Relative Importance Value Research Articles

Criteria in Building Material Selection and The Role of Sustainability

Buildings have become the focal point of sustainability because they consume large amounts of natural resources, especially materials and energy, and produce waste throughout their life cycle. Efforts to make buildings sustainable begin with the sustainability of the materials that govern most of the construction management process. In this study, an attempt was made to determine the importance levels of the criteria to be considered in the sustainability of building materials. For this purpose, a survey study was conducted to evaluate the importance of 25 criteria, grouped under the headings of environmental, social, and economic criteria, in terms of sustainability. The survey was conducted with the participation of 50 people from different professions and with different demographic characteristics, and whether participant opinions differed according to demographic characteristics was examined through inferential analyses. The inferential analyses revealed that the views differed for the work experience and only on economic criteria, and that there was no differentiation according to gender, age, education level and profession. For this reason, it was decided that the results could be generalized, and the relative importance values of the criteria were determined. While water conservation ranks first among all criteria, including environmental, accessibility among social criteria and long-term savings among economic criteria have been determined to be the most important criteria. The results revealed which criteria should be taken into consideration in the sustainability of building materials in order to make the construction industry more sustainable. In this respect, it is evaluated that the study will be a guide for governments, local governments, building material manufacturers, designers, contractors and ultimately users.

Modeling of the effect of gradation and compaction characteristics on the california bearing ratio of granular materials for subbase and landfill liner construction

The California bearing ratio (CBR) of a granular materials are influence by the soil particle distribution indices such as D10, D30, D50, and D60 and also the compaction properties such as the maximum dry density (MDD) and the optimum moisture content (OMC). For this reason, the particle packing and compactibility of the soil play a big role in the design and construction of subbases and landfills. In this research paper, experimental data entries have been collected reflecting the CBR behavior of granular soil used to construct landfill and subbase. The database was utilized in the ratio of 78–22% to predict the CBR behavior considering the artificial neural network (ANN), the evolutionary polynomial regression (EPR), the genetic programming (GP), Extreme Gradient Boosting (XGBoost), Random Forest (RF) and the response surface methodology (RSM) intelligent learning and symbolic abilities. The relative importance values for each input parameter were carried out, which indicated that the (CBR) value depends mainly on the average particle size (D30, 50 & 60). They showed a combined influence index of 66% of the considered parameters in the model exercise. This further shows the importance and structural influence of the particles within the D50 and D60 range in a granular material consistency in the design and construction purposes. Performance indices were also used to study the ability of the models. The ANN model showed the best performance with accuracy of 88%, then GP, EPR and RF with almost the same accuracies of 85% and lastly the XGBoost with accuracy of 81%. Also, the RSM produced an R2 of 0.9464 with a p-value of less than 0.0001. These values show that the ANN produced the decisive model with the superior performance indices in the forecast of CBR of granular material used as subbase and waste compacted earth liner material. The results further show that optimal performance of the CBR depended on D50 and D60 for the design of subgrade, subbase, and liner purposes and also during the performance monitoring phase of the constructed flexible pavement foundations and compacted earth liners.

How Do Off-Season Cover Crops Affect Soybean Weed Communities?

Weeds compete for environmental resources, leading to reduced soybean yield. In this context, integrated weed management strategies related to cultural control with the use of cover crops are necessary. Our aim was to evaluate weed occurrence in soybean systems with different cover crops. Field studies were conducted at Júlio de Castilhos, Santa Maria, Capão do Leão, Barra do Ribeiro, and Santo Ângelo, Rio Grande do Sul, Brazil. A randomized complete block design with four replications was used. Treatments consisted of black oats (Avena strigosa Schreb.), white oats (Avena sativa L.), rye (Secale cereale L.), hairy vetch (Vicia sativa L.), forage turnip (Raphanus sativus L.), and white clover (Trifolium repens L.) in pure stands or in mixtures. The analyzed variables were relative frequency, density, abundance, and importance value index, similarity index of weeds, dry shoot mass of cover crop, and soybean yield. Cover crops containing white or black oats reduced the relative importance value index of weeds, such as Lollium multiforum, Conyza spp., and Bidens pilosa. Forage turnip, hairy vetch, and white clover showed distinct responses. Black oats and forage turnip did not differ from cover crop mixtures in terms of dry shoot mass and grain yield, being superior to fallow, white clover, and hairy vetch.

Artificial neural networks in soil quality prediction: Significance for sustainable tea cultivation

In today's era artificial intelligence is quite popular, one of the most effective algorithms used is Artificial Neural Networks (ANN). In this study, the determination of soil quality using the Soil Management Assessment Framework (SMAF) model in areas where tea cultivation is carried out at the micro-watershed scale and the predictability of soil quality using ANN were evaluated. According to the results, the soil quality indices of tea-growing areas were generally classified as “medium” between 55 and 70 %. Among the evaluated features for determining soil quality, the highest relative importance value was for soil organic carbon content (13 %) and potential mineralizable nitrogen (13 %), whereas the lowest values were for exchangeable potassium (4 %) and sodium adsorption ratio (SAR) (4 %). In addition, when comparing the actual and predicted values for soil quality prediction using ANN, the Lin's concordance correlation coefficient (LCCC), ratio of performance to deviation (RPD), and R2 values were found to be 0.93, 2.95, and 0.89, respectively. Significant properties for the determined values within a 90 % predicted interval were found to be organic matter, microbial biomass carbon, bulk density, and aggregate stability of the soils. Moreover, the uncertainty values (standard deviation) in the model predictions were determined to be within the range of 1.01–4.56 %. Consequently, the Soil Quality Index (SQI) obtained from the SMAF model using 12 soil properties in tea-growing areas could be accurately predicted using ANN. As a result of this study, digital maps showing the spatial distribution of SQI and the predicted uncertainties can help monitor SQI levels in this area.

Patient preferences for generic substitution policies: a discrete choice experiment in China.

Background: Generic substitution policies have been widely implemented worldwide to enhance the accessibility of medications. Nevertheless, certain patients have voiced discontent with these policies. This study aimed to evaluate the patient preferences for generic substitution policies and explore the potential for optimization to enhance patient acceptance. Methods: A discrete choice experiment (DCE) was conducted to estimate the relative importance (RI) of five attributes, including generic consistency evaluation (GCE), reimbursement rate, medication use control, information disclosure, and post-marketing surveillance. Respondents were recruited among inpatients and outpatients in three cities and surveys were conducted face-to-face. Preference coefficients, RI of attributes, and the uptake rate of various policies were computed using a mixed logit model. The interaction effects were also included to examine preference heterogeneity. Results: A total of 302 patients completed the survey. All five attributes significantly impacted policy acceptance. GCE held the highest RI value at 56.64%, followed by reimbursement rate (RI = 12.62%), information disclosure (RI = 12.41%), post-marketing surveillance (RI = 9.54%), and medication use control (RI = 8.80%). Patient preferences varied depending on their gender and income. The patient uptake rate of China's current policy was only 68.56%. If all generics were to pass GCE without altering the other attributes, the uptake rate of policies would rise to 82.63%. Similarly, implementing information disclosure without changing other attributes would result in a 78.67% uptake rate, which is comparable to the effect of a 10% increase in reimbursement rate for generics (78.81%). Combining these policies could mitigate the adverse effects of mandatory substitution on patient. Conclusion: Chinese patient preferences for generic substitution policies were mainly influenced by GCE. China's current generic substitution policy has room for further optimization to enhance patient acceptance.

Ethnomedicinal Plants and Herbal Preparations Used by Rural Communities in Tehsil Hajira (Poonch District of Azad Kashmir, Pakistan).

The present study emphasizes the importance of documenting ethnomedicinal plants and herbal practices of the local rural communities of Tehsil Hajira (Pakistan). The aim was to document, explore and quantify the traditional ethnomedicinal knowledge. Ethnobotanical data were collected using semi-structured questionnaires and analyzed using various quantitative indices. The results showed that 144 medicinal plant species from 70 families and 128 genera play an important role in herbal preparations. The most common type of preparation was powder (19.0%), followed by paste (16.7%), aqueous extract (15.7%), decoction (14.7%) and juice (11.0%). Fragaria nubicola (0.94) and Viola canescens (0.93) had the highest relative frequency of mention (RFC), while Berberis lycium (1.22) and Fragaria nubicola (1.18) had the highest use value (UV). Geranium wallichianum (85.5), Ligustrum lucidum (83) and Indigofera heterantha (71.5) were the most important species in the study area with the highest relative importance (RI) value. The diseases treated were categorized into 17 classes, with diseases of the digestive system and liver having the highest Informant Consensus Factor (ICF) value, followed by diseases of the oropharynx and musculoskeletal system. Important plants mentioned for the treatment of various diseases of the gastrointestinal tract are Zanthoxylum alatum, Berberis lycium, Mentha longifolia, Punica granatum, Rubus ellipticus and Viola canescens. New applications of rarely documented plants from this area are: Oxalis corniculata paste of the whole plant to treat vitiligo, Carthamus tinctorius flowers to treat chicken pox, Dioscorea deltoidea tuber powder to treat productive cough, Inula cappa root decoction to treat miscarriage, Habenaria digitata tuber juice for the treatment of fever, Viola canescens leaves and flowers for the treatment of sore throat and Achillea millefolium root and leaf juice for the treatment of pneumonia. These plants may contain interesting biochemical compounds and should be subjected to further pharmacological studies to develop new drugs. Traditional medicinal knowledge in the area under study is mainly limited to the elderly, traditional healers and midwives. Therefore, resource conservation strategies and future pharmacological studies are strongly recommended.

Benchmarking the quality improvement strategies of wire arc additive manufacturing process using fuzzy QFD approach

PurposeThe purpose of this paper is to improve the productivity and quality of the wire arc additive manufacturing process by benchmarking the strategies from the selected six strategies, namely, heat treatment process, inter pass cooling process, inter pass cold rolling process, peening process, friction stir processing and oscillation process.Design/methodology/approachTo overcome the lack of certainty associated with correlations and relationships in quality functional deployment, fuzzy numbers have been integrated with the quality functional deployment framework. Twenty performance measures have been identified from the literature under five groups, namely, mechanical properties, physical properties, geometrical properties, cost and material properties. Using house of quality weights are allocated to performance measures and groups, relationships are established between performance measures and strategies, and correlations are assigned between strategies. Finally, for each strategy, relative importance, score and crisp values are calculated.FindingsInter pass cold rolling process strategy is computed with the highest crisp value of 15.80 which is followed by peening process, heat treatment process, friction stir processing, inter pass cooling process,] and oscillation process strategy.Originality/valueTo the best of the authors’ knowledge, there has been no research in the literature that analyzes the strategies to improve the quality and productivity of the wire arc additive manufacturing process.

Local knowledge of homegarden plants in Miao ethnic communities in Laershan region, Xiangxi area, China

BackgroundHomegardens are small-scale land use systems with significant implications for local livelihoods, biodiversity conservation, and sustainable development due to their diverse flora and fauna. Conducting homegarden surveys enables researchers to gain insights into the traditional ecological knowledge of indigenous communities, preserve homegarden biodiversity, and promote sustainable livelihoods. This study has two objectives: first, to collect, record, and organize data on homegarden plants and related traditional knowledge from three communities in the Laershan Plateau, and second, to analyze the species and functional diversity of homegarden plants in the region while exploring the factors that contribute to the heterogeneous distribution of these plants among the communities of three townships.MethodsThis research employed field surveys in the Laershan Miao Autonomous Region in Xiangxi, China, from September 2021 to August 2023. Data were collected through observation and semi-structured interviews. The study utilized descriptive statistics and quantitative analysis, including the Relative Importance Value (RI), Use Value Index (UV), Jaccard Index (JI), and Comprehensive Index of Land Use Degree (La), to examine the diversity of local homegarden plants and related traditional knowledge, as well as community heterogeneity.ResultsThe study area exhibited rich biodiversity, with 152 plant species recorded belonging to 62 families and 124 genera. These findings highlight the importance of homegarden plants in maintaining ecological balance and enhancing system resilience against disturbances. Homegarden plants serve multiple functions such as food, ornamental, medicinal, and fodder purposes, with edible and trade plants having the most abundant knowledge. Furthermore, this research revealed that communities with similar forest resource compositions may have similar homegarden plant compositions, demonstrating the connection between cultural exchange among different communities and patterns of plant species distribution.ConclusionsThe Laershan region boasts diverse homegarden plant species crucial for ecological balance and resilience. Their multifunctionality reflects human impact. Plant diversity varies with residents' lifestyles, needs, and cultural exchanges. The close connection between plants and local life is clear. Factors like resource distribution, cultural exchange, and lifestyle influence plant distribution. Further research is needed for conservation and sustainable development. Future research should focus on culturally valuable plant species and traditional knowledge applications.

Quantitative Estimation of the Impacts of Precursor Emissions on Surface O3 and PM2.5 Collaborative Pollution in Three Typical Regions of China via Multi-Task Learning

The coordinated control of PM2.5 and O3 pollution has become a critical factor restricting the improvement of air quality in China. In this work, precursors and related influencing factors were utilized to establish PM2.5 and O3 estimation models in the North China Plain (NCP), the Yangzi River Delta (YRD), and the Pearl River Delta (PRD) using a multi-task-learning (MTL) model. The prediction accuracy of these three MTL models was high, with R2 values ranging from 0.69 to 0.83. Subsequently, these MTL models were used to quantitatively reveal the relative importance of each factor to PM2.5 and O3 collaborative pollution simultaneously. Precursors and meteorological factors were the two most critical influencing factors for PM2.5 and O3 pollution in three regions, with their relative importance values larger than 29.99% and 15.89%, respectively. Furthermore, these models were used to reveal the response of PM2.5 and O3 to each precursor in each region. In the NCP and the YRD, the two most important precursors of PM2.5 pollution are SO2 and HCHO, while the two most critical factors for O3 pollution are HCHO and NO2. Therefore, SO2 and VOC emissions reduction is the most important measure for PM2.5 pollution, while VOC and NO2 emission reduction is the most critical measure for O3 pollution in these two regions. In terms of the PRD, SO2 and NO2 are the most important precursors of PM2.5 pollution, while the most important precursors for O3 pollution are HCHO and SOX, respectively. Thus, NO2, SO2, and VOC emission reduction is the most critical measure for PM2.5 pollution, while VOC and NO2 emission reduction is the most critical measure for O3 pollution in the PRD. Overall, this study provides clues and references for the control of PM2.5 and O3 collaborative pollution in the NCP, the YRD, and the PRD.

Ethnoveterinary medicinal plants and their utilization by indigenous and local communities of Dugda District, Central Rift Valley, Ethiopia

BackgroundEthnoveterinary medicinal plants have been used by the people of Dugda District in the primary health care system to treat various livestock ailments for generations, particularly, in underserved rural areas. However, these ethnoveterinary practices and medicinal plants are dwindling without proper documentation, due to undergoing socio-cultural and environmental changes. Hence, this study aimed at inventory and analysis of ethnoveterinary medicinal plants and the associated indigenous and local knowledge used in the treatment of livestock health problems in Dugda District.MethodsData were collected from 378 local inhabitants through semi-structured interviews, 18 focus group discussions with 6 to 8 participants in each couple with participant field observations. Informant consensus factor (ICF), fidelity-level (FL) and relative importance value (RI) were used to evaluate the agreement of informants on ethnoveterinary practices, healing potential of medicinal plants and the most multipurpose species. Using standard taxonomic procedures, voucher specimens were collected, identified and deposited at the National Herbarium of Addis Ababa University.ResultsIn total, 64 medicinal plants of ethnoveterinary uses, belonging to 33 families were reported to treat 37 livestock health problems. Anthrax, inappetence and diarrhoea were said to be the most prevalent veterinary health problems treated by traditional medicinal plants. Family Fabaceae was the most widely reported (7 spp.), followed by Apocynaceae, Cucurbitaceae and Solanaceae (5 spp. each). Herbs were the dominant life forms (21spp.), followed by shrubs (20 spp.). The most commonly sought plant parts were leaves (55.25%), followed by roots (23.44%). The principal method of preparation was pounding remedial parts (46.85%) and mixing with cold water. The main route of administration was via oral application (72.67%), drenching diseased livestock. Withania somnifera and Kedrostis foetidissima were the most cited medicinal plants with 53 and 43 use reports (URs), respectively. ICF showed that respiratory diseases scored the highest value (0.94), while most of the reported medicinal plants were gastrointestinal agents. RI value analysis revealed that Croton macrostachyus had highest diversity of uses, followed by K. foetidissima and W. somnifera. Ethnoveterinary uses of some medicinal plants such as Phytolacca dodecandra, Calpurnia aurea, Cyphostemma cyphopetalum and Verbascum sinaiticum as prophylaxis against rabies were a new input for ethnoveterinary database.ConclusionThe study revealed that the people of the Dugda District are endowed with rich ethnoveterinary knowledge and medicinal plants. However, ethnoveterinary knowledge associated with medicinal plant species significantly differ (P < 0.05) between general and key informants, young and matured age groups and informants’ educational level. This infers the impact of mode of ethnoveterinary knowledge transfer, literacy, modern education and globalization on ethnoveterinary uses of medicinal plant species. And also most of the medicinal plants are found in wild habitats with nearly no conservation attention. Therefore, it is imperative to implement participatory conservation actions for medicinal plants in collaboration with traditional institutions (Gada system). The disparity of ethnoveterinary knowledge could be also minimized through awareness creation among local communities about the knowledge and its revitalization. Furthermore, medicinal plants, which are widely utilized and multipurpose, should be screened for their phytochemicals, pharmacological and toxicological activities to confirm ethnoveterinary uses and for future development of veterinary pharmaceuticals.

Ethnobotanical investigation of medicinal and aromatic plants used in the traditional treatment of COVID-19 in the rural commune of Bni Hadifa, province of Al Hoceima (Central Rif, Northern Morocco)

This ethnobotanical investigation was conducted in the rural commune of Bni Hadifa belonging to the Al Hoceima province (North of Morocco), to inventory the principal medicinal plants traditionally used to treat Covid-19. Ethnobotanical information was recorded from 84 inhabitants aged over 18 years in the different communes of the study area, using an ethnobotanical survey based on a questionnaire and semistructured interviews. Data were examined by surveying the relative citation frequency (RFC) and family importance value (FIV). The obtained results permitted the inventory of 40 aromatic and medicinal plants (MAPs) species owned by 20 families, the most important of which by their number of species were: Lamiaceae (12 species), Apiaceae (5 species), Asteraceae (3 species), and two species for each of Amaryllidaceae, Myrtaceae, and Rutaceae. Furthermore, the following species: Allium sativum, Thymus glandulosus, Lavandula dentata L, Citrus limon L, Eucalyptus globulus labill, Artemisia herba-alba, and Marrubium vulgare L were the most frequently cited by the RFC index. Leaves were found to be the common plant organ used to treat Covid-19, while decoction was the most frequent preparation mode. This study also showed that over 90% of the respondents proved the efficacy of the plants used against Covid-19. However, most of the users of these plants did not respect the administered doses and were unaware of the toxicity and lethal effects that could be caused by these plants when taking high doses. The results of this survey demonstrate that the plants used to combat Covid-19 may constitute a promising database for future research in the extraction and chemical analysis of potentially effective biomolecules against this virus.

Use of nutrition facts panels and traffic light labelling and perceived healthiness of food: conjoint analysis and cross-sectional survey

PurposeNutrition labels provide a cost-effective method of conveying nutrition information to consumers. This study aimed to assess the use of nutrition facts panels, knowledge of traffic light labelling (TLL) and perceived healthiness of food items using TLL among consumers.Design/methodology/approachA web-based cross-sectional study was conducted among adults in the United Arab Emirates (UAE) (n = 1,322). TLL knowledge score was derived for each participant. Conjoint analysis was used to calculate the utilities and relative importance of the perceived healthiness scores for four attributes (fat, saturated fat, total sugar, salt) at the aggregate level.FindingsParticipants had a positive attitude towards TLL but were less familiar with TLL than the nutrition facts panel (47.4 vs 85.8%). The mean TLL knowledge score was 3.6 out of 7 (51.6%). Younger age, higher education, higher income, and health-related qualifications were associated with higher scores. Conjoint analysis showed that participants tend to choose products with greener labels, especially for sugars (80.1%) and avoid red labels for fats. Sugars had the highest percentage value of relative importance compared to the other attributes (27.1%).Originality/valueThe study outcomes offer valuable insights into the extent of consumer awareness, comprehension and utilization of nutrition facts panels in the UAE. These findings contribute essential knowledge for a deeper understanding of the impact of nutrition labels on consumer behaviour and decision-making in the region.

Preliminary exploration of herbal tea products based on traditional knowledge and hypotheses concerning herbal tea selection: a case study in Southwest Guizhou, China.

Herbal tea usually refers to "beverage plants that do not belong to the genus Camellia", and it holds a significant historical legacy as a traditional beverage among specific regions and ethnic groups. In light of this, our research aims to investigate and analyze the traditional knowledge pertaining to herbal tea plants used by local people in the QianxinanBuyi and Miao Autonomous Prefecture, Guizhou Province. We also initiated preliminary efforts to create tea products from herbal tea leaves using various processing techniques. Additionally, we attempted to test hypotheses to elucidate how local people select herbal tea plants. Data related to the use of herbal tea plants in this study were collected through semi-structured interviews and participatory observations in four villages in Qianxinan. Quantitative indicators, including the relative frequency of citation (RFC) and the relative importance (RI) value, were calculated, and the availability of plants was also evaluated. General linear model was performed to examine the relationship between the frequency of citation and resource availability, as well as the correlation between the relative frequency of citation and the relative importance, to test both the resource availability hypothesis and the versatility hypothesis. Centella asiatica tea was processed using techniques from green tea, black tea and white tea, with a preliminary sensory evaluation conducted. A total of 114 plant species were documented as being used for herbal teas by local residents, representing 60 families and 104 genera. Of these, 61% of herbal tea plants were found growing in the wild, and 11 species were exotic plants. The family with the highest number of species was Asteraceae (20 species). The study identified 33 major medicinal functions of herbal tea, with clearing heat-toxin and diuresis being the most common functions. General linear model revealed a strong correlation (correlation coefficient of 0.72, p < 0.001) between the frequency of citation and plant availability, as well as a significant correlation (correlation coefficient of 0.63, p < 0.001) between RFC and RI. Under different processing conditions, the characteristics of Centella asiatica tea exhibited variations and were found to be suitable for consumption. The consumption of herbal tea serves as a preventive measure against common ailments for local residents. The resource availability hypothesis, diversification hypothesis and the versatility hypothesis were shown to provide some insight into "how and why local communities select plants for use." Exotic herbal tea plants in the study area also possess valuable therapeutic properties. The processing and production of Centella asiatica herbal tea products hold promising prospects.

Medicinal plants used in Gabon for prophylaxis and treatment against COVID-19-related symptoms: an ethnobotanical survey.

Background: Gabon faced COVID-19 with more than 49,000 individuals tested positive and 307 recorded fatalities since the first reported case in 2020. A popular hypothesis is that the low rate of cases and deaths in the country was attributed to the use of medicinal plants in prevention and treatment. This study aimed to document the plants used for remedial and preventive therapies by the Gabonese population during the COVID-19 pandemic and to pinpoint specific potential plant species that merit further investigation. Methods: An ethnobotanical survey involving 97 participants was conducted in Libreville. Traditional healers and medicinal plant vendors were interviewed orally using a semi-structured questionnaire sheet, while the general population responded to an online questionnaire format. Various quantitative indexes were calculated from the collected data and included the relative frequency of citation (RFC), use value (UV), informant consensus factor (ICF), relative importance (RI), and popular therapeutic use value (POPUT). One-way ANOVA and independent samples t-test were used for statistical analyses. p-values ≤0.05 were considered significant. Results: The survey identified 63 plant species belonging to 35 families. Prevalent symptoms treated included fever (18%), cough (16%), fatigue (13%), and cold (12%). The demographic data highlighted that 52.58% of male subjects (p > 0.94) aged 31-44 years were enrolled in the survey, of which 48.45% (p < 0.0001) and 74.73% (p < 0.99) of informants had university-level education. In addition, the results indicated that a total of 66% of the informants used medicinal plants for prophylaxis (34%), for both prevention and treatment (26%), exclusively for treatment (3%), and only for prevention (3%) while suffering from COVID-19, against 34% of the participants who did not use plants for prevention or treatment. Annickia chlorantha, Citrus sp., Alstonia congensis, Zingiber officinale, and Carica papaya emerged as the most commonly cited plants with the highest RFC (0.15-0.26), UV (0.47-0.75), and RI (35.72-45.46) values. Most of these plants were used either individually or in combination with others. Conclusion: The survey reinforces the use of traditional medicine as a method to alleviate COVID-19 symptoms, thereby advocating for the utilization of medicinal plants in managing coronavirus infections.

Data driven approach for weight restricted data envelopment analysis models with single output

This study aims to explore whether a machine learning algorithm can be used to make improvements in assessing unit efficiencies via a data envelopment analysis (DEA) model. In this study, a DEA model is used to calculate the efficiency scores of Desicion Making Units (DMUs). Then, an ML algorithm is trained that aims to predict the single output using inputs. Ranking of input features based on relative feature importance values obtained from the trained ML model is fed to the DEA model as weight restrictions. As a result, the two DEA models are compared with each other. ML-based insights (feature importance ranking) improve the DEA model in the direction of fewer zero weights. The additional weight restrictions are data depdendent, and hence realistic. As a novel approach, this study proposes the use of machine learning-based feature importance values to overcome a limitation of a DEA model.

Influence of bagasse ash on the compressive strength of lime reconstituted expansive soil by Advanced Machine Learning (AML) for sustainable subgrade and liner construction applications

The utilization of expansive soils for the construction of landfill liners and subgrade facilities without stabilization leads to volume changes due to seasonal change between wet and dry. This necessitated the industrial- and agro-industrial-based waste materials reconstitution of expansive soils to fulfil sustainability requirements for the builtenvironment. In this research paper, multiple datasets were collected from mixes of bagasse ash (BA) and lime (Lm) blend reconstituted expensive soil and deployed in the training and validation interface of advanced machine learning (AML) techniques to predict the unconfined compressive strength (UCS) of the treated soil for their usein landfill liner and subgrade application. The relative importance values for each input parameter were evaluated, such as compaction parameters (MDD and OMC), plastic limit (PL), LL, Lm, and BA. The results of all developed models were observed and collected. The relations between calculated and predicted values show that the GP produced a parametric line of fit expression of y = 0.999 × with performance indices as MAE 14.80 kPa, MSE 400.7 kPa, RMSE 20.00 kPa, and R2 of 0.950, EPR produced a parametric line of fit expression of y = 0.992 × with performance indices as MAE 11.6 kPa, MSE 270.9 kPa, RMSE 16.50 kPa, and R2 of 0.963, and ANN produced a parametric line of fit expression of y = 0.997 × with performance indices as MAE 4.26 kPa, MSE 30.8 kPa, RMSE 5.55 kPa, and R2 of 0.996. The results show that the ANN outperforms the GP and the EPR having produced the least error values, the highest coefficient of determination (R2) and zero outliers beyond the ± 25% performance fit envelop and can be concluded that BA has a remarkable influence in the stabilization of expansive soils and its utilization.

Process-driven susceptibility assessment of glacial lake outburst debris flow in the Himalayas under climate change

Global warming is causing glaciers to retreat and glacial lakes to expand in the Himalayas, which amplifies the risk of glacial lake outburst debris flows (GLODFs) and poses a significant threat to downstream lives and infrastructures. However, the complex interplay between GLODF occurrences and associated indicators, coupled with the lack of a comprehensive susceptibility indicator system that considers the entire GLODF process, presents a substantial challenge in assessing GLODF susceptibility in the Himalayas. This study proposes a process-driven GLODF susceptibility assessment indicator system responding to climate change that considers the complete process of GLODF formation, incorporating relevant parameters about upstream, themselves, and downstream of glacial lakes. Furthermore, to mitigate subjective factors associated with traditional evaluation methods, we developed three novel hybrid machine-learning models by integrating classic machine-learning algorithms with the whale optimization algorithm (WOA) to delineate the distribution of GLODF susceptibility in the Himalayas. All the hybrid models effectively predicted the GLODFs occurrence, with the WOA-SVC model demonstrating the highest prediction accuracy. Approximately 34% of the catchments exhibit high and very high susceptibility levels, primarily concentrated along the north and south sides of the Himalayan ridge, particularly in the eastern and central Himalayas. Indicators capturing the physical formation process of hazards, such as topographic potential (highest relative importance value of 40%), can precisely identify GLODF. A total of 128 catchments pose potential transboundary threats, with 24 classified as having a very high susceptibility level and 25 as having a high susceptibility level. Notably, the border region between China and Nepal is a prominent hotspot for transboundary threats of GLODF. These findings can provide valuable clues for disaster prevention, mitigation, and cross-border coordination in the Himalayas.

Artificial neural network modeling to predict the efficiency of phosphoric acid-hydrogen peroxide pretreatment of wheat straw

Phosphoric acid-hydrogen peroxide (PHP) pretreatment is an effective method to obtain a cellulose-enriched fraction from biomass. In this study, artificial neural network (ANN) was used to predict PHP pretreatment efficiency of cellulose content (C-C), cellulose recovery (C-Ry), hemicellulose removal (H-Rl), and lignin removal (L-Rl) under various conditions of pretreatment time (t), temperature (T), H3PO4 concentration (Cp), and H2O2 concentration (Ch). The final optimized topology structure of the ANN models had 1 hidden layers with 9 neurons for C-C and 10 neurons for C-Ry, 10 neurons for H-Rl, and 12 neurons for L-Rl. The actual testing data fit the predicted data with R2 values ranging from 0.8070 to 0.9989. The relative importance (RI) revealed that Cp and Ch were significant factors influencing the efficiency of PHP pretreatment with total RI values ranging from 12% to 62.6%. However, their weights for the three components of biomass were different. The value of T dominated hemicellulose removal effectiveness with an RI value of 78.6%, while t did not seem to be a main factor dominating PHP pretreatment efficiency. The results of this study provide insights into the convenient development and optimization of biomass pretreatment from ANN modeling perspectives.

30 Exploring the Differential Importance of Modifiable Fitness Variables on Cognitive Performance in Older Adults

Objective:To identify the relative contributions and importance of modifiable fitness and demographic variables to cognitive performance in a cohort of healthy older adults.Participants and Methods:Metrics of modifiable fitness (gait speed, respiratory function, grip strength, and body mass index (BMI)) and cognition (executive function, episodic memory, and processing speed) were assessed in 619 older adults from the Health and Retirement Study 2016 wave (mean age = 74.9, sd = 6.9; mean education = 13.4 years, sd = 2.6; 42% female). General linear models were employed to assess the contribution of modifiable fitness variables in predicting three domains of cognition: executive function, episodic memory, and processing speed. Demographics (age, sex, education, time between appointments, and a chronic disease score) were entered as covariates for each model. Relative importance metrics were computed for all variables in each model using Lindeman, Merenda, and Gold (lmg) analysis, a technique which decomposes a given model’s explained variance to describe the average contribution of each predictor variable, independent of its position in the linear model.Results:When all variables were entered into the general linear model, demographic and modifiable fitness variables explained 35%, 24%, and 26% of the variance in executive function, episodic memory, and processing speed, respectively (all three models were significant, p &lt;0.001). Age, education, respiratory function, and walking speed had higher relative importance values (all lmgs &gt; 1.8) compared to BMI, grip strength, and other covariates in all three models (all lmgs &lt; 1.3). Gender was also relatively important in the executive function (lmg = 4.2) and episodic memory models (lmg = 5.0). Of the modifiable fitness variables, walking speed and respiratory function had the greatest lmg values (5.8 and 6.4 respectively) in the executive function model, similar to demographic variables age (lmg = 6.0) and education (lmg = 8.9). When demographic variables were entered as covariates, modifiable fitness variables collectively accounted for an additional 9.7%, 6.3%, and 6.0% variance in the executive function, episodic memory, and processing speed models respectively (all three models were significant, p &lt;0.001).Conclusions:Our findings indicate that walking speed and respiratory function are of similar importance compared to “traditional” demographic variables such as age and education in predicting cognitive performance in a cohort of healthy older adults. Moreover, modifiable fitness variables accounted for unique variance in executive function, episodic memory, and processing speed after accounting for age and education. Modifiable fitness variables explained the most unique variance in executive function. These results extend the current literature by demonstrating that modifiable fitness variables, even when assessed with brief and relatively coarse measures of physical performance, may be useful in predicting cognitive function. Moreover, the results highlight the need to assess metrics of cognitive reserve, such as education, as well as modifiable fitness variables and their respective roles in accounting for cognitive performance. The data further suggest that relative contributions of physical performance metrics may vary by cognitive domain in healthy older adults.

Data augmentation for bias correction in mapping PM2.5 based on satellite retrievals and ground observations

As most air quality monitoring sites are in urban areas worldwide, machine learning models may produce substantial estimation bias in rural areas when deriving spatiotemporal distributions of air pollutants. The bias stems from the issue of dataset shift, as the density distributions of predictor variables differ greatly between urban and rural areas. We propose a data-augmentation approach based on the multiple imputation by chained equations (MICE-DA) to remedy the dataset shift problem. Compared with the benchmark models, MICE-DA exhibits superior predictive performance in deriving the spatiotemporal distributions of hourly PM2.5 in the megacity (Chengdu) at the foot of the Tibetan Plateau, especially for correcting the estimation bias, with the mean bias decreasing from –3.4 µg/m3 to –1.6 µg/m3. As a complement to the holdout validation, the semi-variance results show that MICE-DA decently preserves the spatial autocorrelation pattern of PM2.5 over the study area. The essence of MICE-DA is strengthening the correlation between PM2.5 and aerosol optical depth (AOD) during the data augmentation. Consequently, the importance of AOD is largely enhanced for predicting PM2.5, and the summed relative importance value of the two satellite-retrieved AOD variables increases from 5.5% to 18.4%. This study resolved the puzzle that AOD exhibited relatively lower importance in local or regional studies. The results of this study can advance the utilization of satellite remote sensing in modeling air quality while drawing more attention to the common dataset shift problem in data-driven environmental research.