Fusion Mechanism Research Articles

Spectrum of Resistance Mechanisms to ALK TKIs in NSCLC: Largest Single-Center Experience from India

Abstract Introduction Anaplastic lymphoma kinase (ALK) rearranged non-small cell lung carcinoma (NSCLC) has emerged as a distinct entity with growing number of potent ALK tyrosine kinase inhibitors (TKIs). Despite showing durable responses and promising survival rates, resistance to these ensue. This is the largest series of repeat biopsies from patients of ALK-positive NSCLC progressing on ALK-directed therapy from this part of the world. Using a combinatorial approach of genomics and histology, we describe the spectrum of various resistance mechanisms encountered. Methods This is a cross-sectional study recruiting ALK-positive NSCLC cases who have progressed on any line ALK TKI and have undergone repeated biopsies followed by genomic sequencing by next-generation sequencing (NGS). Results Thirty-two ALK-positive NSCLC patients progressed on TKI were enrolled. Median age was 53 years (range: 36–75 years) with a male predilection (male:female 1.3:1). Twenty-seven (84.4%) cases harbored an additional resistance mechanism. Eighteen of these harbored an on-target ALK alteration, with L1196M gatekeeper mutation being the most common, in 11 cases, and G1202 alteration in 3 cases. In 9 cases an off-target alteration was detected, the most frequent being TP53 mutation in 8 cases, KRAS mutation in 4 cases and MET amplification in 3 cases. Four patients underwent sequential NGS testing and allele frequency changes in ALK fusion and resistance mechanisms were demonstrated. Sixteen patients have been offered lorlatinib therapy, the median progression-free survival of which has not yet been reached. Conclusion This is the largest series depicting ALK resistance mechanisms from a single center to date. The SPACEWALK study which demonstrated ALK TKI resistance mechanisms using plasma-based genotyping was a multicentric study. The spectrum encountered in this study is distinct from the rest of the world, thus highlighting heterogeneity within ALK-rearranged tumors. Comprehensive clinical evaluation at disease progression coupled with NGS-based genotyping will pave the way for lucid understanding of disease biology, thus aiding in the institution of optimal therapy.

GS-DeepLabV3+: A mountain tea disease segmentation network based on improved shuffle attention and gated multidimensional feature extraction

The prevention and control of Camellia Oleifera diseases can produce significantly comprehensive economic benefits. And precisely identifying the types of diseases on oil tea leaves can enhance the effectiveness of pest and disease control. Currently, the most effective deep learning methods for segmentation are suffering from the challenges such as indistinct disease spots on the actual oil tea leaves that are difficult to differentiate from the background, the high similarities in characteristics between different diseases, and the small target area of disease regions that are easily ignored. In this paper, GS-DeepLabV3+ network is proposed, which is an improvement upon DeepLabV3+ and aims to effectively enhance disease identification and segmentation rates. Initially, a gated pyramid feature fusion structure is proposed, utilizing a special module to merge features of different dimensions to enhance differentiation of similar features. Secondly, an improved grouped attention fusion mechanism is introduced, which allocates channel and spatial weights to different feature groups, enhancing the extraction of detailed features. Lastly, we substituted the backbone network of DeepLabV3+ with the more lightweight MobileNetV2, which significantly reduces the number of parameters while more stably extracting multidimensional features. In comparison with the existing segmentation networks on a self-created oil tea leaf disease data set, GS-DeepLabV3+ achieved a mIoU of 87.77% and an average pixel accuracy of 94.55%. Compared to the base DeepLabV3+ network, there was a 4.14% improvement in mIoU, a 3.58% increase in mPA, and a 1.4% rise in precision. The improved attention mechanism contributed to a 1.98% increase in mIoU, and the gated multidimensional fusion mechanism resulted in a 1.03% improvement. These enhancements can provide technical references for crop protection and pest disease segmentation.

Spontaneous and Chemically Induced Genome Doubling and Polyploidization in Vegetable Crops

Plant ploidy manipulation is often required for breeding purposes. However, there is no comprehensive review covering genome doubling in vegetable crops despite the abundance of data for a large number of vegetable species. Similar to other species, genome doubling is required in vegetable crops to obtain doubled haploids (DHs). It is also utilized for the production of polyploids to overcome interspecific hybrid sterility and improve agricultural traits. Spontaneous haploid genome duplication (SHGD) occurs in many Apiaceae, Brassicaceae, Cucurbitaceae, and Solanaceae crops, allowing for the laborious treatment with antimitotic agents to be bypassed. SHGD mechanisms are not fully understood, but existing data suggest that SHGD can occur via nuclear fusion, endoreduplication, or other mechanisms during microspore or ovule early embryogenic development. Other studies show that SHGD can occur at later developmental stages during extended plant growth in vitro or ex vitro, possibly due to the presence of phytohormones in the medium and/or diploid cell competitive advantage. For unresponsive accessions and species with rare SHGD, such as onion (Allium cepa L.) and beet cultivars (Beta vulgaris subsp. vulgaris L.), antimitotic agent treatment has to be applied. Antimitotic agent application efficiency depends on the treatment conditions, especially the agent concentration and exposure time. Also, plant developmental stage is critical for agent accessibility and plant survival. The existing methods can be used to further improve genome doubling methodology for major vegetable crops and other species.

Improved Object Detection Algorithm Based on Multi-scale and Variability Convolutional Neural Networks

This paper proposes an improved object detection algorithm based on a dynamically deformable convolutional network (D-DCN), aiming to solve the multi-scale and variability challenges in object detection tasks. First, we review traditional methods in the field of object detection and introduce the current research status of improved methods based on multi-scale and variability convolutional neural networks. Then, we introduce in detail our proposed improved algorithms, including an improved feature pyramid network and a dynamically deformable network. In the improved feature pyramid network, we introduce a multi-scale feature fusion mechanism to better capture target information at different scales. In dynamically deformable networks, we propose dynamic offset calculations and dynamic convolution operations to achieve dynamic adaptation to the target shape and pose. We also validate our method by conducting experiments on the datasets KITTI and Caltech. Finally, we design a comprehensive loss function that considers both location localization error and category classification error to guide model training. Experimental results show that our improved algorithm achieves significant performance improvements in target detection tasks, with higher accuracy and robustness compared with traditional methods. Our work provides an effective method to solve the multi-scale and variability challenges in target detection tasks and has high practical value and prospects for general application.

Enhancing Multimodal Emotion Recognition through Attention Mechanisms in BERT and CNN Architectures

Emotion detection holds significant importance in facilitating human–computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. The primary research challenge involves developing models that can accurately interpret and analyze emotions from both auditory and textual data, whereby auditory data require optimizing CNNs to detect subtle and intense emotional fluctuations in speech, and textual data necessitate access to large, diverse datasets to effectively capture nuanced emotional cues in written language. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers to enable profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method here undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field.

Data-efficient multimodal human action recognition for proactive human–robot collaborative assembly: A cross-domain few-shot learning approach

With the recent vision of Industry 5.0, the cognitive capability of robots plays a crucial role in advancing proactive human–robot collaborative assembly. As a basis of the mutual empathy, the understanding of a human operator’s intention has been primarily studied through the technique of human action recognition. Existing deep learning-based methods demonstrate remarkable efficacy in handling information-rich data such as physiological measurements and videos, where the latter category represents a more natural perception input. However, deploying these methods in new unseen assembly scenarios requires first collecting abundant case-specific data. This leads to significant manual effort and poor flexibility. To deal with the issue, this paper proposes a novel cross-domain few-shot learning method for data-efficient multimodal human action recognition. A hierarchical data fusion mechanism is designed to jointly leverage the skeletons, RGB images and depth maps with complementary information. Then a temporal CrossTransformer is developed to enable the action recognition with very limited amount of data. Lightweight domain adapters are integrated to further improve the generalization with fast finetuning. Extensive experiments on a real car engine assembly case show the superior performance of proposed method over state-of-the-art regarding both accuracy and finetuning efficiency. Real-time demonstrations and ablation study further indicate the potential of early recognition, which is beneficial for the robot procedures generation in practical applications. In summary, this paper contributes to the rarely explored realm of data-efficient human action recognition for proactive human–robot collaboration.

A Vision/Inertial Navigation/Global Navigation Satellite Integrated System for Relative and Absolute Localization in Land Vehicles.

This paper presents an enhanced ground vehicle localization method designed to address the challenges associated with state estimation for autonomous vehicles operating in diverse environments. The focus is specifically on the precise localization of position and orientation in both local and global coordinate systems. The proposed approach integrates local estimates generated by existing visual-inertial odometry (VIO) methods into global position information obtained from the Global Navigation Satellite System (GNSS). This integration is achieved through optimizing fusion in a pose graph, ensuring precise local estimation and drift-free global position estimation. Considering the inherent complexities in autonomous driving scenarios, such as the potential failures of a visual-inertial navigation system (VINS) and restrictions on GNSS signals in urban canyons, leading to disruptions in localization outcomes, we introduce an adaptive fusion mechanism. This mechanism allows seamless switching between three modes: utilizing only VINS, using only GNSS, and normal fusion. The effectiveness of the proposed algorithm is demonstrated through rigorous testing in the Carla simulation environment and challenging UrbanNav scenarios. The evaluation includes both qualitative and quantitative analyses, revealing that the method exhibits robustness and accuracy.

Multi-source information contrastive learning collaborative augmented conversational recommender systems

Conversational Recommender Systems (CRS) aim to provide high-quality items to users in fewer conversation rounds using natural language. Despite various attempts that have been made, there are still some problems: Previous CRS only learned item representations in a single knowledge graph and ignored item tags; information gaps exist in the same items from different knowledge graphs and information popularity both affect user preferences; system generated responses lack descriptiveness and diversity. To address these problems and fully utilize external knowledge, we propose a Multi-source Information Contrastive Learning Collaborative Augmented method (MCCA\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extbf{MCCA}$$\\end{document}), which aims to mine the potential tag preferences of users in dialogues as well as enhance the accuracy of item representation and user preference modeling. Specifically, we utilize the obtained items and their tags to construct a new knowledge graph that incorporates movie tags. We design a Multi-source Item Fusion mechanism (MIF\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extbf{MIF}$$\\end{document}) to bridge the information gaps between items from different knowledge graphs and then utilize unsupervised contrastive learning to enhance the items’ representation capability after MIF. Additionally, a Multi-Tag Fusion mechanism (MTF\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extbf{MTF}$$\\end{document}) is designed to combine user-perceived information (i.e., tag popularity) and keywords obtained from reviews to co-enhance user preference representations through items and tags, and to incorporate fused item and tag features into the conversation module. Extensive experiments on two datasets show that MCCA significantly outperforms state-of-the-art methods. The source code will be available at https://github.com/lhy-cqut/MCCA.

HIV and influenza fusion peptide interactions with (dis)ordered lipid bilayers: Understanding mechanisms and implications for antimicrobial and antiviral approaches

The interactions of viral fusion peptides from influenza (E4K and Ac-E4K) and human immunodeficiency virus (gp41 and Ac-gp41) with planar lipid bilayers and monolayers was investigated herein. A combination of surface-sensitive techniques, including quartz crystal microbalance with dissipation (QCM-D), Langmuir-Blodgett area-pressure isotherms with Micro-Brewster angle microscopy, and neutron reflectometry, was employed. Differences in the interactions of the viral fusion peptides with lipid bilayers featuring ordered and disordered phases, as well as lipid rafts, were revealed. The HIV fusion peptide (gp41) exhibited strong binding to the DOPC/DOPS bilayer, comprising a liquid disordered phase, with neutron reflectometry (NR) showing interaction with the bilayer's headgroup area. Conversely, negligible binding was observed with lipid bilayers in a liquid ordered phase. Notably, the influenza peptide (E4K) demonstrated slower binding kinetics with DOPC/DOPS bilayers and distinct interactions compared to gp41, as observed through QCM-D. This suggests different mechanisms of interaction with the lipid bilayers: one peptide interacts more within the headgroup region, while the other is more involved in transmembrane interactions. These findings hold implications for understanding viral fusion mechanisms and developing antimicrobials and antivirals targeting membrane interactions. The differential binding behaviours of the viral fusion peptides underscore the importance of considering membrane composition and properties in therapeutic strategy design.

Multi-Scale Fusion Siamese Network Based on Three-Branch Attention Mechanism for High-Resolution Remote Sensing Image Change Detection

Remote sensing image change detection (CD) is an important means in remote sensing data analysis tasks, which can help us understand the surface changes in high-resolution (HR) remote sensing images. Traditional pixel-based and object-based methods are only suitable for low- and medium-resolution images, and are still challenging for complex texture features and detailed image detail processing in HR images. At present, the method based on deep learning has problems such as inconsistent fusion and difficult model training in the combination of the difference feature information of the deep and shallow layers and the attention mechanism, which leads to errors in the distinction between the changing region and the invariant region, edge detection and small target detection. In order to solve the above problems of inconsistent fusions of feature information aggregation and attention mechanisms, and indistinguishable change areas, we propose a multi-scale feature fusion Siamese network based on attention mechanism (ABMFNet). To tackle the issues of inconsistent fusion and alignment difficulties when integrating multi-scale fusion and attention mechanisms, we introduce the attention-based multi-scale feature fusion module (AMFFM). This module not only addresses insufficient feature fusion and connection between different-scale feature layers, but also enables the model to automatically learn and prioritize important features or regions in the image. Additionally, we design the cross-scale fusion module (CFM) and the difference feature enhancement pyramid structure (DEFPN) to assist the AMFFM module in integrating differential information effectively. These modules bridge the spatial disparity between low-level and high-level features, ensuring efficient connection and fusion of spatial difference information. Furthermore, we enhance the representation and inference speed of the feature pyramid by incorporating a feature enhancement module (FEM) into DEFPN. Finally, the BICD dataset proposed by the laboratory and public datasets LEVIR-CD and BCDD are compared and tested. We use F1 score and MIoU values as evaluation metrics. For AMBMFNet, the F1 scores on the three datasets are 77.69%, 81.57%, and 77.91%, respectively, while the MIoU values are 84.65%, 85.84%, and 84.54%, respectively. The experimental results show that ABMFNet has better effectiveness and robustness.

An adaptive multi-scale feature fusion and adaptive mixture-of-experts multi-task model for industrial equipment health status assessment and remaining useful life prediction

Health status (HS) assessment and remaining useful life (RUL) prediction are two essential tasks in prognostics and health management. Though HS assessment and RUL prediction based on multi-task learning have achieved considerable progress, the following three challenges still exist. Firstly, it is assumed that these two tasks are related, and the inter-task correlation is ignored. Secondly, it is difficult to extract complex degradation features using the traditional deep network as the shared-bottom structure. Thirdly, inter-task heterogeneity is not considered, which limits the model's generalization ability to different tasks. To overcome these challenges, this work proposes an adaptive multi-scale feature fusion and adaptive mixture-of-experts multi-task model for HS assessment and RUL prediction. By exploiting inter-task affinity to measure the correlation between tasks, it provides guidance for multi-task modeling of industrial equipment. Then, an adaptive multi-scale feature fusion mechanism is designed as the shared-bottom structure to improve the feature extraction ability of the multi-task model. Besides, considering inter-task heterogeneity, an adaptive mixture-of-experts mechanism is developed to adaptively fuse expert features for specific tasks, which enhances the model's adaptability and generalization to different tasks. Finally, experiments on engine degradation data and tool wear data demonstrate that the proposed model outperforms other state-of-the-art baselines.

Multi-modal lifelog data fusion for improved human activity recognition: A hybrid approach

The rapid growth of lifelog data, collected through smartphones and wearable devices, has driven the need for better Human Activity Recognition (HAR) solutions. However, lifelog data is complex and challenging to analyze due to its diverse sources of information. In response, we introduce an innovative hybrid data fusion framework for HAR. This framework comprises three key elements: a hybrid fusion mechanism, an attention-based classifier, and an ensemble-based recognition approach. Our hybrid fusion mechanism expertly combines the advantages of late and intermediate fusion, enhancing classification performance and improving the network’s ability to learn connections between different data modalities. Additionally, our solution incorporates an attention-based classifier and an ensemble approach, ensuring robust and consistent performance in real-world scenarios. We evaluated our method across multiple public lifelog datasets, demonstrating that our hybrid fusion approach consistently surpasses existing fusion strategies in HAR, promising significant advancements in activity recognition.

Intelligent event-based lip reading word classification with spiking neural networks using spatio-temporal attention features and triplet loss

Lip reading is a visual alternative to enhance the intelligence of traditional speech recognition, which can benefit from retina-like event cameras that focus on dynamic movements. Spiking Neural Networks (SNNs) are inherently well-suited to cooperate with event cameras. However, employing SNN for event-based lip reading presents significant challenges, particularly in effectively extracting spatio-temporal features from input events and distinguishing between phonetically similar elements. To address these challenges, this paper proposes a novel event-based lip-reading model that leverages the SNN framework, enriched by a designed Spatial-Temporal Attention Block (STAB) and a triplet loss. Specifically, STAB comprises both spatial and temporal attention branches, dynamically emphasizing those spatial and temporal characteristics most reflective of lip movements. STAB also includes a fusion mechanism to integrate these spatial and temporal insights, providing a comprehensive and focused representation of lip movements. In addition, we enhance the model by incorporating triplet loss into the SNN training process, further improving the model's ability to distinguish between visually similar words. Experimental results show the superior performance of our SNN and validate the effect of STAB and triplet loss. We also conduct the energy consumption analysis to affirm the model's energy efficiency.

Pointer generation and main scale detection for occluded meter reading based on generative adversarial network

The meter reading with machine vision greatly improves the efficiency of industrial monitoring. However, the pointer and scales of the meter can be occluded by rain or dirt, which greatly reduces the accuracy of the meter reading recognition. To solve this problem, we propose a generative adversarial network (PMS-GAN) with pointer generation and main scale detection for occluded meter reading. Specifically, dilated convolution block is designed to correlate separated pointer features. Then multi-scale feature fusion mechanism is proposed to guarantee the precision of pointer generation and main scale detection with guidance of semantic information. Moreover, feature enhancement mechanism is proposed to construct the long-range relationship for generating pointer under high occlusion. Finally, the reading is accomplished by calculating local angle with generated pointer and detected main scales. Experiments show that PMS-GAN can generate more intact pointer and detect main scales to guarantee the success and accuracy of occluded meter reading.

A novel two-stage multi-objective dispatch model for a distributed hybrid CCHP system considering source-load fluctuations mitigation

Small-scale distributed energy systems with combined cooling, heating, and power (DES-CCHP) production have attracted international interest. However, fluctuating loads and renewable energies continuously disturb the real-time operation of DES-CCHP and even the connected grid, hindering the broad application of grid-connected DES-CCHP. In this paper, a novel model predictive control (MPC) based two-stage strategy is developed for DES-CCHP, with multiple timescales consideration. In the first stage, a multi-objective MPC is built with inheritance and fusion mechanisms of multi-step scheduling instructions, simultaneously minimizing operation costs and power fluctuations. The second stage performs intelligent decision-making on the results of the first stage, which allows appropriate state-switching instructions to ensure economy. Meanwhile, the decision-making rejects the unnecessary one and triggers a second-round flexibility-based interventional optimization to revise scheduling planning. The case studies show that compared to dispatch without MPC, the economic single-objective MPC, single-stage multi-objective MPC (only applies the first-stage models), and two-stage multi-objective MPC save costs by 5.31 %, 4.80 %, and 4.57 %, respectively. As for fluctuations mitigation, the single-stage and two-stage models significantly smooth power fluctuations by 51.66 % and 69.93 %, respectively. The proposed strategy operates DES-CCHP economically, stably, and grid-friendly under a rugged operating environment.

Numerical simulation and experimental analysis of incomplete fusion mechanism of GH4169 and electroformed Ni electron beam welded joint

The quality of electron beam welding between GH4169 and electroformed Ni (E-Ni) has emerged as a pivotal factor in the manufacturing of hydrogen-oxygen engines. The welding process involving dissimilar materials, however, is susceptible to the occurrence of incomplete fusion defects, with the underlying causes of these defects remaining elusive. In order to enhance the welding quality of GH4169 and E-Ni and eliminate incomplete fusion defects, a novel finite element model integrating thermo-electro-magnetic multi-physical fields coupling was established in this study, revealing the formation mechanism of such defects. The results demonstrated that significant thermoelectric effects arose during the welding process due to the disparities in temperature gradients and Seebeck coefficients between GH4169 and E-Ni. The thermoelectric effect induces the emergence of a magnetic field, primarily concentrated within a 10 mm zone above the weld. Subsequently, this magnetic field causes a significant deflection of the electron beam towards the GH4169, specifically by 128 µm. This deviation ultimately results in the occurrence of incomplete fusion defects, compromising the welding quality. Based on the underlying mechanism of the thermoelectric effect on the electron beam, an inclined welding joint was designed, successfully eliminating the incomplete fusion defects at the root of the GH4169 and E-Ni electron beam welding joint. The resulting joint exhibited a remarkable strength of 411 MPa. The present analysis of the incomplete fusion defect formation mechanism provides theoretical support for the improvement of the electron beam welding process for GH4169 and E-Ni, pioneering a novel defect-free welding technique for these materials.

Interpreting the Process of Play Therapy from the Essence of Play Using the Philosophical Perspective of Fusion of Horizons

<p>遊戲治療越來越受到重視，遊戲的本質包含自由、自主、創造、美以及內在語言經驗的樣貌。本文透過高達美詮釋學的視域融合，指出遊戲者與遊戲的第一層視域融合，以及遊戲者與治療師或親子遊戲治療之受訓照顧者的第二層視域融合。治療師要在兩層次視域融合中不斷的貼近、對話及循環，以協助遊戲者在接觸當下時間的意識流中，形成一個帶著過去及未來經驗流的意義，從而達到遊戲治療的目的。在治療的視域融合中，建議作法為：（1）治療師勿過度把自己的創造及自主性放入遊戲，使遊戲者自由及創造力被壓抑；（2）若讓遊戲者在遊戲中擁有無限上綱的自由度，會使視域融合失去對話的空間；（3）讓遊戲者能被允許有容錯容亂的空間；（4）讓遊戲場域有冒險空間，培養遊戲者積極的感覺，表達出原不為人所知的情感路徑。透過視域融合機制，讓遊戲者在遊戲場域開放自己，經歷自主性的自由，貼近內在語言、探索情緒，進而達到視域融合的開放性。遊戲治療存在的多元理論與實務運作，治療師應持開放但保留的態度，反思自己的位置，及審視自己的習慣，而採納有限的觀點與做法，謙卑地開啟未來遊戲治療的更多可能、方式及知識的開展。</p> <p> </p><p>Play is one of the important assets to mankind. The essence of play characteristic includes freedom, autonomy, creativity, beauty, and image that show human inner language experiences. Through Gundam’s interpretation of the theory of knowledge, the fusion of horizons, the article builds two levels of fusion of horizons models: the first-level fusion of horizons model between the player and the play field, and the second-level model between the player and the therapist or the trained companion. In the process of both fusion of horizons models, continuous closeness, and dialogue and circulation, play therapy has formed a meaningful healing ability with the stream of consciousness that exists in the present time along with the past and future experience streams, and achieves the purpose of play therapy goals. The therapist should handle cautiously during the process of play therapy. In order to make the therapy process meaningful, some suggestions from the article are summarized as follows: (1) The therapist should be careful not to put their own creativity and autonomy into the game too much, so that the players themselves can play freely and creativity won’t be suppressed in the game; (2) The unlimited degree of freedom in the game makes the vision of the therapist and the child merge into an invalid dialogue; (3) Allow players a space where errors and disarray are permissible ; (4) There is space for adventure in the game field, which could cultivate the player’s positive feeling, and the player might express the previously unknown emotional path from the game world. Through the fusion mechanism, the player could open himself and have the opportunity to experience the freedom and autonomy from the play, and touch the phenomenon of inner voice to explore the emotions of the player and see the self-appearance. There should be an open and reserved attitude towards the other innovated methods of game therapy in epistemology. In the existing play therapy framework, we should learn from knowledge models and think about whether we are accustomed to controlling this play therapy performance by the own way. The performer of therapy framework should humbly open up the many possibilities, methods and knowledge development of future game therapy.</p> <p> </p>

Study on corrosion characteristics and mechanism of laser powder bed fusion of Mg–Zn–Zr alloy

Laser Powder Bed Fusion (LPBF) presents novel opportunities for the processing and manufacturing of magnesium (Mg) alloys. However, Mg alloys consistently face challenges with poor corrosion resistance. Consequently, it becomes imperative to delve into the corrosion behavior and mechanisms of Mg alloys formed through LPBF. This paper investigated the electrochemical corrosion behavior, the distribution of corrosion products, and the corrosion mechanism of LPBF ZK60 Mg alloy. The results show that the corrosion current density (Icorr) value of LPBF ZK60 Mg alloy is 3.76 μA∙cm−2. The hydrogen evolution in Hank's solution steadily increases with immersion time and reaches a stable state after 24 h. The corrosion rates calculated based on hydrogen evolution and weight loss are 2.1 mm/y and 2.4 mm/y, respectively. The corrosion resistance of LPBF ZK60 Mg alloy is predominantly affected by three factors: uneven microstructure, internal crack defects, and precipitate phases. The melt pool boundary is identified as a corrosion-vulnerable zone, which extends into the columnar crystal zone after corrosion. Crevice corrosion occurs at microcracks, and the precipitate phases within the grains and matrix induces galvanic corrosion. These findings suggest that the corrosion resistance of LPBF ZK60 Mg alloy may be regulated through targeted measures, such as eliminating cracks, achieving microstructure homogenization, and controlling the precipitate phases (including quantity, composition, and distribution).

A grid fault diagnosis framework based on adaptive integrated decomposition and cross-modal attention fusion

In large-scale power systems, accurately detecting and diagnosing the type of faults when they occur in the grid is a challenging problem. The classification performance of most existing grid fault diagnosis methods depends on the richness and reliability of the data, in addition, it is difficult to obtain sufficient feature information from unimodal circuit signals. To address these issues, we propose a deep residual convolutional neural network (DRCNN)-based framework for grid fault diagnosis. First, we design a comprehensive information entropy value (CIEV) evaluation metric that combines fuzzy entropy (FuzEn) and mutual approximation entropy (MutEn) to integrate multiple decomposition subsequences. Then, DRCNN and heterogeneous graph transformer (HGT) are constructed for extracting multimodal features and considering modal variability. In addition, to obtain the implicit information of multimodal features and control the degree of their performance, we propose to incorporate the cross-modal attention fusion (CMAF) mechanism in the synthesis framework. We validate the proposed method on the three-phase transmission line dataset and VSB power line dataset with accuracies of 99.4 % and 99.0 %, respectively. The proposed method also achieves superior performance compared to classical and state-of-the-art methods.

Enhancing instance segmentation: Leveraging multiscale feature fusion and attention mechanisms for automated fish weight estimation

The accurate estimation of fish weight relies on the crucial parameter of individual fish contour features. While instance segmentation proves effective in extracting fish contours, challenges arise from diverse fish postures and reduced image sharpness underwater. Current instance segmentation methods often struggle to effectively balance global and local detailed features, which can result in inaccurate positioning of contour keypoints and consequently limit the accuracy of fish weight estimation. To overcome this, our study introduces a novel instance segmentation network tailored for precise fish contour extraction. The proposed approach incorporates multi-scale feature fusion and an attention mechanism based on the Segmenting Objects by Locations (SOLO) network, referred to as SOLO-MFFA. This paper designs a multi-scale context aggregation module to integrate features with a wider range of receptive fields, augmenting the model's capability to comprehend both local features and global information. At the same time, the introduction of a mixed-domain attention mechanism emphasizes more critical channel features and simultaneously improves the localization accuracy of contour points. Compared with SOLO and its improved model CAM-SOLO on the fish instance segmentation dataset, SOLO-MFFA demonstrated an effective improvement, with a 4.3% and 1.6% increase in mAP (mean Average Precision), respectively. The Decoupled-SOLO-MFFA achieved higher mAP. The visualization results also demonstrate that the contour features extracted in this paper are smoother and more accurately positioned. Additionally, in comparison to other well-known instance segmentation networks, our method has demonstrated significant improvements in both qualitative and quantitative evaluations. Furthermore, the integration of contour features derived from Decoupled-SOLO-MFFA, along with binocular vision, was utilized for the precise estimation of fish perimeter and weight. The findings reveal a strong correlation between the perimeter calculated by Decoupled-SOLO-MFFA and the actual weight, with a notably reduced error in weight estimation. Compared to previous methods, RMSE, MAE, and MAPE of the linear model constructed in this paper decreased by 3.92, 3.19, and 1.4%.