教学课程资源库 更多>>

关键词： Cotton   Crops   Feature extraction   Plant diseases   Convolutional neural networks   Deep learning   Computer science   Convolution neural network (CNN)   lightweight 2D CNN   android application   plant disease diagnosis system   gradient weighted class activation mapping (Grad-CAM)   tomato   cotton  

摘要： Tomatoes are the most widely grown crop in the world, and they may be found in a variety of forms in every kitchen, regardless of cuisine. It is, after potato and sweet potato, the most widely farmed crop on the planet. Cotton is another essential cash crop because most farmers grow it in huge quantities. However, many diseases reduce the quality and quantity of tomato and cotton crops, resulting in a significant loss in production and productivity. It is critical to detect these disorders at an early stage of diagnosis. The purpose of this work is to categorize 14 classes for both cotton and tomato crops, with 12 diseased classes and two healthy classes using a deep learning-based lightweight 2D CNN architecture and to implement the model in an android application named "Plant Disease Classifier" for smartphone-assisted plant disease diagnosis system, the results of the experiments reveal that the proposed model outperforms the pre-trained models VGG16, VGG19 and InceptionV3 despite having fewer parameters. With slightly larger parameters than MobileNet and MobileNetV2, proposed model also attains considerably larger accuracy than these models. The classification accuracy varies between 57% and 92% for these models, and the proposed model's average accuracy is 97.36%. Also, the precision, recall, F1-score of the proposed model is 97 % and Area Under Curve (AUC) score of the model is 99.9% which is an indicator of the very good performance of the model. Class activation maps were shown using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to visually explain the disease detected by the proposed model, and a heatmap was produced to indicate the responsible region for classification. The app works very impressively and classified the correct disease in a shorter period of time of about 4.84 ms due to the lightweight nature of the model.

关键词： Natural language processing   Computer science   Bibliographies   Syntactics   Semantics   Systematics   Corpus   Indonesian language   natural language processing   spell  

摘要： In this study, we present the first spell error corpus for the Indonesian Language (SPECIL). This corpus provides a comprehensive resource for researchers and practitioners to detect and correct spelling errors in Bahasa Indonesia (Indonesian). It should be emphasized that currently, there is no recognized corpus for identifying spelling mistakes in the Indonesian language that has been officially released or made accessible. This study also provides a systematic literature review to identify resources and methodologies for building a corpus for spelling error detection and correction in Indonesia. A corpus was created using a combination of manual and automatic methods. The results of this study are a review of publications relating to corpora and spelling, the novel algorithm of six types of spelling errors, and the production of a corpus comprising over 180,000 tokens in 21,500 sentences, including non-word, real-word, and punctuation errors. Using the developed corpus, various Natural Language Processing (NLP) models, including spell checkers and language models, can be trained and tested to enhance their accuracy and effectiveness in identifying and rectifying errors in Indonesian ***, the corpus can be used to develop and evaluate new algorithms and techniques for spelling error detection and correction in Indonesia. The SPECIL corpus is publicly available and *** is expected that SPECIL will inspire further research in this area and facilitate the development of more accurate and effective spelling error detection and correction tools in Indonesian language.

关键词： Computer Science   Engineering & Technology   MathML  

ISBN: (数字)9788770228046 ISBN: (纸本)9788770228053

摘要： Industry 4.0 is used interchangeably with the fourth industrial revolution and represents a new stage in the organization and control of the industrial value chain. Cyber-physical systems form the basis of Industry 4.0 (e.g., ‘smart machines’). They use modern control systems, have embedded software systems, be addressed via IoT (the Internet of Things), and may use extensive data analytics and/or artificial intelligence systems to operate autonomously. The aim of this book is to provide detailed insights into the state of art techniques in AI, IoT, Blockchain technology and associated technologies which play a vital role in the implementation of a successful project for upcoming and practicing engineers. Owing to its multidisciplinary nature, Industry 4.0 is not a single topic but a combination of a multitude of technologies from different domains. Keeping this in mind the book includes the following topics: • Artificial intelligence • Internet of things • Blockchain technology • Digital manufacturing • Robotics • Cybersecurity. The book will be a comprehensive guide to academicians, engineers who want to align with recent trends of fourth industrial revolution.

关键词： Feature extraction   Linguistics   Computational modeling   Encoding   Mathematical models   Computer science   Machine translation   Abstractive summarization   encoder-decoder   extractive summarization   feature rich model   linguistic features   summarization evaluation  

摘要： Summarization generates a brief and concise summary which portrays the main idea of the source text. There are two forms of summarization: abstractive and extractive. Extractive summarization chooses important sentences from the text to form a summary whereas abstractive summarization paraphrase using advanced and nearer-to human explanation by adding novel words or phrases. For a human annotator, producing summary of a document is time consuming and expensive because it requires going through the long document and composing a short summary. An automatic feature-rich model for text summarization is proposed that can reduce the amount of labor and produce a quick summary by using both extractive and abstractive approach. A feature-rich extractor highlights the important sentences in the text and linguistic characteristics are used to enhance results. The extracted summary is then fed to an abstracter to further provide information using features such as named entity tags, part of speech tags and term weights. Furthermore, a loss function is introduced to normalize the inconsistency between word-level and sentence-level attentions. The proposed two-staged network achieved a ROUGE score of 37.76% on the benchmark CNN/DailyMail dataset, outperforming the earlier work. Human evaluation is also conducted to measure the comprehensiveness, conciseness and informativeness of the generated summary.

关键词： Microservice architectures   Runtime   Visualization   Computer science   Testing   Security   Anti-pattern   dynamic analysis   mapping study   microservice   visualization  

摘要： In the world of microservices, companies must be able to create systems that operate in the most efficient way. To achieve this, anti-patterns must be avoided because of their detriment to the quality of the system. Some of the most troubling anti-patterns are hard to detect because of their appearance at runtime. Effectively removing anti-patterns from a system requires dynamic analysis because of the large size of microservice-based systems. While the detection of anti-patterns is helpful, being able to visualize them offers a great benefit to companies working with microservices. Seeing how the overall system is flowing and recognizing the existence of anti-patterns can help improve microservice-based systems. In this paper, a systematic mapping study was performed to find the current state of research on visualizing anti-patterns in microservices from the dynamic perspective. Several hundred papers were examined and a total of 31 were found to be relevant to the research topic. The papers, when analyzed, revealed that there are mechanisms to detect anti-patterns at runtime in microservices, and there are also mechanisms for visualizing the architecture of a microservice-based system. This study's findings could help to identify and remove anti-patterns that occur during runtime in microservices, as well as a means of visualizing these anti-patterns.

关键词： 1774   Continental Congress   Thirteen British Colonies   Transatlantic cause  

摘要： In the summer of 1774, delegates from across Britain’s thirteen North American colonies established the Continental Congress and to determine how best the colonies could regain rights and liberties they held had been infringed upon by Parliament. Congress hoped to draw as many Britons into their cause of resistance as possible and did so by releasing three addresses: the Address to the People of Great Britain, the Address to the Inhabitants of Quebec, and the Memorial to the Inhabitants of the British Colonies. The primary difficulties to the adoption of this transatlantic cause were the Continental Association’s threat to the British transatlantic economy and the long and important history of conflict between Protestants and Catholics. Alongside these difficulties, the many differences between addresses were used by Loyalist critics of Congress to argue against the cause of resistance, becoming a primary reason why this transatlantic cause would fail. Historians have largely ignored these addresses, despite the insight they provide into the cause of resistance before violent conflict in 1775. The addresses should expand the geography of the American Revolution to include the entire transatlantic and show the potential for dramatic change, through Congress’s willingness to invite Catholics into the cause. The addresses reveal just how uncertain 1774 was, but most importantly, they reveal that in 1774, the cause was simply not common enough to become transatlantic.

关键词： bivariate Lomax-G family of distributions   Lomax-G family of distributions   multivariate  

摘要： This paper presents a novel family of bivariate continuous Lomax generators known as the BFGMLG family, which is constructed using univariate Lomax generator (LG) families and the Farlie Gumbel Morgenstern (FGM) copula. We have derived several structural statistical properties of our proposed bivariate family, such as marginals, conditional distribution, conditional expectation, product moments, moment generating function, correlation, reliability function, and hazard rate function. The paper also introduces four special submodels of the new family based on the Weibull, exponential, Pareto, and log-logistic baseline distributions. The study establishes metrics for local dependency and examines the significant characteristics of the proposed bivariate model. To provide greater flexibility, a multivariate version of the continuous FGMLG family are suggested. Bayesian and maximum likelihood methods are employed to estimate the model parameters, and a Monte Carlo simulation evaluates the performance of the proposed bivariate family. Finally, the practical application of the proposed bivariate family is demonstrated through the analysis of four data sets.

关键词： K-means clustering  

摘要： This paper provides an analysis of H-index and paper citations in the computer science field using K-Means Clustering Algorithm. By leveraging cutting edge visual analytics through the use of Power BI and Orange Data Mining tool with K-Means clustering algorithm, we are able to present a comprehensive review of how H-index and citations impact the scholarly evaluation of authors in computer science field. The analysis obtained will assist academics seeking to expand their research influence while providing additional context to the general audience seeking to understand how machine learning algorithms can contribute to data exploration. The analysis conducted has revealed that area of research which has the highest value of citation and H-index include the following topics: Artificial-Intelligence, Computational-Intelligence, Data-mining, Evolutionary-Algorithms, and Big Data Analytics. Finally, the analysis of this research clearly demonstrated that paper citations remain an important factor for determining scientific impact in disciplines such as computer science given its close relationship with established metrics such as h-index scores. © 2023 by the Authors.

关键词： Computing education research   Flipped classroom   HyFlex   Asynchronous attendance   Course materials   Students  

摘要： Much research has been conducted on the ways in which the hybrid-flexible (HyFlex) and flipped classroom models have impacted college students. However, less is known about how students interact with a course that combines the two models, especially regarding the modality through which they attend lectures. We observed the first flipped HyFlex offering of a particular computer science (CS) course at a large public research-intensive university in the United States. We found that the modality through which students initially planned to attend the course's lectures was impacted by their class standing and, to a lesser extent, their gender; however, a student's race was not found to impact their attendance plans. Secondly, we found that remote attendance had a higher rate of decrease than in-person attendance, while asynchronous attendance was the only modality to rise in the second half of the course. Upon investigating the reason for this difference, we found that the convenience of being able to access lecture recordings asynchronously was the factor that had the most impact on students' decisions to attend lectures and that their unrestricted access to course materials and asynchronous lecture recordings caused some students to perceive synchronous lecture attendance to be less necessary.

关键词： Feature extraction   Logic gates   Task analysis   Data mining   Transforms   Hyperspectral imaging   Computer science   Change detection (CD)   deep learning   gated recurrent unit (GRU)   hyperspectral image (HSI)   Siamese network  

摘要： Hyperspectral image change detection (HSI-CD) is a technique that detects changes in land cover occurring in a specific area within a closed time. At present, most existing methods for HSI-CD employ exceedingly intricate network architectures, leading to a high model complexity that hampers the achievement of a favorable tradeoff between change detection (CD) accuracy and timeliness. Furthermore, existing methods often confine the feature extraction process to a single scale rather than multiple diverse scales. However, employing a multiscale approach for feature extraction allows for capturing fine-grained features encompassing more intricate details, as well as coarse-grained features that aggregate local information over a larger range. On the other hand, most existing methods overemphasize the complexity of the feature extraction process and underestimate the importance of the conversion process from bitemporal features to valuable change features. To this end, a gated transmitting-based multiscale Siamese network (GTMSiam) is proposed, which mainly contains the following two portions: 1) dual branches with the Siamese structure, which capture spatial features of the HSIs at multiple scales while preserving rich spectral information. Moreover, the Siamese design effectively reduces the network parameters, thereby alleviating the computational complexity of the model and 2) gated change information transmitting module (GTM), which utilizes gated neural units to transform bitemporal image features into land cover change information, while progressively transmitting change information at different scales. This enables the network to leverage diverse scale change information for comprehensive discrimination of land object changes. Experimental results on three publicly available datasets demonstrate the superior performance of the proposed GTMSiam. Simultaneously, the complexity analysis experiment proves that the GTMSiam can consider both detection performance and