This study introduces a large-scale, multilingual, and multi-label dataset for Music Emotion Recognition (MER), addressing key limitations in existing resources. Notably, it represents the largest MER dataset to date that incorporates Chinese, offering rich information such as lyrics and metadata. By leveraging user-generated playlist tags from music platforms, the dataset captures diverse emotional attributes using a probabilistic framework across 12 emotion categories, with both discrete and continuous representations. Extensive experiments with various baseline models validate the dataset’s effectiveness, particularly in recognizing complex emotional patterns. A detailed analysis further investigates the influence of annotator quantity and quality on data reliability, demonstrating that increasing annotator numbers and enhancing their expertise improve label consistency and mitigate noise. This dataset serves as a valuable resource for advancing MER research and supports practical applications, including music recommendation and emotion analysis.
Precision agriculture significantly boosts socio-economic growth and national productivity through monitoring accurate periodic biomass and biophysical traits. Numerous Internet of Things (IoT) and Unmanned Aerial Vehicles (UAVs) connected sensors can facilitate the automated collection of these traits, even in adverse conditions. This article introduces SmartAgri-Net (SA-Net), a decision support system that utilizes real-time multi-sensor and multi-temporal data from Edge- IoT-UAV sensors. The SA-Net-Biomass Estimation Framework (SA-BEF) consisting of Occlusion Reconstruction Module (ORM), 3D-2D Transfer Block (3-2DTB), Attention-based Biomass Estimation Block (ABE) approximates biomass from Light Detection and Ranging (LiDAR) 3D-Point clouds. The SA-Net-TCN-Prediction Framework (SA-TPF) implements Temporal Convolution Neural Network (TCN) for predictive analytics over the derived biomass and aggregated biophysical data from IoT sensors to perform decision-making. Finally, we propose engineering and deploying SA-Net recommendation support for smartphone applications.
Increasing concerns regarding plastic waste and its impact on the environment have prompted a global trend to replace plastic films with fiber-based packaging solutions. Though the heat-sealing of polyolefin films provides a simple approach for realizing flexible packaging, paper does not have the natural attributes required for such applications. Therefore, paper sealability must be achieved by other means such as coating or varnishing. This study accordingly investigated the basics of imparting heat-sealability to packaging paper using overprint varnish applied with a lab coater simulating flexographic printing. The sealing and grease resistance properties of the resulting paper were compared with those of commercially available polyethylene dispersion-coated paper and oriented polypropylene/polyethylene laminate. The results confirmed that sufficient capabilities were realized using the proposed method; though the varnished paper exhibited a lower seal strength than the reference plastic films, it exhibited adequate properties for package sealing regardless of applied temperature. These observations were subsequently discussed to inform recommendations for further investigation and development.
Oil palm empty fruit bunches (OPEFB) is byproducts from the palm oil processing mills currently discarded on field with less economic value. Meanwhile, it has a potential as precursor for cellulose feedstock as a membrane main polymer due to its biodegradability, environmental benign, and renewability. However, due to its insolubility in most available solvents, its utilization as a primary polymer matrix is limited. In this study, we transformed native and functionalized cellulose derived from OPEFB into membrane via non-solvent induced phase separation (NIPS) using trifluoroacetic acid (TFA) and dichloroethane (DCE) as the solvent. The fabrication parameters included duration of air exposure ranging for 2,3, and 4 min prior to water immersion for 24 h; and membrane composition, consisting of cellulose as main polymer, TiO2 and PEG as additives. Based on TGA analysis, it suggests that membrane of pure cellulose has the highest decomposition temperature, while FTIR spectra of the synthesized membranes indicate complete dilution of TFA DCE during water immersion. The membranes were characterized to have water affinity indicating hydrophilic properties with water contact angle ranging from 16.12° to 26.4°. The membrane maximum water flux rate accounted for 172.6 L/m2 h bar, while ion removal for Pb2+ Cu2+ and Cr3+, dye ranged from 87.3 to 98.9
Este artigo objetiva identificar as mais recentes tendências das práticas de intervenção social da Educomunicação Socioambiental e os aportes conceituais provenientes de relatos produzidos sobre elas. Procedeu-se com análise documental sobre o conteúdo disponibilizado no site da Associação Brasileira de Pesquisadores e Profissionais em Educomunicação (ABPEducom) e posterior pesquisa bibliográfica para aprofundamento. O texto aborda os precursores, a sistematização e a consolidação do conceito. Na sequência, apresenta as cinco tendências identificadas: (i) nos ecossistemas costeiros e marinhos; (ii) em articulação com os Objetivos de Desenvolvimento Sustentável; (iii) em interface com a Divulgação Científica; (iv) em interface com o campo da Comunicação e Saúde; e (v) em interface com a Educação Ambiental Climática. Por fim, constata a diversidade epistemológica que tem caracterizado essas práticas.
