Performance evaluation of different classification techniques using different datasets

Özdemir, Abdulkadir; Yavuz, Uğur; Dael, Fares Abdulhafidh

doi:10.11591/ijece.v9i5.pp3584-3590

Cited by 15 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contrarily, the distribution of a dataset with more categories was relatively complicated, which was not conducive to discrimination. Thus, dataset was an important factor affecting the performance of models [43,50]. In addition, it could be seen that deep transferred model got the best performance in Oat dataset.…”

Section: Identification Results Analysis On Target Datasetsmentioning

confidence: 99%

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Liu

Bao

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Varieties identification of crop seeds is significant for breeders to screen out seeds with specific traits and for market regulators to detect seeds purity. Hyperspectral imaging technology provides a fast and non-destructive means for varieties identification. And deep learning algorithm is suitable for effective analysis of redundant spectral data. However, deep learning algorithms have serious big data dependency, while collecting high-quality large-scale samples was high-cost in many cases. This made it difficult to build an accurate identification model. This study aimed to explore a rapid and accurate method for varieties identification of different crop seeds under sample-limited condition based on hyperspectral imaging and deep transfer learning.Results: Three deep neural networks with typical structures were designed based on a samples-rich Pea dataset. Obtained the highest accuracy of 99.57 %, VGG-MODEL was transferred to classify four target datasets (Rice, Oat, Wheat, Cotton) with limited samples. The accuracies of deep transferred model achieved 95 %, 99 %, 80.8 %, and 83.86 % on the four datasets, respectively. Using training sets with different sizes, deep transferred model could always obtain higher performance than other traditional methods. Visualization of training process and classification results confirmed the portability of common features of seed spectra and provided an interpreted method for rapid and accurate varieties identification of crop seeds.Conclusions: This study combined hyperspectral imaging and deep transfer learning to identify varieties of different crop seeds, which was proved to be efficient under sample-limited condition. This facilitated crop variety screening process under the scenario of sample scarcity. It also provided a new idea for the detection of other qualities of crop seeds based on hyperspectral imaging under sample-limited condition.

show abstract

Section: Identification Results Analysis On Target Datasetsmentioning

confidence: 99%

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Liu

Bao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…As stated earlier, output that is obtained from the linear regression classification is linear regression model that was built by from the input dataset that is loaded to the WEKA. Linear regression models obtained in this analysis are presented as the Equation (19), Equation 20and Equation 21for years 2016, 2017 and 2018 respectively. The other output on the correlation coefficient, means absolute error, relative absolute error, root relative squared error is in Table 1.…”

Section: Results and Analysis 41 Analysis Using Wekamentioning

confidence: 99%

“…The analysis on the data collected was conducted by using machine leaning software, WEKA in order to identify current problem that is affecting the aircrafts fleet. WEKA is a software tool that is equipped with various data mining techniques and algorithms that can be used in classifying and clustering data [17], [18], [19]. WEKA with linear regression classifier is used in this study in order to identify the relationship between parameters that were collected earlier.…”

Section: Data Analysis Using Machine Learningmentioning

confidence: 99%

Cost Minimization of Aircraft Critical Components for Planning and Maintenance Requirements

Rahim

Noor

Abdullah

et al. 2020

IJIE

View full text Add to dashboard Cite

Spare parts management of the aircrafts is a part of maintenance planning that requires effective and efficient planning in order to reduce aircraft downtime in maintenance processes. Spare parts unavailability during maintenance is one of the factors that affects operational availability of the aircrafts fleet. This study focused on identifying the current problem affecting operational availability of the aircrafts fleet, developing an optimization model for cost minimization of spare parts and assessing the impact on spare parts availability using the cost minimization optimization model. Data analysis using machine learning techniques in WEKA was used to identify the current problem that is affecting aircrafts fleet operational availability. Then, Linear Integer Programming (LIP) and Goal Programming (GP) methods were used to develop the cost minimization optimization model by considering the current stock level of the critical components and the budget constrain. From this study, we discovered that spare parts unavailability during maintenance was the biggest contributing factor to the operational availability of the aircrafts fleet. Besides that, the cost minimization optimization model developed in the research had produced optimum level of inventory for the critical components with minimum cost. Spare parts availability for the aircrafts fleet had been improved with the application of the model which directly maximizes the operational availability of the aircraft fleet.

show abstract

“…3. After understanding the principles of presenting various problem situations and predicting the unknown, we apply a linear regression model and a k-nearest neighbor (kNN) model [26], [27]. These models are actually based on the subject of interest, such as meteorological data analysis, wine quality prediction, prediction of the survival rate of patients with lung cancer, and other topics such as diabetes prediction.…”

Section: Fig 2 Learning Strategy Of Ai Education Modelmentioning

confidence: 99%

Development of an Artificial Intelligence Education Model of Classification Techniques for Non-computer Majors

Lee

Cho

2021

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

In the near future, as artificial intelligence and computing network technology develop, collaboration with artificial intelligence (AI) will become important. In an AI society, the ability to communicate and collaborate among people is an important element of talent. To do this, it is necessary to understand how artificial intelligence based on computer science works. AI is being rapidly applied across industries and is developing as a core technology to enable a society led by knowledge and information. An AI education focused on problem solving and learning is efficient for computer science education. Thus, the time has come to prepare for AI education along with existing software education so that they can adapt to the social and job changes enabled by AI. In this paper, we explain a classification method for AI machine learning models and propose an AI education model using teachable machines. Non-computer majors can understand the importance of data and the AI model concept based on specific cases using AI education tools to understand and experiment with AI even without the knowledge of mathematics, and use languages such as Python, if necessary. Through the application of the machine learning model, AI can be smoothly utilized in their field of interest. If such an AI education model is activated, it will be possible to suggest the direction of AI education for collaboration with AI experts through the application of AI technology.

show abstract

Performance evaluation of different classification techniques using different datasets

Cited by 15 publications

References 11 publications

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

Cost Minimization of Aircraft Critical Components for Planning and Maintenance Requirements

Development of an Artificial Intelligence Education Model of Classification Techniques for Non-computer Majors

Contact Info

Product

Resources

About