检索结果-内蒙古大学图书馆

Improving Plant Disease Classification With Deep-Learning-Based Prediction Model Using Explainable Artificial Intelligence

引用

IEEE ACCESS 2024年 12卷 100005-100014页

作者： Nigar, Natasha Faisal, Hafiz Muhammad Umer, Muhammad Oki, Olukayode Manappattukunnel Lukose, Jose Univ Engn & Technol Dept Comp Sci RCET Lahore 54000 Pakistan Tech Univ Munich Sch Engn & Design D-80333 Munich Germany TEKHQS INC Irvine CA 92620 USA Walter Sisulu Univ Dept Informat Technol ZA-5117 Mthatha South Africa

Plant diseases can have profound effects on the economy, impacting both local and global scales. These diseases can lead to substantial losses in agricultural productivity, affecting crop yields and quality. In this context, deep learning algorithms are widely acknowledged as effective solutions. However, the use of these black-box approaches raises concerns about trust in interpreting and validating the decisions generated by the models. This study proposes an explainable artificial intelligence (XAI) based plant disease classification system to classify and identify distinct ailments with improved accuracy. The system correctly identifies 38 different plant diseases with accuracy, precision, and recall as 99.69%, 98.27%, and 98.26%, respectively. These predictions are subjected to additional analysis employing the local interpretable model-agnostic explanations (LIME) framework to produce visual explanations aligning with prior beliefs and adhering to established best practices in explanations. This system will serve as a promising avenue for revolutionizing disease detection, fostering informed decision-making, and ultimately contributing to global food security.

关键词： Accuracy Plant diseases Feature extraction Solid modeling Computational modeling Predictive models Explainable AI detection algorithms Plant disease detection deep learning explainable artificial intelligence prediction model prediction model

来源：评论

学校读者我要写书评

暂无评论

AdamW plus : Machine Learning Framework to Detect Domain Generation algorithms for Malware

引用

IEEE ACCESS 2024年 12卷 79138-79150页

作者： Javed, Awais Rashid, Imran Tahir, Shahzaib Saeed, Saqib Almuhaideb, Abdullah M. Alissa, Khalid Natl Univ Sci & Technol NUST Coll Signals Islamabad 44000 Pakistan Imam Abdulrahman Bin Faisal Univ Coll Comp Sci & Informat Technol Saudi Aramco Cybersecur Chair Dept Comp Informat Syst Dammam 31441 Saudi Arabia Imam Abdulrahman Bin Faisal Univ Coll Comp Sci & Informat Technol Saudi Aramco Cybersecur Chair Dept Networks & Commun Dammam 31441 Saudi Arabia

Advanced Persistent Threats commonly use Domain Generation algorithms to evade advanced detection methods to establish communication with their command and control servers. To overcome the DNS protocol legitimacy breach, several Domain Generation algorithms detection methods have been proposed. To solve the problem of DGA malware detection amicably, Deep Learning based detection schemes attracted researchers' interest recently. However, Deep Learning has already achieved optimal results and the gap is identified as fine-tuning of Deep Learning model hyper-parameters. The proposed solution is focusing on a model specific hyper-parameter known as the gradient optimizer. Gradient Optimisers are broadly categorised into Stochastic Gradient and Adaptive Moment based Gradient. Moment-based Gradient optimizer approaches are identified with suffering from weight decay and leading to poor generalization. Adaptive Moment (Adam) has improved with weight Decay as AdamW. To optimise moment-based gradient optimizers, Adam and AdamW are analyzed deeply. To optimize the functioning of AdamW, we present AdamW+, a novel solution for detecting DGA algorithms through re-implementing and nullifying the weight decay in AdamW. AdamW+ has been successfully implemented and shown promising results compared to Adam and AdamW optimizers in practice. AdamW+ preserved the properties of Adaptive Optimizer Adam while simplifying the weight decay implementation of AdamW. Empirical analysis has proved that AdamW+ has outperformed Adam and AdamW. The experimental result have substantiated that the proposed algorithm achieves the best accuracy result.

关键词： Deep learning Malware Long short term memory Servers Protocols Domain Name System Arithmetic Optimization methods Threat assessment detection algorithms Stochastic processes Command and control systems Deep learning optimizer LSTM Adam AdamW AdamW plus

来源：评论

学校读者我要写书评

暂无评论

Density-Peak-Based Overlapping Community detection Algorithm

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2022年第4期9卷 1211-1223页

作者： Sun, Liping Ye, Tao Sun, Jian Duan, Xiaoyu Luo, Yonglong Anhui Normal Univ Sch Comp & Informat Anhui Prov Key Lab Network & Informat Secur Wuhu 241003 Peoples R China Nanjing Univ Software Inst Nanjing 210023 Peoples R China

Overlapping community detection is essential for revealing the hidden structure of complex networks. In this work, we present an overlapping community detection algorithm that selects community centers adaptively based on density peaks. The proposed algorithm, called the density-peak-based overlapping community detection (DPOCD) algorithm, defines point link strength and edge link strength to construct distance matrix. Unlike the density peaks clustering algorithm, by which cluster centers are selected manually, the DPOCD algorithm uses the linear fitting method to select community centers. To evaluate the feasibility of the presented algorithm, we compared it with other advanced methods on artificial synthetic network and real complex network datasets. The experimental results demonstrate that our method achieves excellent performance in large-scale complex networks and the robustness of the algorithm.

关键词： Complex networks Clustering algorithms detection algorithms Sun Optimization Image edge detection Robustness Adaptive selection of cluster centers community detection algorithm density peak overlapping community

来源：评论

学校读者我要写书评

暂无评论

MMSRC: A Multidirection Multiscale Spectral-Spatial Residual Network for Hyperspectral Multiclass Change detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 9254-9265页

作者： Ge, Hongmei Tang, Yongsheng Bi, Zuolin Zhan, Tianming Xu, Yang Song, Aibo Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China Nanjing Audit Univ Sch Engn Audit Nanjing 211815 Peoples R China Nanjing Audit Univ Sch Informat Engn Nanjing 211815 Peoples R China Nanjing Audit Univ Jiangsu Key Construct Lab Audit Informat Engn Nanjing 211815 Peoples R China Nanjing Univ Sci & Technol Nanjing 210094 Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China

Recently, deep convolutional neural network (CNN) hyperspectral change detection methods have achieved significant improvement. However, most CNN hyperspectral change detection methods do not make full use of spectral-spatial feature information. In this article, we propose a novel multidirection and multiscale spectral-spatial residual network for hyperspectral multiclass change detection. Specifically, a multiscale structure and a multidirection mechanism are introduced to investigate feature variation of hyperspectral images and improve the accuracy of hyperspectral change detection. Experiments on multiple hyperspectral datasets show that the proposed method achieves improved performance in comparison with other advanced hyperspectral multiclass change detection methods.

关键词： Hyperspectral imaging Feature extraction Convolution Tensors detection algorithms Deep learning Residual neural networks Convolutional neural network (CNN) hyperspectral change detection multidirection multiscale

来源：评论

学校读者我要写书评

暂无评论

SAUNet3+CD: A Siamese-Attentive UNet3+for Change detection in Remote Sensing Images

引用

IEEE ACCESS 2022年 10卷 101434-101444页

作者： Mo, Junsang Seong, Seonkyeong Oh, Jaehong Choi, Jaewan Korea Res Inst Human Settlements Geospatially Enabled Soc Res Div Sejong 30147 South Korea Chungbuk Natl Univ Dept Civil Engn Cheongju 28644 South Korea Korea Maritime & Ocean Univ Dept Civil Engn Interdisciplinary Major Ocean Renewable Energy En Busan 49112 South Korea

With the development of various optical sensors, change detection is one of the most actively researched areas in remotely sensed imagery with high spatial resolution. In particular, deep learning-based change detection techniques are very important for use in various fields, such as land monitoring and disaster analysis, because they can show superior performance compared to traditional unsupervised and supervised change detection methods. This manuscript proposes a Siamese-attentive UNet3+ for change detection (SAUNet3+CD) of multitemporal imagery with high spatial resolution. The existing UNet3+ was modified to a Siamese-based architecture, and a spatial and channel attention module was added to detect various changed areas. The proposed model was trained to effectively detect building growth and decay through the data augmentation of open datasets and a hybrid loss function. In experiments using two open datasets, the proposed deep learning model effectively detected changed areas in multitemporal images better than various methods, such as existing Siamese-based networks and a network for semantic segmentation.

关键词： Semantics Feature extraction Remote sensing Convolutional neural networks Deep learning Spatial resolution detection algorithms Change detection algorithms Change detection attention module deep learning UNet3+ Siamese-based architecture

来源：评论

学校读者我要写书评

暂无评论

EXIT-Aided Scheduled Iterative MIMO detection Under Non-Homogeneous Antenna Propagation Gain Scenarios

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2022年第10期71卷 10600-10614页

作者： Li, Huan Guo, Jing Wang, Xinyi Cao, Congzhe Fei, Zesong Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 1H9 Canada Huawei Technol Canada Co Ltd Heterogeneous Compiler Lab Markham ON L3R 5A4 Canada

The non-homogeneous antenna propagation gain, potentially caused by the diverse large-scale fading effects in wireless communication channels, has a significant impact on the reliabilities of multiple-input multiple-out (MIMO) systems. We propose to utilize extrinsic information transfer (EXIT) to analyze the convergence characteristic of the factor graph (FG) based iterative MIMO detection mechanisms in an effective way. Based on the EXIT analysis, we propose a low-complexity scheduled algorithm for FG-based iterative MIMO detection, which speeds up the convergence of the mutual information exchange between the variable nodes and the observation nodes. To address the complexity issue in 5G new radio (NR) systems, where low-density parity check (LDPC) codes are adopted for data transmission, we also extend the proposed algorithm to concatenated detection and decoding in MIMO-LDPC systems to achieve low complexity. Simulation results show that the convergence speed of MIMO detection can be improved by at most 50%, while for the MIMO-LDPC system, the proposed algorithm can achieve 2 dB gain compared to the conventional minimum mean square error (MMSE) detection mechanism.

关键词： MIMO communication Fading channels Complexity theory Antennas Iterative methods detection algorithms Symbols Convergence EXIT chart factor graph MIMO detection multi-user MIMO system non-homogeneous antenna propagation gain

来源：评论

学校读者我要写书评

暂无评论

NeSiFC: Neighbors' Similarity-Based Fuzzy Community detection Using Modified Local Random Walk

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第10期52卷 10014-10026页

作者： Roy, Uttam K. Muhuri, Pranab K. Biswas, Sajib K. South Asian Univ Dept Comp Sci New Delhi 110021 India

This article proposes a neighbors' similarity-based fuzzy community detection (FCD) method, which we call ``NeSiFC.'' In the proposed NeSiFC approach, we compute the similarity between two neighbors by introducing a modified local random walk (mLRW). Basically, in a network, a node and its' neighbors with noticeable similarities among them construct a community. To measure this similarity, we introduce a new metric, called the peripheral similarity index (PSI). This PSI is used to construct the transition probability matrix for the mLRW. The mLRW is applied for each node until it meets a parameter called step coefficient. The mLRW gives better neighbors' similarity for community detection. Finally, a fuzzy membership function is used iteratively to compute the membership degrees for all nodes with reference to existing communities. The proposed NeSiFC has no dependence on the network characteristics, and no adjustment or fine tuning of more than one parameter is needed. To show the efficacy of the proposed NeSiFC approach, we provide a thorough comparative performance analysis considering a set of well-known FCD algorithms viz., the genetic algorithm for fuzzy community detection, membership degree propagation, center-based fuzzy graph clustering, FMM/H2, and FuzAg on a set of popular benchmarks, as well as real-world datasets. For both disjoint and overlapping community structures, results of various accuracy and quality metrics indicate the outstanding performance of our proposed NeSiFC approach. The asymptotic complexity of the proposed NeSiFC is found as O(n(2)).

关键词： detection algorithms Social networking (online) Measurement Tuning Indexes Benchmark testing Complex networks Community detection complex social network analysis fuzzy community detection (FCD) modified local random walk (mLRW) overlapping communities peripheral similarity index (PSI) quality and accuracy metrics

来源：评论

学校读者我要写书评

暂无评论

EEG Peak detection in Cognitive Conflict Processing Using Summit Navigator and Clustering-Based Ranking

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2022年 30卷 1548-1556页

作者： Dinh, Tran Hiep Singh, Avinash Kumar Linh Trung, Nguyen Nguyen, Diep N. Lin, Chin-Teng Vietnam Natl Univ Univ Engn & Technol JTIRC Hanoi 100000 Vietnam Univ Technol Sydney Australian Artificial Intelligence Inst Sch Comp Sci Fac Engn & Informat Technol Ultimo NSW 2007 Australia Vietnam Natl Univ Univ Engn & Technol Adv Inst Engn & Technol AVITECH Hanoi 100000 Vietnam Univ Technol Sydney Sch Elect & Data Engn Fac Engn & Informat Technol Ultimo NSW 2007 Australia

Correct detection of peaks in electroencephalogram (EEG) signals is of essence due to the significant correlation of those potentials with cognitive performance and disorders. This paper proposes a novel and non-parametric approach to detect prediction error negativity (PEN) in cognitive conflict processing. The PEN candidates are first located from the input signal via an adaptation of a recent effective method for local maxima extraction, processed in a multi-scale manner. The found candidates are then fused and ranked based on their shape and location-based features. False positives caused by candidates' magnitude are eliminated by rotating the sorted candidate list where the one with the second-best ranking score will be identified as PEN. The EEG data collected from a 3D object selection task have been used to verify the efficacy of the proposed approach. Compared with the state-of-the-art peak detection techniques, the proposed method shows an improvement of at least 2.67% in accuracy and 6.27% in sensitivity while requires only about 4 ms to process an epoch. The accuracy and computational efficiency of the proposed technique in the detection of PEN in cognitive conflict processing would lead to promising applications in performance improvement of brain-computer interfaces (BCIs).

关键词： Electroencephalography Feature extraction Electric potential Task analysis Windows detection algorithms Three-dimensional displays Summit navigator peak detection spike detection electroencephalogram (EEG) cognitive conflict prediction error negativity (PEN) error-related positive potential (Pe) clustering

来源：评论

学校读者我要写书评

暂无评论

Machine-Learning-Aided Trajectory Prediction and Conflict detection for Internet of Aerial Vehicles

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第8期9卷 5882-5894页

作者： Cheng, Cheng Guo, Liang Wu, Tong Sun, Jinlong Gui, Guan Adebisi, Bamidele Gacanin, Haris Sari, Hikmet Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing 210003 Peoples R China China Acad Informat & Commun Technol Inst Cloud Comp & Big Data Beijing 100191 Peoples R China Natl Inst Metrol Radio Dept Beijing 100029 Peoples R China Manchester Metropolitan Univ Fac Sci & Engn Dept Engn Manchester M1 5GD Lancs England Rhein Westfal TH Aachen Inst Commun Technol & Embedded Syst D-52062 Aachen Germany

As exploitation of low and medium airspace for air traffic management (ATM) is gaining more attention, aerial vehicles' security issues pose a major challenge to the air-ground-integrated vehicle networks (AGIVNs). Traditional surveillance technology lacks the capacity to support the intensive ATM of the future. Therefore, an advanced automatic-dependent surveillance-broadcast (ADS-B) technique is applied to track and monitor aerial vehicles in a more effective manner. In this article, we propose a grouping-based conflict detection algorithm based on the preprocessed ADS-B data set, and analyze the experimental results and visualize the detected conflicts. Then, in order to further improve flight safety and conflict detection, the trajectories of the aerial vehicles are predicted based on machine learning-based algorithms. The results are fed into the conflict detection algorithm to execute conflict prediction. It was shown that the trajectory prediction model using long short-term memory (LSTM) can achieve better prediction performance, especially when predicting the long-term trajectory of aerial vehicles. The conflict detection results based on the trajectory prediction methods show that the proposed scheme can make it possible to detect whether there would be conflicts within seconds.

关键词： Collision avoidance Trajectory Surveillance detection algorithms Internet of Things Space vehicles Safety Aerial vehicle automatic-dependent surveillance broadcast (ADS-B) conflict detection machine learning trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

iSensMex-POT, a Potentiostat Platform for Human Health Applications

引用

IEEE ACCESS 2024年 12卷 169050-169068页

作者： Zamora-Mejia, Gregorio Carbajal-Gomez, Victor H. Alvarez-Simon, Luis C. Silva-Juarez, Alejandro Bautista-Castillo, Alejandro I. Rosales-Nunez, Sergio A. Rocha-Perez, Jose M. Barbosa-Escudero, Francisco Sanchez-Dominguez, Margarita Durini, Daniel Consejo Nacl Humanidades Ciencia & Tecnol CONAHCyT Mexico City 03940 Mexico Inst Nacl Astrofis Opt & Elect INAOE Puebla 72840 Mexico Benemerita Univ Autonoma Puebla BUAP Dept Elect Sci Puebla 72570 Mexico Ctr Invest Mat Avanzados CIMAV Subsede Monterrey Ciudad Apodaca 66628 Mexico

This work introduces the iSensMEX-POT platform, a potentiostat-based detection system for conducting cyclic voltammetry measurements. It consists of a mixed-mode application-specific integrated circuit (ASIC) and a user digital interface unit based on Raspberry/Python platform. The ASIC consists of three main building blocks: a potentiostat built by three operational amplifiers (OpAmps) working as an analog front-end, a 10-bit R2R digital-to-analog converter (DAC) and a 10-bit successive-approximation analog-to-digital converter (SAR-ADC) composing the mixed signal mode processing stage, and a digital finite state machine using the Inter-Integrated Circuit (I2C) protocol conforming the digital data processing and transmission section. The Raspberry controls the ASIC using the I2C, writes a digital words into the ASIC's registers to replicate a triangular cyclic voltammetry signal with a scan rate of 200 mV/s over a range of +/- 1 V, and reads the digitized data from the SAR-ADC. The Raspberry platform displays the resulting waveform on a touch-screen using a graphical user interface (GUI). Also, a precision model based on the open-loop gain of the amplifier and an output noise quantification model were developed and applied to design a highly accurate potentiostat based on three amplifiers. The proposed platform's functionality and accuracy was validated by comparing the data gathered by the iSensMex-POT with the data obtained with the EVAL-AD5940ELCZ commercial board. The proposed ASIC was mathematically modeled, simulated and fabricated in a 180 nm CMOS standard technology, featuring a silicon area of 1.39 mm2 and a power consumption of 52.99 mW (16.05 mA @ 3.3 V).

关键词： Computer architecture Noise measurement Gain measurement Transistors Universal Serial Bus Microprocessors Electrodes Graphical user interfaces Costs Voltage control detection algorithms Arsenic bacteria creatinine cyclic voltammetry drinking water human health (IC)-C-2 molecules potentiostat virus

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：