A multi-kernel channel attention combined with convolutional neural network to identify spectral information for tracing the origins of rice samples

Article Agronomy

Determination of the quality of tea from different picking periods: An adaptive pooling attention mechanism coupled with an electronic nose

Siyuan Kang et al.

Summary: An efficient nondestructive testing method is developed using an electronic nose combined with data analysis method to inspect the quality of tea from different picking periods. The method shows high accuracy, precision, recall, and F1-score in distinguishing the gas information of tea gathered in different picking periods.

POSTHARVEST BIOLOGY AND TECHNOLOGY (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Lightweight Residual Convolutional Neural Network for Soybean Classification Combined With Electronic Nose

Hualing Lin et al.

Summary: This paper proposes a method based on a lightweight residual convolutional neural network (LRCNN) and an electronic nose (e-nose) for tracing soybean quality. The method obtains soybean gas information using an e-nose, and achieves high-precision identification of soybean quality differences through grouped heterogeneous kernel-based convolution and LRCNN.

IEEE SENSORS JOURNAL (2022)

Add to Collection

Article Engineering, Electrical & Electronic

An adaptive learning method for the fusion information of electronic nose and hyperspectral system to identify the egg quality

Qinglun Zhang et al.

Summary: In this paper, a multi-data-fusion-attention network (MDFA-Net) is proposed to identify the quality of eggs by combining the information from an electronic nose and a hyperspectral system. The network selects effective information through feature adaptive learning and forms a decision network to identify the fusion information, achieving better classification performance and stability.

SENSORS AND ACTUATORS A-PHYSICAL (2022)

Add to Collection

Article Chemistry, Analytical

A residual dense comprehensively regulated convolutional neural network to identify spectral information for egg quality traceability

Hualing Lin et al.

Summary: This paper proposes a new method for identifying the quality of eggs laid by hens under different feeding conditions using a hyperspectral system and a residual dense comprehensively regulated convolutional neural network (RDCR-Net). By extracting features from the spectral information, RDCR-Net achieves high accuracy in classification performance.

ANALYTICAL METHODS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A data fusion method of electronic nose and hyperspectral to identify the origin of rice

Yan Shi et al.

Summary: This study proposed a data fusion method combining electronic nose and hyperspectral technology, and achieved the traceability of rice origin through support vector machine. The method utilized SCARS and MRMR methods for feature selection, and achieved a good classification performance of 98.57%.

SENSORS AND ACTUATORS A-PHYSICAL (2021)

Add to Collection

Article Spectroscopy

A residual network with attention module for hyperspectral information of recognition to trace the origin of rice

Hong Men et al.

Summary: This study proposed a neural network framework combined with residual block and CBAM for hyperspectral information recognition to trace rice quality. By enhancing detection performance, the model achieved a classification accuracy of 96.33%, outperforming other methods, providing an intelligent technology to improve hyperspectral detection and trace rice quality.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2021)

Add to Collection

Article Chemistry, Analytical

Improving performance: A collaborative strategy for the multi-data fusion of electronic nose and hyperspectral to track the quality difference of rice

Yan Shi et al.

Summary: The study presents a collaborative strategy to track the quality difference of rice, combining deep learning and machine learning theories to improve detection performance. By collecting quality information of rice and designing a new CNN structure, along with the GE-ELM model, the fusion system's performance and recognition ability were effectively enhanced.

SENSORS AND ACTUATORS B-CHEMICAL (2021)

Add to Collection

Article Computer Science, Artificial Intelligence