检索结果-内蒙古大学图书馆

Enhanced Disease recognition and Classification in Black Gram Plant Leaves Using Deep learning 1st

Enhanced Disease Recognition and Classification in Black Gra...

1st international Conference on Advances in Artificial Intelligence and machine learning in Big data Processing, AAIMB 2023

作者： Prasanth, K. Kabilamani, P. Sangar, G. Kaliraj, V. Rajasekar, V. SA Engineering College Chennai India SRMIST Vadapalani Chennai India

ISBN: (纸本)9783031730641

While urad bean is an important grain crop in several locations, it is frequently plagued by a number illness that has a devastating effect on harvest yields and quality. Using Convolutional Neural Net- works (CNNs) with 50 Layers, Local Binary pattern and Support Vector machines (SVMs), we offer a deep learning-based method for accurately recognising and categorising disorders of leaves in black gram plants. To begin, we amassed a database of pictures of black gram leaves affected by diseases like leaf blight, leaf spot, and yellow mosaic virus. We did some preliminary processing to clean up the photographs and make them look better. Then, we educated a convolutional neural network model to use to reduce the number of parameters and the LBP used to extract disease classification features from the plant images. Our model’s accuracy was enhanced by employing SVM as a classifier on the CNN50 with LBP model’s outputs features. We were able to decrease the amount of incorrect classifications by using the SVM model to boost classification precision. Using criteria like accuracy, precision, recall, and F1-score, we analysed how well our method performed. Our experiments demonstrate indicates the suggested method executes better than earlier state-of-the- art methods with a degree of 98.69%. In conclusion, we show that deep learning methods, specifically CNN and SVM, may be used to precisely detect and categorise black gram plant leaf diseases. This method may help producers better detect and combat plant illnesses, which would ultimately boost food production and quality. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Seeds Classification and Quality Testing Using Deep learning and YOLO v5 1

Seeds Classification and Quality Testing Using Deep Learning...

引用

1st international Conference on data Science, machine learning and Artificial Intelligence, DSMLAI 2021

作者： Kundu, Nidhi Rani, Geeta Dhaka, Vijaypal Singh Department of Computer and Communication Engineering Manipal University Jaipur Rajasthan Jaipur India

ISBN: (纸本)9781450387637

Segregation of seeds of different crops grown in the mixed cropping is a major cause of concern for the farmers as well as the food industry. Also, the classification and packaging of seeds based on their quality is a challenging task for farmers and agro-industries. Moreover, Post-thrashing separation of seeds by the traditional techniques such as sieving, hand-picking, etc. is a time-consuming and tedious task. Thus, there is a need to automate seed segregation. The potential of deep learning and machine learning techniques in object detection, classification, and pattern recognition motivated the researchers to employ these techniques for the automatic segregation of seeds at the harvesting site. The techniques proposed so far focus on the classification of seeds of different crops. Limited research work is observed that focuses on the classification of seeds of crops grown as a part of mixed cropping as well as seeds of different quality standards. Also, there is a huge scope to improve the classification performance of the proposed models. The purpose of this research to develop the deep learning-based system 'Mixed Cropping Seed Classifier and Quality Tester (MCSCQT)' for accurate classification and quality testing of seeds based on their shape, color, and texture. The system is trained on the dataset comprising labelled images of healthy and diseased seeds of pearl millet and maize. It reports the highest precision and recall of 99%. The efficacy of the system in discriminating the seeds of pearl millet and maize may prove a game-changer for the food industry. Also, its capability in recognition of diseased and healthy seeds of maize enhances its utility in the food industry. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Forex exchange using big data analytics 1

Forex exchange using big data analytics

引用

1st international Conference on Advances in Computational Science and Engineering, ICACSE 2020

作者： Sadhasivam, Jayakumar Arun, M. Deepa, R. Muthukumaran, V. Lokesh Kumar, R. Prasanna Kumar, R.B. Vellore Institute of Technology Vellore India School of Computing Kalasalingam Academy of Research and Education Tamilnadu 626128 India Telangana Hyderabad India Department of Mathematics School of Applied Science REVA University Bengaluru64 India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Vellore632 014 India Department of Computer Science REVA University Bengaluru64 India

Analysis and Prediction of forex has gained immense value in today's economy. The stock price prediction is a difficult process owing to the irregularities in stock prices. Every trader wants to know if the pattern has been repeated in past to know what the possible output of the current situation will be. The primary objective is to propose a methodology that will use a historical dataset and provide a more accurate prediction on stock price. In this paper, we will be using machine learning pattern recognition algorithm on forex tick dataset. The learned model then will produce pattern from the given dataset and on the pattern of increasing or decreasing, the buyer will initiate a buy or sell the stock respectively. We will use python coding to execute the algorithm in jupyter notebook. Matplot library will help us to perform graphing in the process and Numpy will be helpful in doing statistical analysis of data. © Published under licence by IOP Publishing Ltd.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Image recommendation for Wikipedia articles 1

Image recommendation for Wikipedia articles

引用

1st Masters Symposium on Advances in data mining, machine learning, and Computer Vision, MS-AMLV 2019

作者： Onyshchak, Oleh Redi, Miriam Ukrainian Catholic University Lviv Ukraine Wikimedia Foundation London United Kingdom

Multimodal learning, which is simultaneous learning from different data sources such as audio, text, images, is a rapidly emerging field of machine learning. It is also considered as machine learning at the next upper level of abstraction. This allows tackle more complicated problems such as creating cartoons from a plot or speech recognition based on lips movement. In this paper, we propose to research whether state-of-the-art techniques of multimodal learning, will solve the problem of recommending the most relevant images for a Wikipedia article. In other words, we need to create a shared text-image representation of an abstract notion which paper describes, so that having only a text description machine would"understand" which images would visualize the same notion accurately. Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 international (CC BY 4.0).

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Evaluation of Acceleration and Jerk in Human Activity recognition Using machine learning Techniques 1

引用

1st international Conference on Electronics, Biomedical Engineering, and Health Informatics, ICEBEHI 2020

作者： Nurwulan, Nurul Retno Selamaj, Gjergji Sampoerna University Jakarta12780 Indonesia Universiteti Ismail Qemali Vlorë9401 Albania

ISBN: (数字)9789813369269

ISBN: (纸本)9789813369252

Acceleration data have been widely used to study human activity recognition. However, the acceleration data collected from the accelerometer do not consider the force of gravity. Thus, it has a difficulty in discriminating closely similar activities. Jerk, the derivative of acceleration, is able to describe the changes of body accelerations correctly and mutually exclusive from the sensor orientation. This study aimed to compare the performance of jerk compared to acceleration data. The dataset used to do the comparison was collected from a triaxial accelerometer built-in Samsung smartphone with a sampling frequency of 50 Hz attached to the waist of thirty subjects. The subjects performed walking on a flat surface, walking upstairs, walking downstairs, sitting, standing, and lying down. The feature data were then grouped into three categories: acceleration features, jerk features, and combined features of acceleration and jerk. The evaluation was done using k-Nearest neighbors (KNN), linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF). The results showed that jerk features performed worse than the acceleration features. However, the combined acceleration and jerk features yielded the highest accuracy with above 87% for all classifiers. The present findings show that acceleration is still better than jerk in recognizing the pattern in human activity. The present study is, therefore, increasing the understanding of acceleration data and its derivative in human activity recognition. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Soft Exoskeleton Glove for Hand Assistance Based on Human-machine Interaction and machine learning 1

Soft Exoskeleton Glove for Hand Assistance Based on Human-ma...

引用

1st IEEE international Conference on Human-machine Systems (ICHMS)

作者： Chen, Xiaoshi Gong, Li Zheng, Lirong Zou, Zhuo Fudan Univ State Key Lab ASIC & Syst Shanghai Peoples R China

ISBN: (数字)9781728158716

ISBN: (纸本)9781728158716

This paper proposes a human machine interaction system in the field of stroke rehabilitation, based on the concept of mirror therapy (MT). It aims to improve the hand motor function of stroke patients, enabling a true synchronization between the affected hand and non-affected hand (healthy hand) for the stroke patient. It consists of a soft exoskeleton glove, a surface electromyography (sEMG) signal collecting armband and machine learning (ML) algorithms. The glove is developed by integrating low-power motors to provide force strength for the hand movement. Unlike the rigid exoskeleton devices, the glove is comfortable to wear and lightweight, so it is more suitable for rehabilitation training of stroke patients in daily life. The armband collects the sEMG signals for pattern recognition by the ML algorithms. In the experiment, four subjects perform 10 hand gestures to collect data for model training. A comparison of data preprocessing is conducted to find the optimal data segmentation method and feature vector sets. A series of pattern recognition algorithms are developed and assessed in different aspects, including prediction accuracy, training time and predicting time. All 10 gestures can be recognized in offline mode with an accuracy up to 99.4%. The control of soft exoskeleton glove in real-time manner is also carried out, and the accuracy is 82.2%. The experiment result demonstrates the feasibility of the proposed system. The innovations and limitations of the work are discussed at the end of the paper.

关键词： soft exoskeleton glove surface electromyography (sEMG) mirror therapy machine learning

来源：评论

学校读者我要写书评

暂无评论

XI-ML 2020 - Proceedings of the 1st international workshop on Explainable and Interpretable machine learning, co-located with the 43rd German Conference on Artificial Intelligence, KI 2020

XI-ML 2020 - Proceedings of the 1st International Workshop o...

引用

1st international workshop on Explainable and Interpretable machine learning, XI-ML 2020

The proceedings contain 7 papers. The topics discussed include: how to teach a computer to learn about microbes: KG-COVID-19 and microbial graph learning;explaining multivariate time series forecasts: an application to predicting the Swedish GDP;towards participatory design spaces for explainable ai interfaces in expert domains;teaching AI to explain its decisions can affect class balance;foundations for solving classification problems with quantitative abstract argumentation;sequential exceptional pattern discovery using pattern-growth: an extensible framework for interpretable machine learning on sequential data;and a comparative study of explainer modules applied to automated skin lesion classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring

引用

INFORMATION SCIENCES 2020年第0期516卷 401-418页

作者： Plawiak, Pawel Abdar, Moloud Plawiak, Joanna Makarenkov, Vladimir Acharya, U. Rajendra Polish Acad Sci Inst Theoret & Appl Informat Baltycka 5 PL-44100 Gliwice Poland Cracow Univ Technol Fac Comp Sci & Telecommun Dept Informat & Commun Technol Warsaw 24 StF-3 PL-31155 Krakow Poland Univ Quebec Montreal Dept Comp Sci Montreal PQ H2X 3Y7 Canada AGH Univ Sci & Technol Dept Biocybernet & Biomed Engn Fac Elect Engn Automat Comp Sci & Biomed Engn PL-30059 Krakow Poland Ngee Ann Polytech Dept Elect & Comp Engn Clementi 599491 Singapore SUSS Univ Sch Sci & Technol Dept Biomed Engn Clementi 599491 Singapore Kumamoto Univ IROAST Kumamoto Japan

Credit scoring (CS) is an effective and crucial approach used for risk management in banks and other financial institutions. It provides appropriate guidance on granting loans and reduces risks in the financial area. Hence, companies and banks are trying to use novel automated solutions to deal with CS challenge to protect their own finances and customers. Nowadays, different machine learning (ML) and data mining (DM) algorithms have been used to improve various aspects of CS prediction. In this paper, we introduce a novel methodology, named Deep Genetic Hierarchical Network of Learners (DGHNL). The proposed methodology comprises different types of learners, including Support Vector machines (SVM), k-Nearest Neighbors (kNN), Probabilistic Neural Networks (PNN), and fuzzy systems. The statlog German (1000 instances) credit approval dataset available in the UCI machine learning repository is used to test the effectiveness of our model in the CS domain. Our DGHNL model encompasses five kinds of learners, two kinds of data normalization procedures, two extraction of features methods, three kinds of kernel functions, and three kinds of parameter optimizations. Furthermore, the model applies deep learning, ensemble learning, supervised training, layered learning, genetic selection of features (attributes), genetic optimization of learners parameters, and novel genetic layered training (selection of learners) approaches used along with the cross-validation (CV) train-ingtesting method (stratified 10-fold). The novelty of our approach relies on a proper flow and fusion of information (DGHNL structure and its optimization). We show that the proposed DGHNL model with a 29-layer structure is capable to achieve the prediction accuracy of 94.60% (54 errors per 1000 classifications) for the statlog German credit approval data. It is the best prediction performance for this well-known credit scoring dataset, compared to the existing work in the field. (C) 2019 The Authors. Publish

关键词： Credit scoring machine learning data mining Ensemble learning Deep learning Genetic algorithm Feature extraction and selection

来源：评论

学校读者我要写书评

暂无评论

learning from Partially Labeled Sequences for Behavioral Signal Annotation 7th

Learning from Partially Labeled Sequences for Behavioral Sig...

引用

7th international workshop on machine learning and data mining for Sports Analytics (MLSA)

作者： Aniszewska-stepien, Anna Herault, Romain Hacques, Guillaume Seifert, Ludovic Gasso, Gilles INSA Rouen Normandy St Etienne Du Rouvray France Rouen Univ Normandy Mont St Aignan France

ISBN: (纸本)9783030649111;9783030649128

Herewith, we present a learning procedure that allows to deal with a partially labeled sequence dataset, i.e. when each sequence in the train dataset may contain labeled as well as unlabeled chunks. In our application case, this occurs when motor activity has been manually annotated (due to the recognition based on the video recording) and independently registered by the measuring system of high precision (touch sensors): human annotation misses some events that have been captured by the sensors. In the general setting, we aim at predicting the labels for a new fully unlabeled movement sequence, while the training has been performed on the partially labeled dataset. For this purpose we propose to use classical sequence model (hidden Markov model) that is furnished with a constrained Viterbi algorithm, which gives us a quick access to the hard approximation of the correct labeling sequences. We demonstrate, that this simple modification that constrained Viterbi provide, allows the HMM model to be trained on sparse data, and overall results in surprisingly high log-likelihood and accuracy level in annotating the partially labeled behavioral sequences in climbing. The same time we show the way to access correct labeling of the unannotated signal that can be helpful in various sport science studies for movement pattern sequential prediction.

关键词： Partially labeled data Hidden Markov model Constrained viterbi algorithm Behavioral signal labeling Climbing pattern discovery

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Exercise- and Knowledge-Aware learning Network for student Performance Prediction 1st

Graph-Based Exercise- and Knowledge-Aware Learning Network ...

引用

1st CAAI international Conference on Artificial Intelligence, CICAI 2021

作者： Liu, Mengfan Shao, Pengyang Zhang, Kun Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9783030930455

Predicting student performance is a fundamental task in Intelligent Tutoring Systems (ITSs), by which we can learn about students’ knowledge level and provide personalized teaching strategies for them. Researchers have made plenty of efforts on this task. They either leverage educational psychology methods to predict students’ scores according to the learned knowledge proficiency, or make full use of Collaborative Filtering (CF) models to represent latent factors of students and exercises. However, most of these methods either neglect the exercise-specific characteristics (e.g., exercise materials), or cannot fully explore the high-order interactions between students, exercises, as well as knowledge concepts. To this end, we propose a Graph-based Exercise- and Knowledge-Aware learning Network for accurate student score prediction. Specifically, we learn students’ mastery of exercises and knowledge concepts respectively to model the two-fold effects of exercises and knowledge concepts. Then, to model the high-order interactions, we apply graph convolution techniques in the prediction process. Extensive experiments on two real-world datasets prove the effectiveness of our proposed Graph-EKLN. © 2021, Springer Nature Switzerland AG.

关键词： data mining

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：