Number Of Complexity Research Articles

Application of Improved YOLOv8n-seg in Crayfish Trunk Segmentation

The crayfish industry (Procambarus clarkii) is experiencing rapid growth. However, the processing sector continues to face challenges due to a lack of advanced automation, relying heavily on manual visual inspection to assess crayfish specifications and integrity, which limits efficiency and precision in decision-making. To address the issue of intelligent grading of P. clarkii, this work proposes the GHB-YOLOv8-seg algorithm for segmenting the main trunk of P. clarkii shrimp based on the YOLOv8n-seg model. The original main trunk network is replaced through the coupling of Ghost and HGNetV2, and depth-separable convolution is employed to perform the linear transformation of the features. This results in a reduction in the number of parameters and computational complexity while maintaining high accuracy. The computational complexity is reduced; concurrently, introducing the weighted bidirectional feature pyramid network (BiFPN) enables the model to perform multi-scale feature fusion with greater alacrity, thereby enhancing the model’s performance. Ultimately, the intelligent grading of crayfish specifications was achieved by calculating the pixel area after segmentation and converting it to the actual body weight. The results demonstrated that the number of parameters of the improved YOLOv8n-seg model was reduced by 60.5%, the model size was reduced by 55.4%, and the mAP value was increased from 98.9% to 99.2%. The study indicates that the YOLOv8n-seg algorithm model facilitates precise and lightweight segmentation of the crayfish trunk, which can be integrated into diverse mobile devices.

Exploring user engagement behavior with short-form video advertising on short-form video platforms: a visual-audio perspective

PurposeShort-form video advertisements have recently gained popularity and are widely used. However, creating attractive short video advertisements remains a challenge for sellers. Based on the visual-audio perspective and signaling theory, this study investigated the impacts of three visual features (number of shots, pixel-level image complexity and vertical versus horizontal formats) and two audio features (speech rate and average spectral centroid) on user engagement behavior.Design/methodology/approachWe conducted a field study on TikTok. To test our various hypotheses, we used regression analysis on 2,511 videos containing product promotion information posted by 60 sellers between January 1, 2020 and November 20, 2021.FindingsFor visual variables, the number of shots and pixel-level image complexity were found to have nonlinear (inverted U-shaped) relationships with user engagement behavior. The vertical video form was found to have a positive effect on comments and shares. In the case of audio variables, speech rate was found to have a significant positive effect on shares but not on likes and comments. The average spectral centroid was found to have significant negative influences on likes and comments.Practical implicationsThis study provides specific suggestions for sellers who create short-form videos to improve user engagement behavior.Originality/valueThis study contributes to the literature on short-form video advertising by extending the potential drivers of user engagement behavior. Additionally, from a methodological perspective, it contributes to the literature by using computer vision and speech-processing techniques to analyze user behavior in a video-related context, effectively overcoming the limitations of the widely adopted survey method.

Lightweight real-time vehicle collision warning based on deep learning multi-scale feature fusion

With the widespread application of deep learning technology in the field of intelligent driving, machine vision has become the preferred technology for vehicle detection tasks. However, high-precision object detection often involves a large number of parameters and significant computational complexity, making algorithm deployment challenging and hindering real-time system response. This study adopts the lightweight detection model YOLOv8n as the foundational framework, optimizing it to develop BiFCNet-YOLOv8, which aims to balance detection accuracy with computational efficiency for in-vehicle system deployment. In our research, the more efficient Bi-FPN replaces the traditional PANet, enhancing feature interactions across different scales through bidirectional pathways. Additionally, the CBAM attention mechanism is incorporated between the Neck and Head layers to further refine information and enhance local feature representation. Comparative experiments show that the improved model increases Precision by 1.71% and mAP0.5:0.95 by 3.23%, with a parameter growth of only 6.43M and a FLOPS increase of only 15.83B. The detection algorithm integrates TTC and DeepSORT to enhance the driving warning function. Road tests confirm that this algorithm can effectively and accurately detect the position of the vehicle ahead. In simulation tests, key parameters such as relative speed and longitudinal acceleration meet the requirements for collision warning systems. This study provides a lightweight and efficient detection algorithm solution for vehicle collision warning tasks.

Research on Deep Learning Model Enhancements for PCB Surface Defect Detection

With the miniaturization and increasing complexity of electronic devices, the accuracy and efficiency of printed circuit board (PCB) defect detection are crucial to ensuring product quality. To address the issues of small defect sizes and high missed detection rates in PCB surface inspection, this paper proposes an enhanced YOLOv8s model which not only improves detection performance but also achieves a lightweight design. Firstly, the Nexus Attention module is introduced, which organically integrates multiple attention mechanisms to further enhance feature extraction and fusion capabilities, improving the model’s learning and generalization performance. Secondly, an improved CGFPN network is designed to optimize multi-scale feature fusion, significantly boosting the detection of small objects. Additionally, the WaveletUnPool module is incorporated, leveraging wavelet transform technology to refine the upsampling process, accurately restoring detailed information and improving small-object detection in complex backgrounds. Lastly, the C2f-GDConv module replaces the traditional C2f module, reducing the number of model parameters and computational complexity while maintaining feature extraction efficiency. Comparative experiments on a public PCB dataset demonstrate that the enhanced model achieved a mean average precision (mAP) of 97.3% in PCB defect detection tasks, representing a 3.0% improvement over the original model, while reducing Giga Floating Point Operations (GFLOPs) by 26.8%. These enhancements make the model more practical and adaptable for industrial applications, providing a solid foundation for future research.

ILDIM-MFAM: interstitial lung disease identification model with multi-modal fusion attention mechanism.

This study aims to address the potential and challenges of multimodal medical information in the diagnosis of interstitial lung disease (ILD) by developing an ILD identification model (ILDIM) based on the multimodal fusion attention mechanism (MFAM) to improve the accuracy and reliability of ILD. Large-scale multimodal medical information data, including chest CT image slices, physiological indicator time series data, and patient history text information were collected. These data are professionally cleaned and normalized to ensure data quality and consistency. Convolutional Neural Network (CNN) is used to extract CT image features, Bidirectional Long Short-Term Memory Network (Bi-LSTM) model is used to learn temporal physiological metrics data under long-term dependency, and Self-Attention Mechanism is used to encode textual semantic information in patient's self-reporting and medical prescriptions. In addition, the multimodal perception mechanism uses a Transformer-based model to improve the diagnostic performance of ILD by learning the importance weights of each modality's data to optimally fuse the different modalities. Finally, the ablation test and comparison results show that the model performs well in terms of comprehensive performance. By combining multimodal data sources, the model not only improved the Precision, Recall and F1 score, but also significantly increased the AUC value. This suggests that the combined use of different modal information can provide a more comprehensive assessment of a patient's health status, thereby improving the diagnostic comprehensiveness and accuracy of ILD. This study also considered the computational complexity of the model, and the results show that ILDIM-MFAM has a relatively low number of model parameters and computational complexity, which is very favorable for practical deployment and operational efficiency.

Application of artificial intelligence in VSD prenatal diagnosis from fetal heart ultrasound images

BackgroundDeveloping a combined artificial intelligence (AI) and ultrasound imaging to provide an accurate, objective, and efficient adjunctive diagnostic approach for fetal heart ventricular septal defects (VSD).Methods1,451 fetal heart ultrasound images from 500 pregnant women were comprehensively analyzed between January 2016 and June 2022. The fetal heart region was manually labeled and the presence of VSD was discriminated by experts. The principle of five-fold cross-validation was followed in the training set to develop the AI model to assist in the diagnosis of VSD. The model was evaluated in the test set using metrics such as mAP@0.5, precision, recall, and F1 score. The diagnostic accuracy and inference time were also compared with junior doctors, intermediate doctors, and senior doctors.ResultsThe mAP@0.5, precision, recall, and F1 scores for the AI model diagnosis of VSD were 0.926, 0.879, 0.873, and 0.88, respectively. The accuracy of junior doctors and intermediate doctors improved by 6.7% and 2.8%, respectively, with the assistance of this system.ConclusionsThis study reports an AI-assisted diagnostic method for VSD that has a high agreement with manual recognition. It also has a low number of parameters and computational complexity, which can also improve the diagnostic accuracy and speed of some physicians for VSD.

Multiple feature selection based on an optimization strategy for causal analysis of health data

PurposeRecent advancements in information technology and wearable devices have revolutionized healthcare through health data analysis. Identifying significant relationships in complex health data enhances healthcare and public health strategies. In health analytics, causal graphs are important for investigating the relationships among health features. However, they face challenges owing to the large number of features, complexity, and computational demands. Feature selection methods are useful for addressing these challenges. In this paper, we present a framework for multiple feature selection based on an optimization strategy for causal analysis of health data.MethodsWe select multiple health features based on an optimization strategy. First, we define a Weighted Total Score (WTS) index to assess the feature importance after the combination of different feature selection methods. To explore an optimal set of weights for each method, we design a multiple feature selection algorithm integrated with the greedy algorithm. The features are then ranked according to their WTS, enabling selection of the most important ones. After that, causal graphs are constructed based on the selected features, and the statistical significance of the paths is assessed. Furthermore, evaluation experiments are conducted on an experiment dataset collected for this study and an open dataset for diabetes.ResultsThe results demonstrate that our approach outperforms baseline models by reducing the number of features while improving model performance. Moreover, the statistical significance of the relationships between features uncovered through causal graphs is validated for both datasets.ConclusionBy using the proposed framework for multiple feature selection based on an optimization strategy for causal analysis, the number of features is reduced and the causal relationships are uncovered and validated.

Signal modulation waveform recognition method based on STF-Net

Signal modulation waveform recognition is one of the key technologies in the field of spatial spectrum cognition and an important means to realize the monitoring and control of spectrum resources of low-orbit satellites. In view of the problems of large number of parameters and high computational complexity in the current modulation waveform recognition methods based on deep learning, a lightweight signal modulation waveform recognition method based on space-time fusion network (STF-Net) is proposed. The signal is preprocessed into dual-channel data in the form of time domain and frequency domain, and the signal spatial features are extracted and feature redundancy is reduced by convolutional neural network (CNN). Then, the long short-term memory network (LSTM) is used to extract the timing information and output the recognition result. The experimental results show that when the signal-to-noise ratio is greater than 0 dB, the average recognition accuracy of the modulation waveform of the proposed method reaches 91.79%; compared with the same method, the number of parameters of the proposed method is reduced 96%and the efficiency is increased by 2.7 times.

Combinatorial Order Pre-processing Search (COPS): A new pre-processing strategy for large-scale interpretable data analysis in process analytical technologies

Combinatorial Order Pre-processing Search (COPS), a novel approach for optimizing data pre-processing is proposed in this work. Unlike simultaneous hyperparameter optimization, COPS employs a priori optimization to reduce computational time while refining the search space for preprocessing sequences and combinations. It allows for setting a maximum number of pre-processing methods, while efficiently searching through combinations of methods with chemically relevant knowledge. In this work, 67 calibration datasets across various analytical techniques, including fluorescence spectroscopy, gas chromatography (GC), near-infrared spectroscopy (NIR), mid-infrared spectroscopy (MIR), visible-near-infrared spectroscopy (Vis-NIR), Raman spectroscopy, nuclear magnetic resonance (NMR) spectroscopy, and voltammetry were evaluated. COPS yielded significant improvements over existing methodologies based on design of experiment and compounded pre-processing approaches. The COPS outperformed the other methods, resulting in an average root mean square error of prediction (RMSEP) reduction of 31.7%, while also reduced the complexity (number of latent variables) of the model which allows for easier interpretation. This underscores the importance of combinatorial order set theory for the search of pre-processing method combinations (without fixing the sequence of pre-processing methods) to enhance model performance and interpretation. The novel COPS approach can be employed in process analytical technology (such as inline, online or at-line chemical sensing analytics) to enhance predictive accuracy and operational efficiency, fundamentally transforming the quality and reliability of chemical process monitoring and control.

Improving production sequencing in the age of Industry 4.0: A mathematical launching model approach

Purpose: To enhance enterprise efficiency, this study examines the pivotal role of operations management in optimizing the use of materials, technology, equipment, and personnel, especially within the transformative framework of Industry 4.0.Design/methodology/approach: This article investigates operational preparation in the context of Industry 4.0. Through questionnaires and interviews with stakeholders, problems related to operational preparation were identified. To address these problems, a launching model was developed for production systems. The model considers several parameters important for the production process, including business goals, customer needs, and environmental conditions that impact enterprise performance and profit.Findings: The model determines the importance of jobs to be performed in a certain order to optimize production sequence. The proposed parameters are included in a mathematical-algorithmic launching model based on categorical levels related to the production process, such as profit, delivery times, processing times, total number of technological operations, product types, materials, required quality, product complexity, and resource use. The model was developed based on observations and investigations conducted in Kosovo's enterprises on operations research, and it has the potential to significantly improve production efficiency and profitability in the Industry 4.0 era.Practical implications: The findings of this study have practical implications for operations management within the Industry 4.0 framework, proposing a launching model designed to optimize production processes and enhance efficiency.Originality/value: The originality and value of this research lie in the development of a mathematical-algorithmic launching model that addresses operational preparation in the Industry 4.0 context, taking into account various crucial parameters.

Quantum pairwise-parallel mismatch attack on Kyber

Abstract Quantum algorithm uses the quantum parallel method to calculate, which can better solve the encryption and decryption problems in cryptography and secure communication. This paper proposes a quantum pairwise-parallel mismatch attack on Kyber using the quantum binary search method. We first give quantum search methods for finding the secret key and show that our method can be applied to Kyber. Then, According to the proposed quantum search method, we compute the number of queries required and computational complexity for recovering the full key on Kyber. Compared with the existing results, our improved attack significantly reduces the number of queries and computational complexity.

LUT-SLS: A Lightweight Transformer Network Based on U-Net for Skin Lesion Segmentation

In recent years, deep learning has achieved significant advancements in medical image segmentation, primarily focusing on CNN structures and Transformer-based architectures. However, these network architectures often suffer from high computational complexity and a large number of parameters. To address these challenges, this paper proposes a lightweight, novel structured network called LUT-SLS, based on U-Net and Transformer. Firstly, the overall structure integrates U-Net and Transformer, which effectively captures long-range dependencies in image relationships and contextual information, thereby improving segmentation accuracy. Secondly, a novel PLTS module is designed, which replaces the traditional self-attention mechanism with average pooling operations to extract global features and local details. Additionally, a novel MMLP structure is introduced, incorporating residual depth-separable operations into the traditional fully-connected framework. This enhances the processing of pooled features and further improves feature expression capability. Finally, the encoder and decoder parts are connected by the MSBN module, which facilitates the extraction of deep features while fusing encoder features. Experimental results demonstrate that the proposed model achieves competitive advantages in balancing the number of parameters, computational complexity, and performance compared to current leading models on multiple public datasets. This solution enables model deployment on IoT terminals, assisting doctors in making more accurate clinical decisions.

Assembly Theory is an approximation to algorithmic complexity based on LZ compression that does not explain selection or evolution

We formally prove the equivalence between Assembly Theory (AT) and Shannon Entropy via a method based upon the principles of statistical compression that belongs to the LZ family of popular compression algorithms. Such popular lossless compression algorithms behind file formats such as ZIP and PNG have been shown to empirically reproduce the results that AT considers its cornerstone. The same results have also been reported before AT in successful application of other complexity measures in the areas covered by AT such as separating organic from non-organic molecules and in the context of the study of selection and evolution. We demonstrate that the assembly index is equivalent to the size of a minimal context-free grammar. The statistical compressibility of such a method is bounded by Shannon Entropy and other equivalent traditional LZ compression schemes, such as LZ77 and LZW. We also demonstrate that AT, and the algorithms supporting its pathway complexity, assembly index, and assembly number, define compression schemes and methods that are subsumed into algorithmic information theory. We conclude that the assembly index and the assembly number do not lead to an explanation or quantification of biases in generative (physical or biological) processes, including those brought about by (abiotic or biotic) selection and evolution, that could not have been arrived at using Shannon Entropy, or that have not been already reported before using classical information theory or algorithmic complexity.

Visual Feature-Guided Diamond Convolutional Network for Finger Vein Recognition.

Finger vein (FV) biometrics have garnered considerable attention due to their inherent non-contact nature and high security, exhibiting tremendous potential in identity authentication and beyond. Nevertheless, challenges pertaining to the scarcity of training data and inconsistent image quality continue to impede the effectiveness of finger vein recognition (FVR) systems. To tackle these challenges, we introduce the visual feature-guided diamond convolutional network (dubbed 'VF-DCN'), a uniquely configured multi-scale and multi-orientation convolutional neural network. The VF-DCN showcases three pivotal innovations: Firstly, it meticulously tunes the convolutional kernels through multi-scale Log-Gabor filters. Secondly, it implements a distinctive diamond-shaped convolutional kernel architecture inspired by human visual perception. This design intelligently allocates more orientational filters to medium scales, which inherently carry richer information. In contrast, at extreme scales, the use of orientational filters is minimized to simulate the natural blurring of objects at extreme focal lengths. Thirdly, the network boasts a deliberate three-layer configuration and fully unsupervised training process, prioritizing simplicity and optimal performance. Extensive experiments are conducted on four FV databases, including MMCBNU_6000, FV_USM, HKPU, and ZSC_FV. The experimental results reveal that VF-DCN achieves remarkable improvement with equal error rates (EERs) of 0.17%, 0.19%, 2.11%, and 0.65%, respectively, and Accuracy Rates (ACC) of 100%, 99.97%, 98.92%, and 99.36%, respectively. These results indicate that, compared with some existing FVR approaches, the proposed VF-DCN not only achieves notable recognition accuracy but also shows fewer number of parameters and lower model complexity. Moreover, VF-DCN exhibits superior robustness across diverse FV databases.

Research on Applying Deep Learning to Visual–Motor Integration Assessment Systems in Pediatric Rehabilitation Medicine

In pediatric rehabilitation medicine, manual assessment methods for visual–motor integration result in inconsistent scoring standards. To address these issues, incorporating artificial intelligence (AI) technology is a feasible approach that can reduce time and improve accuracy. Existing research on visual–motor integration scoring has proposed a framework based on convolutional neural networks (CNNs) for the Beery–Buktenica developmental test of visual–motor integration. However, as the number of training questions increases, the accuracy of this framework significantly decreases. This paper proposes a new architecture to reduce the number of features, channels, and overall model complexity. The architectureoptimizes input features by concatenating question numbers with answer features and selecting appropriate channel ratios and optimizes the output vector by designing the task as a multi-class classification. This paper also proposes a model named improved DenseNet. After experimentation, DenseNet201 was identified as the most suitable pre-trained model for this task and was used as the backbone architecture for improved DenseNet. Additionally, new fully connected layers were added for feature extraction and classification, allowing for specialized feature learning. The architecture can provide reasons for unscored results based on prediction results and decoding rules, offering directions for children’s training. The final experimental results show that the proposed new architecture improves the accuracy of scoring 6 question graphics by 12.8% and 12 question graphics by 20.14% compared to the most relevant literature. The accuracy of the proposed new architecture surpasses the model frameworks of the most relevant literature, demonstrating the effectiveness of this approach in improving scoring accuracy and stability.

FM‐YOLOv8:Lightweight gesture recognition algorithm

AbstractIn practical production applications, the efficiency and success rate of gesture recognition directly affect the user experience and work efficiency. However, the existing gesture recognition models have the problem of a large number of model parameters and high computational complexity, which makes them unable to meet the needs of end‐to‐end industrial deployment. To solve these problems, this article proposes a gesture recognition model based on YOLOv8. First, FasterNet is adopted as the backbone of YOLOv8, which significantlydecrease the number of parameters and made the model more lightweight. By reducing the number of parameters, the computational complexity of the model can be reduced while maintaining the performance of the model, and the operation efficiency of the model can be improved. Second, recombination convolution ScConv is introduced to replace common convolution operations to further improve the model's efficiency. Recombination convolution can reduce the computation and make up for the loss of precision to some extent. Finally, the MDPIoU loss function is used to optimize target location and prediction, to improve the accuracy of the model. The MDPIoU loss function can better deal with the problem of target boundary frame positioning and prediction so that the model can locate and predict gestures more accurately in gesture recognition tasks. Experiments on a data set containing 10 types of gestures show that the number of parameters and floating point calculations of the improved network model are reduced by 45% and 42.7%, respectively, while the accuracy is unchanged. The improved model can be deployed on edge terminals, providing efficient and accurate gesture recognition.

Insights From Important Event Recounts Told by People With Traumatic Brain Injury.

Communication can be chronically impacted by severe traumatic brain injury (TBI), yet there is a critical lack of research investigating communication recovery beyond 12 months postinjury with discourse measures. This longitudinal study aimed to investigate quantitative and qualitative changes in important event recounts produced by a group of people with severe TBI up to 2 years postinjury. A prospective observational design with an inception cohort was adopted. Thirty-four participants with severe TBI were asked to produce an important event recount at 6, 12, and 24 months postinjury. A mixed-methods approach comprised a quantitative analysis of microlinguistic and macrostructural measures, using the automated discourse command EVAL in Computerized Language Analysis (CLAN) and the CLAN Collaborative Commentary tool, respectively. Statistical analysis included a repeated-measures analysis of variance and the Friedman test. An independent qualitative content analysis was also conducted. The measures revealed significant differences between 6 and 24 months, indicating a protracted recovery trajectory. The microlinguistic analysis showed increased use of revision and repetition over time. The macrostructural analysis indicated changes with orientation to recount characters, evaluative comments, and the number of events or complexity of the recount. The content analysis revealed categories of (a) childhood events, (b) family and relationships, (c) career and education, and (d) grief and loss. Topics at 6 months focused on childhood events and holidays, whereas career and education predominated at 24 months. This is the first study to explore important event recounts told by people with severe TBI as they recovered. Participants showed discourse recovery beyond 12 months, highlighting the need for equivalent timing of service provision. The important event recount shows good potential as an ecologically valid assessment tool to evaluate communication recovery that can also be integrated with advances in computerized analysis. Analyses additionally provided insights into potential therapy targets and content categories for chronic discourse impairments. https://doi.org/10.23641/asha.26499271.

Penetration State Recognition during Laser Welding Process Control Based on Two-Stage Temporal Convolutional Networks.

Vision-based laser penetration control has become an important research area in the field of welding quality control. Due to the complexity and large number of parameters in the monitoring model, control of the welding process based on deep learning and the reliance on long-term information for penetration identification are challenges. In this study, a penetration recognition method based on a two-stage temporal convolutional network is proposed to realize the online process control of laser welding. In this paper, a coaxial vision welding monitoring system is built. A lightweight segmentation model, based on channel pruning, is proposed to extract the key features of the molten pool and the keyhole from the clear molten pool keyhole image. Using these molten pool and keyhole features, a temporal convolutional network based on attention mechanism is established. The recognition method can effectively predict the laser welding penetration state, which depends on long-term information. In addition, the penetration identification experiment and closed-loop control experiment of unequal thickness plates are designed. The proposed method in this study has an accuracy of 98.96% and an average inference speed of 20.4 ms. The experimental results demonstrate that the proposed method exhibits significant performance in recognizing the penetration state from long sequences of welding image signals, adjusting welding power, and stabilizing welding quality.

Return to Work One Year after Moderate to Severe Traumatic Injury in a Working Age Population.

Background/Objectives: Physical trauma may cause long-term disabilities. The importance of place of residence in the return to work after injuries is little researched. The primary aims of this study were to describe return to work or school (RTW) at 6 and 12 months after moderate to severe traumatic injury and to investigate demographic and injury-related predictors for RTW with an initial focus on geographic centrality of residency. The secondary aim was to investigate the association between RTW and functioning. Methods: A prospective cohort study conducted at two Norwegian trauma centres. Inclusion criteria: age 18 to 70 years, at least a two-day hospital stay and a New Injury Severity Score > 9. Information about centrality, demographics, injuries, and return to work were collected. Associations between possible predictors and RTW were assessed using binary logistic regression. Results: Of the 223 participants, 68% had returned to work after 6 months and 77% after 12 months. Twelve-month RTW was 89% after thorax/abdomen injuries, 78% after extremity/spine injuries and 73% after head injuries. More central residency was a significant predictor for RTW in univariable but only within the extremity/spine injury subgroup in multivariable analysis. Negative factors were age, having a blue-collar job, number of injuries and rehabilitation complexity. Function 12 months post-injury was associated with RTW in the multivariable model. Conclusions: RTW after one year was high in all major trauma groups. Demographic and injury-related factors were more important predictors of RTW than centrality of residency. Blue-collar workers and patients with multiple injuries and high rehabilitation complexity should be given special attention to support RTW.

Generic diversity and septal complexity in Cretaceous ammonoids. Effects of oceanic anoxic events on the ammonoid evolutionary dynamic

This paper analyzes the relationship between the number of genera of Cretaceous planiespiral ammonoids and their sutural complexity estimated by their fractal dimension. It is confirmed that the dynamics of generic diversity is associated with the appearance/disappearance of simple suture genera, which are not ascribed to a particular family. The maximum oscillations of generic diversity occur in the Aptian and Albian which are associated with large variations in the number of genera with simple sutures. From the Middle Campanian there is a continued loss of diversity until the end of the Maastrichtian linked to a net reduction of single suture genera. The direct relationship between the number of genera and the range of septal complexity in each substage indicates that different degrees of septal complexity are different ecomorphological strategies of adaptation to different niches. This result confirms that the specialist forms are those with simple sutures while the genera with complex septa are either generalist forms or are adapted to environments that do not undergo major fluctuations over geological time. The ammonoid generic diversity recorded dynamics is different from that of other marine invertebrates, reflecting paleobiological and/or taphonomic differences. The symmetrical distribution of septal complexity values points to the relative fidelity of the fossil record of Cretaceous ammonoids. The effect of seven oceanic anoxic events of the Cretaceous on the number of genera and septal complexity is analyzed, obtaining no statistically distinguishable effects of the oscillations of these variables with respect to those occurring in other intervals where such events are not recorded.