Explore the vast range of titles available.

With the development of artificial intelligence, path planning of Autonomous Mobile Robot (AMR) has been a research hotspot in recent years. This paper proposes the improved A* algorithm combined with the greedy algorithm for a multi-objective path planning strategy. Firstly, the evaluation function is improved to make the convergence of A* algorithm faster. Secondly, the unnecessary nodes of the A* algorithm are removed, meanwhile only the necessary inflection points are retained for path planning. Thirdly, the improved A* algorithm combined with the greedy algorithm is applied to multi-objective point planning. Finally, path planning is performed for five target nodes in a warehouse environment to compare path lengths, turn angles and other parameters. The simulation results show that the proposed algorithm is smoother and the path length is reduced by about 5%. The results show that the proposed method can reduce a certain path length.

Surpassing traditional communications, interactive installations in the digital era prefer a sophisticated integration of sensing technologies and programming languages, so as to provide viewers with more profound experience. In this study interactive installations are taken as media to explore the ecological development of coral reef in further digital process through Arduino and Touch Designer programming. In this way, users can have immersive experience by two-way interactions with the device, thus expanding the understanding between humans and the natural environment. In addition, the innovative use of interactive installations in advancing ecological researches and potential new solutions to environmental problems through the art of programming are also discussed. Therefore, this study inspires new ideas from the harmonious coexistence of humans and the nature, providing insights into coral reef conservation and its sustainable ecological diversity.

Action prediction in videos refers to inferring the action category label by an early observation of a video. Existing studies mainly focus on exploiting multiple visual cues to enhance the discriminative power of feature representation while neglecting important structure information in videos including interactions and correlations between different object entities. In this paper, we focus on reasoning about the spatial–temporal relations between persons and contextual objects to interpret the observed video part for predicting action categories. With this in mind, we propose a novel spatial–temporal relation reasoning approach that extracts the spatial relations between persons and objects in still frames and explores how these spatial relations change over time. Specifically, for spatial relation reasoning, we propose an improved gated graph neural network to perform spatial relation reasoning between the visual objects in video frames. For temporal relation reasoning, we propose a long short-term graph network to model both the short-term and long-term varying dynamics of the spatial relations with multi-scale receptive fields. By this means, our approach can accurately recognize the video content in terms of fine-grained object relations in both spatial and temporal domains to make prediction decisions. Moreover, in order to learn the latent correlations between spatial–temporal object relations and action categories in videos, a visual semantic relation loss is proposed to model the triple constraints between objects in semantic domain via VTransE. Extensive experiments on five public video datasets (i.e., 20BN-something-something, CAD120, UCF101, BIT-Interaction and HMDB51) demonstrate the effectiveness of the proposed spatial–temporal relation reasoning on action prediction.

To address the problem of accurately evaluating age-friendly retrofit indicators in urban communities, this study constructs an evaluation model that takes into account user preferences and their interaction needs based on the social–ecological–technological systems (SETS) theory. The model aims to establish a set of precise community retrofit indicators, covering aspects such as public participation level, public ancillary facilities, green space layout, living environment building, health service support, and accessible design. By employing prioritization strategies, the model seeks to maximize resident satisfaction and promote harmonious coexistence between the community and the environment. Firstly, the retrofit evaluation indicators are formulated using the SETS theory. The entropy weight method (EWM) is then applied to determine the initial weights of these evaluation indicators, followed by the use of the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method to analyze the interrelationships among the indicators. The Kano model is integrated to adjust the weights, reflecting their importance. The final weights of the indicators are determined through normalization. Based on this, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method is employed to rank and analyze the importance of age-friendly retrofits in the community. Finally, six communities in Dalian, Liaoning Province, China, are selected as samples to evaluate and analyze the age-friendly retrofit indicators. Different methods are compared, and their advantages and disadvantages are ranked to validate the effectiveness and feasibility of the proposed approach. Based on the analysis results, specific design schemes for improving the identified shortcomings in age-friendly aspects of these communities are proposed, considering the needs of aging populations and taking into account community public facilities, accessible design renovations, and the enhancement of green space layouts. This study aims to explore the comprehensive benefits of an age-friendly retrofit in urban communities and provide reference for the deep integration of social, ecological, and technological benefits in urban renewal. The evaluation indicators, methods, and conclusions presented can serve as a decision-making basis for the renovation and renewal of aging urban communities, particularly in terms of age-friendly updates.

Lunar dust exhibits exceptionally strong adhesion, abrasiveness, and electrostatic charging due to long-term exposure to extreme temperature cycling (−183 °C to 127 °C), high vacuum, and intense radiation. With the rapid advancement of global lunar exploration programs and the planned construction of lunar bases, lunar dust has become a critical threat to exploration equipment, spacesuits, and spacecraft sealing systems. This paper systematically reviews recent progress in lunar dust mitigation technologies from the perspective of engineering application requirements. Key micro-mechanism factors governing dust adhesion and removal efficiency are analyzed, and the protection mechanisms and application scenarios of traditional lunar dust mitigation technologies are comprehensively discussed, including both active and passive approaches. Active protection technologies generally provide effective dust removal but suffer from high energy consumption, whereas passive strategies can reduce dust adhesion but face challenges in mitigating dynamic dust accumulation. To overcome these limitations, recent studies have increasingly focused on active–passive synergistic strategies that integrate surface modification with dynamic dust removal. Such approaches enable improved efficiency and adaptability by combining long-term dust resistance with real-time removal capability. Based on the latest research advances, this paper further proposes an integrated technical framework for the engineering design of efficient lunar dust protection.

Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages commonsense knowledge of actions from external resources to prompt a powerful pre-trained vision-language model for few-shot classification. We first collect large-scale language descriptions of actions, defined as text proposals, to build an action knowledge base. The collection of text proposals is done by filling in handcraft sentence templates with external action-related corpus or by extracting action-related phrases from captions of Web instruction videos.Then we feed these text proposals into the pre-trained vision-language model along with video frames to generate matching scores of the proposals to each frame, and the scores can be treated as action semantics with strong generalization. Finally, we design a lightweight temporal modeling network to capture the temporal evolution of action semantics for classification.Extensive experiments on six benchmark datasets demonstrate that our method generally achieves the state-of-the-art performance while reducing the training overhead to 0.001 of existing methods.

How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. It requires learning deep and rich features with superior distinctiveness for the subtle and abstract motions. Most existing methods generate features of a layer in a pure feedforward manner, where the information moves in one direction from inputs to outputs. And they rely on stacking more layers to obtain more powerful features, bringing extra non-negligible overheads. In this paper, we propose an Adaptive Recursive Circle (ARC) framework, a fine-grained decorator for pure feedforward layers. It inherits the operators and parameters of the original layer but is slightly different in the use of those operators and parameters. Specifically, the input of the layer is treated as an evolving state, and its update is alternated with the feature generation. At each recursive step, the input state is enriched by the previously generated features and the feature generation is made with the newly updated input state. We hope the ARC framework can facilitate fine-grained action recognition by introducing deeply refined features and multi-scale receptive fields at a low cost. Significant improvements over feedforward baselines are observed on several benchmarks. For example, an ARC-equipped TSM-ResNet18 outperforms TSM-ResNet50 with 48% fewer FLOPs and 52% model parameters on Something-Something V1 and Diving48.

Background Early detection of cancer can help patients with more effective treatments and result in better prognosis. Unfortunately, established cancer screening technologies are limited for use, especially for multi-cancer early detection. In this study, we described a serum-based platform integrating surface-enhanced Raman spectroscopy (SERS) technology with resampling strategy, feature dimensionality enhancement, deep learning and interpretability analysis methods for sensitive and accurate pan-cancer screening. Methods Totally, 1655 early-stage patients with breast cancer (BC, n  = 569), lung cancer (LC, n  = 513), thyroid cancer (TC, n  = 220), colorectal cancer (CC, n  = 215), gastric cancer (GC, n  = 100), esophageal cancer (EC, n  = 38), and 1896 healthy controls (HC) were enrolled. The serum SERS spectra were obtained from each participant. Data dimension enhancement was conducted by heatmap transformation and continuous wavelet transform (CWT). The dimensionalization SERS spectral data were subsequently analyzed by residual neural network (ResNet) as convolutional neural network (CNN) algorithm. Class activation mapping (CAM) method was performed to elucidate the potential biological significance of spectral data classification. Results All participants were divided into a training set and a test set with a ratio of 7:3. The BorderlineSMOTE method was selected as the most appropriate resampling strategy and the deep neural network (DNN) model achieved desirable performance among all groups (accuracy rate: 93.15%, precision rate: 88:46%, recall rate: 85.68%, and F1-score: 86.98%), with the generated AUC values of 0.991 for HC, 0.995 for BC, 0.979 for LC, 0.996 for TC, 0.994 for CC, 0.982 for GC, and 0.941 for EC, respectively. Furthermore, the combination use of SERS spectra data and ResNet (form of heatmap) were also capable of effectively distinguishing different categories and making accurate predictions (accuracy rate: 94.75%, precision rate: 89.02, recall rate: 86.97, and F1-score: 87.88), with the AUC values of 0.996 for HC, 0.995 for BC, 0.988 for LC, 0.999 for TC, 0.993 for CC, 0.985 for GC, and 0.940 for EC, respectively. Additionally, strong wave number range of the spectral data was observed in the CAM analysis. Conclusions Our study has offered a highly effective serum SERS-based approach for multi-cancer early detection, which might shed new light on cancer screening in clinical practice.

Zika virus (ZIKV) is a Flavivirus that has spread globally since its initial reporting. Transmitted to humans via multiple mosquito species, its typical symptoms (e.g., Guillain-Barre syndrome [GBS] and neonatal microcephaly) pose severe public health challenges. Based on existing research, the pathogenic characteristics of ZIKV are largely shaped by host molecular pathways, endowing the virus with an enhanced ability toward specific host cell types. On the other hand, ZIKV achieves intracellular survival and increased pathogenicity by evading the human immune system. Host innate immune responses (autophagy, apoptosis, RNAi, interferon signaling) exert dual effects in ZIKV infection-mediating viral clearance in somatic cells for effective virus control, while aberrant activation or viral evasion of these responses in neural progenitor cells and placental trophoblasts triggers immunopathology, which is the core mechanism of ZIKV neuroinvasion and congenital microcephaly. However, no systematic summary of its precise invasion and defense mechanisms currently exists. This review outlines mechanistic insights into the pathophysiology of ZIKV infection and the strategic mechanisms by which ZIKV evades the host immune system through pathways including autophagy, apoptosis, RNA interference (RNAi), and cell cycle control. We also highlight key limitations in current research, including reliance on in vitro cell lines and animal models that may not fully recapitulate human infection, as well as unresolved mechanistic details of viral-host protein interactions. This work aims to integrate existing knowledge on ZIKV-host crosstalk, providing a framework for future investigations and a basis for developing targeted intervention strategies. Importance. Research on ZIKV is critical due to its global public health impact, particularly its link to severe birth defects like microcephaly and neurological complications. Understanding ZIKV transmission, pathogenesis, and interactions with human hosts provides a scientific basis for the development of potential preventive strategies, diagnostic tools, and vaccine candidates. These studies also illuminate how viruses adapt to novel environments, thereby facilitating preparedness for future outbreaks. Additionally, ZIKV research strengthens global surveillance systems and fosters collaboration across disciplines, benefiting responses to related mosquito-borne diseases. By addressing ZIKV’s unique challenges, this research may help mitigate immediate public health threats posed by ZIKV and provide insights for advancing broader virological knowledge, ultimately protecting vulnerable populations and enhancing long-term health security. The core argument of this review posits that ZIKV engages in a dynamic interplay with the host innate and adaptive immune systems by regulating key pathways such as autophagy, apoptosis, RNAi and cell cycle. The disruption of this equilibrium constitutes the central mechanism underlying pathological features including neurological damage and vertical transmission. This study aims to systematically elucidate the molecular basis of this interaction, thereby providing verifiable theoretical targets for targeted intervention strategies.

Background Chromatin regulators (CRs) play a critical role in tumorigenesis, drug response, and prognosis, with dysregulation of chromatin regulator genes (CRGs) potentially disrupting the tumor immune microenvironment (TME) and influencing immune responses in cervical cancer. However, the prognostic and therapeutic implications of integrating CRGs and TME parameters in cervical cancer remain poorly understood. Methods This study used prognostic CRGs and TME cell signatures identified through Cox regression and Kaplan–Meier survival analyses to construct the CRG and TME score. The CRG score for each cell was calculated by integrating single-cell and spatial transcriptome, which were subsequently integrated to develop a CRG-TME classifier for prognostic prediction. The prognosis, somatic mutations, immune characteristics, therapeutic benefits, and drug sensitivity were then analyzed across CRG-TME defined subgroups. Results Both CRG score and TME score demonstrated prognostic value, and the high CRG score group showed distinct alterations in TME signaling dynamics and increased intensity of intercellular communication. Patients in CRG low /TME high subgroup exhibited enhanced prognosis and therapeutic responses compared to other subgroups, attributable to variations in tumor somatic mutations, immune-related molecules, cancer signaling pathways and drug sensitivity. Additionally, the clinical sample verification and in vitro experiments demonstrated that the key prognostic gene TSPYL2 was downregulated in cervical cancer tissues and overexpression of TSPYL2 inhibited the malignant progression of cervical cancer cells via regulating MAPK pathway and immune escape. Conclusions This study develops a novel CRG-TME classifier to predict prognosis and therapy response in cervical cancer and unveils the inhibitory effect and underlying mechanism of TSPYL2 on cervical cancer progression.