Network Parameters Research Articles

Research on facial expression recognition algorithm based on improved MobileNetV3

Aiming at the problem that face images are easily interfered by occlusion factors in uncontrollable environments, and the complex structure of traditional convolutional neural networks leads to low expression recognition rates, slow network convergence speed, and long network training time, an improved lightweight convolutional neural network is proposed for facial expression recognition algorithm. First, the dilation convolution is introduced into the shortcut connection of the inverted residual structure in the MobileNetV3 network to expand the receptive field of the convolution kernel and reduce the loss of expression features. Then, the channel attention mechanism SENet in the network is replaced by the two-dimensional (channel and spatial) attention mechanism SimAM introduced without parameters to reduce the network parameters. Finally, in the normalization operation, the Batch Normalization of the backbone network is replaced with Group Normalization, which is stable at various batch sizes, to reduce errors caused by processing small batches of data. Experimental results on RaFD, FER2013, and FER2013Plus face expression data sets show that the network reduces the training times while maintaining network accuracy, improves network convergence speed, and has good convergence effects.

Shuffle-fusion pyramid network for bearing fault diagnosis under noisy environments

Abstract Recent advancements in deep learning have propelled the exploration of big data-driven fault diagnosis techniques. Nevertheless, traditional models often suffer from prohibitive computational demands, rendering them impractical for on-site deployment in rolling bearing fault diagnosis. To address this challenge, this paper introduces a novel lightweight fault diagnosis model with the pyramid architecture, named Shuffle-Fusion Pyramid Network (Shuffle-FPN). The model heralds several innovations: (1) A pyramid structure is designed to amalgamate fault signals across various scales, enlarging the network’s breadth and curtailing its depth. (2) Depth wise separable convolutions are adopted to streamline network parameters, thus achieving a lightweight model, and channel shuffling to ensure thorough information fusion across convolutional channels. (3) A global representation module is employed to offset the loss of global context, which accompanies increased convolutional depth. Collectively, these innovations enable Shuffle-FPN to extract nuanced fault features amidst noise and to operate on devices with limited memory, ensuring real-time fault diagnosis even in complex environments. Rigorous experiments on public datasets from Paderborn University (PU), supplemented by validations with our research group’s experiment data, reveal that Shuffle-FPN excels in fault identification under severe noise conditions and reduces memory footprint, which solidifies the superiority of Shuffle-FPN for practical fault diagnosis.

RSTC: Residual Swin Transformer Cascade to approximate Taylor expansion for image denoising

Traditional denoising methods establish mathematical models by employing different priors, which can achieve preferable results but they are usually time-consuming and their outputs are not adaptive on regularization parameters. While the success of end-to-end deep learning denoising strategies depends on a large amount of data and lacks a theoretical interpretability. In order to address the above problems, this paper proposes a novel image denoising method, namely Residual Swin Transformer Cascade (RSTC), based on Taylor expansion. The key procedures of our RSTC are specified as follows: Firstly, we discuss the relationship between image denoising model and Taylor expansion, as well as its adjacent derivative parts. Secondly, we use a lightweight deformable convolutional neural network to estimate the basic layer of Taylor expansion and a residual network where swin transformer block is selected as a backbone for pursuing the solution of the derivative layer. Finally, the results of the two networks contribute to the approximation solution of Taylor expansion. In the experiments, we firstly test and discuss the selection of network parameters to verify its effectiveness. Then, we compare it with existing advanced methods in terms of visualization and quantification, and the results show that our method has a powerful generalization ability and performs better than state-of-the-art denoising methods on performance improvement and structure preservation.

Learning-Based Super-Resolution Imaging of Turbulent Flames in Both Time and 3D Space Using Double GAN Architectures

This article presents a spatiotemporal super-resolution (SR) reconstruction model for two common flame types, a swirling and then a jet flame, using double generative adversarial network (GAN) architectures. The approach develops two sets of generator and discriminator networks to learn topographic and temporal features and infer high spatiotemporal resolution turbulent flame structure from supplied low-resolution counterparts at two time points. In this work, numerically simulated 3D turbulent swirling and jet flame structures were used as training data to update the model parameters of the GAN networks. The effectiveness of our model was then thoroughly evaluated in comparison to other traditional interpolation methods. An upscaling factor of 2 in space, which corresponded to an 8-fold increase in the total voxel number and a double time frame acceleration, was used to verify the model’s ability on a swirling flame. The results demonstrate that the assessment metrics, peak signal-to-noise ratio (PSNR), overall error (ER), and structural similarity index (SSIM), with average values of 35.27 dB, 1.7%, and 0.985, respectively, in the spatiotemporal SR results, can reach acceptable accuracy. As a second verification to highlight the present model’s potential universal applicability to flame data of diverse types and shapes, we applied the model to a turbulent jet flame and had equal success. This work provides a different method for acquiring high-resolution 3D structure and further boosting repeat rate, demonstrating the potential of deep learning technology for combustion diagnosis.

Ventricular segmentation algorithm for echocardiography based on transfer learning and GAN

With the swift progression of computer technology, utilizing deep learning for left ventricular image segmentation in echocardiography is of great significance for automated cardiac function assessment. In this study, a left ventricular segmentation algorithm for echocardiography based on transfer learning and generative adversarial networks (GAN) was proposed. A hierarchical fine-tuning strategy was employed to adaptively adjust network parameters, thereby improving segmentation accuracy. This strategy was based on combining multi-scale GAN and attention mechanisms to enhance segmentation performance, and incorporating the idea of transfer learning into the segmentation network. The algorithm demonstrated efficacy in heart image segmentation tasks, achieving high levels of classification accuracy and producing satisfactory segmentation outcomes. In terms of image segmentation of dual and four chamber images, this method achieved high Dice similarity coefficients and average intersection values. Furthermore, this method demonstrated excellent performance in image segmentation experiments on clinical data, with low average absolute errors in the calculated end diastolic volume, end systolic volume, and ejection fraction. The experimental results demonstrate that the algorithm exhibits satisfactory performance in left ventricular segmentation in echocardiography and is suitable for use in medical clinical data. The study presents a novel approach to ventricular segmentation in echocardiography, which enhances the precision and efficiency of automated cardiac function assessment and has significant clinical applicability.

Semi-supervised abdominal multi-organ segmentation by object-redrawing.

Multi-organ segmentation is a critical task in medical imaging, with wide-ranging applications in both clinical practice and research. Accurate delineation of organs from high-resolution 3D medical images, such as CT scans, is essential for radiation therapy planning, enhancing treatment outcomes, and minimizing radiation toxicity risks. Additionally, it plays a pivotal role in quantitative image analysis, supporting various medical research studies. Despite its significance, manual segmentation of multiple organs from 3D images is labor-intensive and prone to low reproducibility due to high interoperator variability. Recent advancements in deep learning have led to several automated segmentation methods, yet many rely heavily on labeled data and human anatomy expertise. In this study, our primary objective is to address the limitations of existing semi-supervised learning (SSL) methods for abdominal multi-organ segmentation. We aim to introduce a novel SSL approach that leverages unlabeled data to enhance the performance of deep neural networks in segmenting abdominal organs. Specifically, we propose a method that incorporates a redrawing network into the segmentation process to correct errors and improve accuracy. Our proposed method comprises three interconnected neural networks: a segmentation network for image segmentation, a teacher network for consistency regularization, and a redrawing network for object redrawing. During training, the segmentation network undergoes two rounds of optimization: basic training and readjustment. We adopt the Mean-Teacher model as our baseline SSL approach, utilizing labeled and unlabeled data. However, recognizing significant errors in abdominal multi-organ segmentation using this method alone, we introduce the redrawing network to generate redrawn images based on CT scans, preserving original anatomical information. Our approach is grounded in the generative process hypothesis, encompassing segmentation, drawing, and assembling stages. Correct segmentation is crucial for generating accurate images. In the basic training phase, the segmentation network is trained using both labeled and unlabeled data, incorporating consistency learning to ensure consistent predictions before and after perturbations. The readjustment phase focuses on reducing segmentation errors by optimizing the segmentation network parameters based on the differences between redrawn and original CT images. We evaluated our method using two publicly available datasets: the beyond the cranial vault (BTCV) segmentation dataset (training: 44, validation: 6) and the abdominal multi-organ segmentation (AMOS) challenge 2022 dataset (training:138, validation:16). Our results were compared with state-of-the-art SSL methods, including MT and dual-task consistency (DTC), using the Dice similarity coefficient (DSC) as an accuracy metric. On both datasets, our proposed SSL method consistently outperformed other methods, including supervised learning, achieving superior segmentation performance for various abdominal organs. These findings demonstrate the effectiveness of our approach, even with a limited number of labeled data. Our novel semi-supervised learning approach for abdominal multi-organ segmentation addresses the challenges associated with this task. By integrating a redrawing network and leveraging unlabeled data, we achieve remarkable improvements in accuracy. Our method demonstrates superior performance compared to existing SSL and supervised learning methods. This approach holds great promise in enhancing the precision and efficiency of multi-organ segmentation in medical imaging applications.

Trajectory Control of Quadrotors via Spiking Neural Networks

In this study, a novel control scheme based on spiking neural networks (SNNs) has been proposed to accomplish the trajectory tracking of quadrotor unmanned aerial vehicles (UAVs). The update rules for the network parameters have been derived using the Lyapunov stability theorem. Three different trajectories have been utilized in the simulated and experimental studies to verify the efficacy of the proposed control scheme. The acquired results have been compared with the responses obtained for proportional–integral–derivative (PID) and traditional neural network controllers. Simulated and experimental studies demonstrate that the proposed SNN-based controller is capable of providing better tracking accuracy and robust system response in the presence of disturbing factors.

An optimized ensemble model for predicting average localization error of wireless sensor networks

Wireless sensor networks (WSNs) are widely utilized in various applications due to their compact size, cost-effectiveness, and ease of deployment. Nonetheless, one of the biggest problems in WSNs is getting a reasonable estimate of the average location error of a node at the setup in the least amount of time. Wireless sensor networks can undergo changes over time due to various external and internal factors, such as environmental conditions, network congestion, hardware failures, or software updates. When these changes occur, the network may require redesigning, which can incur significant expenses. Traditional WSNs approaches, on the other hand, have been explicitly programmed, which makes it hard for networks to respond dynamically. Therefore, machine learning (ML) techniques can be used to respond appropriately in such scenarios. In this work, we proposed an optimized ML ensemble model for (i) identifying the critical network parameters for node localization when setting up wireless sensor networks with the accuracy needed in a short amount of time and (ii) predicting the average localization error of wireless sensor networks. We used the random forest algorithm with optimized hyperparameters from different optimization techniques to predict average localization error (ALE) using independent features like node density, anchor ratio, transmission range, and iterations.

A novel method for detecting cardiac arrhythmias in electrocardiogram signals using the ANFIS classifier

In general, ventricular repolarization instability with Premature Activations (PA) plays a significant role in the detection of arrhythmia using an electrocardiogram (ECG) signal. However, clinical detection of this instability is challenging. In this work, a unique technique for analyzing QT Interval (QTI) dynamics unreliability and other abnormalities in the ECG signal are utilized to detect ventricular tachycardia based on the identified anomalies. Further, a feature extraction method based on Chopped Displacement Gaussian (CDGa) is adopted and the features are retrieved from the CDGa signal and its size is reduced using Fisher Discrimination Analysis (FDA). Also, the results of the FDA are fed into the Adaptive Neuro-Fuzzy interference (ANFIS) classifier. The performance of the ANFIS classifier is enhanced in this study by integrating the Grasshopper optimization algorithm for optimizing network parameters. As a result, the values in the signals are predicted using an adaptive Least Mean Square (LMS)-based prediction algorithm, which is utilized to forecast the future status of VT-affected patients. Results indicate that the proposed work has an overall accuracy of 96 % which is higher than any other conventional methods. Also, the various additional performance criteria are tested, and it is demonstrated that the CDGa with adaptive LMS outperforms all previous approaches.

Analysis of the effectiveness of two different loss functions in training a neural network in lung image reconstruction using impedance tomography

The article presents research findings on developing a medical diagnostic system based on electrical impedance tomography technology. One of the key components of this project is developing a method for reconstructing the structure of human lungs using this technology. The authors of the article compared the effectiveness of two different loss functions in training a neural network, which is tasked with accurately replicating the lung structure based on electrical impedance tomography data. The researchers analyzed various approaches to calculating loss functions, including cosine embedding loss and InfoNCE loss. They compared the results obtained using these two functions to identify which one performs better in lung structure reconstruction. The findings of these studies may have significant implications for the development of diagnostic systems based on electrical impedance tomography and for improving the effectiveness of lung disease diagnosis. Additionally, the authors discuss potential future directions for the project, including possible applications of the research findings in clinical practice. Future research efforts may focus on optimizing neural network parameters, exploring alternative loss functions, or utilizing advanced machine learning techniques for even more precise lung structure reconstruction. The pursuit of improving such diagnostic systems could lead to significant advancements in the field of medicine, particularly in diagnosing and treating respiratory diseases.

Small-Sample Fault Diagnosis of Axial Piston Pumps across Working Conditions, Based on 1D-SENet Model Migration

Hydraulic pumps are the core components that provide power for hydraulic transmission systems, which are widely used in aerospace, marine engineering, and mechanical engineering, and their failure affects the normal operation of the entire system. This paper takes a single axial piston pump as the research object and proposes a small-sample fault diagnosis method based on the model migration strategy for the situation in which only a small number of training samples are available for axial piston pump fault diagnosis. To achieve end-to-end fault diagnosis, a 1D Squeeze-and-Excitation Networks (1D-SENets) model was constructed based on a one-dimensional convolutional neural network and combined with the channel domain attention mechanism. The model was first pre-trained with sufficient labeled fault data from the source conditions, and then, based on the model migration strategy, some of the underlying network parameters were fixed, and a small amount of labeled fault data from the target conditions was used to fine-tune the rest of the parameters of the pre-trained model. In this paper, the proposed method was validated using an axial piston pump fault dataset, and the experimental results show that the method can effectively improve the overfitting problem in the small sample fault diagnosis of axial piston pumps and improve the recognition accuracy.

YOLOv5s-BiPCNeXt, a Lightweight Model for Detecting Disease in Eggplant Leaves.

Ensuring the healthy growth of eggplants requires the precise detection of leaf diseases, which can significantly boost yield and economic income. Improving the efficiency of plant disease identification in natural scenes is currently a crucial issue. This study aims to provide an efficient detection method suitable for disease detection in natural scenes. A lightweight detection model, YOLOv5s-BiPCNeXt, is proposed. This model utilizes the MobileNeXt backbone to reduce network parameters and computational complexity and includes a lightweight C3-BiPC neck module. Additionally, a multi-scale cross-spatial attention mechanism (EMA) is integrated into the neck network, and the nearest neighbor interpolation algorithm is replaced with the content-aware feature recombination operator (CARAFE), enhancing the model's ability to perceive multidimensional information and extract multiscale disease features and improving the spatial resolution of the disease feature map. These improvements enhance the detection accuracy for eggplant leaves, effectively reducing missed and incorrect detections caused by complex backgrounds and improving the detection and localization of small lesions at the early stages of brown spot and powdery mildew diseases. Experimental results show that the YOLOv5s-BiPCNeXt model achieves an average precision (AP) of 94.9% for brown spot disease, 95.0% for powdery mildew, and 99.5% for healthy leaves. Deployed on a Jetson Orin Nano edge detection device, the model attains an average recognition speed of 26 FPS (Frame Per Second), meeting real-time requirements. Compared to other algorithms, YOLOv5s-BiPCNeXt demonstrates superior overall performance, accurately detecting plant diseases under natural conditions and offering valuable technical support for the prevention and treatment of eggplant leaf diseases.

A method for extracting buildings from remote sensing images based on 3DJA-UNet3+

Building extraction aims to extract building pixels from remote sensing imagery, which plays a significant role in urban planning, dynamic urban monitoring, and many other applications. UNet3+ is widely applied in building extraction from remote sensing images. However, it still faces issues such as low segmentation accuracy, imprecise boundary delineation, and the complexity of network models. Therefore, based on the UNet3+ model, this paper proposes a 3D Joint Attention (3DJA) module that effectively enhances the correlation between local and global features, obtaining more accurate object semantic information and enhancing feature representation. The 3DJA module models semantic interdependence in the vertical and horizontal dimensions to obtain feature map spatial encoding information, as well as in the channel dimensions to increase the correlation between dependent channel graphs. In addition, a bottleneck module is constructed to reduce the number of network parameters and improve model training efficiency. Many experiments are conducted on publicly accessible WHU,INRIA and Massachusetts building dataset, and the benchmarks, BOMSC-Net, CVNet, SCA-Net, SPCL-Net, ACMFNet, MFCF-Net models are selected for comparison with the 3DJA-UNet3+ model proposed in this paper. The experimental results show that 3DJA-UNet3+ achieves competitive results in three evaluation indicators: overall accuracy, mean intersection over union, and F1-score. The code will be available at https://github.com/EnjiLi/3DJA-UNet3Plus.

YOLO-FD: An accurate fish disease detection method based on multi-task learning

Fish diseases often exhibit high risks of contagion, resulting in substantial economic losses. Accurate assessment of fish disease severity during diagnosis using deep learning poses a considerable challenge. Currently, deep learning models mainly focus on single tasks in fish disease detection, such as classification, object detection and segmentation. However, the accurate assessment of fish disease severity requires the integration of multiple dimensions of information, which is beyond the capabilities of traditional single-task methods. Therefore, this paper proposes YOLO-FD, a multi-task learning network specifically designed for simultaneous detection and segmentation. YOLO-FD extends the YOLOv8 backbone by integrating a novel semantic segmentation branch dedicated to precisely segmenting infected areas in diseased fish, while retaining the original object detection branch for identifying infected fish. Weight uncertainty and PCGrad are employed to balance the weights of different losses and to optimize conflicting gradients during the training process. With only a negligible increase in network parameters, YOLO-FD, tested on our constructed Nocardiosis fish dataset, achieves a detection accuracy of 94.2% mAP50 and gets mIOU of 79.4%, showcasing a 0.5% improvement over the baseline YOLOv8 and surpassing the state-of-the-art semantic segmentation network Deeplabv3plus by 4%. Notably, compared to the adapted multi-task network YOLOP, YOLO-FD demonstrates substantial improvements, displaying a 13.7% increase in mAP50-95 and a 15.1% boost in mIOU. On the VOC2012 segmentation dataset, the proposed method exhibits a 3.2% increase in mAP50 and a 2.2% rise in mAP50-95 compared to the baseline. Furthermore, results of the ablation experiment validate the effectiveness and generalization of the proposed multi-task learning approach. Source code is available at https://github.com/feifei-Lee/YOLO-FD.

Generation and Analysis of a Dataset of Optimal Double-Loop Circulant Networks

Optimal circulant networks are of practical interest as graph models of reliable communication networks for supercomputer systems and networks on a chip. A large dataset of parameters of optimal double-loop circulant networks with a number of nodes of up to 50,000 and 451,000 points has been constructed. The dataset contains, for each number of vertices, all generators corresponding to optimal or suboptimal (in the absence of optimal) descriptions of the graph. This made it possible to find analytical dependencies of the parameters that define families of optimal graphs. Based on the analysis of the constructed dataset, the solution to the problem of determining optimal two-dimensional circulant networks is studied. A process is automated for determining analytical, parametric descriptions of the families of optimal double-loop networks, described polynomials of diameter. Having applied the methods of integrating differential evolution and reduced local search to the analysis of the generated dataset, we rediscovered a number of previously known families and found more than 200 new, different from all those known in literature, families of optimal double-loop networks with generators of linear and quadratic types of polynomials. Our new ap­proach can be applied to studing datasets of other promising classes of graphs and networks.

Research on risk assessment of coal and gas outburst during continuous excavation cycle of coal mine with dynamic probabilistic inference

Coal and gas outbursts are a major dynamic hazard in underground coal mining, and predicting these events is challenging due to their complex mechanisms. This study introduces an advanced multistate dynamic probabilistic system designed to evaluate the risk of outbursts prior to each excavation cycle. Through the development of a Bayesian network (BN), we establish a dynamic model that captures the complex interactions among essential variables. The novel integration of time slices facilitates the continuous assessment across successive mining cycles. This study tackles the challenge of maintaining network parameter reliability in the static prediction conditions of outburst-prone coal mines. Specifically, in order to overcome the asynchronism of all variables testing process, the expert knowledge integration of expectation-maximization parameter learning and fuzzy set theory (FST) is built inside the system. Finally, we present a case study illustrating the application of this system across fifty-one consecutive cycles, with regular updates to variable states, showcasing the enhanced predictive capability of Dynamic Bayesian Networks (DBN) over traditional BNs for ongoing risk evaluation in mining operations. Additionally, by integrating backward diagnosis with sensitivity analysis, our approach simplifies the identification of key risk factors, offering valuable insights for improving outburst prevention measures and ensuring the safety of coal mining activities.

An Efficient and Accurate Quality Inspection Model for Steel Scraps Based on Dense Small-Target Detection

Scrap steel serves as the primary alternative raw material to iron ore, exerting a significant impact on production costs for steel enterprises. With the annual growth in scrap resources, concerns regarding traditional manual inspection methods, including issues of fairness and safety, gain increasing prominence. Enhancing scrap inspection processes through digital technology is imperative. In response to these concerns, we developed CNIL-Net, a scrap-quality inspection network model based on object detection, and trained and validated it using images obtained during the scrap inspection process. Initially, we deployed a multi-camera integrated system at a steel plant for acquiring scrap images of diverse types, which were subsequently annotated and employed for constructing an enhanced scrap dataset. Then, we enhanced the YOLOv5 model to improve the detection of small-target scraps in inspection scenarios. This was achieved by adding a small-object detection layer (P2) and streamlining the model through the removal of detection layer P5, resulting in the development of a novel three-layer detection network structure termed the Improved Layer (IL) model. A Coordinate Attention mechanism was incorporated into the network to dynamically learn feature weights from various positions, thereby improving the discernment of scrap features. Substituting the traditional non-maximum suppression algorithm (NMS) with Soft-NMS enhanced detection accuracy in dense and overlapping scrap scenarios, thereby mitigating instances of missed detections. Finally, the model underwent training and validation utilizing the augmented dataset of scraps. Throughout this phase, assessments encompassed metrics like mAP, number of network layers, parameters, and inference duration. Experimental findings illustrate that the developed CNIL-Net scrap-quality inspection network model boosted the average precision across all categories from 88.8% to 96.5%. Compared to manual inspection, it demonstrates notable advantages in accuracy and detection speed, rendering it well suited for real-world deployment and addressing issues in scrap inspection like real-time processing and fairness.

Performance investigation of channel estimation for intelligent reflecting surface assisted wireless communications using neural network

Intelligent reflecting surface (IRS), in which a large number of tunable reflective elements are employed, can enhance the wireless propagation environment in an acceptable manner. Although this issue is operated via intelligently reflecting the electromagnetic waves from the base-station (BS) toward the users, the optimal tuning of the phase shifters at the IRS is arduous. In other words, the passive nature of reflective elements causes some challenges in direct measuring the channels between the IRS, the BS and the users. Even though the conventional methods first estimate the channels and then optimize the system parameters, this paper utilizes an artificial intelligence procedure in which channel estimation has been carried out considering the levenberg-marquardt training algorithm. This is attained via performing some initial processes and trained and estimated each part at different neural network architectures. The estimated output of the system can be expressed via parameters of artificial neural networks which is an important stage for channel estimation. The aforesaid technique is not only making full use of the learning property of neural network, but also by applying this method, there is no need of any matrix computation and the proposed technique is less complex than the traditional pilot-based techniques. Simulation results demonstrate that the offered technique exhibits premiere performance in comparison with conventional common methods.

Machine Learning-based Prediction of Cattle Body Weight Using Muzzle Morphometrics

Body weight measurement of cattle is a tedious farm operation but is essential for their health maintenance at farm. This study proposes a novel and easier approach for cattle body weight prediction using muzzle morphometrics. Vrindavani crossbred cattle of different age groups were considered for the study. The muzzle images were collected and analyzed in MATLAB for determination of muzzle dimensions followed by mapping the dimensions to the body weight of the cattle using artificial neural network with varying network parameters. The results of the showed that all muzzle parameters had good correlation with the body weight of the cattle. Further, it was also observed that the combination of Levenberg-Marquardt training algorithm with logsigmoidal transfer function performed the best with model simulation accuracy of 78.07%. The study concludes that muzzle morphometrics may be used for body weight measurements, however, newer or diverse muzzle parameters may be considered in future works to further improve the model accuracy for a more practical application.

Tillage Practices Effect on Root Distribution and Variation of Soil CO2 Emission under Different Cropping Strategies

Conservation soil management strategies, particularly no-tillage and cropping strategies, have become an effective and widely adopted practice that has a direct influence on root parameters and mitigation of greenhouse gasses. However, the effect of different tillage and cropping strategies on root growth in field conditions is rarely studied. The study aimed to quantify and characterise the relationship between root network development and CO2 emission and how these parameters are affected by different cropping and tillage strategies. Five different crop rotations were tested, with or without the inclusion of catch crops (CC), by growing them in the soil where different tillage practices were applied. Selected cropping strategies differed among themselves in terms of the frequency of CC grown per rotation. The data revealed that in NT treatments, the CO2 emission (both autotrophic and heterotrophic simultaneously) was 25% higher than in CT. The cropping strategies were identified as an important factor influencing CO2 emissions. An increase in CO2 emission varied between 30 and 35% depending on the share of legume and CC inclusion. The frequency of CC grown per rotation has had an effect on the rate of CO2 emission. The cropping strategy when CC was grown every year showed the lowest amount of CO2 (by 26%), while in other cropping strategies, when CC was grown once or twice per rotation, significantly higher CO2 emissions were observed. Root growth and their development were significantly affected (p < 0.05) by soil depth and cropping strategies concerning root length and root volume changes. The inclusion of CC into the rotations led towards a decrease in root volume (by 21%). Root length (R2 = 0.45; p < 0.05) and root volume (R2 = 0.82; p < 0.05) had a significant impact on soil CO2 emissions. The results collected from 2021 to 2023 experiments indicated that cropping strategies and CC management areas are important tools not only for the improvement of root parameters but also for understanding how they affect CO2 emissions. The main message for stakeholders is that the cropping strategies diversification with the inclusion of CC every year in a winter oil-seed rape, spring wheat and pea crop rotation (R/W/P + CC) had demonstrated the possibilities to reduce CO2 emission and improve the root network parameters as compared to the monoculture strategy.