Search Results (1,919)

Recent progress in computer vision and embedded systems has facilitated real-time monitoring of bioprocesses; however, lightweight and scalable solutions for resource-constrained settings remain limited. This work presents a modular framework for monitoring Chlorella vulgaris growth by integrating RGB image processing with multimodal sensor fusion. The system incorporates a Logitech C920 camera and low-cost pH and temperature sensors within a compact photobioreactor. It extracts RGB channel statistics, luminance, and environmental data to generate a 10-dimensional feature vector. A feedforward artificial neural network (ANN) with ReLU activations, dropout layers, and SMOTE-based data balancing was trained to classify growth phases: lag, exponential, and stationary. The optimized model, quantized to 8 bits, was deployed on an ESP32 microcontroller, achieving 98.62% accuracy with 4.8 ms inference time and a 13.48 kB memory footprint. Robustness analysis confirmed tolerance to geometric transformations, though variable lighting reduced performance. Principal component analysis (PCA) retained 95% variance, supporting the discriminative power of the features. The proposed system outperformed previous vision-only methods, demonstrating the advantages of multimodal fusion for early detection. Limitations include sensitivity to lighting and validation limited to a single species. Future directions include incorporating active lighting control and extending the model to multi-species classification for broader applicability. Full article

This study evaluates the effect of incorporating behavioral variables, sleep quality (SQ) and stress level (SL), into neural network models for predicting weight loss. An artificial neural network (ANN) was trained using data from 100 adults aged 18 to 60, integrating demographic, physiological, and behavioral inputs. The findings emphasize that weight change is a multifactorial process influenced not only by caloric intake, basal metabolic rate, and physical activity, but also by psychological and behavioral factors such as sleep and stress. From a medical perspective, the inclusion of SQ and SL aligns with the biopsychosocial model of obesity, acknowledging the metabolic consequences of chronic stress and poor sleep. This integration allows for the development of low-cost, non-invasive, and personalized weight management tools based on self-reported data, especially valuable in resource-limited healthcare settings. Behavioral-aware AI systems such as the one proposed have the potential to support clinical decision-making, enable early risk detection, and guide the development of digital therapeutics. Quantitative results demonstrate that the best-performing architecture achieved a Root Mean Square Error (RMSE) of 1.98%; when SQ was excluded, the RMSE increased to 4.39% (1.8-fold), when SL was excluded it rose to 4.69% (1.95-fold), and when both were removed, the error reached 6.02% (2.5-fold), confirming the substantial predictive contribution of these behavioral variables. Full article

To address the triple bottlenecks of data scarcity, oversized models, and slow inference that hinder Cantonese automatic speech recognition (ASR) in low-resource and edge-deployment settings, this study proposes a cost-effective Cantonese ASR system based on LoRA fine-tuning and INT8 quantization. First, Whisper-tiny is parameter-efficiently fine-tuned on the Common Voice zh-HK training set using LoRA with rank = 8. Only 1.6% of the original weights are updated, reducing the character error rate (CER) from 49.5% to 11.1%, a performance close to full fine-tuning (10.3%), while cutting the training memory footprint and computational cost by approximately one order of magnitude. Next, the fine-tuned model is compressed into a 60 MB INT8 checkpoint via dynamic quantization in ONNX Runtime. On a MacBook Pro M1 Max CPU, the quantized model achieves an RTF = 0.20 (offline inference 5 × real-time) and 43% lower latency than the FP16 baseline; on an NVIDIA A10 GPU, it reaches RTF = 0.06, meeting the requirements of high-concurrency cloud services. Ablation studies confirm that the LoRA-INT8 configuration offers the best trade-off among accuracy, speed, and model size. Limitations include the absence of spontaneous-speech noise data, extreme-hardware validation, and adaptive LoRA structure optimization. Future work will incorporate large-scale self-supervised pre-training, tone-aware loss functions, AdaLoRA architecture search, and INT4/NPU quantization, and will establish an mJ/char energy–accuracy curve. The ultimate goal is to achieve CER ≤ 8%, RTF < 0.1, and mJ/char < 1 for low-power real-time Cantonese ASR in practical IoT scenarios. Full article

Background: A significant body of research has identified ongoing unmet needs among cancer survivors. However, there is limited information about the survivorship experiences of patients in low- and middle-income countries. This study examined the experiences of colorectal cancer (CRC) survivors in Thailand to understand their post-treatment needs and priorities. Methods: A qualitative descriptive study using semi-structured interviews was conducted with 24 colorectal cancer survivors purposively recruited from a large university hospital in Bangkok, Thailand. The interviews lasted 60–90 min, were audio-recorded, and transcribed verbatim. The data were analyzed using hybrid content analysis, guided by the five domains of the Survivors Unmet Needs Survey (SUNS): information, emotional health, financial concerns, access and continuity of care, and relationships. Results: Participants had a mean age of 57 (SD = 10.9) years. Most were male (58.3%) and diagnosed at a late stage (62.5%). All participants had undergone surgical treatment, and the average time since treatment completion was approximately 3.85 (SD = 2.8) years. Participants most often reported unmet needs in the information and emotional health domains. They also described inadequate physical infrastructure (e.g., overcrowded clinic spaces) and minimal involvement of multidisciplinary providers. Despite these challenges, survivors expressed strong trust in physicians and a preference for physician-led care. Telehealth was viewed as a potential solution to reduce access barriers and improve continuity of care. Conclusions: Guided by the SUNS framework, this study identified significant unmet needs among colorectal cancer survivors in Thailand, particularly in health information, psychological support, and care system infrastructure. Strengthening health information delivery, establishing dedicated survivorship clinics, and exploring scalable care models supported by telehealth could help bridge these gaps and promote more equitable survivorship care in low-resource settings. Full article

Newcastle disease (ND) is a highly contagious and economically significant viral infection that affects poultry globally, with recurrent outbreaks occurring even among vaccinated flocks in Egypt. Caused by the Newcastle disease virus (NDV), the disease results in substantial losses due to high mortality rates, decreased productivity, and the imposition of trade restrictions. This study aimed to develop a rapid, sensitive, and field-deployable diagnostic assay based on real-time reverse transcription recombinase-aided amplification (RT-RAA) for the detection of all NDV genotypes in clinical avian specimens. Primers and an exo-probe were designed based on the most conserved region of the NDV matrix gene. After testing ten primer combinations, the pair NDV RAA-F1 and RAA-R5 demonstrated the highest sensitivity, detecting as low as 6.89 EID₅₀/mL (95% CI). The RT-RAA assay showed excellent clinical sensitivity and specificity, with no cross-reactivity to other common respiratory pathogens such as avian influenza virus, infectious bronchitis virus, Mycoplasma gallisepticum or infectious laryngotracheitis virus. All 25 field samples that were tested positive by real-time RT-PCR, including those with high CT values (~35), were detected by RT-RAA in 2–11 min, indicating superior sensitivity and speed. The assay requires only basic equipment and can be performed under isothermal conditions, making it highly suitable for on-site detection in resource-limited or rural settings. The successful implementation of RT-RAA can improve NDV outbreak response, support timely vaccination strategies, and enhance disease control efforts. Overall, the assay presents a promising alternative to conventional diagnostic methods, contributing to the sustainability and productivity of the poultry sector in endemic regions. Full article

Barriers to cancer care, including transportation and Internet insecurity, are of special concern in low-resource communities. A patient-centered, telehealth-based, barrier-focused lay navigator program may mitigate such barriers. We share insights from a quality improvement project wherein we developed and delivered a lay navigator program in a low-resource community in the Mojave Desert. We identified 68 patients scheduled for lung cancer detection/management at our institution, 55 of whom completed a barrier assessment, enrolled in the program, and could be evaluated. Participants were predominantly older (76%), White (84%), had a cancer diagnosis at enrollment (69%), and lived in socioeconomically disadvantaged neighborhoods. Thirty-three (60%) patients had ≥1 barrier, the most common being transportation (31%), Internet (24%), and financial (24%) concerns. These barriers were more frequent among patients with a lung cancer diagnosis at enrollment. Crisis-focused and after-hours encounters were more frequently initiated by older and advanced cancer patients. Transportation and Internet concerns were significantly associated with missed appointment rates. While the scope of our findings is limited, the delivery of a telehealth-based, barrier-focused lay lung navigator program in this low-resource setting was feasible. Neighborhood context and barrier resource planning are important for the implementation of similar programs within our institution’s clinical practice network. Full article

The convergence of genomic selection and artificial intelligence (AI) is redefining precision breeding in dairy cattle, enabling earlier, more accurate, and multi-trait selection for health, fertility, climate resilience, and economic efficiency. This review critically examines how advanced genomic tools—such as genome-wide association studies (GWAS), genomic breeding values (GEBVs), machine learning (ML), and deep learning (DL) models to accelerate genetic gain for complex, low heritability traits. Key applications include improved resistance to mastitis and metabolic diseases, enhanced thermotolerance, reduced enteric methane emissions, and increased milk yield. We discuss emerging computational frameworks that combine sensor-derived phenotypes, omics datasets, and environmental data to support data-driven selection decisions. Furthermore, we address implementation challenges related to data integration, model interpretability, ethical considerations, and access in low-resource settings. By synthesizing interdisciplinary advances, this review provides a roadmap for developing AI-augmented genomic selection pipelines that support sustainable, climate-smart, and economically viable dairy systems. Full article

Limb amputation causes significant challenges for patients in achieving effective mobility and functionality through prosthetic limbs. The prosthetic socket plays a pivotal role in the success of rehabilitation. This review explores the current advancements in prosthetic socket design and fabrication, focusing on traditional techniques like casting and lamination, and emerging technologies such as 3D printing and computer-aided design (CAD). By comparing these methods, this review highlights the advantages, limitations, and suitability for different clinical needs. This article discusses the importance of pressure distribution in socket design, emphasizing the need to relieve pressure in sensitive areas to prevent skin complications. It also examines the materials used in socket fabrication, from high-density polymers to advanced composites, assessing their impact on patient comfort and prosthetic performance. Additionally, we discuss the challenges practitioners face in prosthetic care, particularly in low-resource settings, and propose potential solutions through innovative techniques and materials. Advancements in computational modeling improved socket design and validation, enhancing patient comfort and improving the overall biomechanical interaction between the prosthesis and the user. The manuscript concludes by identifying future research opportunities, particularly in personalized prosthetic design and the integration of smart materials, to further enhance the comfort, functionality, and accessibility of prosthetic sockets. Full article

Small-target detection in Unmanned Aerial Vehicle (UAV) aerial images remains a significant and unresolved challenge in aerial image analysis, hampered by low target resolution, dense object clustering, and complex, cluttered backgrounds. In order to cope with these problems, we present AeroLight, a novel and efficient detection architecture that achieves high-fidelity performance in resource-constrained environments. AeroLight is built upon three key innovations. First, we have optimized the feature pyramid at the architectural level by integrating a high-resolution head specifically designed for minute object detection. This design enhances sensitivity to fine-grained spatial details while streamlining redundant and computationally expensive network layers. Second, a Dynamic Feature Fusion (DFF) module is proposed to adaptively recalibrate and merge multi-scale feature maps, mitigating information loss during integration and strengthening object representation across diverse scales. Finally, we enhance the localization precision of irregular-shaped objects by refining bounding box regression using a Shape-IoU loss function. AeroLight is shown to improve mAP50 and mAP50-95 by 7.5% and 3.3%, respectively, on the VisDrone2019 dataset, while reducing the parameter count by 28.8% when compared with the baseline model. Further validation on the RSOD dataset and Huaxing Farm Drone dataset confirms its superior performance and generalization capabilities. AeroLight provides a powerful and efficient solution for real-world UAV applications, setting a new standard for lightweight, high-precision object recognition in aerial imaging scenarios. Full article

Due to increasing demand for the exploration of marine resources, underwater optical wireless sensor networks (UOWSNs) have emerged as a promising solution by offering higher bandwidth and lower latency compared to traditional underwater acoustic wireless sensor networks (UAWSNs), with their existing routing protocols facing challenges in energy consumption and packet forwarding. To address these challenges, this paper proposes an energy-partitioned routing protocol based on an advancement function (EPAR) for UOWSNs. By dynamically classifying the nodes into high-energy and low-energy ones, the proposed EPAR algorithm employs an adaptive weighting strategy to prioritize the high-energy nodes in relay selection, thereby balancing network load and extending overall lifetime. In addition, a tunable advancement function is adopted by the proposed EPAR algorithm by comprehensively considering the Euclidean distance and steering angle toward the sink node. By adjusting a tunable parameter α, the function guides forwarding decisions to ensure energy-efficient and directionally optimal routing. Additionally, by employing a hop-by-hop neighbor discovery mechanism, the proposed algorithm enables each node to dynamically update its local neighbor set, thereby improving relay selection and mitigating the impact of void regions on the packet delivery ratio (PDR). Simulation results demonstrate that EPAR can obtain up to about a 10% improvement in PDR and up to about a 30% reduction in energy depletion, with a prolonged network lifetime when compared to the typical algorithms adopted in the simulations. Full article

Cervical cancer remains a significant public health challenge, disproportionately affecting women in low- and middle-income countries (LMICs). Persistent infection with high-risk types of human papillomavirus (HPV), particularly HPV16 and HPV18, is the central cause of cervical carcinogenesis, driven by the viral oncoproteins E6 and E7, which disrupt the host tumor suppressors p53 and retinoblastoma protein (pRb). Advances in molecular understanding have catalyzed effective primary and secondary prevention strategies. Prophylactic HPV vaccination, especially the nonavalent formulation, has demonstrated high efficacy in reducing HPV infections and cervical precancer. Concurrently, HPV deoxyribonucleic acid (DNA) testing, self-sampling, and screen-and-treat protocols are transforming screening paradigms, particularly in resource-limited settings. However, global disparities in vaccine access, screening coverage, and health infrastructure persist, impeding progress toward the World Health Organization’s (WHO) 90–70–90 elimination targets. By synthesizing recent advances in virology, prevention strategies, and implementation innovations, such as therapeutic vaccines, artificial-intelligence (AI)-driven diagnostics, and mobile health solutions, this review sheds light on their potential to narrow these equity gaps. Full article

As severe selection and declining population numbers in many breeds have resulted in losses in the worldwide livestock genetic biodiversity, human concern about the situation of genetic variety in livestock breeds and their conservation has grown. In this context, genomic techniques now allow for more exact monitoring of adaptive traits and inbreeding, while reproductive techniques such as somatic cell nuclear transfer and IVF (In Vitro Fertilization) help to preserve and recover rare genetic lines. AI-powered (Artifficial Inteligence) risk assessment models and digital herdbooks contribute to data-driven reproductive strategies, particularly in smallholder settings. Nonetheless, these advances face persistent hurdles, including a lack of legislative frameworks, high costs, limited accessibility in low-resource settings, and unresolved ethical problems. The findings highlight the importance of a balanced, interdisciplinary strategy that combines new biotechnologies with traditional knowledge, collaborative practices, and strong policy to assist in preserving the long-term viability of livestock genetic resources. This review intends to assess modern and traditional methods for the preservation of livestock breeds, analyzing references published between 2019 and the present. Full article

Federated learning enables collaborative model training across distributed devices while preserving data privacy. However, in real-world environments such as smart cities, heterogeneous and resource-constrained edge devices often render existing methods impractical. Low-power sensors and cameras struggle to complete full-model training, while high-performance devices remain idly waiting for others. Knowledge distillation approaches rely on public datasets that are rarely available or poorly aligned with urban data, which limits their effectiveness in deployment. These limitations lead to inefficiencies, unstable convergence, and poor adaptability in diverse urban networks. Partial training alleviates some challenges by allowing clients to train submodels tailored to their capacity, but existing methods still incur high computational costs for identifying important parameters and suffer from uneven parameter updates, reducing model effectiveness. To address these challenges, we propose Parameter-Level Dynamic Submodel Extraction (PLDSE), a lightweight and adaptive framework for federated learning. PLDSE estimates parameter importance using gradient-based scores on a server-side validation set, reducing overhead while accurately identifying critical parameters. In addition, it integrates a rolling scheduling mechanism to rotate unselected parameters, ensuring full coverage and consistent model updates. Experiments on CIFAR-10, CIFAR-100, and Fashion-MNIST demonstrate superior accuracy and faster convergence, with PLDSE achieving 62.82% on CIFAR-100 under low heterogeneity and 61.51% under high heterogeneity, outperforming prior methods. Full article

This study aims to develop a multi-dimensional framework to systematically identify optimal adjustment zones for converting orchard land into cultivated land, thereby providing a reference for spatial optimization of cultivated land within the context of integrating diverse land occupation activities into the requisition–compensation balance system. The research incorporates land quality evaluation, land-use conversion cost assessment, ecological loss analysis, and scenario-based simulations. The study demonstrates that (1) compared to the common practice of directly converting orchard land to cultivated land by only considering the slope, our multi-scenario optimization model for cultivated land reduces both economic and ecological losses. (2) For cities prioritizing ecological or economic development, selecting strategies under corresponding priority scenarios can maximize the protection of local ecological environments or maintain economic levels, thereby providing reserve resources for cultivated land optimization and adjustment. (3) Under the MMEG (EG: Ecological priority scenario) and MMEM (EM: Economic priority scenario) scenarios (MM: conversion of medium-low-grade orchard land to medium-high-grade cultivated land), the area of cultivated land optimal adjustment zones is the largest. The method of comprehensively identifying cultivated land optimal adjustment zones through multi-dimensional scenario settings is more comprehensive than the conventional approach that only considers slope. This method enhances cultivated land quality more effectively and protects both the ecosystem and the economy. Full article

Background: Neurocysticercosis (NCC) and HIV co-infection frequently occur in sub-Saharan Africa, yet the accuracy of available serological tests for NCC in immunosuppressed patients is uncertain. Methodology: We performed a cross-sectional diagnostic study on 101 people living with HIV from two endemic districts in Tanzania. Participants provided serum for cysticercosis antigen ELISA and Western Blot IgG; any positive result prompted neuroimaging investigation with cerebral computed tomography. NCC was diagnosed according to the 2017 revised Del Brutto criteria based on cCT according to Del Brutto criteria modified to exclude serology. Sensitivity, specificity, and area under the receiver–operating–characteristic curve (AUC) were calculated and adjusted for CD4 count and HIV stage. Two algorithms were compared: parallel testing (“either-test-positive”) and sequential screening (Ag ELISA screen, western blot IgG confirm). Results: NCC prevalence was 23%. Western Blot IgG outperformed Ag ELISA (sensitivity 57% vs. 30%; specificity 87% vs. 86%; AUC 0.73 vs. 0.57). Western blot IgG sensitivity declined to 54% when CD4 < 500 cells µL⁻¹, while Ag ELISA remained low. Western blot IgG positivity independently predicted NCC (adjusted odds ratio 4.1, 95% CI 1.4–11.9); Ag ELISA did not. When we counted a positive if either test was positive (parallel rule), sensitivity rose to 78% and NPV to 87%. When we ran Ag ELISA only if IgG was negative (sequential rule), we saved 70% of IgG strips, kept specificity at 95%, and PPV at 69%, but sensitivity fell to 39%. Conclusions: Western blot IgG is the most reliable single serological test for NCC in PLHIV. Parallel testing increased sensitivity and NPV and may suit better primary-level facilities without routine imaging. Sequential testing achieved high specificity, PPV, and conserved test kits, making it ideal for centers with limited reagents or scanner access. Tiered use of these assays can streamline NCC diagnosis in T. solium endemic, resource-limited settings. Full article