- Research Article
1
- 10.1016/j.asoc.2026.114617
A hybrid NSGA-II and delayed local search approach for home healthcare scheduling and routing optimization
- Apr 01, 2026
- Applied Soft Computing
- Radhia Zaghdoud + 4 more +4
Publications from 2021 to 2026
Showing 10 of 360 papers
A hybrid NSGA-II and delayed local search approach for home healthcare scheduling and routing optimization
Deciphering the dose-dependent nephrotoxic mechanisms of etoxazole: Insights from redox signaling and Wnt/β-catenin axis.
Comparative Evaluation of Hanging Objects as Environmental Enrichment Tools on Broiler Behavior, Welfare, Growth, Serum Chemistry, and Meat Quality Traits.
This study evaluated the effects of different environmental enrichment tools on broiler chickens from 1 to 21 days of age. A total of 120,000 one-day-old broiler chicks were randomly assigned to five treatments, each consisting of four replicates with 6000 birds per replicate. Replicates were housed in pens measuring approximately 362 m2. The treatments included: T1, green balls (approximately 40 balls per pen); T2, hanging toys (8-10 toys per pen); T3, hanging strings (8-10 string bundles per pen); T4, rotational use of green balls, hanging toys, and strings at equivalent densities; and T5, a control group without enrichment. Data were collected on growth performance, foot health, behavioral activity, serum biochemical parameters, and carcass and meat quality traits. Birds provided with hanging enrichment tools showed significantly improved growth performance (p ≤ 0.05) compared with the control group. Among enriched treatments, T2 yielded the highest body weight and weight gain, as well as the lowest feed conversion ratio. Enrichment treatments also resulted in significant improvements (p ≤ 0.05) in carcass characteristics and selected meat quality parameters, including lightness (L*) and pH stability. Behavioral observations indicated substantially higher activity levels in enriched groups relative to the control. Toe damage scores differed significantly among treatments (p = 0.004), with the lowest scores observed in T1 and the highest in T4; however, no significant differences were detected in footpad dermatitis or hock burn scores (p > 0.05). In conclusion, hanging environmental enrichment tools, particularly hanging toys, can effectively enhance growth performance, behavioral activity, and selected carcass and meat quality traits in broiler production systems, while their effects on footpad health appear limited under the conditions of this study.
Read moreAn Interpretable Hybrid SFNet Deep Learning Framework for Multi-Site Bone Fracture Detection in Medical Imaging.
Background/Objectives: Accurate bone fracture detection is essential for orthopedic diagnosis and trauma management. Manual interpretation of X-ray or CT images can be time-consuming and may lead to inter-observer variability, particularly in subtle or multi-site fracture cases. This study proposes an interpretable Hybrid Selective Feature Network (Hybrid SFNet) to improve multi-site bone fracture detection performance and boundary localization. Methods: The proposed Hybrid SFNet extends the original SFNet architecture by incorporating multi-scale convolutional feature extraction and a semantic flow mechanism to enhance structural representation and fracture boundary delineation. Preprocessing techniques, including Canny edge detection, normalization, and data augmentation, were applied to improve feature quality. Model interpretability was addressed using Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize regions contributing to predictions. The model was evaluated on publicly available multi-site fracture datasets using both standard and class-weighted loss configurations. Results: For binary fracture classification, the proposed model achieved 90 accuracy, 94% precision, 77% recall, and an F1-score of 85% for fractured cases. When class-weighted loss was applied, recall improved to 85%, reducing false negatives from 145 to 94 cases (approximately 35%). Under the weighted configuration, Cohen's Kappa reached 0.79 and the Matthews Correlation Coefficient (MCC) reached 0.76. Conclusions: The proposed Hybrid SFNet provides an interpretable and effective framework for multi-site bone fracture detection. The integration of multi-scale feature extraction and semantic flow mechanisms enhances detection performance and boundary localization, while Grad-CAM supports clinical interpretability. These results indicate the model's potential for supporting clinical decision-making in orthopedic imaging.
Read moreSustainable Destination Marketing in Saudi Arabia: Effects of Sustainability Storytelling and Smart Tourism Interactivity on Responsible Visit Intention via Destination Trust
This study investigates the impact of sustainable destination marketing on enhancing tourists’ intention for responsible visitation in Saudi Arabia by fostering destination trust through two manageable digital levers: the quality of sustainability storytelling and the interactivity of smart tourism. Based on a trust-based S-O-R framework and supplemented by signaling and uncertainty reduction theories, the research posits that high-quality, credible sustainability narratives and responsive, two-way smart touchpoints serve as trust indicators that lead to enhanced responsibility-oriented intentions. An online survey of digitally engaged tourists and potential tourists (N = 420) was used to gather the data. We used SmartPLS, version 4.1.1.7 (SmartPLS GmbH, Monheim am Rhein, Germany), with bootstrapping (5000 resamples) to assess the measurement and structural models. The findings demonstrate that the quality of sustainability storytelling significantly predicts destination trust (β = 0.418, p < 0.001), as does smart tourism interactivity (β = 0.347, p < 0.001). Destination trust positively affects responsible visit intention (β = 0.318, p < 0.001) and partially mediates the impacts of storytelling quality (β = 0.133, p < 0.001) and interactivity (β = 0.110, p < 0.001) on responsible visit intention. The model elucidates 40.9% of the variance in destination trust and 40.6% in responsible visit intention, underscoring trust as a pivotal mechanism by which credible sustainability storytelling and efficient smart interactivity can promote more responsible visitation.
Read moreAutomated Construction of a Multi-Dialectal Saudi Corpus Using Generative Language Models
The lack of high-quality linguistic resources, especially large and diverse Arabic dialect corpora, is a major challenge in the development of Natural Language Processing (NLP) applications. By taking advantage of the generative power of Large Language Models (LLMs), this research proposes an efficient approach for the automatic construction of a large-scale corpus of Saudi dialects. We specifically translated 51,840 sentences from Modern Standard Arabic (MSA) into three major Saudi dialects: Qassim (Central), Makkah/Jeddah (Western), and Al-Ahsa (Eastern) using Google’s Gemini 1.5 Pro model. Only two items were flagged by the system as invalid outputs and removed, yielding a pipeline-level invalid output rate below 0.01%. Both quantitative and qualitative differences between MSA and its dialects were discovered through extensive linguistic analyses. Although dialectal sentences had significantly higher lexical density and type token ratios, they were always shorter and more concise. These results suggest that the generated dialectal outputs reflect expected tendencies of informal registers in this controlled, domain-specific setting, while highlighting persistent challenges for dialectal NLP—particularly orthographic variation and the lack of standardized spelling.
Read moreArtificial Intelligence in Predicting Surgical Problems and Postoperative Morbidity in Mandibular Third Molar Extractions.
Mandibular third molar (MTM) extractions are among the most frequent oral surgical procedures, often associated with variable surgical difficulty and postoperative complications. Artificial intelligence (AI) offers potential in predicting these outcomes to enhance preoperative planning. This study was done to evaluate the utility of AI in predicting surgical difficulty and postoperative morbidity in MTM extractions using cone-beam computed tomography (CBCT) data and patient variables. A cross-sectional study of 40 patients undergoing MTM extraction was conducted. AI algorithms (random forest and convolutional neural networks) analyzed CBCT features and clinical parameters to predict difficulty and morbidity. Statistical evaluation was done using SPSS version 26. The AI model demonstrated an overall accuracy of 87.5% in predicting surgical difficulty and 82.3% for postoperative morbidity. Significant predictors included root morphology, proximity to the inferior alveolar nerve, and patient age (P < 0.05). AI-based models can effectively predict MTM extraction difficulty and postoperative morbidity, facilitating personalized treatment planning.
Read moreProtective Effect of Arbutin Against Diabetic Nephropathy: Targeting Oxidative Stress, Inflammation, and Nrf2/HO-1 Pathway
Diabetic nephropathy (DN) is a severe complication of diabetes that may lead to end-stage renal disease (ESRD). Arbutin (ARB), a naturally occurring glycoside with known therapeutic properties, has shown potential benefits for diabetes. This study explored the efficacy of ARB in modulating DN through its influence on Nrf2/HO-1 signaling, along with its ability to suppress inflammation and oxidative stress. Streptozotocin (STZ) injection was used to induce diabetes, and ARB was administered orally for 8 weeks. The results revealed that ARB effectively alleviated hyperglycemia and attenuated weight loss and renal hypertrophy and damage. ARB significantly attenuated kidney oxidative stress, reduced pro-inflammatory markers, and inhibited apoptosis, as evidenced by decreased levels of MDA, NO, NF-κB p65, IL-1β, TNF-α, Bax, and caspase-3, and myeloperoxidase activity. These improvements were associated with upregulated Nrf2, HO-1 and NQO-1, enhanced antioxidant defenses, inhibition of Keap1, and upregulation of Bcl-2. Molecular docking studies further corroborated the binding affinity of ARB to NF-κB p65, caspase-3, iNOS, Keap1, and HO-1. ARB mitigates DN progression by reducing hyperglycemia, inflammation, and oxidative stress while strengthening antioxidant and signaling mechanisms involving Nrf2/HO-1 pathway.
Read morePeople-Centered Lean Manufacturing: Drivers of Operational Performance in Saudi Arabian Industries
This study addresses a critical gap in understanding how Lean Manufacturing (LM) practices, particularly people-centered approaches, can enhance operational performance within the unique industrial context of Saudi Arabia’s Vision 2030 economic transformation. The concept of Lean Manufacturing involves a systematic approach and principles aimed at enhancing efficiency, minimizing inefficiencies, and boosting output in manufacturing operations. While LM principles are well-established globally, their application in Gulf Cooperation Council (GCC) economies remains understudied, particularly regarding the central role of workforce engagement in successful implementation. The main objective of the study is to investigate the implications of LM on the productivity of the industry sector. Specifically, this research examines how the integration of people-centered practices with traditional LM constructs (Just-in-Time, Jidoka, Stability and Standardization) influences operational outcomes in Saudi manufacturing firms. A survey was conducted among specific private and public enterprises to collect data, yielding a 55.8% response rate and 67 valuable responses from a pool of 120 contacted companies. The sample encompassed small, medium, and large enterprises across seven manufacturing sectors. SmartPLS 3 and SPSS were used to assess the structural and measurement models. Common method bias was evaluated using Harman’s single-factor test. The findings demonstrate that implementing the recommended LM structural model significantly enhances operational performance. Notably, people integration exhibited the strongest influence on operational performance (β = 0.361), suggesting that human-centered approaches may be particularly salient in the Saudi context. These findings offer practical guidance for manufacturing firms seeking to align lean initiatives with Vision 2030 objectives.
Read moreHarnessing plant growth-promoting bacteria for nanoparticle biosynthesis: a systematic review of mechanisms, agricultural applications, and biomedical potential.
The rapid expansion of nanotechnology has opened novel opportunities to share for addressing global challenges related to food security, environmental sustainability, and human health. Conventional physical and chemical methods for the synthesis of nanoparticles (NPs) often involve hazardous chemicals, high energy demands, and poor biocompatibility. In contrast, bacterial-synthesized NPs are considered eco-friendly and multifunctional with their enormous potential in agriculture, bioremediation, and biomedical applications. The study highlights the importance of Bacteriogenic NPs as a sustainable alternative to chemically and physically produced NPs due to their reduced toxicity and lower energy consumption. Hence, bacteriogenic NPs, particularly those derived from Bacillus and Pseudomonas species, exhibit remarkable stability, biocompatibility, and multifunctional spectrum due to inherent reducing and capping biomolecules secreted by those bacteria. This review highlights the biosynthetic mechanisms, characterization techniques, and diverse applications of bacterial-based NPs. Initially, in agriculture, silver NPs synthesized by Bacillus xiamenesis enhanced rice growth while suppressing Xanthomonas oryzae, the causal agent of bacterial blight. Then, in environmental remediation, Bacillus pumilus-derived silver nanoparticles demonstrated 96.99% degradation of Congo red dye, underscoring their catalytic efficiency. And, in biomedical sciences, selenium NPs biosynthesized from Streptomyces minutiscleroticus exhibited antiviral activity against dengue virus type 1, highlighting their therapeutic promise. Key findings reveal that these NPs can enhance stress tolerance, nutrient uptake, and disease resistance, along with remediating harmful pollutants from the environment. They also exhibit strong antimicrobial and anticancer properties. Despite all these advancements, much work is still needed to optimize NPs' yield, uniformity, and functionality, as well as environmental and health safety assessment. Integrating omics approaches and nanobiotechnology innovations may unlock new opportunities for precision agriculture, environmental restoration, and advanced therapeutics. In a nutshell, bacterially mediated nanotechnology emerges as a sustainable and transformative tool to address pressing societal and ecological concerns.
Read more