The Electronic Nose is an advanced technology that emulates the human olfactory system, aiming to simulate and interpret odors and gas components. With the increasing demand for gas analysis in industries, the environment, and medical fields, the Electronic Nose has garnered widespread attention as a fast, convenient, and efficient gas identification tool. However, accurate gas type discrimination and concentration prediction have remained challenging in Electronic Nose research due to the complexity and diversity of gas samples. Therefore, we proposed an innovative multi-task learning approach, GRU-CNN-MTL, combining a Gated Recurrent Unit and a One-dimensional Convolutional Neural Network for gas-type discrimination and concentration prediction tasks. Attention mechanisms were separately integrated into GRU and 1D CNN, allowing the model to automatically learn and focus on critical features relevant to the studies, thereby enhancing discrimination and prediction accuracy. Additionally, Bayesian optimization algorithms were employed to discover the optimal hyperparameter combinations, further optimizing the model’s performance. Experiments were conducted on two publicly available datasets, demonstrating outstanding performance with 99.84% accuracy and 97.57% R ² achieved on the first dataset, 99.92% accuracy and 99.97% R ² performed on the second dataset. These results further validated the potential application of our proposed method in the field of gas analysis and provided valuable insights for future research.

Velocity estimation of cotton flow is usually used to improve the accuracy of foreign fibre elimination machines. A hybrid approach based on image cross-correlation and Kalman filter is presented in this paper. Two linear CCD cameras at different locations were used to capture the images of the cotton flow synchronously. Afterwards, the captured images were preprocessed and segmented by connected region method to obtain separated cotton images. Subsequently, image cross-correlation registration technology was used to calculate the coordinate transformation parameters. For image registration, the Kalman filter tracking method was utilized to predict the possible location to speed up the image registration and solve the problem when the image registration fails. Lastly, the velocity was calculated by the pixel difference and the actual distance of two cameras. The experiment setup was designed to validate the proposed method. The hybrid approach based on image cross-correlation and Kalman filter algorithm measure the dynamic cotton flow velocity with the average 3.31% error. Moreover, the executing efficiency is prior to regular cross-correlation without Kalman filter prediction.

Textile materials have demonstrated significant potential in sound noise reduction due to their porous, lightweight, and easily processed nature. However, the current experimental setup for measuring the sound absorption of small-sized samples is expensive. Additionally, there is a lack of suitable equipment for measuring the sound absorption of flexible textiles as it is challenging to mount flexible samples into an impedance tube. This paper presents the design, fabrication, and testing of impedance tubes specifically designed for measuring the sound absorption coefficients of textile materials. The impedance tubes were designed based on the transfer function and two-microphone methods, with diameters of 100 mm and 30 mm. These tubes covered frequency ranges from 200–1600 Hz and 500–6400 Hz, respectively. Furthermore, improved sample holders were developed to mount flexible textile materials without altering the acoustic impedance characteristics of the front surface of the test sample. Validation experiments were conducted on melamine foams, and the results were compared with those obtained from the commercial B&K 4206 setup. The results obtained from the designed setup showed good agreement with those from the B&K 4206 system. The maximum error observed was 8% at 2800 Hz for the 30 mm diameter tube and 8.3% at 1600 Hz for the 100 mm diameter tube. Finally, the designed system was used to measure the sound absorption coefficients of textile materials with varying densities. The results obtained were consistent with the material properties, demonstrating the effectiveness of the designed setup.