Rice Grading Research Articles

A Monitoring Device and Grade Prediction System for Grain Mildew.

Mildew infestation is a significant cause of loss during grain storage. The growth and metabolism of mildew leads to changes in gas composition and temperature within granaries. Recent advances in sensor technology and machine learning enable the prediction of grain mildew during storage. Current research primarily focuses on predicting mildew occurrence or grading using simple machine learning methods, without in-depth exploration of the time series characteristics of mildew process data. A monitoring device was designed and developed to capture high-quality microenvironment parameters and image data during a simulated mildew process experiment. Using the "Yongyou 15" rice varieties from Zhejiang Province, five simulation experiments were conducted under varying temperature and humidity conditions between January and May 2023. Mildew grades were defined through manual analysis to construct a multimodal dataset for the rice mildew process. This study proposes a combined model (CNN-LSTM-A) that integrates convolutional neural networks (CNN), long short-term memory (LSTM) networks, and attention mechanisms to predict the mildew grade of stored rice. The proposed model was compared with LSTM, CNN-LSTM, and LSTM-Attention models. The results indicate that the proposed model outperforms the others, achieving a prediction accuracy of 98%. The model demonstrates superior accuracy and more stable performance. The generalization performance of the prediction model was evaluated using four experimental datasets with varying storage temperature and humidity conditions. The results show that the model achieves optimal prediction stability when the training set contains similar storage temperatures, with prediction accuracy exceeding 99.8%. This indicates that the model can effectively predict the mildew grades in rice under varying environmental conditions, demonstrating significant potential for grain mildew prediction and early warning systems.

Quality Assessment of Rice Using Convolution Neural Networks and Other Machine Learning Techniques- A Comparative Study

Rice holds its position as the most widely cultivated crop worldwide, its demand steadily rising alongside population growth. The precise identification of grains, especially wheat and rice, holds significant importance as their ultimate utilization depends on the quality of grains prior to processing. Traditionally, grain identification tasks have been predominantly manual, relying on experienced grain inspectors and consuming considerable time. However, this manual classification process is susceptible to variations influenced by individual perception, given the subjective nature of human image interpretation. Consequently, there is an urgent need for an automated recognition system capable of accurately identifying grains under diverse environmental conditions, necessitating the application of digital image processing techniques. In this study, we focus on grading five distinct varieties of rice based on their quality, employing a range of convolution neural networks (CNN) namely, Efficientnetb0, Googlenet, MobileNetV2, Resnet50, Resnet101, and ShuffleNet. The performance of CNN towards identification and grading of rice grain is also compared to that of other parametric and Non-parametric classifiers namely, Linear Discriminant Analysis (LDA), K-Nearest Neighbor (K-NN), Naive Bayes (NB), and Back Propagation Neural Network (BPNN) using Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM) based texture features. The image dataset comprises five grades of rice, each containing 100 images, resulting in a comprehensive collection of 500 samples for analysis. It is observed that, Convolution neural networks can grade five different qualities of rice with highest accuracy of 64.4% in case of GoogleNet. Results show that, rice grading using texture features performs better with highest accuracy of 99.2% (using GLCM) and 93.4% (using GLRLM).

Yield, milling quality, rice quality and preferences of superior and specific location rice varieties

Abstract Grain and rice characteristics are a description of the post-harvest quality of rice which is a consideration for farmers, traders, and consumers in choosing rice to be developed and consumed. This study aims to determine the yield, milling quality, rice quality and preference of 5 rice varieties in Indonesia, they were Inpari 32 HDB, Inpari 42 Agritan GSR, Inpari 45 Dirgahayu, Pamelen and Inpari IR Nutri Zinc. The study used a non-factorial Randomized Group Design, rice varieties as treatments, 5 replications. Rice was harvested using 2 methods, namely sickle (manual harvesting) and combine harvester. Determination of Milling Quality, rough rice was milled using a mini electric grain whitener LTJM-2008 then measured the percentage of hulled rice, unhulled rice, bran, and husk. Determination of rice quality, 25 grams of rice samples were sorted manually and measured the percentage of head rice, broken, groats and damaged then determined the grade of rice based on SNI 6128: 2015. The results showed that the rice yield manually and using a combine harvester was different from the potential yield. The milling quality and rice quality of each variety were significantly different (p=0.05%). Rice quality classification based on SNI 6128:2015 shows that Inpari 42 Agritan GSR and Inpari IR Nutri Zinc was included in Medium I, pamelen and Inpari 32 HDB were included in Medium II, and Inpari 45 Dirgahayu was under Medium III. Inpari 32 HDB was the rice variety with the highest preference.

Effectiveness of heat tolerance rice cultivars in preserving grain appearance quality under high temperatures in Japan – A meta-analysis

BackgroundClimate change, particularly rising temperatures, negatively affects rice grain quality, increasing chalky grain percentage (CG) and hampering rice grade and price. Heat-tolerant cultivars have been bred and released since the 2000 s, but the effectiveness of heat tolerance in reducing the occurrence of CG has yet to be quantified. ObjectivesThis study aimed to measure the effectiveness of breeding for better heat tolerance in reducing the negative impact of high temperatures on rice quality. MethodsThrough a systematic literature search, we developed a dataset including 1297 field observations covering 48 cultivars from five different heat tolerant ranks (HTRs) at 44 sites across Japan. A linear mixed-effect model (LME) and a random forest model (RF) were fitted to the data to analyze the effect of HTR and climatic factors such as the cumulative mean air temperature above 26 °C (TaHD), mean solar radiation, and mean relative humidity for 20 days after heading on CG. ResultsThe LME model explained 63% of the variation of the whole dataset with a 14% RMSE. The RF partial dependence plot revealed that the logit-transformed CG response to climate factors was linear, supporting the assumption of the LME. The statistical analysis showed that CG increased as a function of TaHD (P < 0.001), with significant differences among HTRs (P < 0.001). The strongest effect of TaHD was obtained for the lowest HTR and was found to decrease with increasing HTR. CG also increased with higher relative humidity (P < 0.001) and solar radiation (P < 0.01). Based on our modeling, we estimated that as TaHD increased from 20 to 80 °Cd (equivalent to a mean temperature increase from 27 °C to 30 °C), CG increased by 66% points (difference in CG) for cultivars with the lowest HTR, 45% points for cultivars with an intermediate HTR, and 19% points for cultivars with the highest HTR. Raising HTR by just one step (from intermediate to moderately tolerant) is projected to increase the proportion of first-grade rice at a grain-filling temperature of 27 °C, but tolerance levels need to be improved further in case of stronger warming. ConclusionsThe effect of high temperatures on CG was highly dependent on the cultivar’s HTR. Improvements in HTR effectively reduce the negative impacts of high temperatures on rice grain quality. SignificanceHeat-tolerant cultivars are projected to suppress the prevalence of CG more than threefold compared with heat-sensitive cultivars when grain-filling temperature increases from 27 to 30 °C.

Construction of aroma association network of cooked rice based on gas chromatography–mass spectrometry (GC–MS) and sensory analysis

AbstractThe aroma of cooked rice is a key factor in the evaluation of taste quality for rice grading, which greatly affects consumer acceptance. Combining the results of instrumental analysis and sensory evaluation to comprehensively analyse the aroma of cooked rice is a new strategy. The aroma characteristics of fifteen cooked rice varieties were analysed by gas chromatography–mass spectrometry (GC–MS) and descriptive sensory analysis. Based on the aroma descriptors obtained by gas chromatography‐olfactometry (GC‐O) analysis and the odour activity value (OAV) of aroma compounds, the aroma profiles of cooked rice were preliminarily explained by bipartite network and aroma fingerprint. The Pearson correlation coefficients between the OAV results of aroma compounds and sensory data were calculated to construct the aroma association network. The results showed that the aroma attributes of cooked rice were significantly correlated with certain aroma compounds identified by GC–MS, such as aldehydes and heterocycles. The aroma attributes of cooked grain, popcorn, grassy, nutty, and fruity could be well explained by the results of GC–MS analysis. The purpose of the study is to better understand the relationship between aroma characteristics and chemical composition, as well as to provide a theoretical basis for evaluating and predicting the aroma of cooked rice using GC–MS analysis.

Consistency assessment of rice milling quality results from USDA‐FGIS official procedures and commercial mills

AbstractBackground and ObjectivesThe milling quality and grade of rice are typically appraised by milling and inspecting samples collected from a rice lot following US Department of Agriculture (USDA) official procedures using a laboratory mill, which should represent milling quality and grade results of rice milled in commercial mills. The objective of this study was to assess whether the official USDA laboratory mill and procedures provide consistent results with those obtained from commercial mills.FindingsThe results showed that the laboratory mill with the official standard procedures had significantly higher (p &lt; .05) total milled rice yield (TRY) (1.6 percentage points) and head rice yield (HRY) (2.6 percentage points), but lower whiteness index (4.4 units) on average than those of commercial mills. The average TRYs of laboratory‐milled rice of long, medium, and short‐grain varieties were 1.8, 1.7, and 1.0 percentage points higher than those from the commercial operations. The milling characteristics of pureline and hybrid rice differed between official standard mills and commercial mills.ConclusionIf the rice samples were milled to the same whiteness as the official standard procedures, the TRYs and HRYs could be close to the results from the commercial mills.Significance and NoveltyThis study provides important information that could be used to improve the consistency and accuracy of rice quality assessment of laboratory mills following the official procedures and assure that milling results are comparable to those of commercial milling processes.

Thai Hom Mali rice grading using machine learning and deep learning approaches

&lt;span lang="EN-US"&gt;Thai Jasmine rice or Thai Hom Mali rice is a well-known rice type that originated in Thailand. Rice grain qualities are important in determining market pricing and are used in grading systems. The purpose of this research is to use machine learning and deep learning to improve the grading of Thai Hom Mali rice following standardized grading criteria. The appearance of grains and foreign items will determine the grade of rice. The experiment has two parts: grain categorization and rice grading. Multi-class support vector machine (SVM) and convolutional neural network (CNN) are proposed. There are 15 features used as input for multi-class SVM, including morphology and color features. With ImageNet pre-trained weights, CNN with DenseNet201 architecture is implemented. The experiment also tested into how CNN worked with both original and preprocessed images. The results are then compared to a neural network (NN) baseline approach. The CNN approach, which identified each rice variety using preprocessed images, archieved the greatest accuracy rate of 98.25%, with an average accuracy of 94.52% across six categories of rice grading.&lt;/span&gt;

A MEASURE OF QUALITY AND IDENTIFY THE BREED OF RICE GRAIN

Rice is the most consuming food all over the world and the market for rice is always high. In rice manufacturing industries the market demand is always centred on quality of rice. The analysis of grain type, grading, and quality criteria are still determined by skilled persons manually. Because it depends on a number of variables, including human factors, working conditions, cleaning and salvage recovery rates, this process is complex. Deep learning and image processing methods may be used to overcome this. In the food business, quality testing is becoming more significant for grading and classifying grains. In deep learning-based testing, we take into account both physical (grain form and size) and chemical (amylose content, gel consistency) features. The quality and grading of rice grains were examined using this proposed algorithm's average values for the features that were taken out of the network Since grain quality directly affects human health, it is very important for people. Thus, it is crucial to evaluate grain quality and spot low-quality components. The mix of physical and chemical properties makes up rice quality. Two physical traits are grain size and shape. Using canny edge detection, the derived physical characteristics are used to classify the rice grains. This essay offers a solution to the issue of quality analysis in the rice sector. Compared to conventional human-based inspection methods, computer vision-based inspection offers an option that is quick, accurate, convenient, and safe. This article offers a technique for determining the rice grain's quality and categorising it according to various breed types. In this we are going to use three types of rice grains: - 1. Basmati Rice 2. Sonamasoori Rice 3. jhilli Rice Key words: Image processing, CNN, Rice Grading.

Novel Grade Classification Tool with Lipidomics for Indica Rice Eating Quality Evaluation.

The eating quality evaluation of rice is raising further concerns among researchers and consumers. This research is aimed to apply lipidomics in determining the distinction between different grades of indica rice and establishing effective models for rice quality evaluation. Herein, a high-throughput ultrahigh-performance liquid chromatography coupled with quadrupole time-of-flight (UPLC-QTOF/MS) method for comprehensive lipidomics profiling of rice was developed. Then, a total of 42 significantly different lipids among 3 sensory levels were identified and quantified for indica rice. The orthogonal partial least-squares discriminant analysis (OPLS-DA) models with the two sets of differential lipids showed clear distinction among three grades of indica rice. A correlation coefficient of 0.917 was obtained between the practical and model-predicted tasting scores of indica rice. Random forest (RF) results further verified the OPLS-DA model, and the accuracy of this method for grade prediction was 90.20%. Thus, this established approach was an efficient method for the eating grade prediction of indica rice.

An Artificial-Intelligence-Based Novel Rice Grade Model for Severity Estimation of Rice Diseases

The pathogens such as fungi and bacteria can lead to rice diseases that can drastically impair crop production. Because the illness is difficult to control on a broad scale, crop field monitoring is one of the most effective methods of control. It allows for early detection of the disease and the implementation of preventative measures. Disease severity estimation based on digital picture analysis, where the pictures are obtained from the rice field using mobile devices, is one of the most effective control strategies. This paper offers a method for quantifying the severity of three rice crop diseases (brown spot, blast, and bacterial blight) that can determine the stage of plant disease. A total of 1200 images of rice illnesses and healthy images make up the input dataset. With the help of agricultural experts, the diseased zone was labeled according to the disease type using the Make Sense tool. More than 75% of the images in the dataset correspond to one disease label, healthy plants represent more than 15%, and multiple diseases represent 5% of the images labeled. This paper proposes a novel artificial intelligence rice grade model that uses an optimized faster-region-based convolutional neural network (FRCNN) approach to calculate the area of leaf instances and the infected regions. EfficientNet-B0 architecture was used as a backbone as the network shows the best accuracy (96.43%). The performance was compared with the CNN architectures: VGG16, ResNet101, and MobileNet. The model evaluation parameters used to measure the accuracy are positive predictive value, sensitivity, and intersection over union. This severity estimation method can be further deployed as a tool that allows farmers to obtain perfect predictions of the disease severity level based on lesions in the field conditions and produce crops more organically.

Prediction and determination of mildew grade in grain storage based on FOA-SVM algorithm

AbstractGrain mildew is a significant hazard that causes food loss and poses a serious threat to human health when severe. Therefore, effective prediction and determination of mildew grade is essential for the prevention and control of mildew and global food security. In the present study, a model for predicting and determining the mildew grade of rice was constructed using logistic regression, back propagation neural network and GS-SVM (a grid search-based support vector machine algorithm) based on laboratory culture data and actual data from a granary, respectively. The results show that the GS-SVM model has a better prediction effect, but the model cannot automatically adjust the parameters and is more subjective, and the accuracy may decrease when the data set changes. Therefore, this paper establishes a new model for a support vector machine based on a fruit fly optimization algorithm (FOA-SVM), which can achieve automatic parameter search and automatically adjust its parameters to find the best result when the data set changes, with a strong ability of self-adjustment of parameters. In addition, the FOA-SVM converges quickly and the model is stable. The results of this study provide a technical method for early identification of mildew grade during grain storage, which is beneficial for the prevention and control of rice mildew during grain storage.

Monitoring rice lodging grade via Sentinel-2A images based on change vector analysis

ABSTRACT Lodging stress influences the yield, quality, and mechanical harvesting ability of rice (Oryza sativa L.). It is of great significance for the quantitative and objective evaluation of rice yield loss to obtain the rice lodging distribution and grade information rapidly and nondestructively. The purpose of this paper was to establish a remote sensing monitoring method for the grade of rice lodging based on change vector analysis via Sentinel-2A images before and after lodging. Taking the lodging ratio (LR) of rice in the parcel as the characterization index, the changes in spectral reflectance and vegetation index of the rice canopy under different lodging grade stresses were analyzed. A 7-dimensional space vector was composed of a canopy spectral reflectance and vegetation index. A new angle vector was formed by the angle between each vector object and the axis of the canopy spectrum (vegetation index). Based on the difference in feature vectors before and after lodging, a lodging grade monitoring model based on rice parcels was constructed, and the accuracy of the model was verified using field observations. The results showed that the spectral reflectance of the rice canopy after lodging increased with the increase in lodging stress. The difference in vegetation index before and after lodging increased with the increase in lodging severity. Based on the change in the magnitude of the canopy spectral reflectance and its angle vector, and the vegetation index and its angle vector, the R 2 of the rice lodging model was 0.66, 0.66, 0.60, and 0.59, respectively, and the RMSE values were 21.03%, 20.37%, 22.13%, and 22.84%, respectively. Therefore, the accuracy of the model constructed using the vegetation index was the highest. The canopy spectral reflectance and difference in the vegetation index of rice changed regularly with lodging grade stress. The model based on the change magnitude of the vegetation index could effectively realize remote sensing monitoring of the grade of rice lodging in Wuchang.

Antioxidant and phytochemical content of commercial brown rice (Ecobrown) and white rice (Jasmine, Jati Super Special and Manggo Thai) for potential cosmetic rice powder raw materials

Cosmetic rice powder or “bedak sejuk'' has long being used as part of traditional skincare routine. The powdered rice extract is applied on the face, usually at night and will be rinsed off the next morning to obtain smooth and clear skin complexion. Usually, the regular rice available in one’s kitchen is used to make the cosmetic rice powder but different grades of rice (based on the price) will give different effects to the skin. This study aims to investigate and compare the bioactivities and phytochemical composition of different grades of rice available in the market. The rice sample used in this study was Ecobrown rice, Jasmine White rice, Jati Super Special Tempatan rice and Manggo Thai rice. All rice samples were extracted using distilled water by maceration process. The bioactivities; antioxidant capacity was measured using DPPH assay. Phytochemical content was determined as total phenolic and flavonoid contents (TPC and TFC). High Performance Liquid Chromatography (HPLC) was also used to determine phenolic content expressed as gallic acid equivalent (GAE). The result showed that brown rice had significantly higher antioxidants with IC50 values of 6.4 mg/mL in DPPH assay. The observed activities were corresponding with total phenolic content, where EcoBrown rice has a significantly higher amount of phenolic content (p?0.05) compared to other samples. Meanwhile, almost similar TFC was observed in all rice samples with Jati Super Special. The analysis of phenolic content was correlated with HPLC analysis, where brown rice was shown to have the highest amount of gallic acid content. In conclusion, brown rice can be considered as a better choice to produce “bedak sejuk”.

Trading off consumer preferences induced by cultural and colonial heritage: Lessons from New Rice for Africa (NERICA) in Casamance, Senegal

Abstract Breeders face the challenging task of tailoring crop varieties to complex consumer preferences shaped through culture and history. The Casamance rice sector in Senegal is an interesting case; while the region is endowed with a 3,000-year-old cultural heritage of African rice domestication, it has also been exposed to century-long colonial import substitution policies, leading to massive influx of cheap, broken Asian rice. Markets have responded to the amalgam of consumer preferences that have emerged as a result of cultural and colonial heritage by offering three standard grades of rice: 100 per cent broken, semi-broken (35–60 per cent broken), and unbroken. To disentangle the trade-off between indigenous and ‘imported’ traits and inform breeding priorities, we conducted framed field experiments with urban women in the Casamance. We assessed consumers’ revealed price premiums for replacing imported, broken Asian rice with three locally produced New Rice for Africa (NERICA) hybrids between African and Asian rice: (i) broken, fragrant NERICA 1; (ii) broken NERICA 4; and (iii) unbroken NERICA 6 featuring medium/bold grain shape. Consumers with genealogical lineages tracing back to the original domesticators of African rice put significantly higher value on locally produced NERICAs relative to immigrants from the north and northeast, who put premiums on ‘imported’ traits such as rice fragrance. Driven by preferences for both broken and unbroken rice, NERICA 6 outcompeted all other varieties as it mimics the grain shape of semi-broken rice while being unbroken. The latter exemplifies how breeders can strike an optimal compromise in the trade-off between cultural and colonial heritage-induced preferences.

Evaluation and grading of climatic conditions on nutritional quality of rice: A case study of Xiaozhan rice in Tianjin

AbstractBased on the daily meteorological monitoring data of Xiaozhan rice in Tianjin planting area from 2010 to 2020 and the observation data of nutritional quality of Xiaozhan rice in Tianjin from 2014 to 2020, comprehensive characterization parameter M of nutritional quality of Xiaozhan rice in Tianjin and the evaluation model of meteorological conditions' influence on the nutritional quality of rice was established by principal component analysis, ordered sample optimal clustering method and stepwise regression method. The climatic evaluation grades of nutritional quality of Xiaozhan rice in Tianjin were divided into four grades. The comprehensive characterization parameter (M) of nutritional quality of Xiaozhan rice can be determined using five quality factors (protein, amylose, gel consistency, amino acid and chalkiness) into three weighted sums, and the coefficients are is the proportion of the eigenvalues corresponding to the three principal components to the total variance of the original variables. The thresholds of M corresponding to the four grades of ‘general’, ‘good’, ‘excellent’, ‘extra‐superior’, in the climatic evaluation of nutritional quality of Xiaozhan rice in Tianjin were M &lt; 0.3, 0.3 ≤ M &lt; 0.45, 0.45 ≤ M &lt; 0.7, 0.7 ≤ M, respectively. The results showed that M was related to 14 meteorological factors such as average temperature, minimum temperature, maximum temperature, precipitation, sunshine duration and daily range in different months of rice growth period. Among them, the temperature condition in September was the key factor affecting the nutritional quality of Xiaozhan rice, including amylose, gel consistency, protein, chalkiness and the comprehensive characterization parameter (M). September is the period from grain filling (the grain filling stage of rice refers to the period from the end of flowering to the beginning of glume closure to grain maturity) to mature harvest of Xiaozhan rice in Tianjin. That is to say, the temperature in this period has a very significant effect on the final nutritional quality of Xiaozhan rice. The correlation between the 14 factors and M is high, and all 29 pass the Pearson correlation significance test of p &lt; 0.01. The absolute value of lowest correlation coefficient is sunshine hours in May, |R| = 0.839; and the absolute value of highest correlation coefficient was the highest temperature in June, R = 0.982. Among the 14 factors, 9 factors are related to temperature (including the day difference in June), and all of them positively correlated with climate evaluation index M of nutritional quality, 3 factors are related to sunshine hours, and 2 factors are related to precipitation, indicating that the temperature condition in the whole growth period of Xiaozhan rice is the most important climate factor to determine its nutrition quality formation. The root mean square error of the simulation results of the climate evaluation model for the nutritional quality of Xiaozhan rice is 0.0236, which indicates that the model can be used for the climate impact evaluation of the nutritional quality of Xiaozhan rice in Tianjin, so as to determine the nutritional quality grade of Xiaozhan rice and provide scientific reference for reasonably predicting the market price of Xiaozhan rice.

Primary Volatile Aroma Compounds in Phka Rumduol, Cambodia

Phka Rumduol is a leading variety in Cambodian rice. Analysis and qualification of volatile aroma compounds of Cambodian rice were not reported yet, limiting a few papers about only 2-acetyl-1-pyrroline (2-AP). Although Cambodia has been very impressive and progressed for milling rice exports over the last 10 years, rice qualities in her value chain are still remained much more improvement, especially in domestic market. In this paper, volatile aroma compounds in Phka Rumduol (brown rice), cultivated by Cambodian Agricultural Research and Development Institute (CARDI) was analyzed by gas chromatograph mass spectrum (GCMS) and aroma extract dilution analysis (AEDA). As the results, 2-AP and other 21 aroma compounds were detected. Its flavor dilution (FD) factor of 2-AP was extremely high at 10,000. Since 2-AP was dominant aroma in Phka Rumduol, the analytical measure of 2-AP by solid phase micro extraction (SPME) and gas chromatograph (GC) in rice kernels were investigated. With the purpose to compare qualities between Phka Rumduol (CARDI) and Phka Rumduol purchased in a Cambodian market (commercial), 2-AP concentration of both samples, the changes of 2-AP by different milling degrees, using both samples and 2-AP concentration in red kernels in commercial were analyzed. The results showed that 2-AP of Phka Rumduol (CARDI) and Phka Rumduol (commercial) were 800 and 380 ppb respectively, that after 0, 1, 2, 3 and 4 minutes-milling, the 2-AP in CARDI ranged in 800 to 420 ppb, while commercial did in 380 to 250 ppb and that 2-AP of whole red kernels in commercial was 50 ppb. From the results changes of milling time, 2-AP was located more in out-layer than inside of rice kernel. Phka Rumduol (CARDI) was very good qualities, while Phka Rumduol (commercial) showed less 2-AP concentration with larger percentages of broken, red kernels and lower qualified kernels like immature, chalky, damaged ones etc. Aroma which is one of important factors for Cambodian consumers will be decreased by rice type and grade of processing in market. This paper also referred a little to decrease in qualities by excess milling and/or polishing.

Lean management in the rice industry; case study at Widasari, Indramayu district

Rice is a strategic product in Indonesia development because it becomes an essential aspect of economic growth. The inefficiency of food agribusiness system becomes a crucial aspect of developing the sustainable industry. Those affected by the lack of using technology that impacts the high amount of waste and losses, the inefficiency of time, etc. It could impact the competitiveness, equity of value-added, unstable price and poverty. Some amount of rice grade materials rejected from the production line due to the unsatisfactory quality. This article aimed to analyze efficiency in the food industry as a preparation in the development of agricultural digital supply chain. The analysis shows that inefficiency in the rice industry due to a lot of manual activities that impact the time and expense efficiency (labor intensive rather than the use of technologies). Improving efficiency in the food industry is not only about time and cost management, but it becomes complex issues which are involved in several barrier factors. It should be anticipated with appropriate technology, improving skills, and also develop an integrated logistics system. Importantly, improving efficiency in rice industry needs to develop soft skill as the key success factors to improve efficiency in the digital supply chain for the rice industry.

Overall evaluation of resistance capability of different rice varieties to Sogatella furcifera (Hemiptera: Delphacidae) using radar charts

Plant resistance is a key component of management programs for the planthoppers in rice. Focusing on white-backed planthopper (WBPH, Sogatella furcifera) and a set of resistant and moderately resistant rice varieties (with rice TN1 as the susceptible standard), we measured several indices for each of three crucial components of resistance (tolerance, antixenosis and antibiosis). We evaluated the genotypes in pot experiments in 2016, and investigations into oviposition and population of planthoppers were included. We integrated these various indices and the results of pot experiments into an overall index of resistance using radar charts. In order to verify the previous results, field surveys of the population of planthoppers were performed in 2017. We found that leaf yellowing days were significantly related to resistance grades of rice. TN1 attracted more WBPH than the resistant rice. The survival rate of WBPH that fed on resistant rice was much lower than TN1. Field trials confirmed the validity of the result of pot experiments. The radar chart provided a nice visualization of the resistance characteristics, making easier to see the overall resistance capability of each genotype. It is the first time that this approach is applied to evaluate rice resistance to WBPH. This study provides a method of performing an overall evaluation of rice which may help screen and evaluate kinds of rice varieties in the control of insect pests such as WBPH.

Post-harvest kernel discoloration and fungi activity in long-grain hybrid, pureline and medium-grain rice cultivars as influenced by storage environment and antifungal treatment

Milled rice grade is diminished as the quantity of discolored kernels increases. This study evaluated the magnitude of kernel discoloration and relationship to fungal growth for long-grain hybrid (XL 753), long-grain pureline (Roy J.) and medium-grain (Titan) rice, exposed to storage moisture contents (MCs) of 16 and 21%, wet basis, temperatures of 20, 30, 40 °C, and durations up to 16 weeks. Impact of postharvest treatments with the antifungal agents, natamycin and sodium chloride, on rice discoloration and fungal growth was compared with untreated (control) samples. Subsamples were taken every four weeks to determine total fungal counts, discoloration, and water activity. Rice stored at 40 °C had six-to eleven-times more discoloration than at 20 °C. Increased storage duration significantly increased discoloration. Discoloration was not different between MC levels. Discoloration was significantly lower by sodium chloride treatment, while natamycin was not effective compared to control. Rice samples treated with sodium chloride also had significantly less water activity (mean aw = 0.73) compared to samples treated with natamycin (mean = 0.84) and control samples (mean = 0.83). Hybrid rice had significantly less discoloration compared to pureline and medium-grain. Fungal counts were similar across all cultivars. Increasing temperature and duration decreased fungal count. An inverse relation between fungi and discoloration suggests microbe activities did not explain discoloration. The findings provide important information to growers and processors on conditions necessary to maintain rice quality.

Adaptive Neuro-Fuzzy Inference System Based Grading of Basmati Rice Grains Using Image Processing Technique

Grading of rice intents to discriminate broken and whole grain from a sample. Standard techniques for image-based rice grading using advanced statistical methods seldom take into account the domain knowledge associated with the data. In the context of a high product value basmati rice with an image based grading process, one ought to consider the physical properties of grain and the associated knowledge. In this present work, a model of quality grade testing and identification is proposed using a novel digital image processing and knowledge-based adaptive neuro-fuzzy inference system (ANFIS). The rationale behind adopting a grading system based on fuzzy rules relies on capabilities of ANFIS to simulate the behaviour of an expert in the characterization of rice grain using the physical properties of rice grains. The rice kernels are characterized with the help of morphological descriptors and geometric features which are derived from sample images of milled basmati rice. The predictive capability of the proposed technique has been tested on a sufficient number of training and test images of basmati rice grain. The proposed method outperforms with a promising result in an evaluation of rice quality with &gt;98.5% classification accuracy for broken and whole grain as compared to standard machine learning technique viz. support vector machine (SVM) and K-nearest neighbour (KNN). The milling efficiency is also assessed using the ratio between head rice and broken rice percentage and it is 77.27% for the test sample. The overall results of the adopted methodology are promising in terms of classification accuracy and efficiency.