scholarly journals A Study of Tangerine Pest Recognition Using Advanced Deep Learning Methods

2018 ◽  
Author(s):  
Marely Lee ◽  
Shuli Xing
Keyword(s):  
Deep Learning ◽  
Crop Yield ◽  
Nearest Neighbors ◽  
Experimental Results ◽  
Classification Error ◽  
Learning Methods ◽  
K Nearest Neighbors ◽  
Minimum Classification Error ◽  
Citrus Pests

To improve the tangerine crop yield, the work of recognizing and then disposing of specific pests is becoming increasingly important. The task of recognition is based on the features extracted from the images that have been collected from websites and outdoors. Traditional recognition and deep learning methods, such as KNN (k-nearest neighbors) and AlexNet, are not preferred by knowledgeable researchers, who have proven them inaccurate. In this paper, we exploit four kinds of structures of advanced deep learning to classify 10 citrus pests. The experimental results show that Inception-ResNet-V3 obtains the minimum classification error.

scholarly journals A Review Paper on Deep Learning Approach for Crop Yield Prediction Assessment

2021 ◽  
Vol 7 (05) ◽  
pp. 127-132
Author(s):  
Richa Verma & Ayushi
Keyword(s):  
Deep Learning ◽  
Crop Yield ◽  
Review Paper ◽  
Learning Approach ◽  
Yield Prediction ◽  
Learning Methods ◽  
Remote Sensor ◽  
The Cross ◽  
Precise Assessment

Precise assessment of harvest yield is a difficult field of work. The equipment and programming stage to foresee the harvest yield relies on different components like climate, soil fruitfulness, genotype, and different collaborating wards. The assignment is unpredictable inferable from the information that should be gathered in volumes to comprehend crop yield through remote sensor organizations and distant detecting. This paper audits the previous 15 years of exploration work in the improvement of assessing crop yield utilizing profound learning calculations. The meaning of examining progressions utilizing profound learning methods will help in dynamic for foreseeing the harvest yield. The cross breed mix of profound learning with distant detecting and remote sensor organizations can give accuracy agribusiness later on.

scholarly journals Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting

2021 ◽  
Author(s):  
Qingyi Pan ◽  
Wenbo Hu ◽  
Ning Chen
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Data Augmentation ◽  
Multivariate Time Series ◽  
Time Series Forecasting ◽  
Experimental Results ◽  
Learning Methods ◽  
Forecasting Accuracy ◽  
Sliding Windows ◽  
Scheme Of Series

It is important yet challenging to perform accurate and interpretable time series forecasting. Though deep learning methods can boost forecasting accuracy, they often sacrifice interpretability. In this paper, we present a new scheme of series saliency to boost both accuracy and interpretability. By extracting series images from sliding windows of the time series, we design series saliency as a mixup strategy with a learnable mask between the series images and their perturbed versions. Series saliency is model agnostic and performs as an adaptive data augmentation method for training deep models. Moreover, by slightly changing the objective, we optimize series saliency to find a mask for interpretable forecasting in both feature and time dimensions. Experimental results on several real datasets demonstrate that series saliency is effective to produce accurate time-series forecasting results as well as generate temporal interpretations.

Semi-Supervised Clustering Algorithm Based on Small Size of Labeled Data

2011 ◽  
Vol 121-126 ◽  
pp. 4675-4679
Author(s):  
Ming Wei Leng ◽  
Xiao Yun Chen ◽  
Jian Jun Cheng ◽  
Long Jie Li
Keyword(s):  
Data Mining ◽  
Clustering Algorithm ◽  
Clustering Algorithms ◽  
Nearest Neighbors ◽  
Experimental Results ◽  
K Nearest Neighbors ◽  
Supervised Clustering ◽  
The Core ◽  
Knn Classification ◽  
Core Problem

In many data mining domains, labeled data is very expensive to generate, how to make the best use of labeled data to guide the process of unlabeled clustering is the core problem of semi-supervised clustering. Most of semi-supervised clustering algorithms require a certain amount of labeled data and need set the values of some parameters, different values maybe have different results. In view of this, a new algorithm, called semi-supervised clustering algorithm based on small size of labeled data, is presented, which can use the small size of labeled data to expand labeled dataset by labeling their k-nearest neighbors and only one parameter. We demonstrate our clustering algorithm with three UCI datasets, compared with SSDBSCAN[4] and KNN, the experimental results confirm that accuracy of our clustering algorithm is close to that of KNN classification algorithm.

scholarly journals An Efficient Method for Generating Adversarial Malware Samples

Electronics ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 154
Author(s):  
Yuxin Ding ◽  
Miaomiao Shao ◽  
Cai Nie ◽  
Kunyang Fu
Keyword(s):  
Deep Learning ◽  
Efficient Method ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Experimental Results ◽  
Learning Models ◽  
Learning Methods ◽  
Gradient Based ◽  
Novel Method

Deep learning methods have been applied to malware detection. However, deep learning algorithms are not safe, which can easily be fooled by adversarial samples. In this paper, we study how to generate malware adversarial samples using deep learning models. Gradient-based methods are usually used to generate adversarial samples. These methods generate adversarial samples case-by-case, which is very time-consuming to generate a large number of adversarial samples. To address this issue, we propose a novel method to generate adversarial malware samples. Different from gradient-based methods, we extract feature byte sequences from benign samples. Feature byte sequences represent the characteristics of benign samples and can affect classification decision. We directly inject feature byte sequences into malware samples to generate adversarial samples. Feature byte sequences can be shared to produce different adversarial samples, which can efficiently generate a large number of adversarial samples. We compare the proposed method with the randomly injecting and gradient-based methods. The experimental results show that the adversarial samples generated using our proposed method have a high successful rate.

scholarly journals End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification

2017 ◽  
Author(s):  
Zheng Li ◽  
Yu Zhang ◽  
Ying Wei ◽  
Yuxiang Wu ◽  
Qiang Yang
Keyword(s):  
Deep Learning ◽  
Domain Adaptation ◽  
Sentiment Classification ◽  
Classification Error ◽  
Target Domain ◽  
Learning Methods ◽  
Cross Domain ◽  
Memory Network ◽  
End To End ◽  
Two Parameter

Domain adaptation tasks such as cross-domain sentiment classification have raised much attention in recent years. Due to the domain discrepancy, a sentiment classifier trained in a source domain may not work well when directly applied to a target domain. Traditional methods need to manually select pivots, which behave in the same way for discriminative learning in both domains. Recently, deep learning methods have been proposed to learn a representation shared by domains. However, they lack the interpretability to directly identify the pivots. To address the problem, we introduce an end-to-end Adversarial Memory Network (AMN) for cross-domain sentiment classification. Unlike existing methods, our approach can automatically capture the pivots using an attention mechanism. Our framework consists of two parameter-shared memory networks: one is for sentiment classification and the other is for domain classification. The two networks are jointly trained so that the selected features minimize the sentiment classification error and at the same time make the domain classifier indiscriminative between the representations from the source or target domains. Moreover, unlike deep learning methods that cannot tell us which words are the pivots, our approach can offer a direct visualization of them. Experiments on the Amazon review dataset demonstrate that our approach can significantly outperform state-of-the-art methods.

Bagging and boosting variants for handling classifications problems: a survey

2013 ◽  
Vol 29 (1) ◽  
pp. 78-100 ◽  
Author(s):  
Sotiris B. Kotsiantis
Keyword(s):  
Ensemble Learning ◽  
Experimental Results ◽  
Classification Error ◽  
Learning Methods ◽  
Research Directions ◽  
Open Framework ◽  
Performance Guarantees ◽  
Theoretical Issues ◽  
Theoretical Performance

AbstractBagging and boosting are two of the most well-known ensemble learning methods due to their theoretical performance guarantees and strong experimental results. Since bagging and boosting are an effective and open framework, several researchers have proposed their variants, some of which have turned out to have lower classification error than the original versions. This paper tried to summarize these variants and categorize them into groups. We hope that the references cited cover the major theoretical issues, and provide access to the main branches of the literature dealing with such methods, guiding the researcher in interesting research directions.

A Method for UAV’s Images Seamless Stitching

2014 ◽  
Vol 556-562 ◽  
pp. 5076-5080
Author(s):  
Peng Jun Li ◽  
Jian Zeng Li
Keyword(s):  
Random Sample ◽  
Nearest Neighbors ◽  
Experimental Results ◽  
Image Stitching ◽  
Feature Points ◽  
K Nearest Neighbors ◽  
Fusion Technique ◽  
Speeded Up Robust Features ◽  
Random Sample Consensus ◽  
Ransac Algorithm

Image stitching is an important technology to build a panorama image by combing several images with overlapped areas. In this study, we develop a image seamless mosaic and fusion technique to obtain a prefect panorama image after stitching. At first, it is usingspeeded-up robust features(SURF) algorithm to extract features form the images for stitching. Then,k-nearest neighbors(KNN) method is used to match the feature points andRandom sample consensus(RANSAC) algorithm is used to clear them. Thirdly, a method is improved to achieve seamless stitching based on optimal suture of the overlapped areas. Experimental results indicate that this method can eliminate cohesion gap of two stitching images very well.

scholarly journals Modeling Pan Evaporation Using Gaussian Process Regression K-Nearest Neighbors Random Forest and Support Vector Machines; Comparative Analysis

Atmosphere ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 66 ◽  
Author(s):  
Sevda Shabani ◽  
Saeed Samadianfard ◽  
Mohammad Taghi Sattari ◽  
Amir Mosavi ◽  
Shahaboddin Shamshirband ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Gaussian Process ◽  
Gaussian Process Regression ◽  
Nearest Neighbors ◽  
Support Vector ◽  
Pan Evaporation ◽  
Learning Methods ◽  
K Nearest Neighbors ◽  
Machine Learning Methods

Evaporation is a very important process; it is one of the most critical factors in agricultural, hydrological, and meteorological studies. Due to the interactions of multiple climatic factors, evaporation is considered as a complex and nonlinear phenomenon to model. Thus, machine learning methods have gained popularity in this realm. In the present study, four machine learning methods of Gaussian Process Regression (GPR), K-Nearest Neighbors (KNN), Random Forest (RF) and Support Vector Regression (SVR) were used to predict the pan evaporation (PE). Meteorological data including PE, temperature (T), relative humidity (RH), wind speed (W), and sunny hours (S) collected from 2011 through 2017. The accuracy of the studied methods was determined using the statistical indices of Root Mean Squared Error (RMSE), correlation coefficient (R) and Mean Absolute Error (MAE). Furthermore, the Taylor charts utilized for evaluating the accuracy of the mentioned models. The results of this study showed that at Gonbad-e Kavus, Gorgan and Bandar Torkman stations, GPR with RMSE of 1.521 mm/day, 1.244 mm/day, and 1.254 mm/day, KNN with RMSE of 1.991 mm/day, 1.775 mm/day, and 1.577 mm/day, RF with RMSE of 1.614 mm/day, 1.337 mm/day, and 1.316 mm/day, and SVR with RMSE of 1.55 mm/day, 1.262 mm/day, and 1.275 mm/day had more appropriate performances in estimating PE values. It was found that GPR for Gonbad-e Kavus Station with input parameters of T, W and S and GPR for Gorgan and Bandar Torkmen stations with input parameters of T, RH, W and S had the most accurate predictions and were proposed for precise estimation of PE. The findings of the current study indicated that the PE values may be accurately estimated with few easily measured meteorological parameters.

scholarly journals Ransomware Detection Based On Opcode Behavior Using K-Nearest Neighbors Algorithm

2021 ◽  
Vol 50 (3) ◽  
pp. 495-506
Author(s):  
Deris Stiawan ◽  
Somame Morianus Daely ◽  
Ahmad Heryanto ◽  
Nurul Afifah ◽  
Mohd Yazid Idris ◽  
...  
Keyword(s):  
Detection Method ◽  
Nearest Neighbors ◽  
Information Privacy ◽  
Control Flow ◽  
Experimental Results ◽  
Control Flow Graph ◽  
K Nearest Neighbors ◽  
Flow Graph ◽  
Behavioural Characteristics

Ransomware is a malware that represents a serious threat to a user’s information privacy. By investigating howransomware works, we may be able to recognise its atomic behaviour. In return, we will be able to detect theransomware at an earlier stage with better accuracy. In this paper, we propose Control Flow Graph (CFG) asan extracting opcode behaviour technique, combined with 4-gram (sequence of 4 “words”) to extract opcodesequence to be incorporated into Trojan Ransomware detection method using K-Nearest Neighbors (K-NN)algorithm. The opcode CFG 4-gram can fully represent the detailed behavioural characteristics of Trojan Ransomware.The proposed ransomware detection method considers the closest distance to a previously identifiedransomware pattern. Experimental results show that the proposed technique using K-NN, obtains the best accuracyof 98.86% for 1-gram opcode and using 1-NN classifier.

Sign in / Sign up

Export Citation Format

Share Document