Interval Estimation: A Signal Reconstruction Approach with Multi-channel Input and Channel-Wise Attention Mechanism

Remote Inter-beat Interval Estimation: A Signal Reconstructi...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Wang, Shengze Bouazizi, Mondher Ohtsuki, Tomoaki Graduate School of Science and Technology Keio University Yokohama Japan Department of Information and Computer Science Faculty of Science and Technology Keio University Yokohama Japan

ISBN: (纸本)9798350350548

This paper presents a radar-based heart rate monitoring and Inter-beat interval (IBI) estimation. Traditional IBI estimation relies on peak detection combined with signal processing techniques. Our approach uses signal reconstruction with a neural network, which significantly improves the accuracy and robustness of IBI estimation compared to conventional methods. By utilizing multi-channel input data, our approach effectively mitigates various sources of noise and interference, resulting in highly accurate and reliable IBI predictions. Instead of relying solely on peak detection, we use the U-net architecture and cross-channel attention mechanism to reconstruct the triangular waveform generated from the ground truth ECG signals. The incorporation of multi-channel input and channel-wise attention mechanism improves our model’s ability to discriminate and emphasize critical features from different input channels, further improving IBI estimation accuracy. To evaluate the accuracy and robustness of our proposed method, we trained our model on the open-source dataset [1], and then performed leave-one-subject-out validation, which ensures our approach to be evaluated only on unseen independent subjects. We have achieved a Root Mean Square Error (RMSE) of 26.7 ms for the IBI of each heart-beat. Our results demonstrate the transformative potential of adopting signal reconstruction methods supported by state-of-the-art deep learning techniques. This shift in perspective promises more accurate and robust heart rate and IBI estimation, opening new avenues for improving the accuracy and reliability of cardiac monitoring systems. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Reduction of Microarray Data Dimensions to Enhance Performance of Naïve Bayes in Classification 4

Reduction of Microarray Data Dimensions to Enhance Performan...

引用

4th International Conference of science and information technology in Smart Administration, ICSINTESA 2024

作者： Ramadhani, Putri Tsatsabila Nababan, Erna Budhiarti Efendi, Syahril Universitas Sumatera Utara Faculty of Computer Science and Information Technology Medan Indonesia

ISBN: (纸本)9798350376111

According to data Global Burden of Cancer Survey (Globocan) by World Health Organization (WHO) in 2018 there were 18.1 million new cases with a death rate of 9.6 million deaths, where 1 in 8 men and 1 in 11 women died of cancer. The death rate could be prevented with a comprehensive management system that starts with early detection, prevention, and treatment [2]. In the study of microarray data for cancer early detection, the properties of high-dimensional data, small sample sizes, and noise, must be treated seriously because they can affect the classifier's performance. This is critical for dealing with the curse of dimensionality and the inability to identify important information hidden in microarray data. Therefore, we propose PCA method for dimensionality reduction of microarray data to support Naive Bayes algorithm to complish classification tasks. Based on the studies we conducted, we discovered an increases of performance classification where the accuracy achieved is 9 2. 1 1%, precision 9 0. 2 0% and the f 1-score is 9 3. 8 8% for ovarian cancer and prostate cancer had the accuracy is 93.55%, precision and f 1 - score reached 9 2. 8 6%. © 2024 IEEE.

关键词： classification data science machine learning reduction dimension

来源：评论

学校读者我要写书评

暂无评论

Generating synthetic mixed-type tabular data by decoding samples from a latent-space: a case study in healthcare 28th

Generating synthetic mixed-type tabular data by decoding sam...

引用

28th International Conference on Knowledge Based and Intelligent information and Engineering Systems, KES 2024

作者： Drapala, Jaroslaw Swiatek, Jerzy Department of Computer Science and Systems Engineering Faculty of Information and Communication Technology Wroclaw University of Science and Technology Wroclaw50-370 Poland

Medical data are subject to privacy regulations, which severely limit AI specialists who wish to construct decision support systems for medicine. Large amounts of this data are tabular, indicating that they are organized into a table format, where patient records are represented in rows and measured variables in columns. Furthermore, the variables come in different types-some are numerical, while others are categorical. In this work, we introduce a novel method for constructing generators of synthetic tabular data with mixed types. The key point of our approach is the explicit utilization of a latent space to represent the original data. A case study using real medical data is presented. © 2024 The Authors.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

High-Dimensional Data Integration Model to Improve the Plants Quality

High-Dimensional Data Integration Model to Improve the Plant...

引用

2024 International Conference on Control and Automation, Electronics, Robotics, Internet of Things, and Artificial Intelligence, CERIA 2024

作者： Hasibuan, Nelly Astuti Sihombing, Poltak Nababan, Erna Budhiarti Amalia Universitas Sumatera Utara Faculty of Computer Science and Information Technology Medan Indonesia

ISBN: (纸本)9798331511166

High Dimensional Data is data that has many dimensions or features with the aim of providing more complete and detailed information about an object or phenomenon. Plant images are objects that have data with many dimensions or features. Plant images can be analyzed to determine plant quality. For example, coffee plant images can be analyzed to determine the quality of coffee plants. Determination of coffee plant quality in previous studies only used one object such as leaves or stems and or fruit. In this study, the quality of coffee plants is measured using leaves, stems, fruit, and hypotheses from coffee plant experts. Analysis of coffee plant images can produce information in the form of size, color and health of plants. This information can be found by extracting image features. However, the large number of features is an obstacle in grouping. Clustering techniques are used to group the large amount of data in the dataset. Expert hypotheses will be used to validate the dataset, determine centroid values and determine weight values to determine plant quality. The obstacle in analyzing multidimensional data is the difficulty of visualizing the number of variables because the available methods generally only process low-dimensional data. The purpose of this study is to produce an integration model for analyzing plant quality datasets by optimizing machine learning to group high-dimensional data. © 2024 IEEE.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

Improved Salsa20 Stream Cipher Diffusion Based on Random Chaotic Maps

引用

Informatica (Slovenia) 2022年第7期46卷 95-102页

作者： Muhalhal, Lamia A. Alshawi, Imad S. Department of Computer Science College of Computer Science and Information Technology University of Basrah Basrah Iraq

To enhance stream ciphers, numerous studies have concentrated on the randomness, unpredictable nature, and complexity of keystream. Numerous stream algorithms have been put forth. Most of them require a significant amount of computational power. Salsa20 is a high-performance stream encryption solution that works on computers with fewer resources and uses a secure method that is faster than AES. They suggest Salsa20 for encryption in common cryptographic applications. Users who value speed over certainty should utilize the Salsa20 family of reduced-round ciphers, such as the (8,12) round cipher. It uses a 256-bit key and a hash algorithm. A successful fusion makes use of both the Salsa20 algorithm's and the random maps' advantages to improve the Salsa20 algorithm's shortcomings by increasing its unpredictability. Particularly now that Salsa20/7 has been hacked and Salsa20/12 is no longer as secure as it previously was. As a result, Salsa20 needs to achieve a high level of diffusion to withstand known attacks. Right now, salsa20 and its shortened versions rank among the fastest ciphers. This study presents a novel lightweight approach to construct a strong keystream that is sufficiently random to avoid being predicted by adversaries, achieve good diffusion, and withstand known assaults. A NIST test found that the performance of the (Salsa20-chaotic maps) approach in terms of data integrity and secrecy is nearly 0.3131 higher than that of the Salsa20. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Spatial Recognition of Citrus Trees, Seedlings, and Gaps: A Deep Learning and Geometric Approach on Satellite-Based RGB Imagery

Spatial Recognition of Citrus Trees, Seedlings, and Gaps: A ...

引用

2024 International Conference on Horizons of information technology and Engineering, HITE 2024

作者： Hussain, Muhammad Hamza Atif Mehdi, Syed Atif, Kanwal University of Central Punjab Faculty of Information Technology and Computer Science Lahore Pakistan

ISBN: (纸本)9798331516055

Global food deprivation is one of the key concerns in recent years leading to the development of several techniques to increase food production. A decisive factor in increasing the overall food production is the optimum use of agricultural land. When planting orchards, proper planning and monitoring is required. Failure to do so can lead to tree gaps or blank spots in the plantation either due to the planting irregularity, or natural reasons like weather, pests, and diseases. Research work has been done on the monitoring of trees and crops using remotely sensed data, but we find limited work on finding gaps in agricultural plantations such as fruit orchards. Contributing to this, we have proposed a deep-learning-based approach that uses satellite data to detect individual tree gaps in citrus orchards in Pakistan. Very High-resolution (VHR) satellite images were collected using the Google Earth application. A custom-trained convolutional neural network is applied to the images. A specialized algorithm based on geometric information computes the location and count of individual trees, seedlings, and tree gaps in the given satellite image. Our proposed technique can detect trees with an F-score of 0.997, seedlings with an F-score of 0.964, and tree gaps with an F-score of 0.951. © 2024 IEEE.

关键词： Satellite imagery

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：