Quality Grade Research Articles

Research on wheat impurity identification method based on terahertz imaging technology

The traditional detection of impurities in wheat has difficulties such as low precision, time-consuming, and cumbersome, therefore, it is important to study the method of rapid and accurate detection of impurities in wheat for correctly assessing the quality grade of wheat. Terahertz (THz) technology has many superior properties such as transient, broadband, low-energy, and penetrating, which can realize rapid and nondestructive detection of wheat quality. In this study, a classification and recognition algorithm AHA-RetinaNet-X for wheat impurity terahertz images based on RetinaNet and Artificial hummingbird algorithm (AHA) is proposed.A THz three-dimensional tomography imaging system is used to image wheat and its impurities, and two THz image datasets, respectively the wheat and impurity dataset for verifying the classification effect of wheat and impurities and the impurity dataset for verifying the classification effect of impurities. The experimental results show that the AHA-RetinaNet-X model outperforms other detection and classification models in terms of accuracy, F1-score, precision, recall, and specificity, and is able to achieve 96.1%, 94.9%, 95.2%, 95.8%, 95.5%, 95.3%, and 93.3% for the wheat and impurity dataset and the impurity dataset, respectively, 95.6%, 96.3%, and 95.2%, and the mAP value of AHA-RetinaNet-X is also higher than the other models and can reach 92.1%. The combination of THz imaging technology and AHA-RetinaNet-X can realize the classification and identification of wheat and impurities, which provides a new method for the non-contact rapid nondestructive detection and identification of wheat and impurities, and also provides a reference for the research of the identification and detection methods of other substances.

Classification of tea quality grades based on hyperspectral imaging spatial information and optimization models

Classification of tea quality grades based on hyperspectral imaging spatial information and optimization models

Thermal desorption-photoionization ion mobility-electronic nose (TD-PIM-Nose) with distance-probability joint decision SVM algorithm: A novel system for Daqu Grade identification

Electronic nose is a bionic technology that uses sensor arrays and pattern recognition algorithms to mimic the human olfactory system. This study developed a thermal desorption-photoionization ion mobility-electronic nose (TD-PIM-Nose) system, employing thermal desorption for direct sampling and humidity control, with a photoionization ion mobility tube as virtual sensor array for component separation and detection, and pattern recognition algorithms for signal processing to differentiate and identify samples. Furthermore, it was applied to assess four quality grades of Daqu samples (“Excellent+”, “Excellent”, “Grade I”, and “Grade II”) determined by the Check-All-That-Apply (CATA) method. Characteristic compound differences among these grades were identified using fingerprint spectra and reduced mobility values. A distance-probability joint decision support vector machine (SVM) algorithm model was established, validated against sensory CATA standards. Results showed identification accuracies: 90 %, 90 %, 96.88 %, and 100 % for respective grades. These findings demonstrated the promising potential of the TD-PIM-Nose system in Daqu quality grading.

Influence of Head Teachers’ Leadership Practices on Pupils’ Learning Outcomes in Public Primary Schools in Narok North Sub County, Kenya

This study sought to investigate the influence of head teachers’ instructional leadership practices on pupils’ learning outcomes/expectations in public primary schools in Narok North Sub-County, Kenya. This was specifically addressed by seeking to establish the influence of instructional supervision and motivational strategies on pupils’ learning outcomes/expectations in public primary schools in Narok North Sub-County, Kenya. The study employed the descriptive survey design. The target population constituted 54 public primary schools in Narok North Sub-County presented by 54 headteachers and 100 grade 5 teachers. Random sampling design was used to sample 129 respondents (45 head teachers and 84 teachers) from the target population. The descriptive analysis was used to establish the perceived level of head teachers’ instructional supervision, motivational strategies and pupils’ learning outcomes. Multiple Linear regression analysis was used to establish the influence of head teachers’ instructional supervision, motivational strategies and resource provision on the pupils’ academic performance and if the influences explained was statistically significant. Multiple Linear regression analysis was used to establish the influence of head teachers’ instructional supervision and motivational strategies on the pupils’ academic performance and if the influences explained was statistically significant. The study revealed that headteachers’ instructional leadership practices consisted of classroom visitation, delegation of teaching duties, evaluation of records of work, holding conferences with teachers, lesson preparations and evaluation of pupils’ exercise books which considerably improved the learning outcomes of grade 5 Pupils in all the five subjects. Finally, the study recommended that Re-engineering workshops by the Ministry of Education should emphasize on curriculum instructional supervision leadership practices and learners’ motivational strategies with a view to improving the quality of Grade 5 Pupils’ learning outcomes in all the five subjects’ areas.

Tingkat Keterbacaan dan Keefektifan Kalimat pada Teks Narasi sebagai Bahan Ajar Membaca Pemahaman di Buku Narasi Literasi Bahasa Indonesia Kelas IX Terbitan Direktorat Pendidikan

Reading comprehension skills are a major focus in Indonesian language learning, especially in grade IX, as narrative comprehension helps students relate information in a broader context. The purpose of this study is to provide comprehensive guidelines for the development of more effective Indonesian learning materials and to strengthen the reading comprehension skills of grade IX students. This study evaluates the readability using Fry's Graph Formula and the effectiveness of sentences in narrative texts as teaching materials for reading comprehension in grade IX Indonesian literacy narrative books. By using the Fry's Graph Formula analysis method, this research helps to adapt the text to the intended grade level. Of the six narrative texts analyzed, there are three that have good readability, two that have poor readability, and one that has poor readability. In addition, this study analyzed sentence ineffectiveness. Sentence ineffectiveness can be caused by various reasons, such as word inefficiency, inaccurate use of conjunctions, inaccuracy in word usage, inaccurate use of punctuation, and meaninglessness. The results of the study provide insight into the quality of grade IX Indonesian literacy narrative teaching materials and contribute to improving students' reading comprehension and ability. The readability and effectiveness of the sentences in the grade IX Indonesian literacy narrative book are very important to ensure that the material presented can be well understood by students, thus having a positive impact on the learning process and the achievement of learning objectives.

County-Level Cultivated Land Quality Evaluation Using Multi-Temporal Remote Sensing and Machine Learning Models: From the Perspective of National Standard

Scientific evaluation of cultivated land quality (CLQ) is necessary for promoting rational utilization of cultivated land and achieving one of the Sustainable Development Goals (SDGs): Zero Hunger. However, the CLQ evaluation system proposed in previous studies was diversified, and the methods were inefficient. In this study, based on China’s first national standard “Cultivated Land Quality Grade” (GB/T 33469-2016), we constructed a unified county-level CLQ evaluation system by selecting 15 indicators from five aspects—site condition, environmental condition, physicochemical property, nutrient status and field management—and used the Delphi method to calculate the membership degree of the indicators. Taking Jimo district of Shandong Province, China, as a case study, we compared the performance of three machine learning models, including random forest, AdaBoost, and support vector regression, to evaluate CLQ using multi-temporal remote sensing data. The comprehensive index method was used to reveal the spatial distribution of CLQ. The results showed that the CLQ evaluation based on multi-temporal remote sensing data and machine learning model was efficient and reliable, and the evaluation results had a significant positive correlation with crop yield (r was 0.44, p < 0.001). The proportions of cultivated land of high-, medium- and poor-quality were 27.43%, 59.37% and 13.20%, respectively. The CLQ in the western part of the study area was better, while it was worse in the eastern and central parts. The main limiting factors include irrigation capacity and texture configuration. Accordingly, a series of targeted measures and policies were suggested, such as strengthening the construction of farmland water conservancy facilities, deep tillage of soil and continuing to construct well-facilitated farmland. This study proposed a fast and reliable method for evaluating CLQ, and the results are helpful to promote the protection of cultivated land and ensure food security.

64 Effects of alternative finishing methods on performance and carcass quality of beef feeder steers

Abstract There has been an interest in directly locally marketing finished beef end products in Arkansas; however, most beef operations do not have the infrastructure to finish cattle conventionally. The objective of this study was to evaluate two non-traditional finishing methods (pasture-based with supplement) compared with a conventional finishing method on live performance and carcass quality of feeder steers. Crossbred beef steers (n = 63; 363.9 ± 28.7 kg) were blocked by body weight (BW) and assigned to pens (n = 3 steers/pen) with 7 pens randomly allocated to each treatment: conventional feedlot finishing diet with roughage included in the ration (FDLT); high starch supplement fed at 2 to 2.25% of BW with ad libitum access to bermudagrass pasture (STCH); or high by-product supplement fed at 2-2.25% of BW with ad libitum access to bermudagrass pasture (BYPD). Steers were fed their respective diets once daily and weighed on d 0, 28, 56, 84, 112, 140, and 161. Once cattle reached their targeted endpoint, they were transported to and harvested at a commercial slaughter facility in Arkansas City, Kansas. Carcass data were collected including hot carcass weight (HCW), preliminary yield grade (PYG), yield grade (YG), quality grade (QG), dressing percentage (DP), and final carcass value. Data were analyzed using PROC GLIMMIX and MIXED (SAS 9.4); pen was the experimental unit, treatment was a fixed effect, and block was considered a random effect. Cattle fed FDLT and BYPD had a greater BW on d 84, 112, and 140 (P ≤ 0.02) and greater overall carcass-adjusted BW (P = 0.03) compared with STCH. Average daily gain (ADG) was greater on d 84 (P = 0.03) for FDLT compared with STCH and BYPD. Overall carcass-adjusted ADG tended (P = 0.09) to be greater for FDLT and BYPD compared with STCH. As expected, cattle fed FDLT had greater dry matter intake (DMI) compared with STCH and BYPD for the entire study (P ≤ 0.0005). Both STCH and BYPD had a more efficient feed-only feed conversion on d 28, 56, 112, 140, and 0-161 (P ≤ 0.05) and were more economical (P < 0.0001) than FDLT. In this study, cattle fed BYPD were more profitable (P ≤ 0.04) compared with STCH and FDLT. Hot carcass weight tended (P = 0.13) to be greater and final carcass value (P = 0.01) was greater for BYPD and FDLT compared with STCH. No differences (P ≤ 0.78) were noted for PYG, YG, QG, or DP. Data from this study suggests feeding supplemental diets to beef cattle grazing pasture could successfully be used as an alternative finishing method without affecting carcass quality.

367 Changing the conversation: Evaluating feedyard closeouts and the beef system on a carcass basis

Abstract Beef cattle genetics, management, technologies and nutritional strategies are ever evolving, and current US trends favor feeding cattle to heavier carcass endpoints and optimizing quality grade. The average number of days on feed (DOF) in the US has increased year after year, averaging 195 and 183 DOF for steers and heifers, respectively, as reported by Elanco Benchmark data in 2021. As DOF increase, cattle live performance, including average daily gain and feed efficiency decline; however, hot carcass weight (HCW) becomes significantly heavier. Although a reduction in live feed conversion occurs as cattle are fed for extended DOF, the kilograms of additional live gain that result as kilograms of gain on the carcass, termed carcass transfer, increase linearly. As DOF are extended, carcass transfer has been reported to increase up to 88 %. As a result of genetic advancements, technologies, and feeding longer, HCW has trended heavier over the last 60 yr, with 2024 USDA HCW reported for April as 11.3 and 9.5 kg heavier for steers and heifers, respectively, year after year. According to mandatory price reporting data, approximately 74 % of fat cattle marketed in the US are sold as dressed beef. As we continue to feed to heavier endpoints and longer DOF, the profitability of selling on a carcass-basis increases. With the increase in carcass transfer as DOF extend, this presentation will attempt to address that cattle live performance should be adjusted to a carcass-basis for feedyards to appropriately capture the inflection point at which cost of additional gain equals the price received for the additional gain.

Contingent valuation versus choice experiment: estimating the willingness to pay for organic oranges in Vietnam

PurposeThe study estimates the willingness to pay for organic oranges and identifies its influencing factors among consumers in the Mekong Delta, Vietnam.Design/methodology/approachThe study used survey data from 413 households in the Mekong Delta from March 2022 to July 2022. The choice experiment (CE) and contingent valuation method (CVM) were employed to analyze consumers’ willingness to pay (WTP). STATA 17 software was used to analyze research data in the logit model and mixed logit model.FindingsThe research results from the CVM approach show that a number of demographic characteristics have a direct impact on WTP, such as education, educational attainment, family size, the presence of children and the elderly in the household, food safety and environmental awareness. The CE model shows product attributes that influence consumers’ WTP, such as country of origin, traceability, quality grade, organic certification, ecolabel and organic content. Both approaches show that price is the main barrier to organic orange consumption.Research limitations/implicationsThe study surveyed four large cities in four provinces representing the Mekong Delta region.Practical implicationsOur study helps administrators have a deeper insight into consumer preferences and behavior, specifically the factors that affect consumers' WTP, an important indicator of demand for the success of manufacturers and marketers in developing as well as improving marketing strategies. Knowledge of a product’s WTP on behalf of (potential) customers plays an important role in many areas of marketing management, such as pricing decisions or new product development.Social implicationsFurthermore, this understanding will inform policymakers about the future of agricultural markets in Vietnam and help them better prepare for the making of sustainable agricultural policies. Develop organic agriculture to both protect human health, protect the living environment and protect the soil from degradation, ensuring sustainable agricultural production. This is also one of the measures to help people stay away from diseases to limit the social burden.Originality/valueThe study confirms that both CVM and CE models can be used to estimate WTP. However, CVM fits the overall WTP estimate, while CE is more appropriate when estimating WTP for individual scenarios through combining attributes with different levels.

A multi-view multi-label fast model for Auricularia cornea phenotype identification and classification

The identification and classification of various phenotypic features of Auricularia cornea fruit bodies are crucial for quality grading and breeding efforts. The phenotypic features of Auricularia cornea fruit bodies encompass size, number, shape, color, pigmentation, and damage. These phenotypic features are distributed across various views of the fruit bodies, making the task of achieving both rapid and accurate identification and classification challenging. This paper proposes a novel multi-view multi-label fast network that integrates two different views of the Auricularia cornea fruiting body, enabling rapid and precise identification and classification of six phenotypic features simultaneously. Initially, a multi-view feature extraction model based on partial convolution was constructed. This model incorporates channel attention mechanisms to achieve rapid phenotypic feature extraction of the Auricularia cornea fruiting body. Subsequently, an efficient multi-task classifier was designed, based on class-specific residual attention, to ensure accurate classification of phenotypic features. Finally, task weights were dynamically adjusted based on heteroscedastic uncertainty, reducing the training complexity of the multi-task classification. The proposed network achieved a classification accuracy of 94.66% and an inference speed of 11.9 ms on an image dataset of dried Auricularia cornea fruiting bodies with three views and six labels. The results demonstrate that the proposed network can efficiently and accurately identify and classify all phenotypic features of Auricularia cornea.

Impact of planting and harvest dates on yam infestation by white grubs

AbstractThe white grub, Diaprepes abbreviatus L. (Coleoptera: Curculionidae), is a significant pest of yam tubers and the second cause of tuber rot in Haiti. Larval feeding inflicts severe damage to tubers, leading to notable losses due to decreased tuber quality, reduced marketability and increased susceptibility to secondary parasites and pathogens. This study examined the influence of planting and harvesting dates on the vulnerability of yam tubers to white grub infestation and the resulting tuber quality across 24 farmers' fields. At harvest, we assessed the level of tuber infestation, white grub density and the tuber quality index. The results indicated that 85% of grub populations were found in fields planted on the traditional date. In addition, 69.5% of tuber damage occurred in early‐planted fields with fewer tubers damaged (30%) when harvested early. In contrast, in fields planted 30 days after the traditional date, the harvest date did not affect tuber infestation and damage by the pest. Overall, both planting and harvest dates impacted the quality grade of yam tubers. Delayed planting by 30 days and early harvesting (34th–38th week after planting) improved the marketability of yams. These findings highlight the importance of optimising planting and harvest schedules to better manage white grub infestation and enhance the marketability of yam tubers.

NTS-CAM classification model with channel attention mechanism for grading In-Vitro Fertilization (IVF) blastocyst quality

An automated-based intelligence approaches have widely used for quantifying In-Vitro Fertilisation (IVF) blastocyst image features that offer automation in morphology assessment as well as embryo selection to improve embryo implantation. Since the IVF blastocyst co-existed three main features of Zona Pellucida (ZP), Trophectoderm (TE) and Inner Cell Mass (ICM), this has made it crucial to consider the informative regions of all features in image morphology assessment. Although the implementation of Navigator-Teacher-Scrutinizer Network (NTS-net) has been detected most informative regions under the guidance of the Teacher network, there still limitation on calculation of the feature extraction process of different blastocyst features that led to poor classification performance. Therefore, this study proposes a new classification model namely NTS-CAM to improve extracted blastocyst features by assigning weights to channel features in channel attention mechanism (CAM) while extracting informative regions of each blastocyst feature. The benchmarking dataset showed significant performance of classification accuracy for ZP, TE, and ICM features with 80.5 %, 67.4 %, and 76.3 %, and the clinical dataset showed 74.1 %, 71.8 %, and 63.5 %, respectively. In conclusion, the proposed NTS-CAM model to predict grade of IVF blastocyst quality has improved the performance compared to classic NTS model. Furthermore, the improved model can be used for clinical decision making as well as for quality control in IVF procedure.

Evaluation of the accuracy and readability of ChatGPT-4 and Google Gemini in providing information on retinal detachment: a multicenter expert comparative study

BackgroundLarge language models (LLMs) such as ChatGPT-4 and Google Gemini show potential for patient health education, but concerns about their accuracy require careful evaluation. This study evaluates the readability and accuracy of ChatGPT-4 and Google Gemini in answering questions about retinal detachment.MethodsComparative study analyzing responses from ChatGPT-4 and Google Gemini to 13 retinal detachment questions, categorized by difficulty levels (D1, D2, D3). Masked responses were reviewed by ten vitreoretinal specialists and rated on correctness, errors, thematic accuracy, coherence, and overall quality grading. Analysis included Flesch Readability Ease Score, word and sentence counts.ResultsBoth Artificial Intelligence tools required college-level understanding for all difficulty levels. Google Gemini was easier to understand (p = 0.03), while ChatGPT-4 provided more correct answers for the more difficult questions (p = 0.0005) with fewer serious errors. ChatGPT-4 scored highest on most challenging questions, showing superior thematic accuracy (p = 0.003). ChatGPT-4 outperformed Google Gemini in 8 of 13 questions, with higher overall quality grades in the easiest (p = 0.03) and hardest levels (p = 0.0002), showing a lower grade as question difficulty increased.ConclusionsChatGPT-4 and Google Gemini effectively address queries about retinal detachment, offering mostly accurate answers with few critical errors, though patients require higher education for comprehension. The implementation of AI tools may contribute to improving medical care by providing accurate and relevant healthcare information quickly.

Research on Silage Corn Forage Quality Grading Based on Hyperspectroscopy

Corn silage is the main feed in the diet of dairy cows and other ruminant livestock. Silage corn feed is very susceptible to spoilage and corruption due to the influence of aerobic secondary fermentation during the silage process. At present, silage quality testing of corn feed mainly relies on the combination of sensory evaluation and laboratory measurement. The sensory review method is difficult to achieve precision and objectivity, while the laboratory determination method has problems such as cumbersome testing procedures, time-consuming, high cost, and damage to samples. In this study, the external sensory quality grading model for different qualities of silage corn feed was established using hyperspectral data. To explore the feasibility of using hyperspectral data for external sensory quality grading of corn silage, a hyperspectral system was used to collect spectral data of 200 corn silage samples in the 380–1004 nm band, and the samples were classified into four grades: excellent, fair, medium, and spoiled according to the German Agricultural Association (DLG) standard for sensory evaluation of silage samples. Three algorithms were used to preprocess the fodder hyperspectral data, including multiplicative scatter correction (MSC), standard normal variate (SNV), and S–G convolutional smoothing. To reduce the redundancy of the spectral data, variable combination population analysis (VCPA) and competitive adaptive reweighted sampling (CARS) were used for feature wavelength selection, and linear discriminant analysis (LDA) algorithm was used for data dimensionality reduction, constructing random forest classification (RFC), convolutional neural networks (CNN) and support vector machines (SVM) models. The best classification model was derived based on the comparison of the model results. The results show that SNV-LDA-SVM is the optimal algorithm combination, where the accuracy of the calibration set is 99.375% and the accuracy of the prediction set is 100%. In summary, combined with hyperspectral technology, the constructed model can realize the accurate discrimination of the external sensory quality of silage corn feed, which provides a reliable and effective new non-destructive testing method for silage corn feed quality detection.

Development of a true density-based automated quality grading device for unboiled arecanut kernels

The automated sorting of arecanut kernels is a significant challenge that has not been effectively addressed thus far. Scientific grading techniques are necessary given the paradigm change toward investigating alternative uses for arecanuts in industry and the medical field. This research work emphasizes the relatively unexplored aspect of the post-harvest process; quality grading of kernels based on physical properties. It aimed to develop a novel approach for classifying unboiled (Chali) arecanut kernels cultivated in Goa, India based on their true density, using a combination of mechanical and visual techniques. The study explored the potential of true density as a quality indicator for real-time grading of the kernels. To achieve this, automated grading equipment was devised, utilizing a load cell to measure the kernel's mass and the ellipsoid approximation method to estimate its volume. A machine vision system captured the top and side images of the kernels to measure their volume. Python programs were created to enable image acquisition, processing, object detection, measurement and kernel segregation. Real-time kernel classification was accomplished by establishing serial data communication between the Python code and the Arduino board. The kernel segregation process was facilitated by servomechanism and a stepper motor. The kernels were classified into acceptable and non-acceptable categories based on a threshold value of true density. The research successfully established a method that utilizes the physical attributes of arecanut kernels as parameters for quality grading. However, the study encountered challenges with the density measurements, as the paired t-test results revealed significant differences between the kernel true density measured by the device and the true density estimated using the weighing scale-water displacement method, indicating a percentage error of 13.2%. Addressing these challenges would lead to more accurate density calculations, thereby enhancing the overall effectiveness of the kernel classification process. Furthermore, the technique allowed for the offline estimation of the kernels' porosity, which was found to be 45.3%. In future research, the integration of density and porosity measurement systems could be explored for real-time quality evaluation based on porosity, offering potential opportunities for further enhancement and optimization of the grading process. The technology could be further applied to other types of nuts and agricultural products, thereby overcoming the limitations of color-based sorting using image processing. Key words: Quality grading, True density, Machine vision, Arecanut kernel, Python

Seasonal Variation in Nematode Infestation Across Bahar Treatments in Pomegranate Cultivation

This study investigates the influence of three Bahar treatments—Ambe Bahar (spring flowering), Mrig Bahar (monsoon flowering), and Hasta Bahar (autumn flowering)—on the extent of nematode infestation in pomegranate orchards. The research was conducted in major pomegranate-growing regions of India, where soil samples were collected from fields practicing each of the Bahar treatments. The results revealed significant differences in nematode infestation levels across the three Bahar treatments. Mrig Bahar exhibited the lowest nematode density, with an average of 80 nematodes per 100g of soil, compared to 120 in Hasta Bahar and 150 in Ambe Bahar. Additionally, Mrig Bahar treatment was associated with the highest average yield (12.8 kg per plant) and superior fruit quality (Grade A). The findings suggest that Mrig Bahar offers a more conducive environment for nematode management, likely due to its timing relative to environmental conditions that may suppress nematode activity. The results revealed significant differences in nematode infestation levels across the three Bahar treatments. Mrig Bahar exhibited the lowest nematode density, with an average of 80 nematodes per 100g of soil, compared to 120 in Hasta Bahar and 150 in Ambe Bahar. Additionally, Mrig Bahar treatment was associated with the highest average yield (12.8 kg per plant) and superior fruit quality (Grade A). The findings suggest that Mrig Bahar offers a more conducive environment for nematode management, likely due to its timing relative to environmental conditions that may suppress nematode activity. This study underscores the importance of selecting the appropriate Bahar treatment to mitigate nematode infestation and optimize pomegranate production. The insights gained from this research can guide farmers in choosing the most effective cultivation practices, ultimately contributing to sustainable pomegranate farming and improved economic outcomes. Further research is recommended to explore the underlying mechanisms that confer resistance in Mrig Bahar and to develop integrated nematode management strategies tailored to specific Bahar treatments.

Analysis of Forecasting Methods on Rice Price Data at Milling Level According to Quality

Rice is a primary source of carbohydrates for many Indonesians, and its prices often surge due to uncontrolled demand. Therefore, the government is crucial in monitoring rice prices to maintain stability. Information technology, particularly data mining such as forecasting, is essential for providing accurate information on future rice prices. It will assist various stakeholders in making informed pricing policy decisions. This study employs Random Forest Regression and Gradient Boosting Regressor methods to predict rice prices using a dataset that includes monthly average rice prices at milling levels, categorized by quality (Premium and Medium), spanning from January 2013 to April 2024. The dataset consists of 136 rows, each representing a unique combination of year, month, and quality, and is stored in CSV format. Methodological steps include data collection, preprocessing, modeling, and model evaluation using monthly average rice prices at milling levels based on quality, including premium and medium grades. The results from Random Forest Regression indicate Root Mean Square Error (RMSE) values of 24.90 for premium rice and 25.47 for medium rice. The study reveals that Random Forest Regression outperforms Gradient Boosting Regressor in this context. Future research should explore additional prediction methods and consider other variables influencing rice prices to enhance model accuracy.

Novel multifractal-based classification model for the quality grades of surrounding rock within tunnels

Understanding the variation patterns of tunnel boring machine (TBM) operational parameters is crucial for assessing engineering geological conditions and quality grades of surrounding rock within tunnels. Studying the multifractal characteristics of the TBM operational parameters can help identify the patterns, but the relevant research has not yet been explored. This paper proposed a novel classification model for quality grades of surrounding rock in TBM tunnels based on multifractal analysis theory. Initially, the statistical characteristics of eight TBM cycle data with different grades of surrounding rock were explored. Subsequently, the method of calculating and analyzing the multifractal characteristic parameters of the TBM operational data was deduced and summarized. The research results showed that the TBM operational parameters of cutterhead torque, total thrust, advance rate, and cutterhead rotation speed have significant multifractal characteristics. Its multifractal dimension, midpoint slope of the generalized fractal spectrum, and singularity strength range can be used to evaluate the surrounding rock grades of the tunnel. Finally, a novel classification model for the tunnel surrounding rocks based on the multifractal characteristic parameters was proposed using the multiple linear regression method, and the model was verified through four TBM cycle data containing different surrounding rock grades. The results showed that the proposed multifractal-based classification model for tunnel surrounding rocks has high accuracy and applicability. This study not only achieves multifractal feature representation and surrounding rock classification for TBM operational parameters but also holds the potential for adaptive adjustment of TBM operational parameters and automated tunneling applications.

Water quality assessment and its pollution source analysis from spatial and temporal perspectives in small watershed of Sichuan Province, China.

Rapid socio-economic development has led to many water environmental issues in small watersheds such as non-compliance with water quality standards, complex pollution sources, and difficulties in water environment management. To achieve a quantitative evaluation of water quality, identify pollution sources, and implement refined management in small watersheds, this study collected monthly seven water quality indexes of four monitoring points from 2010 to 2023, and ten water quality indexes of 23 sampling points in the Shiting River and Mianyuan River which are tributaries of the Tuojiang River Basin. Then, water quality evaluation and pollution source analysis were conducted from both temporal and spatial perspectives using the Water Quality Index (WQI) method, the Absolute Principal Component Scores/Multiple Linear Regression (APCS-MLR) method, and the Positive Matrix Factorization (PMF) receptor modeling technique. The results indicated that except for total nitrogen (TN), the concentrations of other water quality indexes exhibited a decreasing trend, and all were divided into two obvious stages before and after 2016. Furthermore, the proportion of water quality grade of Good and above increased from 73.96 to 84.94% from 2010-2015 to 2016-2023, and the water quality grade of Good and above from upstream to downstream dropped from 100 to 23.33%. From the temporal scale, four and five pollution sources were identified in the first and second stages, respectively. The distinct TN pollutant is mainly affected by agricultural non-point sources (NPS), whose impact is enhanced from 17.76 to 78.31%. Total phosphorus (TP) was affected by the phosphorus chemical industry, whose contribution gradually weakened from 50.8 to 24.9%. From a spatial perspective, four and five pollution sources were identified in the upstream and downstream, respectively. Therefore, even though there are some limitations due to the data availability of water monitory and hydrology data, the proposed research framework of this study can be applied to the water environmental management of other similar watersheds.

Association and Path Coefficient Analysis of Some Arsi Coffee Accesions (<i>Coffea arabica </i>L.) for Quality Traits at Mechara, Ethiopia

Coffee is still one of Ethiopian’s primary agricultural export crops accounting for more than 25% of export earnings. Arsi coffee is known to produce Harar C coffee quality grade and known for its unique flavor and aroma. Therefore, this study was conducted to determine association among coffee bean quality traits and, the direct and indirect effects of bean quality traits on overall quality of coffee. A total of 56 Arsi coffee accessions and four Hararghe coffee varieties were evaluated for bean physical and organoleptic coffee quality traits using Completely Randomized Design with three replications. The analysis of variance results showed significant variation among Arsi coffee accession for all traits except astringency, bitterness, and odor. The overall coffee quality had positive and significant phenotypic and genotype correlations with aromatic intensity, aromatic quality, acidity, body, flavor, overall standard quality and overall cup quality. These traits also had positive direct effects on overall coffee quality however; aromatic intensity and body exerted negligible negative direct effects at genotypic level whereas aromatic quality had negative direct effect at phenotypic level. All these traits through overall standard quality, and aromatic intensity, aromatic quality and acidity via each other and through body and flavor exerted positive direct effects on overall coffee quality at genotypic level. Thus majority of quality traits could be used for indirect selection of genotypes for overall coffee quality.