Search Results (48)

With the ongoing miniaturization of smart devices, fine-grained hand gesture recognition using millimeter-wave radar has attracted increasing attention, yet practical deployment remains challenging in continuous-gesture segmentation, robust feature extraction, and reliable classification. This paper presents an end-to-end fine-grained gesture recognition framework based on frequency modulated continuous wave(FMCW) millimeter-wave radar, including gesture design, data acquisition, feature construction, and neural network-based classification. Ten gesture types are recorded (eight valid gestures and two return-to-neutral gestures); for classification, the two return-to-neutral gesture types are merged into a single invalid class, yielding a nine-class task. A sliding-window segmentation method is developed using short-time Fourier transformation(STFT)-based Doppler-time representations, and a dataset of 4050 labeled samples is collected. Multiple signal classification(MUSIC)-based super-resolution estimation is adopted to construct range–time and angle–time representations, and instance-wise normalization is applied to Doppler and range features to mitigate inter-individual variability without test leakage. For recognition, a variable-channel deep residual shrinkage network (DRSN) is employed to improve robustness to noise, supporting single-, dual-, and triple-channel feature inputs. Results under both subject-dependent evaluation with repeated random splits and subject-independent leave one subject out(LOSO) cross-validation show that DRSN architecture consistently outperforms the RefineNet-based baseline, and the triple-channel configuration achieves the best performance (98.88% accuracy). Overall, the variable-channel design enables flexible feature selection to meet diverse application requirements. Full article

Under the dual driving forces of negative population growth and the cross-regional agglomeration of factors, the trend of urban shrinkage in China continues to intensify. This study examines 461 small towns in 26 mountainous counties of Zhejiang Province, constructing a multi-dimensional shrinkage identification model based on “population–economy–land use.” The spatiotemporal patterns of shrinkage were visualized using ArcGIS 10.8, while the driving factors were analyzed using the MGWR method. ① From 2010 to 2020, the shrinkage phenomenon in small towns across the 26 mountainous counties rapidly spread, with medium- and severe-shrinking towns increasing markedly, showing an irreversible trend. ② The spatial evolution pattern shows a phased characteristic, transitioning from “disordered scattered points” to “striped aggregation.” A “V”-shaped shrinkage belt formed along the “Kaihua–Jingning–Yongjia” axis, demonstrating strong spatial aggregation. ③ The shrinkage of small towns is driven by multiple factors. Rugged mountainous terrain constrains development, while urbanization and industrial restructuring, coupled with outmigration of young and middle-aged workers, accelerate aging and limit local specialty industries. Transportation, social services, and policy frameworks further influence shrinkage patterns. In response to the continuous shrinkage trend of small towns in mountainous areas, future efforts should adopt coordinated strategies such as smart shrinkage, industrial restructuring, and institutional innovation to achieve structural and systemic reshaping. Full article

Concrete structure integrity is significantly compromised by the primary problem of cracking. Typically, surface cracking (predominantly shrinkage-induced and thermal microcracking) is rectified using costly and time-consuming repair methods involving mortar and other techniques. Research efforts have recently shifted towards developing smart materials to reduce concrete’s propensity for cracking, enhance its structural stability, and prevent damage to its framework. Concrete designs with self-healing capabilities can safeguard against degradation and enhance long-term durability. Despite extensive research, a consensus on the optimal preparation and mechanical properties of self-healing concrete has yet to be reached. Within self-healing concrete that utilizes microcapsules, repair agents are dispersed throughout the matrix to form a bond and seal cracks as damage develops. From the viewpoint of a sustainable society, this approach appears to promote the use of construction materials. This study examined the impact of Dawson/urea–formaldehyde microcapsule-based self-healing concrete using strength tests, where the effectiveness of different microcapsule quantities (0.5–2% microcapsule by weight of cement) was assessed. Following the data and data analysis, it becomes evident that among all samples, the 1% microcapsule sample yields outstanding results for both 7-day and 28-day compressive strength. Full article

Efficient spectrum utilization is critical for meeting the growing data demands of modern wireless communication networks. Automatic Modulation Classification (AMC) plays a key role in enhancing spectrum efficiency by accurately identifying modulation schemes in received signals—an essential capability for dynamic spectrum allocation and interference mitigation, particularly in cognitive radio (CR) systems. With the increasing deployment of smart edge devices, such as IoT nodes with limited computational and memory resources, there is a pressing need for lightweight AMC models that balance low complexity with high classification accuracy. In this study, we propose a low-complexity, lightweight deep learning (DL) AMC model optimized for resource-constrained edge devices. We introduce a dual-path deep residual shrinkage network (DP-DRSN) with garrote thresholding for effective signal denoising, and we designed a compact hybrid CNN-LSTM architecture comprising only 27,072 training parameters. The proposed model achieved average classification accuracies of 61.20%, 63.78%, and 62.13% on the RML2016.10a, RML2016.10b, and RML2018.01a datasets, respectively, demonstrating a strong balance between model efficiency and classification performance. These results highlight the model’s potential for enabling accurate and efficient AMC on edge devices with limited resources, despite not surpassing state-of-the-art accuracy owing to its deliberate emphasis on computational efficiency. Full article

This mini-review article is focused on polymeric materials that comprise thermoresponsive and fluorescent organic units. The combination of fluorescent clusters/dots embedded in or grafted with polymers is not considered in this article. Here we review the preparation, characterization, and application of thermoresponsive polymers functionalized covalently with organic fluorescent compounds either compartmentalized or randomly distributed: block-copolymers, self-assembled micelles or vesicles, core–shell nanogels, and their temperature driven self-assembly/shrinkage/expansion and resulting effect in fluorescence: quenching, enhancing, shifting. The applications suggested for these smart-materials are reviewed in the last ten years and range from nanothermometers, drug delivery systems, agents for bioimaging, sensors, and advanced materials for theranostics focused on cancer treatment. This article is organized reviewing the preparation methods, the main characterization techniques, and the application, depending on polymer architecture and the emission wavelength of the fluorophores. Finally, comments, suggestions, and problems to be solved for the advancement of these materials in the future prior to real-life applications are given. Full article

This study explores the migration intentions of university students—representing the potential creative class—in Erzurum, a medium-sized city in eastern Turkey experiencing shrinkage. Within the theoretical framework of shrinking cities, it investigates how economic, social, physical, and personal factors influence students’ post-graduation stay or leave decisions. Survey data from 742 Architecture and Fine Arts students at Atatürk University were analyzed using factor analysis, logistic regression, and correlation to identify key migration drivers. Findings reveal that, in addition to economic concerns such as limited job opportunities and low income, personal development opportunities and social engagement also play a decisive role. In particular, the perception of limited chances for skill enhancement and the belief that Erzurum is not a good place to meet people emerged as the strongest predictors of migration intentions. These results suggest that members of the creative class are influenced not only by economic incentives but also by broader urban experiences related to self-growth and social connectivity. This study highlights spatial inequalities in access to cultural, educational, and social infrastructure, raising important questions about spatial justice in shrinking urban contexts. This paper contributes to the literature on shrinking cities by highlighting creative youth in mid-sized Global South cities. It suggests smart shrinkage strategies focused on creative sector development, improved quality of life, and inclusive planning to retain young talent and support sustainable urban revitalization. Full article

Automation in textile manufacturing plays a pivotal role in enhancing production efficiency, precision, and innovation. This study investigates the integration of intelligent technologies in the knitting sector, focusing on industrial flat knitting machines from a leading manufacturer and the use of the advanced software platform M1plus V7.5. The software’s capabilities for the digital design and simulation of complex patterned and structural knits are explored through the development and production of five experimental knitted designs. Each sample is evaluated in terms of its structural characteristics and dimensional behaviour after washing. The results highlight the potential of software-driven optimisation to improve product accuracy, reduce shrinkage variability, and support smart manufacturing practices in the textile industry. Full article

Accurate photovoltaic (PV) power forecasting is crucial for effective smart grid management, given the intermittent nature of PV generation. To address these challenges, this paper proposes the Temporal Bottleneck-enhanced Bidirectional Temporal Convolutional Network with Multi-Head Attention and Autoregressive (TB-BTCGA) model. It introduces a temporal bottleneck structure and Deep Residual Shrinkage Network (DRSN) into the Temporal Convolutional Network (TCN), improving feature extraction and reducing redundancy. Additionally, the model transforms the traditional TCN into a bidirectional TCN (BiTCN), allowing it to capture both past and future dependencies while expanding the receptive field with fewer layers. The integration of an autoregressive (AR) model optimizes the linear extraction of features, while the inclusion of multi-head attention and the Bidirectional Gated Recurrent Unit (BiGRU) further strengthens the model’s ability to capture both short-term and long-term dependencies in the data. Experiments on complex datasets, including weather forecast data, station meteorological data, and power data, demonstrate that the proposed TB-BTCGA model outperforms several state-of-the-art deep learning models in prediction accuracy. Specifically, in single-step forecasting using data from three PV stations in Hebei, China, the model reduces Mean Absolute Error (MAE) by 38.53% and Root Mean Square Error (RMSE) by 33.12% and increases the coefficient of determination ($R^2$) by 7.01% compared to the baseline TCN model. Additionally, in multi-step forecasting, the model achieves a reduction of 54.26% in the best MAE and 52.64% in the best RMSE across various time horizons. These results underscore the TB-BTCGA model’s effectiveness and its strong potential for real-time photovoltaic power forecasting in smart grids. Full article

Smart concrete is a structural element that can combine both sensing and structural capabilities. In addition, smart concrete can monitor the curing of concrete, positively impacting design and construction approaches. In concrete, if the curing process is not well developed, the structural element may develop cracks in this early stage due to shrinkage, decreasing structural mechanical strength. In this paper, a system of measurement using fiber Bragg grating (FBG) sensors for monitoring the curing of concrete was developed to evaluate autogenous shrinkage strain, temperature, and relative humidity (RH) in a single system. Furthermore, K-type thermocouples were used as reference temperature sensors. The results presented maximum autogenous shrinkage strains of 213.64 $\mu \epsilon$, 125.44 $\mu \epsilon$, and 173.33 $\mu \epsilon$ for FBG4, FBG5, and FBG6, respectively. Regarding humidity, the measured maximum relative humidity was 98.20 %RH, which was reached before 10 h. In this case, the recorded maximum temperature was 63.65 °C and 61.85 °C by FBG2 and the thermocouple, respectively. Subsequently, the concrete specimen with the FBG strain sensor embedded underwent a bend test simulating beam behavior. The measurement system can transform a simple structure like a beam into a smart concrete structure, in which the FBG sensors’ signal was maintained by the entire applied load cycles and compared with FBG strain sensors superficially positioned. In this test, the maximum strain measurements were 85.65 $\mu \epsilon$, 123.71 $\mu \epsilon$, and 56.38 $\mu \epsilon$ on FBG7, FBG8, and FBG3, respectively, with FBG3 also monitoring autogenous shrinkage strain. Therefore, the results confirm that the proposed system of measurement can monitor the cited parameters throughout the entire process of curing concrete. Full article

In the context of ongoing global urbanization, the disparity in urban development, marked by the dual phenomena of urban sprawl and urban shrinkage at the regional level, has become increasingly evident. In this vein, two land-related governance strategies—smart growth (SG) and smart shrinkage (SS)—emerge as potential remedies to these challenges, targeting urban expansion and shrinkage, respectively. This study bridges the gap in the fragmented discourse surrounding SG and SS by conducting a comprehensive comparative review on the respective literatures. Utilizing the Scopus database, our research employs trend analysis, text and topic mining, time node analysis, and regional analysis, augmented by qualitative reviews of seminal papers. The findings reveal a notable shift in research focus, with interest in SS surging around 2010 (the number of SS-related papers published after 2010 accounts for 92.3% of the total number of the entire study period) as attention to SG waned, suggesting an impending paradigm shift in urban sustainability. The analysis indicates that SS research lacks the disciplinary diversity, thematic breadth, and empirical depth of SG studies, underscoring a need for a more robust theoretical foundation to support urban sustainability. Furthermore, while both SG and SS derive from environmental science foundations, SG predominantly addresses the physical and landscape attributes of urban areas, whereas SS focuses more on socio-economic dimensions. Our findings point to an intrinsic link between SG and SS, which could lay the groundwork for their integration into a unified theoretical framework to better advance urban sustainability. Full article

Estimating and monitoring chlorophyll content is a critical step in crop spectral image analysis. The quick, non-destructive assessment of chlorophyll content in rice leaves can optimize nitrogen fertilization, benefit the environment and economy, and improve rice production management and quality. In this research, spectral analysis of rice leaves is performed using hyperspectral and fluorescence spectroscopy for the detection of chlorophyll content in rice leaves. This study generated ninety experimental spectral datasets by collecting rice leaf samples from a farm in Sichuan Province, China. By implementing a feature extraction algorithm, this study compresses redundant spectral bands and subsequently constructs machine learning models to reveal latent correlations among the extracted features. The prediction capabilities of six feature extraction methods and four machine learning algorithms in two types of spectral data are examined, and an accurate method of predicting chlorophyll concentration in rice leaves was devised. The IVSO-IVISSA (Iteratively Variable Subset Optimization–Interval Variable Iterative Space Shrinkage Approach) quadratic feature combination approach, based on fluorescence spectrum data, has the best prediction performance among the CNN+LSTM (Convolutional Neural Network Long Short-Term Memory) algorithms, with corresponding RMSE-Train (Root Mean Squared Error), RMSE-Test, and RPD (Ratio of standard deviation of the validation set to standard error of prediction) indexes of 0.26, 0.29, and 2.64, respectively. We demonstrated in this study that hyperspectral and fluorescence spectroscopy, when analyzed with feature extraction and machine learning methods, provide a new avenue for rapid and non-destructive crop health monitoring, which is critical to the advancement of smart and precision agriculture. Full article

Considerable attention has been paid to (1E)-1,2-diaryldiazenes (azo dyes) possessing liquid–crystalline (LC) and optical properties because they can switch color through thermal phase transitions and photoisomerizations. Although multifunctional molecules with both LC and fluorescent properties based on a donor–π-acceptor (D-π-A)-type tolane skeleton have been developed, functional molecules possessing LC and dye properties have not yet been developed. Therefore, this study proposes to develop LC dyes consisting of (1E)-1,2-diaryldiazenes with a D–π-A-type tolane skeleton as the aryl moiety. The (1E)-1,2-diaryldiazene derivatives exhibited a smectic phase, regardless of the flexible-chain structure, whereas the melting temperature was significantly increased by introducing fluoroalkyl moieties into the flexible chain. Evaluation of the optical properties revealed that compounds with decyloxy chains exhibited an orange color, whereas compounds with semifluoroalkoxy chains absorbed at a slightly blue-shifted wavelength, which resulted in a pale orange color. The thermal phase transition caused a slight color change accompanied by a change in the absorption properties, photoisomerization-induced shrinkage, and partial disappearance of the LC domain. These results indicate that (1E)-1,2-diaryldiazenes with a D–π-A-type tolane skeleton can function as thermo- or photoresponsive dyes and are applicable to smart windows and in photolithography. Full article

The coexistence of urban expansion and shrinkage in China has become increasingly apparent; therefore, the current strategic model of growth-oriented urban planning as the top-level design needs to be adjusted. This paper focuses on the city of Baishan, which is a typical shrinking city in China, and explores the feasibility of implementing the concept of smart shrinkage planning in shrinking cities in China by constructing a coupled PLUS-SD model. The results demonstrate the following conclusions: (1) The overall simulation of the coupled PLUS-SD model is superior to that of the PLUS model. In Baishan, the areas with the most changes in construction land will be located at the edges of the landforms by 2030. (2) Using the traditional planning scenario would only exacerbate the rate of construction land expansion in Baishan, deepening the incongruity between the city’s population and construction land. (3) The smart shrinkage scenario will require strict control of the scale of construction land and optimization of the structure of the urban construction land, which would push the city in the direction of healthy and sustainable development. (4) The concept of smart shrinkage planning is a scientific and feasible plan for realizing the efficient and sustainable use of construction land in shrinking cities. Full article

Vulnerabilities in smart contracts may trigger serious security events, and the detection of smart contract vulnerabilities has become a significant problem. In this paper, to solve the limitations of current deep learning-based vulnerability detection methods in extracting various code critical features, using the multi-scale cascade encoder architecture as the backbone, we propose a novel Multi-Scale Encoder Vulnerability Detection (MEVD) approach to hit well-known high-risk vulnerabilities in smart contracts. Firstly, we use the gating mechanism to design a unique Surface Feature Encoder (SFE) to enrich the semantic information of code features. Then, by combining a Base Transformer Encoder (BTE) and a Detail CNN Encoder (DCE), we introduce a dual-branch encoder to capture the global structure and local detail features of the smart contract code, respectively. Finally, to focus the model’s attention on vulnerability-related characteristics, we employ the Deep Residual Shrinkage Network (DRSN). Experimental results on three types of high-risk vulnerability datasets demonstrate performance compared to state-of-the-art methods, and our method achieves an average detection accuracy of 90%. Full article

The recent advances in smart beekeeping focus on remote solutions for bee colony monitoring and applying machine learning techniques for automatic decision making. One of the main applications is a swarming alarm, allowing beekeepers to prevent the bee colony from leaving their hive. Swarming is a naturally occurring phenomenon, mainly during late spring and early summer, but it is extremely hard to predict its exact time since it is highly dependent on many factors, including weather. Prevention from swarming is the most effective way to keep bee colonies; however, it requires constant monitoring by the beekeeper. Drone bees do not survive the winter and they occur in colonies seasonally with a peak in late spring, which is associated with the creation of drone congregation areas, where mating with young queens takes place. The paper presents a method of early swarming mood detection based on the observation of drone bee activity near the entrance to a hive. Audio recordings are represented by Mel Frequency Cepstral Coefficients and their first and second derivatives. The study investigates which MFCC coefficients, selected by the Least Absolute Shrinkage and Selection Operator, are significant for the worker bee and drone bee classification task. The classification results, obtained by an autoencoder neural network, allow to improve the detection performance, achieving accuracy slightly above 95% for the chosen set of signal features, selected by the proposed method, compared to the standard set of MFCC coefficients with only up to 90% accuracy. Full article