Bag Technique Research Articles

The Impact of Laminations on the Mechanical Strength of Carbon-Fiber Composites for Prosthetic Foot Fabrication

Carbon-fiber composites are considered to be one of the suitable materials for the fabrication of prosthetic feet. However, commercially available composites-based prosthetic foot designs present several problems for lower limb amputees, such as low tensile strength, reduced impact resistance, high cost, and weight structure. Modulating the mechanical properties of carbon-fiber composites using a simplified method can help reduce these issues. Therefore, our present research aims to identify the impact of increasing the concentration of carbon fiber in the fabrication of carbon-fiber composites by using the hand layup method without the vacuum bagging technique. To improve the mechanical strength of carbon-fiber laminates, an increasing number of carbon-fiber layers are used in sample preparation. This study aims to determine the tensile strength of the laminates with a different number of carbon-fiber laminations. For the preparation of the sample specimen, black 100% 3 K 200 gsm carbon fiber with a cloth thickness of 0.2 mm and tensile strength of 4380 Mpa was laminated with two parts of epoxy resin Araldite® LY556 and Aradur hardener at a ratio of 100:30 to make the test specimen. The results indicated an overall improvement in the tensile strength of carbon-fiber laminates owing to the increase in the number of carbon-fiber layers in successive samples. The maximum achieved tensile strength through the present experimental protocol is 576.079 N/mm2, depicted by a prepared specimen of 10 layers of carbon fiber. Secondly, an increase in the deformation rate has also been observed by increasing the loading rate from 2 mm/min to 5 mm/min during the tensile testing of fabricated samples. These sample carbon-fiber composites can be used in the fabrication of prosthetic feet by controlling the experimental conditions. The fabricated prosthetic foot will assist in rehabilitating lower-limb amputees.

An Automation System Equivalent to the Douglas Bag Technique Enables Continuous and Repeat Metabolic Measurements in Patients Undergoing Mechanical Ventilation

PurposeTo develop a system that is equivalent to the gold standard Douglas Bag (DB) technique for measuring oxygen consumption (V̇o2), carbon dioxide generation (V̇co2), and respiratory quotient (RQ) and to validate its use in clinical settings. MethodsThis was a prospective, observational study conducted at a suburban, quaternary care teaching hospital. Healthy volunteers and patients 18 years or older who received mechanical ventilation were enrolled. FindingsData from 3 healthy volunteers and 7 patients were analyzed in this study. The interrater reliability between the automation device and DB methods were 0.999, 0.993, and 0.993 for V̇o2, V̇co2, and RQ, respectively. In healthy volunteers, mean (SD) V̇o2, V̇co2, and RQ measured by DB were 411 (100) mL/min, 288 (79) mL/min, and 0.70 (0.03) at high fraction of inspired oxygen (Fio2) and 323 (46) mL/min, 280 (45) mL/min, and 0.85 (0.05) at normal Fio2, respectively. V̇o2 was significantly higher (P < 0.05) and RQ was lower (P < 0.01) in the high Fio2 group as compared to those in the normal Fio2 group. Values measured by the automation system were 227 (31) mL/min, 141 (18) mL/min, and 0.62 (0.04) at high Fio2 and 209 (25) mL/min, 147 (18) mL/min, and 0.70 (0.06) at normal Fio2, respectively. RQ was significantly lower (P < 0.05) in the high Fio2 group as compared to the normal Fio2 group. We also successfully performed continuous and repeat measurements by using the device. The longest measurement reached 12 hours 15 minutes, including 50 cycles of repeat measurements that are equivalent to the DB technique as described above. ImplicationsWe developed an automation system that enables repeat measurements of V̇o2, V̇co2, and RQ, and the accuracy was equivalent to the DB technique. High Fio2 may decrease RQ because of an increase in V̇o2.

Comparison of a three-step in vitro method and the mobile nylon bag technique for determining the intestinal digestibility of rumen-protected products in dairy cows

The objectives of this study were to develop a three-step in vitro method to assess intestinal digestibility of rumen-protected products in dairy cows, and compare this method with the mobile nylon bag technique. A 3 × 4 × 3 factorial experiment was performed to determine an optimal combination of pancreatin (0.8, 1.0, and 1.2 g/30 mL), sodium cholate (0, 1.0, 2.0, and 3.0 g/30 mL), and incubation length (8, 16, 24 h) for maximizing lipid digestion of a hydrogenated fat product. Following the preliminary study, a 23 factorial experiment was conducted to investigate the effects of ruminal incubation (with or without 16 h rumen in situ incubation), gastric pH (pH = 1.0 or 2.0), and gastric acid incubation time (1 or 2 h) on digestion of the hydrogenated fat and a calcium salts of long chain fatty acids product. Once optimal culture parameters were determined, the developed in vitro method was compared with the mobile nylon bag technique. The pancreatin × sodium cholate and sodium cholate × incubation time interactions were significant in the intestinal digestibility of the hydrogenated fat product (P < 0.001), and the best case scenario was observed when the hydrogenated fat was incubated in 30 mL buffer solution containing 1.0 g pancreatin and 2.0 g sodium cholate for 24 h. A ruminal incubation × pH × incubation time interaction was detected for the intestinal digestibility of the hydrogenated fat (P = 0.002), and a ruminal incubation × pH interaction was observed for the calcium salts of fatty acids (P = 0.04). The digestion of hydrogenated fat was maximized when it was incubated in gastric pH 1.0 solution for 2 h following 16 h ruminal incubation. However, ruminal incubation had no effect on the intestinal digestibility of the calcium soap when incubated in gastric pH 1 solution (P < 0.05). The developed in vitro method had greater DM intestinal digestibility than the mobile nylon method (on average 0.78 versus 0.33), implying the mobile nylon bag method might have underestimated the DM intestinal digestibility of rumen-protected products. However, no significant difference was observed on intestinal digestibility of Met, Lys and choline in the rumen fat-protected products. Overall, the developed method could be used as an alternative approach for screening and evaluating intestinal digestibility of rumen-protected products.

Nutrient return through decomposing Coriaria nepalensis litter in degraded hills of Kumaun Himalaya, India

Coriaria nepalensis, a nitrogen-fixing actinorhizal shrub, is a prominent and successful colonizer of bare rocks and landslide affected degraded lands. Field experiments were conducted to determine the differences in biomass decomposition and nutrient release pattern of different plant parts ofC. nepalensisusing litter bag technique. Results showed that the leaves decomposed completely within 6 months while only 46.55% of the lateral roots were decomposed with slowest decomposition rate of 0.14% day–1. The decomposition rate was in the order: Leaves &amp;gt; Reproductive parts &amp;gt; Twigs (&amp;lt; 5 mm) &amp;gt; Twigs (&amp;gt; 5 mm) &amp;gt; Bark &amp;gt; Fine roots &amp;gt; Lateral roots. The decay rate coefficient was highest (0.003–0.014) for leaves and lowest (0.001–0.002) for lateral roots. During the decomposition cycle (364 days), overall increase was reported in nitrogen and phosphorus concentration, while potassium concentration decreased continuously in residual litters. The nutrient mobility was in the order: K &amp;gt; P &amp;gt; N. Climatic factors like temperature, relative humidity and rainfall significantly affected the decomposition process and among these factors, rainfall pattern emerged as a most effective environmental driver. Thus, taking into account initial nutrient content, nutrient release and decay rates, the leaves and reproductive parts ofC. nepalensisproved to be more important as nutrient source than other components.

Electrospinning Pullulan to Nanoencapsulate Milk Derived Peptides

Background: Milk proteins are a source of bioactive peptides, which are concealed until released and activated. There is a growing interest and necessity for the use of biologically active milk protein-derived peptides with health-promoting properties in food. Despite several health benefits and functionalities, consumption of bioactive peptides through foods is poor due to their unfavorable flavour or bitter taste, low solubility, poor stability during processing and poor oral bioavailability. Electrospinning is an adaptable process for encapsulation since it does not involve severe temperature and requirement of chemicals for the preparation of encapsulate in the form of nanofibres. Methods: The peptide-loaded electrospun nanofibres are characterized for its surface morphology, encapsulation efficiency, zeta potential and interaction between wall material and peptides. In vitro release studies by dialysis bag technique and antioxidant property by DPPH method. Result: Pullulan at 10, 12 and 14% (w/w) concentrations was used for electrospinning of peptides. Scanning electron micrograph revealed the formation of clean beadfree peptides-loaded pullulan nanofibres at 12 and 14% concentrations. Encapsulation efficiency ranged from 73.00-86.00%. FTIR spectrum and XRD diffractograms showed the nonappearance of interactions between the functional groups of biopolymer pullulan and peptides in the electrospun nanofibres. The peptides from electrospun nanofibres showed sustained release. The antioxidant activity of peptides and those which are in the nanofibres was comparable. The physico-chemical and sensory analysis of milk fortified with peptide loaded nanofibres did not show noticeable difference.

Self-Nanoemulsifying Drug Delivery System of 2-Methoxyestradiol Exhibits Enhanced Anti-Proliferative and Pro-Apoptotic Activities in MCF-7 Breast Cancer Cells.

(1) Background: 2-Methoxyestradiol (2ME) is a metabolite of estrogens and possesses promising anti-proliferative and cytotoxic activities. However, it suffers unfavorable pharmacokinetic characteristics such as absorption after oral administration. The aim of this study was to prepare an optimized 2ME self-nanoemulsifying drug delivery system (2ME-SNEDDS) and evaluate its cytotoxicity and pro-apoptotic activities in MCF-7 breast cancer cells. (2) Methods: For optimization of the 2ME-SNEDDS, a three-component system was used in the D-optimal mixture experimental study. MCF-7 cells were incubated with the 2ME-SNEDDS and subjected to an assessment of growth inhibition, cell cycle progression, annexin V staining, caspase-3 concentration, Bax, Bcl-2, and cyclin D1 mRNA expression, and reactive oxygen species (ROS) generation. (3) Results: The optimized formula had a globule size of 94.97 ± 4.35 nm. Zeta potential was found to be −3.4 ± 1.2 mV with a polydispersity index (PDI) of 0.34. In addition, 96.3 ± 4.3% of 2ME was released from the 2ME-SNEDDS within 24 h using the activated analysis bag technique. Moreover, the prepared 2ME-SNEDDS exhibited a significant enhancement of the anti-proliferative activity against MCF-7 cells in comparison to raw 2ME. This was associated with cyclin D1 expression down-regulation and the accumulation of cells in the G0/G1 and G2/M phases. The pro-apoptotic activities of the 2ME-SNEDDS were confirmed by annexin V staining, which indicated enhanced early and late cell death. This accompanied modulation of the mRNA expression of Bax and Bcl-2 in favor of apoptosis. The 2ME-SNEDDS significantly enhanced cleaved caspase-3 concentration in comparison to raw 2ME. In addition, the 2ME-SNEDDS significantly increased the generation of ROS in MCF-7 cells. (4) Conclusions: The 2ME-SNEDDS exhibits enhanced cytotoxicity and pro-apoptotic activity in MCF-7 cells. This is mediated by, at least partially, ROS generation.

Evaluation of Gas Production, Fermentation Parameters, and Nutrient Degradability in Different Proportions of Sorghum Straw and Ammoniated Wheat Straw

The purpose of this study was to investigate the optimum proportion of sorghum straw and ammoniated wheat straw in vitro and in vivo to apply in ruminant diets. One-factor and two-factor experimental designs were used in the in vitro tests, with different ratios of sorghum straw to ammoniated wheat straw (S:AWS) of 2:8, 3:7, 4:6, 5:5, 6:4, 7:3, and 8:2 to measure the in vitro total gas production, CH4 production, in vitro dry matter degradability (IVDMD), in vitro organic matter degradability (IVOMD) and in vitro fermentation parameters. Additionally, the nylon bag technique was used to determine the dynamic degradation of these different ratios of mixed feedstuffs for incubating in sheep rumen for 6 h, 12 h, 24 h, and 48 h. The results show that IVDMD, IVOMD, and the molar ratio of propionate were the highest when the ratio of S:AWS was 8:2 (p &lt; 0.05) in vitro; however, this ratio released much more CH4 (p &lt; 0.05). In addition, the degradability of DM, OM, CP, and ash and the effective degradability of DM and CP were the highest when the ratio of S:AWS was 8:2 cultured in sheep rumen for 48 h (p &lt; 0.05). In the in vitro and in situ nylon bag tests, IVDMD, IVOMD, rumen nutrient degradability, and effective degradability of DM and CP increased with the increase in the sorghum straw proportion. In conclusion, the higher the proportion of sorghum straw, the higher the nutrient degradability in vivo and in vitro, but also the higher the emissions of CH4. Therefore, when the ratio of S:AWS is 8:2, ruminants can effectively utilize nutrients in feed.

Optimal Nonparametric Inference with Two-Scale Distributional Nearest Neighbors

ABSTRACT The weighted nearest neighbors (WNN) estimator has been popularly used as a flexible and easy-to-implement nonparametric tool for mean regression estimation. The bagging technique is an elegant way to form WNN estimators with weights automatically generated to the nearest neighbors (Steele 2009; Biau, Cérou, and Guyader 2010); we name the resulting estimator as the distributional nearest neighbors (DNN) for easy reference. Yet, there is a lack of distributional results for such estimator, limiting its application to statistical inference. Moreover, when the mean regression function has higher-order smoothness, DNN does not achieve the optimal nonparametric convergence rate, mainly because of the bias issue. In this work, we provide an in-depth technical analysis of the DNN, based on which we suggest a bias reduction approach for the DNN estimator by linearly combining two DNN estimators with different subsampling scales, resulting in the novel two-scale DNN (TDNN) estimator. The two-scale DNN estimator has an equivalent representation of WNN with weights admitting explicit forms and some being negative. We prove that, thanks to the use of negative weights, the two-scale DNN estimator enjoys the optimal nonparametric rate of convergence in estimating the regression function under the fourth-order smoothness condition. We further go beyond estimation and establish that the DNN and two-scale DNN are both asymptotically normal as the subsampling scales and sample size diverge to infinity. For the practical implementation, we also provide variance estimators and a distribution estimator using the jackknife and bootstrap techniques for the two-scale DNN. These estimators can be exploited for constructing valid confidence intervals for nonparametric inference of the regression function. The theoretical results and appealing finite-sample performance of the suggested two-scale DNN method are illustrated with several simulation examples and a real data application.

An integrated approach of artificial neural networks and polynomial chaos expansion for prediction and analysis of yield and environmental impact of oil shale retorting process under uncertainty

Shale oil reserves exploration is getting huge investments due to the depletion of conventional reserves. Computational methods have been used to realize optimum design and operation of shale oil and gas reserves exploration and processing. The uncertainty associated with the composition of shale reserves and operating conditions during processing put a challenge to the realization of high yield and mitigation of environmental impact. In the current work, machine learning (ML) based models are proposed for the estimation of the yield and environmental impact of the oil shale retorting process under uncertainty. An artificial uncertainty of 1% was inserted in feed composition and process conditions of an Aspen model of the process to generate data for the development of the ML models. Artificial Neural Network (ANN), Least Square Boosting (LSB), and Bagging techniques were compared to find the best ML model. ANN models, with the highest correlation coefficient of 0.995 and 0.999 for the oil yield and CO2 content respectively, are used as surrogates in a Polynomial Chaos Expansion (PCE) framework for the uncertainty analysis of the process. For 1% uncertainty in feed composition and process conditions, a mean absolute deviation of 0.319 and 0.580 was obtained for the oil yield and carbon dioxide emissions respectively. To find the hierarchy in the process inputs in terms of their effect on the oil yield and carbon dioxide emissions, the ANN model is used as a surrogate in sensitivity analysis through Sobol and Fourier Amplitude Sensitivity Test (FAST) indices. The most sensitive input variables were feed temperature and air molar flow rate. The proposed modeling framework will provide a base for future real-time monitoring and analysis of the oil shale retorting processes.

Modeling the organic matter of water using the decision tree coupled with bootstrap aggregated and least-squares boosting

The purpose of the work is to investigate the use of decision tree (DT) enhanced by bootstrap aggregates (Bag) and least-squares boosting (Lsboost) in modeling the organic matter of water according to its physicochemical parameters. An entire database of 500 samples of 21 physicochemical parameters, including organic matter, was used to build the DT, DT_Bag, and DT_Lsboost models. Training data (364 data points) is resampled using a bootstrap technique to form different training datasets to train different models. The models built were validated by a dataset of 91 samples. The predicted outputs obtained from the developed DT models are then combined by simple averaging. On the other hand, the data was also boosted with the Lsboost technical aid to increase the strength of a weak learning algorithm. The model trains the first weak learner with equal weight across all data points in the training set, then trains all other weak learners based on the updated weight aimed at the validation result to minimize the squared error medium. Good agreement between the predicted and experimental organic matter concentrations for the DT_Lsboost model was obtained (the correlation coefficient for the validation dataset was 0.9992), followed by the DT-Bag model with a correlation coefficient of 0.9949. The comparison between DT, DT_Bag, and DT_Lsboost revealed the superiority of the DT_Lsboost model (the mean root of the squared errors for the dataset were 0.1295 for the DT_Lsboost, 0.1664 for the DT_Bag, and 0.5444 for the DT). These results show that Lsboost technology dramatically improved the DT model. This result is also confirmed by the results of tests on models (interpolation data of 45 points). It should also be noted that the Bag technique was also very effective in optimizing the DT model, as the results obtained with this technique were very close to the DT_Lsboost model. • The concentration of organic matter in the water was predicted using various models. • The decision tree (DT) model was coupled by bootstrap aggregates (Bag) and least-squares boosting (Lsboost) techniques. • Significant Physico-chemical parameters on the organic matter were identified using the decision tree (DT) and the ensemble trees model (DT_Bag and DT_Lsboost). • The decision of tree (DT) and the ensemble trees model made it possible to highlight the significant interactions. • Bootstrap aggregates (Bag) and least-squares boosting (Lsboost) techniques have improved and developed the decision tree model.

Distributed Denial of Service Attack Detection and Prevention Model for IoT based Computing Environment using Ensemble Machine Learning Approach

Defending against Distributed Denial of Service (DDoS) in the Internet of Things (IoT) computing environment is a challenging task. DDoS attacks are type of collective attack in which attackers work together to compromise internet security and services. The resource-constrained devices used in IoT deployments have made it even easier for an attacker to break, because of the vast number of vulnerable IoT devices with significant compute power. This paper proposed an ensemble machine learning (ML) model using the bagging technique to detect and prevent DDoS attacks in the IoT computing environment. We carried out an Machine Learning experiment and evaluated our proposed model with the most recent DDoS attacks (CICDoS2019) dataset. We use seven validation metrics (classification accuracy, precision rate, recall rate, f1-score, Matthews Correlation Coefficient, false negative rate and false positive rate) to evaluate the performance of the proposed model. The results obtained in our experiment shows an improved performance with an overall maximum classification accuracy of 99.75%, precision rate of 99.99%, recall rate of 99.76%, f1-score of 99.87%, Matthews Correlation Coefficient of 0.000000214, false negative rate of 0.24% and 4.42% false positive rate.

In Vitro Measurements of True Digestibility and Products of Digestion Using Multiple Cultivars of Non-Extracted and CBD-Extracted Industrial Hemp Biomass (Cannabis sativa)

Since 2018, the growth of industrial hemp (Cannabis sativa) for extraction of cannabidiol (CBD) oil has increased in popularity. By-products resulting from the extraction of the oil have become more available but remain largely unutilized due to their novelty and current restrictions on animal feeding. One potential use for the leftover inflorescence may be as a feedstuff, but reports examining its nutrient quality are limited. Therefore, experiments were conducted to evaluate 9 cultivars of non-extracted and 9 separate cultivars of CBD-extracted foliage. Ground alfalfa cubes were included in experiments as a control. All samples were analyzed for ash, ether extract, crude protein, lignin, ash-free neutral detergent fiber, acid detergent insoluble crude protein, and neutral detergent insoluble crude protein. Total digestible nutrients (TDN) were calculated using summative equations. In vitro true digestibility (IVTD) was determined using a filter bag technique and 48-h digestion period. Cumulative gas production was measured in batch culture over a 48-h period, with methane and ammonia production, volatile fatty acid (VFA) formation, and dry matter disappearance (DMD) measured following this period. Substrates for gas production measurements were composed of the hemp sample, rye silage, and ground corn mixed at a 30:35:35 ratio. Grind size (0.5 vs. 2.0 mm) was evaluated using non-extracted hemp and did not influence IVTD. Nutrient composition ranges of non- and CBD-extracted samples were similar, except for a numerically higher mean ether extract (17.66% vs. 9.29%) and TDN (73.01% vs. 54.03%) in non-extracted hemp. None of the measured nutrients for alfalfa cubes fell within the observed concentration ranges of either hemp group, but TDN was numerically similar to that of CBD-extracted hemp. IVTD was numerically similar between both hemp groups and alfalfa cubes. In comparison to alfalfa cubes, VFA (both concentration and molar proportions), ammonia concentrations, pH, DMD, methane, and total gas production were numerically similar with concurrently run non- and CBD-extracted hemp groups. The results of this study serve as a foundation from which a larger database of nutrient component values for hemp may be compiled. Such databases are necessary to fully evaluate the feasibility of a feedstuff for inclusion in animal diets.

The study of cross-validated bagging fuzzy-ID3 algorithm for breast cancer classification

Globally, the second most common cause of death for female cancer patients is breast cancer. In the United States, about 11,000 females aged below 40 are diagnosed with invasive breast cancer each year. Early detection of breast cancer is the foundation for preventing the progression of the disease, and the diagnosis can be conducted using intelligent systems for quicker detection. Based on the FUZZYDBD method and bootstrap aggregation (bagging) technique, the Bagging fuzzy-ID3 algorithm (BFID3) was proposed for this study. This method combined the techniques of the fuzzy system, ID3 algorithm and bagging. For BFID3’s data fuzzification, the automatic fuzzy database definition method, known as the FUZZYDBD method, would assist in developing the fuzzy database. One of the weaknesses of the ID3 algorithm is its incapability to handle continuous data. The problem was resolved via the linguistic variable replacement and data fuzzification in the BFID3. Meanwhile, this paper’s implementation of the bagging technique improved the generalization ability and reduced overfitting. Additionally, BFID3 was verified through an extensive comparison with several existing methods to investigate the competency of the proposed method. The study identified that BFID3 was proficient in breast cancer classification.

Incorporation of topotecan into sesame oil - Nanoemulsion potentiates its cytotoxic effect in cancer cells

PurposeTo incorporate the topoisomerase I inhibitor, topotecan (TOPO), into oil-in-water nanoemulsion delivery system based on sesame oil (SO-NE), with the aim to enhance its anti-proliferative effect on MCF-7 breast, HCT116 colon, HeLa cervical, and HepG2 liver cancer cells. MethodsSO-NE was formulated by mixing different volume fractions of SO (3%), Tween 80 (10%), Span 20 (5%), and water (82%) using the high-pressure ultrasonication technique. SO-NE and TOPO-loaded SO-NE (TOPO–SO–NE) were physically characterized by zeta sizer and transmission electron microscope. The in vitro drug release of TOPO–SO–NE relative to the free TOPO solution was assessed by the dialysis bag technique. The cytotoxicity of the TOPO–SO–NE formula was determined in vitro using crystal violet assay. DAPI fluorescent stains were used for cellular morphology and death assessments. Additionally, TOPO cellular uptake and inflammatory effect after TOPO loading into SO-NE formula were determined. ResultsSO-NE formula was found to have negatively charged nanosized particles even after TOPO loading (Z-diameter = 73.66 ± 5.5 nm, Zetapotential = −7.63 ± 0.24 mV). In addition, TOPO–SO–NE formulation exhibited a beneficial TOPO prolonged and sustained release over 24 h. In all tested cell lines, TOPO–SO–NE formula exhibited considerable anti-proliferation effect with decreased IC50 and caused distinct apoptotic changes in cancer cells, which was evidenced by the enhanced cellular uptake of TOPO. The concentrations of interlukin-6 (IL-6), an inflammatory marker, in MCF-7, HCT116 and HepG2 cells were suppressed by TOPO–SO–NE treatment, but they got reversed in HeLa cells. ConclusionIncorporation of TOPO into SO-NE has remarkably improved its cytotoxicity in MCF-7, HCT116, HeLa and HepG2 cancer cells. The mechanisms of cell death were through the induction of apoptosis, enhancement of TOPO cellular accumulation ratios and affecting the inflammatory agent, interlukin-6 (IL-6), concentrations.

Nutritive value assessment of orange pulp ensiled with urea using gas production and nylon bag techniques

Nutritive value assessment of orange pulp ensiled with urea using gas production and nylon bag techniques

Intrascleral fixation of capsular bag and intraocular lens in cases with large zonular dialysis.

To evaluate the clinical outcomes of sutureless capsular bag and intraocular lens (IOL) fixation with flattened, flanged intrascleral fixation technique in patients with large zonular dialysis. Fifty-five eyes of 51 patients who underwent flattened flanged intrascleral capsular bag and IOL fixation and optic capture for traumatic cataract, subluxated cataract, and pseudoexfoliation syndrome (PEX) with zonular dialysis greater than 180° were included in the study. The main difference of this technique from the Yamane technique is that it has a flattened flange with sharp borders at the haptic tip. Uncorrected visual acuity, corrected distance visual acuity (CDVA), astigmatism, endothelial cell loss, IOL tilt, and intraoperative and postoperative complications were evaluated. The mean age of the patients was 57.4 ± 15.1years (range 18-83). Of the patients, 28 (55%) were male and 23 (45%) were female. The mean duration of follow-up after surgery was 19.3 ± 6.5months (range 12-36). The mean preoperative and postoperative CDVA were 0.71 ± 0.16 logMAR and 0.13 ± 0.20 logMAR, respectively (p < 0.001). The mean preoperative and postoperative astigmatism were 2.0 ± 1.4 D and 1.0 ± 0.7 D, respectively (p < 0.001). The mean IOL tilt was 5.7° ± 5.2°. The mean endothelial cell loss was 9% (range 0.9-19.5). Anterior capsular phimosis was developed in 2 eyes (4%). The flattened flanged intrascleral technique of the capsular bag combined with optic capture provides good visual outcomes, robust capsular bag-IOL fixation, and minimal adverse events. However, further studies with more patients are needed for long-term results.

Sule Lamido University Journal of Science and Technology (SLUJST) Vol. 3 No. 1&amp;2 [June, 2022], pp. 113-121113Obesity Level ClassificationBased on Decision Tree and Naïve Bayes Classifiers

This paper proposed an approach for obesity levels classification. The main contribution of this work is the use of boosting and bagging techniques in the decision tree (DT) and naïve Bayes (NB) classification model to improve the accuracy of obesity levels classification. This is achieved by introducing a boosting and bagging technique to further improve the recognition rate of obesity levels in the DT model, eliminating the correlated features, and eliminating the zero observations problem in the NB model. To validate the accuracy of the proposed approach, empirical evaluation was carried out using WEKA to determine the accuracy, precision, and recall. The results show that the DT classification model performs better in terms of accuracy and average precision. The proposed approach can help in software development for the classification of individuals with obesity

Using Machine Learning Algorithms to Estimate the Compressive Property of High Strength Fiber Reinforced Concrete.

The low tensile strain capacity and brittle nature of high-strength concrete (HSC) can be improved by incorporating steel fibers into it. Steel fibers’ addition in HSC results in bridging behavior which improves its post-cracking behavior, provides cracks arresting and stresses transfer in concrete. Using machine learning (ML) techniques, concrete properties prediction is an effective solution to conserve construction time and cost. Therefore, sophisticated ML approaches are applied in this study to predict the compressive strength of steel fiber reinforced HSC (SFRHSC). To fulfil this purpose, a standalone ML model called Multiple-Layer Perceptron Neural Network (MLPNN) and ensembled ML algorithms named Bagging and Adaptive Boosting (AdaBoost) were employed in this study. The considered parameters were cement content, fly ash content, slag content, silica fume content, nano-silica content, limestone powder content, sand content, coarse aggregate content, maximum aggregate size, water content, super-plasticizer content, steel fiber content, steel fiber diameter, steel fiber length, and curing time. The application of statistical checks, i.e., root mean square error (RMSE), determination coefficient (R2), and mean absolute error (MAE), was also performed for the assessment of algorithms’ performance. The study demonstrated the suitability of the Bagging technique in the prediction of SFRHSC compressive strength. Compared to other models, the Bagging approach was more accurate as it produced higher, i.e., 0.94, R2, and lower error values. It was revealed from the SHAP analysis that curing time and super-plasticizer content have the most significant influence on the compressive strength of SFRHSC. The outcomes of this study will be beneficial for researchers in civil engineering for the timely and effective evaluation of SFRHSC compressive strength.

AN APPROACH TOWARD PREDICTION OF SM-CO ALLOY’S MAXIMUM ENERGY PRODUCT USING FEATURE BAGGING TECHNIQUE

The work aims to solve the problem of predicting magnetic properties on the example of Sm-Co alloy using artificial intelligence. In particular, the authors solved the Sm-Co alloys maximum energy product prediction task using the feature bagging technique. To implement this approach, we have chosen the Random Forest algorithm, which efficiently processes short data sets by reducing variance and, as a result, reducing the impact/avoidance of overfitting. Experimental modelling was based on a short set of data (190 observations) collected by the authors with many independent attributes. As a result, it has been experimentally established that the studied machine learning method provides a high value of the coefficient of determination - 0.78 when solving Sm-Co alloy’s maximum energy product prediction task. Furthermore, by comparing with other ensemble methods from different classes, the highest accuracy of the researched process is established based on various performance indicators.

Reduced neural network based ensemble approach for fault detection and diagnosis of wind energy converter systems

Wind energy (WE) is one of the most important technology to produce energy and an efficient source of renewable energy (RE) available in the atmospheric environment due to different air-currents spread over the stratosphere and troposphere. Wind energy conversion (WEC) system has become a focal point in the research of RE in recent years. Moreover, fault detection and diagnosis (FDD) plays an important role in ensuring WEC safety. In the past decades, neural networks (NN) has provided an effective performance in fault diagnosis. On the other hand, ensemble learning (EL) techniques have gained significant attention from the scientific community. EL is a technique that creates and combines multiple machine learning models in order to produce one optimal predictive model which gives improved results. The goal of this paper is to develop and validate effective neural networks based ensemble approach. First, an ensemble classifier based on neural networks techniques and using bagging, boosting, and random subspace combination techniques is proposed. Second, an improved extension of the proposed neural networks-based ensemble technique is presented. Finally, the results obtained from the proposed neural networks-based ensemble techniques are compared with other methods to illustrate and validate the advantages of the proposed techniques.