Enhancing fairness in deep learning: key tasks, measurement methods, and experimental validation

Purpose In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Design/methodology/approach In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Findings In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Originality/value In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.

Health state estimation of cutting tools is a key component for maintaining the reliability and stability of the manufacturing process. Although deep learning (DL) based tool wear indirect monitoring methods have been presented, most of them require a substantial amount of data to avoid high misclassification rates. To this end, this article proposes a novel estimation approach based on data-enhanced deep transfer learning (TL) methodology, which integrates multivariate data enhancements, deep convolution network, and generative adversarial learning for state assessment of the tool wear under small sample size. The proposed method includes three innovative points: 1) a multi-step data enhancement method is employed to augment the wavelet scalogram data as model input; 2) a novel training process is adopted to obtain optimal hyperparameters of TL-AlexNet and TL-VGGNet-16 model; 3) a deep transfer learning model for the enhanced data is presented to adaptively estimate the health state of the cutting tools. The proposed approach only requires a small quantity of data to achieve satisfactory estimation performance compared with other DL methods through experimental validation, and the average prediction accuracy for each stage is greater than 95%, which demonstrates the effectiveness and superiority of the presented model.

Image restoration is a key task in the field of computer vision, which aims to recover high-quality clear images from degraded images. Degraded images may be produced for various reasons, such as noise, blurring, compression, etc. In recent years, the rapid development of deep learning technology has brought new breakthroughs in the field of image restoration, and various image restoration methods based on deep learning continue to emerge, and their performance is better than the previous GAN-based methods. Nevertheless, comprehensive and enlightening reviews of image restoration based on diffusion models are still scarce. This paper summarizes the latest research progress in image restoration in recent years, including cue learning, model scaling, generative prior, state space model, basic model and so on, and compares and analyzes their experimental results. Although the image restoration methods based on deep learning have achieved remarkable progress, there are still some challenges. Therefore, this paper analyzes the challenges in the field of image restoration and looks forward to the future research direction.

In the task of music genre classification, feature extraction and classifier modeling are the two key parts that directly affect the classification accuracy. In the traditional classification method, the feature extraction and classification processes are designed separately. First, the features are extracted manually from the original music signal, and then a reasonable classifier is selected to build a model and classify the extracted features. Although the traditional methods have achieved good results in many classification tasks, the feature extraction process is complex and difficult to achieve, and the features required for different classification tasks need to be specially designed, and the extracted features lack of universality. With the successful application and continuous development of deep learning models in other fields, more and more studies begin to use music spectra as the input of deep learning models to classify music genres. However, so far, the accuracy of existing classification methods based on deep learning is not ideal, so this paper mainly studies a classification method based on deep learning to improve the classification accuracy of music genre classification model. In this paper, a parallel structured deep attention classification model is proposed. By training BRNN, it can automatically learn music features from samples. The linear attention model calculates the attention probability distribution on this feature according to the learned features, and reassigns it to the feature representation. Finally, the classification is realized according to the eigenvectors with different weights. Besides the linear attention model with simple structure, a CNN attention model with stronger learning ability is also designed. In order to verify the feasibility and validity of the model, validation experiments were conducted on two standard datasets, GTZAN and Extended Ballroom. The experimental results show that the classification model based on deep parallel attention mechanism has good classification robustness, and the accuracy of classification based on BRNN and parallel CNN attention model reaches 92.7% on Extended Ballroom data set, which is better than the existing classification method based on deep learning. The validity and feasibility of the classification model are proved.

Dysarthria is a motor speech disorder resulting from impaired control of the muscles involved in speech, such as the tongue and lips. This condition affects the coordination, strength, or movement of these muscles, leading to reduced clarity, naturalness, and intelligibility in verbal communication. In recent years, deep learning (DL) techniques have become prominent in medical diagnostics, including the detection of speech disorders. DL offers robust tools for the automated analysis of speech signals, enabling earlier and more accurate identification of conditions such as dysarthria. In this study, a novel framework called EDSDCSI-DLHHS (Early Detection of Speech Disorders in Children with Speech Impairments using Deep Learning and Hybrid Heuristic Search Algorithms) is proposed. The framework combines deep learning (DL) with advanced optimization methods to enhance diagnostic accuracy. Initially, speech recordings are preprocessed to reduce noise. Then, linear prediction coding is used to extract significant speech features. A graph attention network is employed for classifying speech disorders, and its hyperparameters are fine-tuned using a hybrid optimization model combining Siberian Tiger and Sand Cat Swarm Optimization. Experimental validation using a benchmark dataset shows that the proposed model achieves 99.00% accuracy, outperforming existing approaches in detecting dysarthria in children. This framework supports early intervention and personalized treatment planning.

Small data, big challenges: Machine- and deep-learning strategies for data-limited drug discovery.

The application area of unmanned aerial vehicles increases significantly recent years due to progress in hardware and algorithms for data acquisition and processing. Object detection and classification (recognition) in imagery acquired by unmanned aerial vehicle are the key tasks for many applications, and usually in practice an operator solves these tasks. Growing amount of data of different types and of different nature provides the possibility for deep machine learning which nowadays shows high level results for object detection and recognition. Two key problems are to be solved for applying deep learning for object recognition task when dealing with multi-spectral imagery: (a) availability of representative dataset for neural network training and testing and (b) effective way of multi-spectral data fusion during neural network training. The paper proposes the approaches for solving these problems. For creating a representative dataset synthetic infra-red images are generated using several real infra-red images and 3D model of a given object. An technique for realistic infra-red texturing based on accurate infra-red image exterior orientation and 3D model pose estimation is developed. It allows in automated mode to produce datasets of required volume for deep learning and automatically generate ground truth data for neural network training and testing. Two approaches for multi-spectral data fusion for object recognition are developed and evaluated: data level fusion and results level fusion. The results of the evaluation of both techniques on generated multi-spectral dataset are presented and discussed.

Background: The parallel mechanism plays an important role in various fields. The multifunctional integrated innovation experiment platform can improve the utilization rate of the mechanism and be applied in many fields. Objective: The main objective of the study is to establish an integrated innovation experiment platform based on the 3-PRS parallel mechanism, which can be used in typical application and related technology development. Methods: The integrated innovation experiment platform is established and analyzed based on the 3-PRS parallel mechanism. According to the 3D model of the experiment platform, the kinematics and dynamics are analyzed. The force/position control strategy of the system is adopted. According to the function of the experiment platform, two kinds of application and the position and pose measurement technology are developed. The experiment platform is developed by the following methods: (1) The XY table is set up on the fixing platform of the 3-PRS parallel mechanism, so that the mechanism has five degrees of freedom, and the many kinds of workpiece can be easily processed. (2) By selecting the impedance parameter, the experiment platform can realize the compliant control of plantar flexion/dorsiflexion and varus/eversion simultaneously. (3) The binocular vision position and pose measurement method is used to obtain the marked images of the experiment platform through dual cameras, and the position and pose is obtained through image processing, 3D reconstruction and stereo matching, etc. (4) The position and pose detection based on deep learning is divided into two parts: one is to detect the slider height using the regression Convolutional Neural Network (CNN); the other is to compute the position and pose using the Back Propagation Neural Network (BPNN). Results: The experiment results show that the function of the 3-PRS parallel mechanism integrated innovation experiment platform can be effectively realized. The position and pose can be accurately measured in real time using the proposed two measurement methods. The impedance parameters are selected to achieve the rehabilitation training function of the 3-PRS ankle rehabilitation robot and the characters are processed to verify the function of the 3-PRS-XY series-parallel machine tool. Conclusion: The integrated innovation experiment platform based on the 3-PRS parallel mechanism can achieve the function of mechanical processing and rehabilitation training, and can also measure the state of motion in real time through machine vision and deep learning.

An increased posterior tibial slope (PTS) corresponds with an increased risk of graft failure after anterior cruciate ligament (ACL) reconstruction (ACLR). Validated methods of manual PTS measurements are subject to potential interobserver variability and can be inefficient on large datasets. To develop a deep learning artificial intelligence technique for automated PTS measurement from standard lateral knee radiographs. It was hypothesized that this deep learning tool would be able to measure the PTS on a high volume of radiographs expeditiously and that these measurements would be similar to previously validated manual measurements. Cohort study (diagnosis); Level of evidence, 2. A deep learning U-Net model was developed on a cohort of 300 postoperative short-leg lateral radiographs from patients who underwent ACLR to segment the tibial shaft, tibial joint surface, and tibial tuberosity. The model was trained via a random split after an 80 to 20 train-validation scheme. Masks for training images were manually segmented, and the model was trained for 400 epochs. An image processing pipeline was then deployed to annotate and measure the PTS using the predicted segmentation masks. Finally, the performance of this combined pipeline was compared with human measurements performed by 2 study personnel using a previously validated manual technique for measuring the PTS on short-leg lateral radiographs on an independent test set consisting of both pre- and postoperative images. The U-Net semantic segmentation model achieved a mean Dice similarity coefficient of 0.885 on the validation cohort. The mean difference between the human-made and computer-vision measurements was 1.92° (σ = 2.81° [P = .24]). Extreme disagreements between the human and machine measurements, as defined by ≥5° differences, occurred <5% of the time. The model was incorporated into a web-based digital application front-end for demonstration purposes, which can measure a single uploaded image in Portable Network Graphics format in a mean time of 5 seconds. We developed an efficient and reliable deep learning computer vision algorithm to automate the PTS measurement on short-leg lateral knee radiographs. This tool, which demonstrated good agreement with human annotations, represents an effective clinical adjunct for measuring the PTS as part of the preoperative assessment of patients with ACL injuries.

Along with the popularity of intelligent services and mobile services, service recommendation has become a key task, especially the task based on quality-of-service (QoS) in edge computing environment. Most existing service recommendation methods have some serious defects, and cannot be directly adopted in edge computing environment. For example, most of existing methods cannot learn deep features of users or services, but in edge computing environment, there are a variety of devices with different configurations and different functions, and it is necessary to learn deep features behind those complex devices. In order to fully utilize hidden features, this paper proposes a new matrix factorization (MF) model with deep features learning, which integrates a convolutional neural network (CNN). The proposed mode is named Joint CNN-MF (JCM). JCM is capable of using the learned deep latent features of neighbors to infer the features of a user or a service. Meanwhile, to improve the accuracy of neighbors selection, the proposed model contains a novel similarity computation method. CNN learns the neighbors features, forms a feature matrix and infers the features of the target user or target service. We conducted experiments on a real-world service dataset under a batch of cases of data densities, to reflect the complex invocation cases in edge computing environment. The experimental results verify that compared to counterpart methods, our method can consistently achieve higher QoS prediction results.

EVlncRNA-net: A dual-channel deep learning approach for accurate prediction of experimentally validated lncRNAs.

As in other areas of medical image analysis, e.g. semantic segmentation, deep learning is currently driving the development of new approaches for image registration. Multi-scale encoder-decoder network architectures achieve state-of-the-art accuracy on tasks such as intra-patient alignment of abdominal CT or brain MRI registration, especially when additional supervision, such as anatomical labels, is available. The success of these methods relies to a large extent on the outstanding ability of deep CNNs to extract descriptive visual features from the input images. In contrast to conventional methods, the explicit inclusion of geometric information plays only a minor role, if at all. In this work we take a look at an exactly opposite approach by investigating a deep learning framework for registration based solely on geometric features and optimisation. We combine graph convolutions with loopy belief message passing to enable highly accurate 3D point cloud registration. Our experimental validation is conducted on complex key-point graphs of inner lung structures, strongly outperforming dense encoder-decoder networks and other point set registration methods. Our code is publicly available at https://github.com/multimodallearning/deep-geo-reg .

Gestures are necessary and indispensable in people’s ordinary life communication. And gestures have become an important part of human-computer interaction. With the gradual maturity of human-computer interaction systems, the role of gestures in human-computer interaction is becoming more and more important. Due to the variety of gestures in practical use, coupled with factors such as environment and light changes, it makes it very difficult for computers to recognize the correct gestures from image information. Deep learning has achieved certain research results through several years of development, which provides new research ideas for gesture recognition. This paper firstly introduces the common methods and processes of gesture recognition, and then proposes a new convolutional neural network structure by studying convolutional neural networks and adding Inception structure to the network to improve the performance of the network. Finally, experimental validation is conducted, and the experimental results show that the new convolutional neural network achieves an average recognition rate of 97.8% on the test set, which is a good result.

Simple SummaryNon-invasive temperature monitoring during hyperthermia cancer treatment is of paramount importance. It allows physicians to verify the therapeutic temperature is reached in the treated area. Currently, only superficial or invasive thermometry is performed on a clinical level. Magnetic resonance thermometry has been proposed as a a non-invasive alternative but its applicability is limited. Conversely, microwave imaging based thermometry is a potential low cost candidate for non-invasive temperature monitoring. This works presents a computational study in which the use of deep learning is proposed to face the challenges related to the use of microwave imaging in hyperthermia monitoring.The paper deals with the problem of monitoring temperature during hyperthermia treatments in the whole domain of interest. In particular, a physics-assisted deep learning computational framework is proposed to provide an objective assessment of the temperature in the target tissue to be treated and in the healthy one to be preserved, based on the measurements performed by a microwave imaging device. The proposed concept is assessed in-silico for the case of neck tumors achieving an accuracy above 90%. The paper results show the potential of the proposed approach and support further studies aimed at its experimental validation.

This study presents what we believe to be a novel trace gas sensor integrating a rollar-type resonator photoacoustic spectroscopy (PAS) system with a nested U-shaped deep learning network (U-Net++) to achieve high sensitivity, noise suppression, and long-term stability. The rollar-type acoustic resonator, optimized via finite element simulations, amplifies photoacoustic signals by 21% compared to conventional cylindrical designs, with a resonance frequency of 1040 Hz and a quality factor of 80. The U-Net++ architecture, featuring nested skip pathways and deep supervision, dynamically processes spectral data to suppress noise, achieving a three-orders-of-magnitude reduction in standard deviation (12.91 ppm to 0.0138 ppm) for methane (CH4) measurements. Allan variance analysis demonstrates enhanced stability, with a minimum detectable concentration (MDC) improving from 1.41 ppm to 0.173 ppb, corresponding to an enhancement factor of over 8100. Experimental validation across varying CH4 concentrations (5-30 ppm) confirms significant signal-to-noise ratio (SNR) improvements (e.g., 5.5 to 293.3 at 5 ppm) and reduced variability, highlighting the sensor's precision and robustness. This work advances PAS technology by synergizing an optimized resonator design with deep learning, enabling high-precision gas detection for environmental monitoring, industrial safety, and medical diagnostics.