Structural Information Research Articles

Earnings management in the family business groups of Pakistan: the role of corporate governance

Purpose This paper aims to examine the role of corporate governance (CG) in the earnings management (EM) of affiliated companies in family business groups (FBGs) listed on the Pakistan Stock Exchange (PSX), using principal–principal agency theory. Design/methodology/approach The sample of 327 nonfinancial firms of the PSX, consisting of 187 group-affiliated firms and 140 nonaffiliated firms has been used in this study for the period of 2010 to 2019. The study uses different regression models for analysis, with robustness tests of various alternative measures of EM and FBG affiliation. In addition, endogeneity is controlled with the propensity score matching method. Findings The findings show that EM is less prevalent in affiliated firms compared to nonaffiliated companies. The results show a negative and significant relationship between FBGs affiliated firms and EM. Moreover, the results also show a positive relationship between EM and the interaction term of the CG index and group affiliation. It refers to the fact that effective governance cannot reduce EM in affiliated companies of FBGs as well as in the nonfinancial companies of the PSX. In addition, the quality of CG is higher in affiliated companies compared to its counterpart in nonaffiliated firms. The findings support the principal–principal agency theory that CG cannot mitigate the expropriating behavior of controlling shareholders against minority shareholders by reducing EM in emerging markets due to the ownership concentration phenomenon. Research limitations/implications This research study has implications for small investors, government agencies and regulators. The findings of the study show that CG code should make it mandatory for companies to reveal information about their complex ownership structure and ownership information about affiliated companies and directors. Furthermore, it is suggested to revisit the code of CG in the Pakistani context of principal–principal conflict instead of the agent–principal explanation of agency theory based on Anglo–Saxon countries. Originality/value This research study has contributed to the CG and FBG literature in relation to EM in idiosyncratic settings of Pakistan. One of the prime contributions of the paper is the development of a comprehensive CG index. This research study used detailed, manually collected novel data on affiliated firms of FBGs in Pakistan.

Peculiarities of Frequency-Following Response in Healthy Individuals when Listening to Complex Sounds

INTRODUCTION: Studies of recent years showed that functional disorders in the brainstem may be one of factors causing inability to perceive speech by normal-hearing individuals. Frequency-following response (FFR) is an auditory evoked potential emerging in different regions of the brain in response to a sound or a change in the sound frequency. The initiation of this potential is associated with the correct processing of auditory information in the subcortical structures of the brain. However, until the moment, there is no regulatory framework that could permit use of this potential in routine examinations. AIM: To identify and analyze the peculiarities of FFR in healthy adult individuals when listening to a complex sound. MATERIALS AND METHODS: The study included 29 healthy subjects aged from 18 to 48 years (mean age 28 ± 10 years). Electrical activity of the brain was recorded from 32 electrodes. Sampling frequency 2000 Hz, transmission frequency 0.1 Hz–500 Hz. The stimulus was a 30-s sound that included simple sounds of five different frequencies (600 Hz, 800 Hz, 1000 Hz, 2000 Hz, 4000 Hz) changing in a random order every 100 ms. FFR was isolated in each frequency change in the complex sound. The resulting FFR included two peaks, for each amplitude, latency, and dipole sources were calculated. RESULTS: FFR was obtained in all the subjects and included two peaks. In some subjects, FFR peaks had a statistically higher amplitude and lower latency. In subjects with a higher amplitude FFR peaks, three dipoles were identified for the first peak: in the brainstem and in the cortex of the right hemisphere (Brodmann areas 6 and 39). For the second peak, one dipole was identified in the cortex (Brodmann area 19). In subjects with low amplitude FFR peaks, for the first peak one source in the brainstem was identified. For the second peak, two dipoles were identified: in the posterior cingulate cortex (Brodmann area 23) and in the medial thalamus. CONCLUSION: The data obtained suggest that the method of recording and analyzing FFR can be used to assess the functional integrity and correct participation of the midbrain in the perception of auditory stimuli. The peculiarities of amplitude-time parameters of its peaks probably reflect the individual ability to finely differentiate stimuli.

Structure-based investigation of a DNA aptamer targeting PTK7 reveals an intricate 3D fold guiding functional optimization

DNA aptamers have emerged as novel molecular tools in disease theranostics owing to their high binding affinity and specificity for protein targets, which rely on their ability to fold into distinctive three-dimensional (3D) structures. However, delicate atomic interactions that shape the 3D structures are often ignored when designing and modeling aptamers, leading to inefficient functional optimization. Challenges persist in determining high-resolution aptamer-protein complex structures. Moreover, the experimentally determined 3D structures of DNA molecules with exquisite functions remain scarce. These factors impede our comprehension and optimization of some important DNA aptamers. Here, we performed a streamlined solution NMR-based structural investigation on the 41-nt sgc8c, a prominent DNA aptamer used to target membrane protein tyrosine kinase 7, for cancer theranostics. We show that sgc8c prefolds into an intricate three-way junction (3WJ) structure stabilized by long-range tertiary interactions and extensive base-base stackings. Delineated by NMR chemical shift perturbations, site-directed mutagenesis, and 3D structural information, we identified essential nucleotides constituting the key functional elements of sgc8c that are centralized at the core of 3WJ. Leveraging the well-established structure-function relationship, we efficiently engineered two sgc8c variants by modifying the apical loop and introducing L-DNA base pairs to simultaneously enhance thermostability, biostability, and binding affinity for both protein and cell targets, a feat not previously attained despite extensive efforts. This work showcases a simplified NMR-based approach to comprehend and optimize sgc8c without acquiring the complex structure, and offers principles for the sophisticated structure-function organization of DNA molecules.

Graph constrained empirical wavelet transform and its application in bearing fault diagnosis

Abstract The signal decomposition based on frequency domain distribution is a fundamental methodology for mechanical component fault diagnosis. However, existing methods face challenges such as susceptibility to noise interference and limited adaptability. Therefore, this paper proposes the graph constrained empirical wavelet transform (GCEWT) method. This method introduces structured information, such as the interrelationships among different parts of the frequency domain distribution of vibration signals, into the boundary detection process of empirical wavelet transform. The high-dimensional connectivity among different parts of the time-frequency distribution is utilized to construct an adjacency matrix. By constructing an adjacent graph, the proposed method encodes the adjacency relationships among frequency bands to constrain the low-dimensional spatial relationships between them. In conjunction with spectral clustering algorithms, the GCEWT method determines the boundaries for empirical wavelet transformation in the frequency domain. This approach achieves structured and adaptive decomposition of vibration signals from components of critical equipment, facilitating the structured and adaptive extraction of fault features. The effectiveness of the proposed method is validated using vibration data from both wind turbine drivetrain systems and aircraft engines. The experimental results demonstrate that the proposed method yields more reasonable signal decomposition results compared to traditional algorithms. Additionally, the proposed method proves to be more effective in extracting weak fault features of bearings in the presence of noise.

A Cognitive View on Prosodic Relations

The paper presents a new F0 contour partitioning approach by using the category of prosodic relations also used by Ladd (2008) for improving the F0 contour descriptions based on phonological categories. The new approach involves a cognitive view on the low-high and high-low ’metrical’ structures of prosodic relations, by relating them to the structures of cognitive relations generated during speech object representations at the cortical level. In section 2, the paper presents the information structure model by defining the cognitive categories that describes prosodic relations of F0 contours involving their two overlapped structures and nuclear positions. CU_predicate-CU_argument and CU_theme-CU_rheme are the two structural levels of prosodic relations. The model proposes a binary-tree hierarchy to describe the articulation of prosodic relations within utterances. Two rules are formulated for the identification of nuclear constituents of prosodic relations. The utterances analysed in section 3 illustrate how prosodic and prominence relations can be identified by analysing acoustic cues of their F0 contours. Utterances correspond to English borad focus and narrow focus statements. Focus positions are deduced by only using the rule of the cognitive model.

Multi-view subspace clustering based on multi-order neighbor diffusion

AbstractMulti-view subspace clustering (MVC) intends to separate out samples via integrating the complementary information from diverse views. In MVC, since the structural information in the graph is crucial to the graph learning, most of the existing algorithms construct the superficial graph from the original data by directly measuring the similarity between the first-order complementary nearest neighbors. However, the information provided by the superficial graph structure would be influenced by contaminated or absent samples. To address this problem, in the proposed method, the higher-order complementary neighbor graphs are exploited to discover the latent structural information between the samples, and fusing the latent structural information across different orders to achieve the MVC. Specifically, the higher-order neighbor graphs under different views are leveraged to estimate the missing samples. Then, to integrate the neighbor graphs of different orders, the multi-order neighbor diffusion fusion is proposed. Nevertheless, the above problem of diffusion fusion is an intractable non-convex issue. Thus, to address it, the multi-order neighbor diffusion fusion is considered as a combination problem of the solution under different order, and the heuristic algorithm is leveraged to solve it. In this way, not only the data representation under different view and also the neighbor structure under different order can be diffused under a joint optimization framework, thus the consistency and integral information among various perspectives and orders can be utilized effectively and simultaneously. Experiments on both incomplete and complete multi-view dataset demonstrate the convincingness of the high-order neighborhood structure based subspace clustering scheme by comparing with the existing approaches.

HyperCARS: Using Hyperbolic Embeddings for Generating Hierarchical Contextual Situations in Context-Aware Recommender Systems

Contextual situations, such as having dinner at a restaurant on Friday with the spouse, became a useful mechanism to represent context in context-aware recommender systems (CARS). Prior research has shown important advantages of using latent embedding representation approaches to model contextual information in the Euclidean space leading to better recommendations. However, these traditional approaches have major challenges with the construction of proper embeddings of hierarchical structures of contextual information, as well as with interpretations of the obtained representations. To address these problems, we propose the HyperCARS method that models hierarchical contextual situations in the latent hyperbolic space. HyperCARS combines hyperbolic embeddings with hierarchical clustering to construct contextual situations, which allows loose coupling of the contextual modeling component with recommendation algorithms and, therefore, provides flexibility to use a broad range of previously developed recommendation algorithms. We demonstrate empirically that HyperCARS better captures and interprets hierarchical contextual representations, leading to better context-aware recommendations. Because hyperbolic embeddings can also be used in many other applications besides CARS, we also propose the latent embeddings representation framework that systematically classifies prior work on embeddings and identifies novel research streams for hyperbolic embeddings across information systems applications.

TransMVAN: Multi-view Aggregation Network with Transformer for Pneumonia Diagnosis.

Automated and accurate classification of pneumonia plays a crucial role in improving the performance of computer-aided diagnosis systems for chest X-ray images. Nevertheless, it is a challenging task due to the difficulty of learning the complex structure information of lung abnormality from chest X-ray images. In this paper, we propose a multi-view aggregation network with Transformer (TransMVAN) for pneumonia classification in chest X-ray images. Specifically, we propose to incorporate the knowledge from glance and focus views to enrich the feature representation of lung abnormality. Moreover, to capture the complex relationships among different lung regions, we propose a bi-directional multi-scale vision Transformer (biMSVT), with which the informative messages between different lung regions are propagated through two directions. In addition, we also propose a gated multi-view aggregation (GMVA) to adaptively select the feature information from glance and focus views for further performance enhancement of pneumonia diagnosis. Our proposed method achieves AUCs of 0.9645 and 0.9550 for pneumonia classification on two different chest X-ray image datasets. In addition, it achieves an AUC of 0.9761 for evaluating positive and negative polymerase chain reaction (PCR). Furthermore, our proposed method also attains an AUC of 0.9741 for classifying non-COVID-19 pneumonia, COVID-19 pneumonia, and normal cases. Experimental results demonstrate the effectiveness of our method over other methods used for comparison in pneumonia diagnosis from chest X-ray images.

LVPocket: integrated 3D global-local information to protein binding pockets prediction with transfer learning of protein structure classification

BackgroundPrevious deep learning methods for predicting protein binding pockets mainly employed 3D convolution, yet an abundance of convolution operations may lead the model to excessively prioritize local information, thus overlooking global information. Moreover, it is essential for us to account for the influence of diverse protein folding structural classes. Because proteins classified differently structurally exhibit varying biological functions, whereas those within the same structural class share similar functional attributes.ResultsWe proposed LVPocket, a novel method that synergistically captures both local and global information of protein structure through the integration of Transformer encoders, which help the model achieve better performance in binding pockets prediction. And then we tailored prediction models for data of four distinct structural classes of proteins using the transfer learning. The four fine-tuned models were trained on the baseline LVPocket model which was trained on the sc-PDB dataset. LVPocket exhibits superior performance on three independent datasets compared to current state-of-the-art methods. Additionally, the fine-tuned model outperforms the baseline model in terms of performance.Scientific contributionWe present a novel model structure for predicting protein binding pockets that provides a solution for relying on extensive convolutional computation while neglecting global information about protein structures. Furthermore, we tackle the impact of different protein folding structures on binding pocket prediction tasks through the application of transfer learning methods.Graphical

Accelerating Formulation Design via Machine Learning: Generating a High-throughput Shampoo Formulations Dataset

Liquid formulations are ubiquitous yet have lengthy product development cycles owing to the complex physical interactions between ingredients making it difficult to tune formulations to customer-defined property targets. Interpolative ML models can accelerate liquid formulations design but are typically trained on limited sets of ingredients and without any structural information, which limits their out-of-training predictive capacity. To address this challenge, we selected eighteen formulation ingredients covering a diverse chemical space to prepare an open experimental dataset for training ML models for rinse-off formulations development. The resulting design space has an over 50-fold increase in dimensionality compared to our previous work. Here, we present a dataset of 812 formulations, including 294 stable samples, which cover the entire design space, with phase stability, turbidity, and high-fidelity rheology measurements generated on our semi-automated, ML-driven liquid formulations workflow. Our dataset has the unique attribute of sample-specific uncertainty measurements to train predictive surrogate models.

Sparse sampling photoacoustic reconstruction with a graph regularization group sparse dictionary

Photoacoustic tomography (PAT) has emerged as a promising biomedical imaging technique. The combination of optical contrast and ultrasound spatial resolution in photoacoustic tomography overcomes the limitations of optical scattering, enabling clear imaging of tissue structures. However, achieving high-resolution photoacoustic images typically requires a large number of sensor detection elements for sufficient angular coverage. This demand for extensive data acquisition and processing raises concerns about efficiency and system complexity. While sparse sampling strategies can improve efficiency, preserving detailed structural information becomes challenging with a minimal number of detectors. To address the challenges of sparse sampling, compressed sensing (CS) techniques have been successfully applied for image reconstructions in 2D and 3D photoacoustic embodiments. In this context, we propose a joint graph regularization group sparse dictionary and total variational regularization (GRGS-TV) algorithm based on our previous work of a group sparse dictionary. It preserves structured information and geometric relationships among dictionary atoms. Moreover, TV regularization effectively preserves edge structures while exhibiting a certain degree of robustness and flexibility. Numerical simulations and in vivo experiments on mice validate the effectiveness of this method in improving photoacoustic image quality and suppressing artifacts. Comparative evaluations against other algorithms show enhanced performance in terms of image reconstruction evaluation indices. This innovative approach holds promise for advancing photoacoustic imaging in biomedical research and clinical diagnostics.

Ambulance professionals' experiences of teamwork in the context of a team training programme – a qualitative study

BackgroundTeamwork in the context of ambulance services exhibits unique characteristics, as this environment involves a small core team that must adapt to a dynamic team structure that involves health care professionals and emergency services. It is essential to acquire a deeper understanding of how ambulance teams operate. Therefore, this study aimed to explore the experiences of ambulance professionals with teamwork and how they were influenced by the implementation of a team training programme.MethodsA qualitative descriptive study was conducted involving ambulance professionals who took part in focus group interviews carried out both before and after the implementation of a team training program across seven ambulance stations within a Norwegian hospital trust. The data were analysed using reflexive thematic analysis based on a deductive-inductive approach.ResultsOur analysis revealed 15 subthemes that characterised ambulance professionals’ experiences with teamwork and a team training programme, which were organised according to the five main themes of team structure, communication, leadership, situation monitoring, and mutual support. Ambulance professionals’ experiences ranged from the significance of team composition and interpersonal and professional relationships to their preferences regarding different communication styles and the necessity of team leaders within the ambulance service. The team training programme raised awareness of teamwork, while the adoption of teamwork tools was influenced by both individual and contextual factors. The Introduction/Identity, Situation, Background, Assessment and Recommendation (ISBAR) communication tool was identified as the most beneficial aspect of the programme due to its ease of use, which led to improvements in the structure and quality of consultations and information handover.ConclusionsThis study documented the diverse characteristics and preferences associated with teamwork among ambulance professionals, emphasising the particular importance of proficient partnerships in this context. Participation in a team training programme was perceived as a valuable reminder of the significance of teamwork, thus providing a foundation for the enhancement of communication skills.Trial registrationClinicalTrials.gov—ID: NCT05244928.

Impact of Financial Regulations on Bank Profitability in Uganda

Purpose: The aim of the study was to assess the impact of financial regulations on bank profitability in Uganda. Methodology: This study adopted a desk methodology. A desk study research design is commonly known as secondary data collection. This is basically collecting data from existing resources preferably because of its low cost advantage as compared to a field research. Our current study looked into already published studies and reports as the data was easily accessed through online journals and libraries. Findings: Financial regulations significantly influence bank profitability, primarily by affecting operational costs, risk management practices, and lending activities. Stricter capital requirements, such as those imposed by Basel III, generally enhance financial stability but may reduce profitability by limiting leverage and increasing the cost of compliance. Regulatory measures aimed at consumer protection and transparency, while beneficial for market integrity, can also impose additional administrative burdens and costs on banks. Conversely, deregulation periods often see increased profitability due to relaxed constraints on lending and investment activities. However, this can come at the expense of higher risk exposure and potential financial instability. Overall, the balance between regulatory stringency and bank profitability hinges on the specific regulations in place and the banks' ability to adapt and innovate within those frameworks. Implications to Theory, Practice and Policy: Agency theory, capital structure theory and information asymmetry theory may be used to anchor future studies on assessing the impact of financial regulations on bank profitability in Uganda. Practitioners should advocate for risk-based regulation that tailors regulatory requirements to banks' risk profiles and systemic importance. Policymakers should prioritize efforts to harmonize financial regulations across jurisdictions, especially in global banking hubs.

Heuristic approaches for non-exhaustive pattern-based change detection in dynamic networks

AbstractDynamic networks are ubiquitous in many domains for modelling evolving graph-structured data and detecting changes allows us to understand the dynamic of the domain represented. A category of computational solutions is represented by the pattern-based change detectors (PBCDs), which are non-parametric unsupervised change detection methods based on observed changes in sets of frequent patterns over time. Patterns have the ability to depict the structural information of the sub-graphs, becoming a useful tool in the interpretation of the changes. Existing PBCDs often rely on exhaustive mining, which corresponds to the worst-case exponential time complexity, making this category of algorithms inefficient in practice. In fact, in such a case, the pattern mining process is even more time-consuming and inefficient due to the combinatorial explosion of the sub-graph pattern space caused by the inherent complexity of the graph structure. Non-exhaustive search strategies can represent a possible approach to this problem, also because not all the possible frequent patterns contribute to changes in the time-evolving data. In this paper, we investigate the viability of different heuristic approaches which prevent the complete exploration of the search space, by returning a concise set of sub-graph patterns (compared to the exhaustive case). The heuristics differ on the criterion used to select representative patterns. The results obtained on real-world and synthetic dynamic networks show that these solutions are effective, when mining patterns, and even more accurate when detecting changes.

Image smoothing method based on global gradient sparsity and local relative gradient constraint optimization

Removing texture while preserving the main structure of an image is a challenging task. To address this, this paper propose an image smoothing method based on global gradient sparsity and local relative gradient constraints optimization. To reduce the interference of complex texture details, adopting a multi-directional difference constrained global gradient sparsity decomposition method, which provides a guidance image with weaker texture detail gradients. Meanwhile, using the luminance channel as a reference, edge-aware operator is constructed based on local gradient constraints. This operator weakens the gradients of repetitive and similar texture details, enabling it to obtain more accurate structural information for guiding global optimization of the image. By projecting multi-directional differences onto the horizontal and vertical directions, a mapping from multi-directional differences to bi-directional gradients is achieved. Additionally, to ensure the consistency of measurement results, a multi-directional gradient normalization method is designed. Through experiments, we demonstrate that our method exhibits significant advantages in preserving image edges compared to current advanced smoothing methods.

Multi-graph attention fusion graph neural network for remaining useful life prediction of rolling bearings

Abstract Graph neural network (GNN) has the proven ability to learn feature representations from graph data, and has been utilized for the tasks of predicting the machinery remaining useful life (RUL). However, existing methods only focus on a single graph structure and cannot integrate the correlation information contained in multi-graph structures. To address these issues, a multi-graph structure GNN prediction method with attention fusion (MGAFGNN) is proposed in this paper for GNN-based bearing RUL prediction. Specifically, a multi-channel graph attention module (MCGAM) is designed to effectively learn the similar features of node neighbors from different graph data and capture the multi-scale latent features of nodes through the nonlinear transformation. Furthermore, a multi-graph attention fusion module (MGAFM) is proposed to extract the collaborative features from the interaction graph, thereby fusing the feature embeddings from different graph structures. The fused feature representation is sent to the long short-term memory (LSTM) network to further learn the temporal features and achieve RUL prediction. The experimental results on two bearing datasets demonstrate that MGAFGNN outperforms existing methods in terms of prediction performance by effectively incorporating multi-graph structural information.

Tensor Completion for Alzheimer's Disease Prediction From Diffusion Tensor Imaging.

Alzheimer's disease (AD) is a slowly progressive neurodegenerative disorder with insidious onset. Accurate prediction of the disease progression has received increasing attention. Cognitive scores that reflect patients' cognitive status have become important criteria for predicting AD. Most existing methods consider the relationship between neuroimages and cognitive scores to improve prediction results. However, the inherent structure information in interrelated cognitive scores is rarely considered. In this article, we propose a relation-aware tensor completion multitask learning method (RATC-MTL), in which the cognitive scores are represented as a third-order tensor to preserve the global structure information in clinical scores. We combine both tensor completion and linear regression into a unified framework, which allows us to capture both inter and intra modes correlations in cognitive tensor with a low-rank constraint, as well as incorporate the relationship between biological features and cognitive status by imposing a regression model on multiple cognitive scores. Compared to the single-task and state-of-the-art multi-task algorithms, our proposed method obtains the best results for predicting cognitive scores in terms of four commonly used metrics. Furthermore, the overall performance of our method in classifying AD progress is also the best. Our results demonstrate the effectiveness of the proposed framework in fully exploring the global structure information in cognitive scores. This study introduces a novel concept of leveraging tensor completion to assist in disease diagnoses, potentially offering a solution to the issue of data scarcity encountered in prolonged monitoring scenarios.

Open-world Structured Sequence Learning Via Dense Target Encoding

Structured sequences are popularly used to describe graph data with time-evolving node features and edges. A typical real-world scenario of structured sequences is that unknown class labels continuously arrive and thus the training and testing often across different class spaces. This scenario is also referred to as the open-world learning problem on structured sequences. In this paper, we present a new Dense Open-world Structured Sequence Learning model (DOSSL for short) to learn graph streams in the open-world learning setting. To capture both structural and temporal information, DOSSL uses a GNN-based stochastic recurrent neural network for learning node representation in graph streams, then a truncated Laplacian distribution to describe the latent distribution of graph nodes, and a sampling function is used to generate node representations. Further, DOSSL learns dense target embeddings for the known classes to improve the compactness of known class distribution and reserve enough space for open-world unknown classes. The ultimate open-world classifier is optimized to detect the samples from unknown classes under the constraints of DVAE loss, label loss, class uncertainty loss, and dense target loss. Through empirical analysis conducted on real-world datasets, it has been demonstrated that the advanced technique known as DOSSL exhibits the ability to acquire precise node classifiers by harnessing the power of graph streams.

Contribution of Temporal Fine Structure Cues to Concurrent Vowel Identification and Perception of Zebra Speech.

Introduction The limited access to temporal fine structure (TFS) cues is a reason for reduced speech-in-noise recognition in cochlear implant (CI) users. The CI signal processing schemes like electroacoustic stimulation (EAS) and fine structure processing (FSP) encode TFS in the low frequency whereas theoretical strategies such as frequency amplitude modulation encoder (FAME) encode TFS in all the bands. Objective The present study compared the effect of simulated CI signal processing schemes that either encode no TFS, TFS information in all bands, or TFS only in low-frequency bands on concurrent vowel identification (CVI) and Zebra speech perception (ZSP). Methods Temporal fine structure information was systematically manipulated using a 30-band sine-wave (SV) vocoder. The TFS was either absent (SV) or presented in all the bands as frequency modulations simulating the FAME algorithm or only in bands below 525 Hz to simulate EAS. Concurrent vowel identification and ZSP were measured under each condition in 15 adults with normal hearing. Results The CVI scores did not differ between the 3 schemes (F (2, 28) = 0.62, p = 0.55, η 2 p = 0.04). The effect of encoding TFS was observed for ZSP (F (2, 28) = 5.73, p = 0.008, η 2 p = 0.29). Perception of Zebra speech was significantly better with EAS and FAME than with SV. There was no significant difference in ZSP scores obtained with EAS and FAME ( p = 1.00) Conclusion For ZSP, the TFS cues from FAME and EAS resulted in equivalent improvements in performance compared to the SV scheme. The presence or absence of TFS did not affect the CVI scores.

Structural prior-driven feature extraction with gradient-momentum combined optimization for convolutional neural network image classification

Recent image classification efforts have achieved certain success by incorporating prior information such as labels and logical rules to learn discriminative features. However, these methods overlook the variability of features, resulting in feature inconsistency and fluctuations in model parameter updates, which further contribute to decreased image classification accuracy and model instability. To address this issue, this paper proposes a novel method combining structural prior-driven feature extraction with gradient-momentum (SPGM), from the perspectives of consistent feature learning and precise parameter updates, to enhance the accuracy and stability of image classification. Specifically, SPGM leverages a structural prior-driven feature extraction (SPFE) approach to calculate gradients of multi-level features and originalimages to construct structural information, which is then transformed into prior knowledge to drive the network to learn features consistent with the original images. Additionally, an optimization strategy integrating gradients and momentum (GMO) is introduced, dynamically adjusting the direction and step size of parameter updates based on the angle and norm of the sum of gradients and momentum, enabling precise model parameter updates. Extensive experiments on CIFAR10 and CIFAR100 datasets demonstrate that the SPGM method significantly reduces the top-1 error rate in image classification, enhances the classification performance, and outperforms state-of-the-art methods.