An extreme learning machine optimized by differential evolution and artificial bee colony for predicting the concentration of whole blood with Fourier Transform Raman spectroscopy

Wang, Qiaoyun; Song, Shuai; Li, Lei; Wen, Ding; Shan, Peng; Li, Zhigang; Fu, Yongqing

doi:10.1016/j.saa.2023.122423

Cited by 11 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ELM initializes the connection weights between the input and hidden layers in a random manner, and then maps the input signals to the hidden layers using a high-dimensional nonlinear function. After the mapping is complete, the ELM quickly learns the weights of the output layer by least squares or regularization methods to approximate the objective function ( Li and Wu, 2022 ; Qiaoyun et al., 2023 ). Compared with traditional neural networks, ELM does not require iterative weight adjustment, has fast training speed and well generalization ability.…”

Section: Methodsmentioning

confidence: 99%

Research on non-destructive and rapid detection technology of foxtail millet moisture content based on capacitance method and Logistic-SSA-ELM modelling

Qiu,

Li,

Huang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Moisture content testing of agricultural products is critical for quality control, processing efficiency and storage management. Testing foxtail millet moisture content ensures stable foxtail millet quality and helps farmers determine the best time to harvest. A differential capacitance moisture content detection device was designed based on STM32 and PCAP01 capacitance digital converter chip. The capacitance method combined with the back-propagation(BP) algorithm and the extreme learning machine(ELM) algorithm was chosen to construct an analytical model for foxtail millet moisture content, temperature, and volume duty cycle. This work performs capacitance measurements on foxtail millet with different moisture contents, temperatures, and proportions of the measured substance occupying the detection area (that is, the volumetric duty cycle). On this foundation, the sparrow search algorithm (SSA) is used to optimize the BP and ELM models. However, SSA may encounter problems such as falling into local optimization solutions due to the reduction of population diversity in the late iterations. As a consequence, Logistic algorithm is introduced to optimize SSA, making it more appropriate for solving specific problems. Upon comparative analysis, the model predicted using the Logistic-SSA-ELM algorithm was more accurate. The results indicate that the predicted values of prediction set coefficient of determination (RP), prediction set root mean square error (RMSEP) and prediction set ratio performance deviation (RPDP) were 0.7016, 3.7150 and 1.4035, respectively. This algorithm has excellent prediction performance and can be used as a model for detection of foxtail millet moisture content. In view of the important role of foxtail millet moisture content detection in acquisition and storage, it is particularly important to study a nondestructive and fast online real-time detection method. The designed capacitive sensor with differential structure has well stabilization and high accuracy, which can be further studied in depth and gradually move towards the general trend of agricultural development of smart agriculture and precision agriculture.

show abstract

Section: Methodsmentioning

confidence: 99%

Research on non-destructive and rapid detection technology of foxtail millet moisture content based on capacitance method and Logistic-SSA-ELM modelling

Qiu,

Li,

Huang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Manipulation using SAWs can be realized by either using two opposing SAWs that interfere with each other to generate standing SAWs (SSAWs) [3,5,[8][9][10][11][12], by using a traveling SAWs (TSAWs) propagating in one direction [4], or by using a combination of both of these waves such as in multi-stage devices [13,14]. SSAW-based manipulation typically relies on the generation of acoustic radiation forces (ARFs) to actuate objects toward the generated nodes and anti-nodes [15][16][17][18], for separating blood components and isolation of circulating tumor cells [19] and cancer cells [20], bacteria [21] and other biological cells [22][23][24][25]. However, the patterns generated by SSAWs are often restricted to half-wavelength periodic distances between nodes or anti-nodes.…”

Section: Introductionmentioning

confidence: 99%

Acoustofluidic patterning in glass capillaries using travelling acoustic waves based on thin film flexible platform

Wang,

Maramizonouz,

Stringer Martin

et al. 2024

Ultrasonics

Self Cite

View full text Add to dashboard Cite

“…[24][25][26][27][28][29] Compared with IR, Raman spectroscopy can be used to analyze the components of physiological fluids without labeling reagents, or sample preparations. 2,[30][31][32] Raman spectra can provide sharper peaks, less overlapped peaks, and less disturbances from water and temperature. Raman spectroscopy has been investigated for the components in serum, such as glucose and cholesterol.…”

Section: Introductionmentioning

confidence: 99%

“…The main disadvantage of the infrared spectroscopy (IR) method is sensitive to water absorption 24–29 . Compared with IR, Raman spectroscopy can be used to analyze the components of physiological fluids without labeling reagents, or sample preparations 2,30–32 . Raman spectra can provide sharper peaks, less overlapped peaks, and less disturbances from water and temperature.…”

Section: Introductionmentioning

confidence: 99%

Quantitative analysis of blood glucose by FT‐Raman spectroscopy and multivariate statistical analysis

Sun,

Song,

Qian

et al. 2023

Micro & Optical Tech Letters

Self Cite

View full text Add to dashboard Cite

Diabetes is one of the common chronic diseases in worldwide and increasing among young children. Testing glycated hemoglobin levels as well as blood glucose levels is a method for detecting diabetes. In this article, with multivariate statistical analysis was used to monitor the blood glucose levels by the Fourier Transform Raman spectroscopy. Principal component regression with direct orthogonal signal correction is developed and applied to analyze the glucose concentration with the blood Raman spectroscopy. The root means square error of calibration is 3.0824 mg/dL (0.1712 mmol/L), the root means square error of prediction is 3.2688 mg/dL (0.1816 mmol/L), the correlation coefficients (R2) is .9946 and ratio of performance to deviation is 6.4789 and, respectively. The results show that this method can be used as a strong potential diagnostic tool for diabetes mellitus.

show abstract

An extreme learning machine optimized by differential evolution and artificial bee colony for predicting the concentration of whole blood with Fourier Transform Raman spectroscopy

Cited by 11 publications

References 37 publications

Research on non-destructive and rapid detection technology of foxtail millet moisture content based on capacitance method and Logistic-SSA-ELM modelling

Research on non-destructive and rapid detection technology of foxtail millet moisture content based on capacitance method and Logistic-SSA-ELM modelling

Acoustofluidic patterning in glass capillaries using travelling acoustic waves based on thin film flexible platform

Quantitative analysis of blood glucose by FT‐Raman spectroscopy and multivariate statistical analysis

Contact Info

Product

Resources

About