Search Results (35)

This article examines how the Ecuadorian national digital press has represented the relationship between criminal violence, declining mobility, tourism contraction, and the erosion of intangible cultural access in Machala, Puerto Bolívar, and the route to Jambelí during 2025. This study aims to explain how mediated representations of insecurity can contribute to the symbolic narrowing of culturally meaningful urban–coastal spaces, even when those spaces remain materially present and formally open. The article responds to a gap in the literature at the intersection of critical heritage studies, media framing, urban fear, and Latin American security studies. The existing research has examined heritage as social practice, media representation of crime, and urban securitization, but has rarely connected these fields to explain how criminal violence erodes lived access to intangible cultural environments in secondary port cities of the Global South. Methodologically, this study applies qualitative content analysis to a purposive corpus of eight focal journalistic texts published in Ecuadorian digital outlets, such as El Universo, El Comercio, Expreso, El Mercurio, Extra, Primicias, GK, and La Hora. Deductive–inductive coding was complemented by descriptive article-level indicators of themes, keyword clusters, and temporal distribution. The findings show that the press did not merely report violent events; it progressively reorganized the symbolic meaning of Machala by re-signifying Puerto Bolívar, the marine environment, the cabotage pier, and the maritime route to Jambelí as spaces of risk, interruption, and conditional access. This study contributes conceptually by defining intangible cultural access and symbolic enclosure, empirically by documenting the mediated erosion of coastal public–cultural life, and practically by proposing integrated policy actions for security governance, cultural reactivation, local commerce, maritime mobility, and responsible public communication. Full article

With the rapid growth of e-commerce, recommender systems have been widely adopted across diverse online services by presenting products aligned with user preferences. Moreover, review-based recommender systems have been studied to alleviate the sparsity of interaction data. However, many studies directly use full review texts, which may contain redundant semantics or noise that is irrelevant to recommendations, thereby degrading data quality and recommendation performance. To address this limitation, this study proposes summarized reviews fusion for adaptive recommendation (SuReFAR), which predicts ratings by summarizing reviews into key information using a multi-summarization strategy. Specifically, SuReFAR utilizes TextRank and bidirectional and auto-regressive transformers (BART) to generate extractive and abstractive summaries of user and item review sets, respectively. Subsequently, we apply an attention mechanism to emphasize salient information within each summary representation and fuse multiple summary representations by adaptively controlling their contributions through a gated multimodal unit (GMU) to predict ratings. We conducted experiments on Amazon and Yelp review datasets, demonstrating that the proposed model consistently outperforms baseline models and captures user preferences more effectively via personalized summary representations. Full article

The emergence of the Smart Cities paradigm and the rapid expansion and integration of Internet of Things (IoT) technologies within this context have created unprecedented opportunities for high-resolution behavioral analytics, urban optimization, and context-aware services. However, this same proliferation intensifies privacy risks, particularly those arising from cross-modal data linkage across heterogeneous sensing platforms. To address these challenges, this paper introduces a comprehensive, statistically grounded framework for generating synthetic, multimodal IoT datasets tailored to Smart City research. The framework produces behaviorally plausible synthetic data suitable for preliminary privacy risk assessment and as a benchmark for future re-identification studies, as well as for evaluating algorithms in mobility modeling, urban informatics, and privacy-enhancing technologies. As part of our approach, we formalize probabilistic methods for synthesizing three heterogeneous and operationally relevant data streams—cellular mobility traces, payment terminal transaction logs, and Smart Retail nutrition records—capturing the behaviors of a large number of synthetically generated urban residents over a 12-week period. The framework integrates spatially explicit merchant selection using K-Dimensional (KD)-tree nearest-neighbor algorithms, temporally correlated anchor-based mobility simulation reflective of daily urban rhythms, and dietary-constraint filtering to preserve ecological validity in consumption patterns. In total, the system generates approximately 116 million mobility pings, 5.4 million transactions, and 1.9 million itemized purchases, yielding a reproducible benchmark for evaluating multimodal analytics, privacy-preserving computation, and secure IoT data-sharing protocols. To show the validity of this dataset, the underlying distributions of these residents were successfully validated against reported distributions in published research. We present preliminary uniqueness and cross-modal linkage indicators; comprehensive re-identification benchmarking against specific attack algorithms is planned as future work. This framework can be easily adapted to various scenarios of interest in Smart Cities and other IoT applications. By aligning methodological rigor with the operational needs of Smart City ecosystems, this work fills critical gaps in synthetic data generation for privacy-sensitive domains, including intelligent transportation systems, urban health informatics, and next-generation digital commerce infrastructures. Full article

Online review images shape consumer perceptions by offering visual cues of product quality and use. Existing studies focus on aesthetics or object presence but overlook the functional balance among image types. This study introduces the Holistic Image Proportion (HIP)—the ratio of holistic to detailed review images—as a key determinant of visual information completeness. Using deep learning (ResNet-101) to classify over 240,000 images from 4450 clothing products, we find an inverted U-shaped relationship between HIP and sales: a balanced mix (HIP ≈ 0.5) maximizes performance. A follow-up experiment confirms that balanced image composition enhances perceived completeness, which fully mediates its effect on purchase intention. Review sentiment further moderates this relationship, amplifying the effect under positive sentiment. This research extends information completeness theory to visual data, highlighting that completeness emerges from functional image composition rather than quantity or aesthetics, offering new insights for multimodal persuasion and e-commerce design. Full article

Using a balanced provincial panel of 31 Chinese regions (2014–2022), this study examines how Digital Inclusive Finance (DIF) and Rural E-Commerce (RE) jointly shape the urban–rural income gap. Two-way fixed effects and instrumental-variable estimators mitigate confounding. Both DIF and RE are associated with narrower gaps, and the interaction term is negative and robust across specifications. Mechanism evidence indicates that the coupling operates through higher Agricultural Green Total Factor Productivity, expanded rural credit supply, and stronger entrepreneurship. Effects are larger in Central/Western provinces and are most pronounced when DIF’s usage-depth and digital-support components are salient. For policymakers and managers, the findings support bundled investments in digital rails, platform logistics, and e-commerce–linked credit, with priority to lagging regions and programs that deepen usage. Overall, the results provide a tractable systems approach to aligning finance and markets for inclusive rural transformation. Full article

Recommender systems are data-driven tools designed to assist or automate users’ decision-making. With the growing demand of personalized sequential recommendations in business intelligence or e-commerce, effectively capturing temporal information from massive user-sequence data has become a crucial challenge. State-of-the-art attention-based models often struggle to balance performance with computational cost, while traditional convolutional neural networks suffer from limited receptive fields and rigid architectures that inadequately model dynamic user interests. To address these limitations, this paper proposes TimeWeaver, a time-aware dual-stream network for sequential recommendation, whose core innovations comprise three key components. First, it employs a re-parameterized large-kernel convolution to expand the effective receptive field. Second, we design a Time-Aware Augmentation mechanism that integrates inter-event time-interval information into positional encodings of items. This allows it to perceive the temporal dynamics of user behavior. Finally, we propose a dual-stream architecture to jointly capture dependencies across different time scales. The context stream employs a modern Temporal Convolutional Network (TCN) structure to strengthen the memorization of users’ medium- and long-term interests. In parallel, the dynamic stream leverages an Exponential Moving Average (EMA) mechanism to weight recent behaviors for sensitively capturing users’ immediate interests. This dual-stream design allows TimeWeaver to comprehensively extract both long- and short-term sequential features. Extensive experiments on three public e-commerce datasets demonstrate TimeWeaver’s superiority. Compared to the strongest baseline model, TimeWeaver achieves average relative improvements of 4.62%, 9.59%, and 4.59% across all metrics on the Beauty, Sports, and Toys datasets, respectively. Full article

As information technology advances, digital content has become widely adopted across diverse fields such as news broadcasting, entertainment, commerce, and forensic investigation. However, the availability of sophisticated multimedia editing tools has significantly increased the risk of video and image forgery, raising serious concerns about content authenticity at both societal and individual levels. To address the growing need for robust and accurate detection methods, this study proposes a novel video forgery detection model that integrates both spatial and frequency-domain features. The model is built on a ResNet-LSTM framework enhanced by a Convolutional Block Attention Module (CBAM) for spatial feature extraction, and further incorporates Discrete Cosine Transform (DCT) to capture frequency domain information. Comprehensive experiments were conducted on several mainstream benchmark datasets, encompassing a wide range of forgery scenarios. The results demonstrate that the proposed model achieves superior performance in distinguishing between authentic and manipulated videos. Additional ablation and comparative studies confirm the contribution of each component in the architecture, offering deeper insight into the model’s capacity. Overall, the findings support the proposed approach as a promising solution for enhancing the reliability of video authenticity analysis under complex conditions. Full article

Postal services have re-emerged across numerous emerging economies worldwide as essential logistics providers, harnessing their vast coverage and dependability in the face of expanding e-commerce platforms and technological innovations. This study investigates India Post, one of the largest postal networks globally, to determine the key logistics service parameters prioritized by customers in southern India. Quantitative data obtained from 255 India Post end-users were evaluated using the logistics service quality (LSQ) scale, assessing eight dimensions including information quality, timeliness, ordering procedure, order accuracy, order condition, personal contact quality, order discrepancy handling, and order release quantities. The Analytical Hierarchy Process (AHP) ranked these elements, while Quality Function Deployment (QFD) bridged customer expectations with service improvements. The findings highlight the need to improve sorting and distribution processes to meet customer demands for timely, high-quality delivery. By refining logistics efficiency, this study provides suggestions and recommendations for boosting satisfaction and profitability, shedding light on service-led economic advancement for postal services in emerging economies. These insights equip postal service providers to cultivate loyalty and maintain competitiveness within the dynamic logistics landscape. Full article

The rapid growth in the global apparel market and the rise of online consumption underscore the necessity for intelligent clothing recommendation systems that balance visual compatibility with personalized preferences, particularly price sensitivity. Existing recommendation systems often neglect nuanced consumer price behaviors, limiting their ability to deliver truly personalized suggestions. To address this gap, we propose DeepFMP, a multimodal deep learning framework that integrates visual, textual, and price features through an enhanced DeepFM architecture. Leveraging the IQON3000 dataset, our model employs ResNet-50 and BERT for image and text feature extraction, alongside a comprehensive price feature module capturing individual, statistical, and category-specific price patterns. An attention mechanism optimizes multimodal fusion, enabling robust modeling of user preferences. Comparative experiments demonstrate that DeepFMP outperforms state-of-the-art baselines (LR, FM, Wide & Deep, GP-BPR, and DeepFM), achieving AUC improvements of 1.6–12.2% and NDCG@10 gains of up to 3.2%. Case analyses further reveal that DeepFMP effectively improves the recommendation accuracy, offering actionable insights for personalized marketing. This work advances multimodal recommendation systems by emphasizing price sensitivity as a pivotal factor, providing a scalable solution for enhancing user satisfaction and commercial efficacy in fashion e-commerce. Full article

Circular economy theorists and advocates typically describe traditional market economies as linear “take, make, use and dispose” systems. Various policy interventions, from green taxes to extended producer responsibility, are therefore deemed essential to ensure the systematic (re)introduction of residuals, secondary materials and components in manufacturing activities. By contrast, many nineteenth- and early twentieth-century writers documented how the profit motive, long-distance trade and actors now largely absent from present-day circularity discussions (e.g., waste dealers and brokers) spontaneously created ever more value out of the recovery of residuals and waste. These opposite assessments and underlying perspectives are perhaps best illustrated in the nineteenth classical liberal and early twenty-first century interventionist writings on circularity of Fellows, members and collaborators of the near tricentennial British Royal Society for the Encouragement of Arts, Manufactures and Commerce. This article summarizes their respective contributions and compares their stance on market institutions, design, intermediaries, extended producer responsibility and long-distance trade. Some hypotheses as to the sources of their analytical discrepancies and current beliefs on resource recovery are then discussed in more detail. A final suggestion is made that, if the analysis offered by early contributors is more correct, then perhaps the most important step towards greater circularity is regulatory reform (or deregulation) that would facilitate the spontaneous recovery of residuals and their processing in the most suitable, if sometimes more distant, locations. Full article

Automatic clothes pattern recognition is important to assist visually impaired people and for real-world applications such as e-commerce or personal fashion recommendation systems, and it has attracted increased interest from researchers. It is a challenging texture classification problem in that even images of the same texture class expose a high degree of intraclass variations. Moreover, images of clothes patterns may be taken in an unconstrained illumination environment. Machine learning methods proposed for this problem mostly rely on handcrafted features and traditional classification methods. The research works that utilize the deep learning approach result in poor recognition performance. We propose a deep learning method based on an ensemble of convolutional neural networks where feature engineering is not required while extracting robust local and global features of clothes patterns. The ensemble classifier employs a pre-trained ResNet50 with a non-local (NL) block, a squeeze-and-excitation (SE) block, and a coordinate attention (CA) block as base learners. To fuse the individual decisions of the base learners, we introduce a simple and effective fusing technique based on entropy voting, which incorporates the uncertainties in the decisions of base learners. We validate the proposed method on benchmark datasets for clothes patterns that have six categories: solid, striped, checkered, dotted, zigzag, and floral. The proposed method achieves promising results for limited computational and data resources. In terms of accuracy, it achieves 98.18% for the GoogleClothingDataset and 96.03% for the CCYN dataset. Full article

Urban memory involves the re-creation of a city’s physical, historical, social, and cultural elements in the memories of its inhabitants. However, urban transformation and commercial tourism-oriented projects may threaten the continuity of this memory. This study aims to provide an understanding of the relationship between urban memory and spatial experience while exploring how urban memory elements convey meanings to daily users and local inhabitants of a touristic settlement. The research focuses on Misi Village in Bursa, Turkey, a settlement with a 2000-year history known for its traditional architecture and natural beauty. Over the past two decades, local authorities have pursued extensive restoration projects to rebrand Misi Village as an Art and Tourism Village. The research employs the oral history method, focusing on two user groups: tourists and locals. The findings reveal that while tourists appreciate Misi Village for its natural beauty and recreational activities, they lack a deeper understanding of its history and the transformation of its identity. Instead, they mostly focus on commerce-oriented spatial experiences. In contrast, local residents emphasize daily life and traditional practices as they strive to sustain their livelihoods. By highlighting this difference, strategic planning is proposed to preserve Misi Village’s unique urban memory and promote sustainable, culturally centered tourism. Full article

The impact of freight on the transportation system is accentuated by the fact that trucks consume a greater roadway capacity than other vehicles and therefore cause more significant problems including traffic congestion, traffic delays, crashes, and pavement damage. Evaluating the actual repercussions of truck traffic becomes paramount in locales where roadway expansion is unfeasible. Trucks are vital to the economy, providing essential services to commerce and industry, and yet it is crucial that their operation does not contribute to the deterioration of infrastructural quality or compromise public safety. Currently, we lack methodologies in practice for the real-time management of traffic, specifically for truck routing, to minimize travel times and prevent delays due to non-recurrent congestion, such as traffic incidents. Accordingly, this study aimed to devise a truck routing strategy utilizing a traffic micro-simulation model (VISSIM) and to assess its effects on reducing travel delays. This involved the development of real-time truck re-routing simulation models that take into account non-recurrent congestion and the resulting travel delays and fuel consumption. The VISSIM model was applied to the I-75 corridor in Marion County, Florida, focusing on non-recurrent congestion effects on travel delays and fuel consumption. The initial findings suggest that the implementation of a dynamic truck re-routing system can significantly alleviate traffic congestion, resulting in a marked decrease in travel delays and fuel usage, demonstrating the potential for such strategies to enhance the overall efficiency of the transportation system. Full article

Artificial intelligence (AI) is advancing across technology domains including healthcare, commerce, the economy, the environment, cybersecurity, transportation, etc. AI will transform healthcare systems, bringing profound changes to diagnosis, treatment, patient care, data, medicines, devices, etc. However, AI in healthcare introduces entirely new categories of risk for assessment, management, and communication. For this topic, the framing of conventional risk and decision analyses is ongoing. This paper introduces a method to quantify risk as the disruption of the order of AI initiatives in healthcare systems, aiming to find the scenarios that are most and least disruptive to system order. This novel approach addresses scenarios that bring about a re-ordering of initiatives in each of the following three characteristic layers: purpose, structure, and function. In each layer, the following model elements are identified: 1. Typical research and development initiatives in healthcare. 2. The ordering criteria of the initiatives. 3. Emergent conditions and scenarios that could influence the ordering of the AI initiatives. This approach is a manifold accounting of the scenarios that could contribute to the risk associated with AI in healthcare. Recognizing the context-specific nature of risks and highlighting the role of human in the loop, this study identifies scenario s.06—non-interpretable AI and lack of human–AI communications—as the most disruptive across all three layers of healthcare systems. This finding suggests that AI transparency solutions primarily target domain experts, a reasonable inclination given the significance of “high-stakes” AI systems, particularly in healthcare. Future work should connect this approach with decision analysis and quantifying the value of information. Future work will explore the disruptions of system order in additional layers of the healthcare system, including the environment, boundary, interconnections, workforce, facilities, supply chains, and others. Full article

As e-commerce platforms grow, consumers increasingly purchase clothes online; however, they often need clarification on clothing choices. Consumers and stores interact through the clothing recommendation system. A recommendation system can help customers to find clothing that they are interested in and can improve turnover. This work has two main goals: enhancing fashion classification and developing a fashion recommendation system. The main objective of fashion classification is to apply a Vision Transformer (ViT) to enhance performance. ViT is a set of transformer blocks; each transformer block consists of two layers: a multi-head self-attention layer and a multilayer perceptron (MLP) layer. The hyperparameters of ViT are configured based on the fashion images dataset. CNN models have different layers, including multi-convolutional layers, multi-max pooling layers, multi-dropout layers, multi-fully connected layers, and batch normalization layers. Furthermore, ViT is compared with different models, i.e., deep CNN models, VGG16, DenseNet-121, Mobilenet, and ResNet50, using different evaluation methods and two fashion image datasets. The ViT model performs the best on the Fashion-MNIST dataset (accuracy = 95.25, precision = 95.20, recall = 95.25, F1-score = 95.20). ViT records the highest performance compared to other models in the fashion product dataset (accuracy = 98.53, precision = 98.42, recall = 98.53, F1-score = 98.46). A recommendation fashion system is developed using Learning Robust Visual Features without Supervision (DINOv2) and a nearest neighbor search that is built in the FAISS library to obtain the top five similarity results for specific images. Full article