Freshness Classification of Hog Plum Fruit Using Deep Learning

Arunachalaeshwaran, V. R.; Mahdi, Hussain Falih; Choudhury, Tanupriya; Sarkar, T.; Bhuyan, Bikram Pratim

doi:10.1109/hora55278.2022.9799897

Cited by 10 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also carried out a detailed review of the method that are used to detect and classify various objects. In [17], a deep learning-based technique is used for the freshness classification of Hog Palm fruit. This work uses four CNN-based models, which were fine-tuned on imageNet Dataset.…”

Section: Related Workmentioning

confidence: 99%

Automatic Fruits Freshness Classification Using CNN and Transfer Learning

Amin

Shahzad

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Fruit Freshness categorization is crucial in the agriculture industry. A system, which precisely assess the fruits’ freshness, is required to save labor costs related to tossing out rotten fruits during the manufacturing stage. A subset of modern machine learning techniques, which are known as Deep Convolution Neural Networks (DCNN), have been used to classify images with success. There have recently been many changed CNN designs that gradually added more layers to achieve better classification accuracy. This study proposes an efficient and accurate fruit freshness classification method. The proposed method has several interconnected steps. After the fruits data is gathered, data is preprocessed using color uniforming, image resizing, augmentation, and image labelling. Later, the AlexNet model is loaded in which we use eight layers, including five convolutional layers and three fully connected layers. Meanwhile, the transfer learning and fine tuning of the CNN is performed. In the final stage, the softmax classifier is used for final classification. Detailed simulations are performed on three publicly available datasets. Our proposed model achieved highly favorable results on all three datasets in which 98.2%, 99.8%, and 99.3%, accuracy is achieved on aforesaid datasets, respectively. In addition, our developed method is also computationally efficient and consumes 8 ms on average to yield the final classification result.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Fruits Freshness Classification Using CNN and Transfer Learning

Amin

Shahzad

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Naive Bayes is a classification using probability and statistical methods based on the British scientist Thomas Bayes, which is to predict the future chances of past experience [12][13] [14]. Good potential is also ascribed to the Naive Bayes method of classification, determining the accuracy and efficiency of product data [15] [16].…”

Section: Introductionmentioning

confidence: 99%

Classification Analysis of Product Sales Results at Alfamart Using the Naïve Bayes Method

Yuyun,

Silaban,

Sitepu

et al. 2024

ENIGMA

View full text Add to dashboard Cite

This research focuses on the analysis of the number of products sold, especially stock items from the distribution center to Alfamart stores. The main problem discussed in this study is the result of the number of unsold and sold products, which causes overstocking in the warehouse area. To overcome this problem, it will be solved using the Naive Bayes classification method. This research uses sample data of 100 products and uses data collection techniques such as observation and interviews. The collected data is analysed through a classification approach. This research aims to predict goods that sell and do not sell using Rapidminer using the NaïveBayes method. And to produce more accurate data for the product sales process. The reason for using this naïve bayes algorithm in the process of processing and analysing data is because the way this algorithm works uses statistical methods and probability in predicting future results. The validation results show that the Naive Bayes classification method implemented through Rapidminer provides a significant explanation with a fairly high accuracy and a positive effect on the prediction of sales of goods based on consumer demand and needs.

show abstract