检索结果-内蒙古大学图书馆

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 121-133页

作者： Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Birla Institute of Technology and Science Department of Computer Science and Information Systems Pilani333031 India University of Hradec Kralove Center for Basic and Applied Science Faculty of Informatics and Management Hradec Kralove50003 Czech Republic Skoda Auto University Mlada Boleslav29301 Czech Republic Universiti Teknologi Malaysia Malaysia Japan International Institute of Technology Kuala Lumpur81310 Malaysia Jadavpur University Department of Computer Science and Engineering Kolkata700032 India

Deep convolutional neural networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and analyzing region-based partial feature descriptors. Also, computationally expensive ensemble learning schemes fusing multiple CNNs have been studied in earlier works. This work proposes a region attention scheme for modeling long-range dependencies by building a correlation among different regions within an input image. The attention method enhances feature representation by learning the usefulness of context information from complementary regions. Spatial pyramidal pooling and average pooling pairs aggregate partial descriptors into a holistic representation. Both pooling methods establish spatial and channelwise relationships without incurring extra parameters. A context gating scheme is applied to refine the descriptiveness of weighted attentional features, which is relevant for classification. The proposed region attention network for food items and agricultural stress recognition method, dubbed RAFA-Net, has been experimented on three public food datasets, and has achieved state-of-the-art performances with distinct margins. The highest top-1 accuracy of RAFA-Net is 91.69%, 91.56%, and 96.97% on the UECFood-100, UECFood-256, and MAFood-121 datasets, respectively. In addition, better accuracies have been achieved on two benchmark agricultural stress datasets. The best top-1 accuracies on the Insect Pest (IP-102) and PlantDoc-27 plant disease datasets are 92.36%, and 85.54%, respectively;implying RAFA-Net's generalization capability. © 2023 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

GPU Acceleration of the Enhanced Jaya Optimization Algorithm for Solving Large Systems of Nonlinear Equations 4th

GPU Acceleration of the Enhanced Jaya Optimization Algorit...

引用

4th International Conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

作者： Silva, Bruno Guerreiro Lopes, Luiz Doctoral Program in Informatics Engineering University of Madeira Madeira Island Funchal Portugal Regional Secretariat for Education Science and Technology Regional Government of Madeira Funchal Portugal Faculty of Exact Sciences and Engineering University of Madeira Madeira Island Funchal9020-105 Portugal

ISBN: (纸本)9783031812408

This paper presents a GPU-based parallel implementation of the Enhanced Jaya (EJAYA) algorithm for solving large-scale systems of nonlinear equations. EJAYA is a gradient-free metaheuristic optimization scheme based on the population-based parameter-less Jaya algorithm that has recently been shown to be capable of solving nonlinear equation systems, a class of challenging problems that are difficult to solve by traditional approaches, particularly as systems become larger. The proposed parallel algorithm was implemented using the Julia programming language on a high-performance GeForce RTX 3090 GPU with 10 496 CUDA cores and 24 GB GDDR6X VRAM and was tested using a set of difficult scalable nonlinear equation system problems. The obtained results, with average speedups up to 122.25x, evidenced the capability of the proposed GPU-based parallel algorithm to meet the computational demands of the important class of problems under consideration. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Generalization Evaluation of Seq2seq based Fog Computing Application Placement Algorithm on Limited Dataset 3

Generalization Evaluation of Seq2seq based Fog Computing App...

引用

3rd International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2023

作者： Pakpahan, Michael S. M. Nugroho, Lukito Edi Widyawan, Widyawan Wardhana, Ajie Kusuma Muhammad Ardian, R.A. Astagenta, Rangga Satria Universitas Gadjah Mada Dept. of Electrical and Information Engineering Yogyakarta Indonesia Universitas Amikom Yogyakarta Faculty of Computer Science Dept. Informatics Yogyakarta Indonesia

ISBN: (纸本)9798350394559

Addressing its growing number and vital role, decentralization of cloud computing becoming a necessity. Fog computing aims to bring application closer to the data source-typically at the network's edge by leveraging local resources to provide faster data processing and decision-making. Fog computing then has to place application strategically to use its limited fog resource to improve application performance metrics. This problem known as Fog Application Placement Problem (FAPP) has been approached using previous methods that rely on rules and prior knowledge that may not be adaptive, but rather being overly specialized to specific problems. Deep learning with its learning mechanism, can offer more adaptable and dynamic solutions for a wide range of scenarios, especially in fog network that continuously evolve. This research investigate Seq2seq placement model inherent limitations, notably the impracticality of generating every possible pattern from all potential request configurations. We aim to address and answer the following critical questions: 1) How does the model's performance vary when confronted with unseen requests or an augmented number of modules, especially considering the limitations in training data?;2) Can the seq2seq model, even with its training limitations, adhere to the heuristic rules of the dataset when dealing with unfamiliar problems? This research shows that in similar availability, there is a reduction of almost half of the response time with 183.03 ms, 2.93 number of hops, and 0.87 megabyte of transmitted messages against the hop3 algorithm. Moreover, we highlight the ability of seq2seq model to follow heuristic rules in unseen scenarios. © 2023 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Estimating Chlorophyll Content from Hyperspectral Data Using Gradient Features 23rd

Estimating Chlorophyll Content from Hyperspectral Data Usin...

引用

23rd International Conference on Computational science, ICCS 2023

作者： Ruszczak, Bogdan Wijata, Agata M. Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Opole Poland Faculty of Biomedical Engineering Silesian University of Technology Zabrze Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Gliwice Poland KP Labs Gliwice Poland

ISBN: (纸本)9783031360206

Non-invasive estimation of chlorophyll content in plants plays an important role in precision agriculture. This task may be tackled using hyperspectral imaging that acquires numerous narrow bands of the electromagnetic spectrum, which may reflect subtle features of the plant, and inherently offers spatial scalability. Such imagery is, however, high-dimensional, therefore it is challenging to transfer from the imaging device, store and investigate. We propose a machine learning pipeline for estimating chlorophyll content from hyperspectral data. It benefits from the Savitzky-Golay filtering to smooth the (potentially noisy) spectral curves, and from gradient-based features extracted from such a smoothed signal. The experiments revealed that our approach significantly outperforms the state of the art according to the widely-established estimation quality metrics obtained for four chlorophyll-related parameters. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Word vs. Character Embedding for Machine Learning Based Detection of Malicious URLs and DGA-Generated Domains 15

Comparative Analysis of Word vs. Character Embedding for Mac...

引用

15th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2023

作者： Ayodele, Oludayo C. Yerima, Suleiman Y. School of Computer Science and Informatics De Montfort University Leicester United Kingdom British University in Dubai Faculty of Engineering and Information Technology Dubai United Arab Emirates

ISBN: (纸本)9798350324433

This study presents a comprehensive comparative analysis of the effectiveness of word-level and character-level embeddings in the context of machine learning-based detection of malicious URLs and DGA-generated domains. Utilizing distinct datasets comprising DGA-generated domains and Spam URLs, we systematically evaluate various machine learning models coupled with word-level and character-level tokenization techniques. Our findings indicate that character-level tokenization yields superior results in identifying DGA-generated domains, particularly due to the random character composition of these URLs. Conversely, both word-level and character-level embeddings exhibit comparable success rates in classifying Spam URLs, owing to the non-random nature of their URL structures. The study sheds light on the importance of tailoring tokenization strategies based on the unique characteristics of the data. We recommend character-level embeddings for detecting DGA-generated domains characterized by random characters. In contrast, the choice between word-level and character-level embeddings is less critical when dealing with Spam URLs, as both approaches yield effective results. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled LoRa Wireless Sensor Network for Real-Time Air Quality Monitoring with Geographic Information System Mapping

IoT-Enabled LoRa Wireless Sensor Network for Real-Time Air Q...

引用

2023 International Conference on informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Maulana, Nurhuda Matheus Edward, Ian Joseph Universitas Pembangunan Nasional Veteran Jakarta Faculty of Computer Science Jakarta12450 Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung40132 Indonesia

ISBN: (纸本)9798350307306

The Internet of Things (IoT) can potentially change how humans interact with the environment. This technology is able to be applied in various fields, such as urban management, agriculture, environmental monitoring, health, and transportation. Conventional air quality monitoring systems are complex sensing equipment and they can measure various parameters of air pollutants. This system requires very high costs and maintenance. Therefore, a low-cost air quality measurement system is required and is able to measure the surrounding air pollutants. By using wireless sensor network technology as the acquisition of environmental monitoring sensor data. A system design was created in the form of geographic information capable of describing air quality in a particular area. The air parameters used are carbon monoxide, dust particulate, light intensity, temperature, and relative humidity. The wireless network uses the LoRa module connected to the gateway. The web server provides a database and geographic information system interface from the gateway through the MQTT broker. Data transmission using a radio frequency of 915 Mhz and able to send data sensors from various points. Outdoor testing at many buildings is capable of transmitting sensor data with a packet loss of 0% at a distance of fewer than 111 meters and the largest packet loss of 51.28% at a distance of 442 meters. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML-Based Methods for Malware Classification

引用

computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait Mohammad Alshinwan Sahar A.El-Rahman Didi Rosiyadi Diaa Salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine Learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAS malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering

来源：评论

学校读者我要写书评

暂无评论

An Improved Modified Jaya Optimization Algorithm: Application to the Solution of Nonlinear Equation Systems 4th

An Improved Modified Jaya Optimization Algorithm: Applicatio...

引用

4th International Conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

ISBN: (纸本)9783031812408

Population-based metaheuristic algorithms have been used to solve challenging optimization problems, and numerous modifications to make these algorithms more efficient have been proposed. Jaya is one of these algorithms that has been modified and utilized to solve many hard optimization problems. One such modification to the original algorithm is the Modified Jaya (MJAYA) algorithm, which, like Jaya, uses information about the best and worst candidate solutions to determine the population’s search direction, thereby limiting and focusing the search. Recent research has demonstrated that the MJAYA algorithm is not effective at solving systems of nonlinear equations transformed into equivalent nonlinear optimization problems. Systems of nonlinear equations are probably the most difficult class of numerical mathematics problems to solve, which justifies the use of metaheuristic approaches in their resolution. This paper proposes a new population-based optimization algorithm, the Improved Modified Jaya (IM-Jaya) algorithm, which, despite being a generic metaheuristic optimization algorithm, is here used to solve systems of nonlinear equations. The proposed algorithm strikes a better balance between global exploration and local exploitation, allowing for a broader and more exhaustive exploration of the search space as well as a more efficient local search in its most promising regions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Bi-Directional LSTM And Transfer Learning in Correcting Typing Errors on Twitter Social Media Posts 11

Comparison Between Bi-Directional LSTM And Transfer Learning...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Lubis, Arif Ridho Prayudani, Santi Hamzah, Muhammad Luthfi Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia Universitas Islam Negeri Sultan Syarif Kasim Riau Faculty of Science and Technology Pekanbaru Indonesia

ISBN: (纸本)9798350305968

Typing errors are a behavior that often occurs in communication via short messages or posts on social media platforms. In communicating on social media, many individuals without realizing it often make typing errors that can affect the meaning of sentences. This research will apply a model that can check typing errors using Bi-Directional LSTM and transfer learning which results in the Bi-Directional LSTM model achieving an accuracy of 78% after being trained for 20 epochs with a batch size of 64. On the other hand, the transfer learning model achieves an accuracy of 80% with the same epoch and batch size settings. Furthermore, when the Bi-Directional LSTM model was set with 20 epochs and batch size 64, the accuracy increased to 83%, while the transfer learning model achieved 87% accuracy. Finally, with 20 epochs and a batch size of 64, the Bi-Directional LSTM model achieved 87% accuracy, while the transfer learning model achieved an impressive accuracy of 93%. © 2023 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Change Management in Preparing Indonesian Team to IOI 35

Change Management in Preparing Indonesian Team to IOI

引用

35th International Olympiad in informatics, IOI 2023

作者： Jingga, Felix Isal, Yugo K. Cendranata, Andreas Liem, Inggriani Mulyanto, Adi Indonesia Faculty of Computer Science University of Indonesia Indonesia Bebras Indonesia National Board Organization Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Indonesia

Indonesia has been participating at the International Olympiad in informatics (IOI) since 1995. The process of selecting the four contestants remains unchanged. All medalists in the national level competition were invited to take a series of training camps to select competitively the candidates. In the first two decades of participation in IOI, Indonesia have collected two gold medals, and these surprising achievements were merely more because of luck, and not as a result of a reliable training/selection process. We believe reliable and good training is a basis to predict and expect a stable achievement. Through careful observations and reflections, a change of course of action is needed to bring Indonesia’s achievement to the next level. This paper shares Indonesia’s experience in changing and implementing strategies during the national training camps to better prepare the four contestants to IOI. What are the changes taken by the coaching team that have been exercised that made it possible for Indonesia to achieve three gold in the last four consecutive years? © 2023 IOI, Vilnius University.

关键词： Human resource management

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：