Search results

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

This paper aims to develop a novel grey Bernoulli model with memory characteristics, which is designed to dynamically choose the optimal memory kernel function and the length of memory dependence period, ultimately enhancing the model's predictive accuracy.

This paper enhances the traditional grey Bernoulli model by introducing memory-dependent derivatives, resulting in a novel memory-dependent derivative grey model. Additionally, fractional-order accumulation is employed for preprocessing the original data. The length of the memory dependence period for memory-dependent derivatives is determined through grey correlation analysis. Furthermore, the whale optimization algorithm is utilized to optimize the cumulative order, power index and memory kernel function index of the model, enabling adaptability to diverse scenarios.

The selection of appropriate memory kernel functions and memory dependency lengths will improve model prediction performance. The model can adaptively select the memory kernel function and memory dependence length, and the performance of the model is better than other comparison models.

The model presented in this article has some limitations. The grey model is itself suitable for small sample data, and memory-dependent derivatives mainly consider the memory effect on a fixed length. Therefore, this model is mainly applicable to data prediction with short-term memory effect and has certain limitations on time series of long-term memory.

In practical systems, memory effects typically exhibit a decaying pattern, which is effectively characterized by the memory kernel function. The model in this study skillfully determines the appropriate kernel functions and memory dependency lengths to capture these memory effects, enhancing its alignment with real-world scenarios.

Based on the memory-dependent derivative method, a memory-dependent derivative grey Bernoulli model that more accurately reflects the actual memory effect is constructed and applied to power generation forecasting in China, South Korea and India.

Classification of remote sensing images (RSI) is a challenging task in computer vision. Recently, researchers have proposed a variety of creative methods for automatic recognition of RSI, and feature fusion is a research hotspot for its great potential to boost performance. However, RSI has a unique imaging condition and cluttered scenes with complicated backgrounds. This larger difference from nature images has made the previous feature fusion methods present insignificant performance improvements.

This work proposed a two-convolutional neural network (CNN) fusion method named main and branch CNN fusion network (MBC-Net) as an improved solution for classifying RSI. In detail, the MBC-Net employs an EfficientNet-B3 as its main CNN stream and an EfficientNet-B0 as a branch, named MC-B3 and BC-B0, respectively. In particular, MBC-Net includes a long-range derivation (LRD) module, which is specially designed to learn the dependence of different features. Meanwhile, MBC-Net also uses some unique ideas to tackle the problems coming from the two-CNN fusion and the inherent nature of RSI.

Extensive experiments on three RSI sets prove that MBC-Net outperforms the other 38 state-of-the-art (STOA) methods published from 2020 to 2023, with a noticeable increase in overall accuracy (OA) values. MBC-Net not only presents a 0.7% increased OA value on the most confusing NWPU set but also has 62% fewer parameters compared to the leading approach that ranks first in the literature.

MBC-Net is a more effective and efficient feature fusion approach compared to other STOA methods in the literature. Given the visualizations of grad class activation mapping (Grad-CAM), it reveals that MBC-Net can learn the long-range dependence of features that a single CNN cannot. Based on the tendency stochastic neighbor embedding (t-SNE) results, it demonstrates that the feature representation of MBC-Net is more effective than other methods. In addition, the ablation tests indicate that MBC-Net is effective and efficient for fusing features from two CNNs.

To guide the stable radius clearance choice of water-lubricated bearings for single screw compressors, this paper aims to analyze the effects of turbulence and cavitation on bearing performance under two conditions of specified external load and radius clearance.

A modified Reynolds equation considering turbulence and cavitation is adopted, based on the Jakobsson–Floberg–Olsson boundary condition, Ng–Pan model and turbulent factors. The equation is solved using the finite difference method and successive over-relaxation method to investigate the bearing performance.

The turbulent effect can increase the hydrodynamic pressure and cavitation. In addition, the turbulent effect can lead to an increase in the equilibrium radius clearance. The turbulent region exhibits a higher load capacity and cavitation rate. However, the increased cavitation negatively impacts the frictional coefficient and end flow rate. The impact of turbulence increases as the radius clearance decreases. As the rotating speed increases, the turbulence effect has a greater impact on the bearing characteristics.

The research can provide theoretical support for the design of water-lubricated journal bearings used in high-speed water-lubricated single screw compressors.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-01-2024-0029/

Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.

First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.

This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.

To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.

Vision, audition, olfactory, tactile and taste are five important senses that human uses to interact with the real world. As facing more and more complex environments, a sensing system is essential for intelligent robots with various types of sensors. To mimic human-like abilities, sensors similar to human perception capabilities are indispensable. However, most research only concentrated on analyzing literature on single-modal sensors and their robotics application.

This study presents a systematic review of five bioinspired senses, especially considering a brief introduction of multimodal sensing applications and predicting current trends and future directions of this field, which may have continuous enlightenments.

This review shows that bioinspired sensors can enable robots to better understand the environment, and multiple sensor combinations can support the robot’s ability to behave intelligently.

The review starts with a brief survey of the biological sensing mechanisms of the five senses, which are followed by their bioinspired electronic counterparts. Their applications in the robots are then reviewed as another emphasis, covering the main application scopes of localization and navigation, objection identification, dexterous manipulation, compliant interaction and so on. Finally, the trends, difficulties and challenges of this research were discussed to help guide future research on intelligent robot sensors.

Solder bumps for chip interconnections are downsizing from current approximately 100 µm to the expected 1 µm in future. As a result, the Cu-Ni cross-interaction in Cu/Solder/Ni solder joints will be more complicated and then strongly influence the growth of the intermetallic compounds (IMCs). Thus, it is critical to understand the fundamental aspects of interfacial reaction in micro solder joints. This paper aims to reveal the effect mechanism of reflow temperature and solder size on the interfacial reaction in Cu/Solder/Ni solder joints.

The Cu-Ni cross-interaction in the Cu/Sn/Ni micro solder joints with 50 and 100 µm solder sizes at 250°C and 300°C were observed, respectively. The line-type interconnects were soaked in silicone oil, and the temperature of the line-type interconnects was 250 ± 3°C and 300 ± 3°C, which were monitored by a fine K-type thermocouple, and followed by an isothermal aging process at various times. After aging, the specimens were removed from the silicone oil and cooled in the air to room temperature.

The major interfacial reaction product on both interfaces was (Cu,Ni)₆Sn₅, and the asymmetric growth of (Cu,Ni)₆Sn₅, evidenced by the thickness of (Cu,Ni)₆Sn₅ IMCs at the Sn/Ni interface was always larger than that at the Sn/Cu interface, resulted from the directional migration of Cu atoms toward the Sn/Ni interface under Cu concentration gradient. The morphology of (Cu,Ni)₆Sn₅ IMC at Sn/Cu interface was columnlike at 250°C, and which changed from columnlike to scallop with large aspect ratio at 300°C, while that at Sn/Ni interface gradually evolved from needlelike to the mixture of needlelike and layered at 250°C, and which evolved from needlelike to scallop with large aspect ratio at 300°C. The evolution of morphology of (Cu,Ni)₆Sn₅ is attributed to the content of Ni. Furthermore, the results indicate that the Cu-Ni cross-interaction was stronger with small solder size and relatively low temperature in the Cu/Sn/Ni micro solder joints.

The asymmetric growth of (Cu,Ni)₆Sn₅ in the Cu/Sn/Ni micro solder joints, evidenced by the thickness of (Cu,Ni)₆Sn₅ IMCs at the Sn/Ni interface, was always larger than that at the Sn/Cu interface. The morphology evolution of (Cu,Ni)₆Sn₅ IMC at both interfaces was attributed to the content of Ni. The Cu-Ni cross-interaction was stronger with small solder size and relatively low temperature in the Cu/Sn/Ni micro solder joints.

This review provides an overview of recent advances in electrochemical sensors for analyte detection in saliva, highlighting their potential applications in diagnostics and health care. The purpose of this paper is to summarize the current state of the field, identify challenges and limitations and discuss future prospects for the development of saliva-based electrochemical sensors.

The paper reviews relevant literature and research articles to examine the latest developments in electrochemical sensing technologies for saliva analysis. It explores the use of various electrode materials, including carbon nanomaterial, metal nanoparticles and conducting polymers, as well as the integration of microfluidics, lab-on-a-chip (LOC) devices and wearable/implantable technologies. The design and fabrication methodologies used in these sensors are discussed, along with sample preparation techniques and biorecognition elements for enhancing sensor performance.

Electrochemical sensors for salivary analyte detection have demonstrated excellent potential for noninvasive, rapid and cost-effective diagnostics. Recent advancements have resulted in improved sensor selectivity, stability, sensitivity and compatibility with complex saliva samples. Integration with microfluidics and LOC technologies has shown promise in enhancing sensor efficiency and accuracy. In addition, wearable and implantable sensors enable continuous, real-time monitoring of salivary analytes, opening new avenues for personalized health care and disease management.

This review presents an up-to-date overview of electrochemical sensors for analyte detection in saliva, offering insights into their design, fabrication and performance. It highlights the originality and value of integrating electrochemical sensing with microfluidics, wearable/implantable technologies and point-of-care testing platforms. The review also identifies challenges and limitations, such as interference from other saliva components and the need for improved stability and reproducibility. Future prospects include the development of novel microfluidic devices, advanced materials and user-friendly diagnostic devices to unlock the full potential of saliva-based electrochemical sensing in clinical practice.

Ferrofluids are aqueous or non-aqueous solutions with colloidal particles of iron oxide nanoparticles with high magnetic characteristics. Their magnetic characteristics enable them to be controlled and manipulated when ferrofluids are exposed to magnetic fields. This study aims to inspect the features of unsteady stagnation point flow (SPF) and heat flux from the surface by incorporating ferromagnetic particles through a special kind of second-grade fluid (SGF) across a movable sheet with a nonlinear heat source/sink and magnetic field effect. The mass suction/injection and stretching/shrinking boundary conditions are also inspected to calculate the fine points of the features of multiple solutions.

The leading equations that govern the ferrofluid flow are reduced to a group of ordinary differential equations by applying similarity variables. The converted equations are numerically solved through the bvp4c solver. Afterward, study and discussion are carried out to examine the different physical parameters of the characteristics of nanofluid flow and thermal properties.

Multiple solutions are revealed to happen for situations of unsteadiness, shrinking as well as stretching sheets. Greater suction slows the separation of the boundary layers and causes the critical values to expand. The region where the multiple solutions appear is observed to expand with increasing values of the magnetic, non-Newtonian and suction parameters. Moreover, the fluid velocity significantly uplifts while the temperature declines due to the suction parameter.

The novelty of the work is to deliberate the impact of mass suction/injection on the unsteady SPF through the special second-grade ferrofluids across a movable sheet with an erratic heat source/sink. The confirmed results provide a very good consistency with the accepted papers. Previous studies have not yet fully explored the entire analysis of the proposed model.

This study aims to examine the negative effects of excessive product packaging (EPP), greenwashing and green confusion on green brand equity (GBE). Furthermore, the moderating role of brand credibility in mitigating the negative effects of green marketing was investigated.

A within-subject experiment was conducted to evaluate excessive versus minimal product packaging to test the proposed hypotheses. Data analysis was performed with SmartPLS 3.3.3, which analyzed data from 206 consumers.

The results showed that EPP positively predicts greenwashing and green confusion. However, greenwashing has a negative impact on GBE. Brand credibility was also discovered to moderate the negative relationship between greenwashing and GBE, thereby reducing the negative effect of greenwashing.

The findings imply that marketing managers should understand the consumers’ concerns for the environment, making product and brand strategies that promote environmental protection and sustainability.

This study contributes to the green marketing literature by empirically validating the positive impacts of EPP on greenwashing and green confusion, as well as the negative influence of greenwashing on GBE. Furthermore, it reveals how brand credibility can reduce the harmful effects of greenwashing on GBE.

Examinamos los efectos negativos del embalaje excesivo de los productos, el “greenwashing” y la confusión verde sobre el valor de la marca verde. Además, se investigó el papel moderador de la credibilidad de la marca para mitigar los efectos negativos del marketing ecológico.

Se llevó a cabo un experimento intra-sujeto para evaluar el embalaje excesivo de los productos frente al mínimo envase posible, con el fin de comprobar las hipótesis propuestas. El análisis de los datos se realizó con SmartPLS 3.3.3, con una muestra de 206 consumidores.

Los resultados mostraron que el embalaje excesivo de los productos predice positivamente el greenwashing y la confusión ecológica. Sin embargo, el greenwashing tiene un impacto negativo en el valor de la marca verde. También se descubrió que la credibilidad de la marca modera la relación negativa entre el greenwashing y el valor de la marca verde, reduciendo así el efecto negativo del greenwashing.

Las conclusiones implican que los directores de marketing deben comprender las preocupaciones de los consumidores por el medio ambiente, elaborando estrategias de producto y de marca que promuevan la protección del medio ambiente y la sostenibilidad.

Este estudio contribuye a la bibliografía sobre el marketing ecológico al validar empíricamente los efectos positivos del embalaje excesivo de los productos sobre el greenwashing y la confusión ecológica, así como la influencia negativa del greenwashing sobre el valor de la marca ecológica. Además, revela cómo la credibilidad de la marca puede reducir los efectos perjudiciales del greenwashing sobre el valor de la marca verde.

我们研究了产品过度包装、洗绿和绿色混淆对绿色品牌资产的负面影响。此外, 我们还研究了品牌信誉在减轻绿色营销负面影响中的调节作用。

我们进行了一项受试者内实验, 以评估产品过度包装和最小包装, 从而检验所提出的假设。用SmartPLS 3.3.3进行数据分析, 该软件分析了206来自名消费者的数据。

结果显示, 过度的产品包装正向预测了洗绿和绿色混淆。然而, 洗绿对绿色品牌资产有负面的影响。品牌信誉也被发现可以调节洗绿和绿色品牌资产之间的负面关系, 从而减少洗绿的负面影响。

研究结果表明, 营销经理应该了解消费者对环境的关注, 制定促进环境保护和可持续发展的的产品和品牌战略。

本研究通过实证验证产品过度包装对洗绿和绿色混淆的积极影响, 以及洗绿对绿色品牌资产的负面影响, 为绿色营销文献做出了贡献。此外, 它还揭示了品牌信誉如何减少洗绿对绿色品牌资产的有害影响。

绿色营销, 洗绿, 绿色混淆, 品牌资产, 品牌信誉, 以及产品过度包装

文章类型： 研究型论文