Layer Feed Research Articles

Fault Classification Accuracy Measurement for a Distribution System with Artificial Neural Network without using Signal Processing Technique

Faults occurring on electrical distribution network are unpredictable and needs to be cleared at the earliest so as to reduce power outage time. Hence fault detection and their classification plays important role. In this research paper the fault classification accuracy was measured for an electrical power distribution network with artificial neural network without using any signal processing method. Although many digital signal processing methods are developed to enhance electrical fault classification accuracy, it is essential to measure it for comparison when no signal processing method is used. Fault classification was considered as a pattern recognition application of neural networks. Two layer feed forward back propagation neural network was used as classifier. IEEE 13 bus distribution feeder was simulated in MATLAB with Simulink for collecting the input data. The simulation results show that the faults can be classified satisfactorily. L-G, L-L and L-L-L faults were simulated for measuring the accuracy of fault classification.

RETRACTED:An assessment of software defined networking approach in surveillance using sparse optimization algorithm

Abstract Unmanned aerial vehicles (UAV) can be used as basic elements of the sensor network or an upgrade of existing network that are built with static wireless sensor nodes. Wireless Networks (WN) are utilized across in surveillance in all domains like natural disasters, agriculture, water, forest, military, buildings, health monitoring, disaster relief & emergency management, area and industrial surveillance, due to its wider applicability. Software Defined Networking (SDN) provide a hopeful resolution in bendy supervision WSNs by allowing the separation of the control logic from the sensor nodes/actuators. The advantage with this SDN-based supervision in structure of WSNs is that it enables centralized control of the entire WSN making it simpler to deploy network-wide management protocols and applications on demand. Synthetic Aperture Radar (SAR) images are difficult to analyze due to the presence of speckle noise. Speckle noise must be filtered out before applying to other image processing applications. Three Layered Feed Forward Back Propagation Neural Network (TLFFBPNN) has been proposed to suppress the speckle noise. GLCM properties have been extracted and Back propagation training algorithm is used to train the neural network.

Meta-analysis of the effect of probiotic-yeast (

Context Probiotics are attracting wide attention today as a non-antibiotic feed additive in layer feed, and the number of studies in this field is on the increase. However, the results of the effects of probiotic-yeast supplementation on egg-production indices in laying hens are contradictory. Aim Therefore, the aim of the present study was to use meta-analytical methods to ascertain whether yeast-based diets improve feed intake (FI), feed conversion ratio (FCR), hen-day egg production (HDEP), egg mass (EM), egg weight (EW), Haugh unit (HU) and eggshell thickness (EST) in laying hens. Methods A search of four electronic databases for studies on the impact of yeast supplementation on egg-production indices published in English using a combination of search terms yielded 164 studies. Sixteen research publications with 20 771 laying hens met the criteria for inclusion in the meta-analysis. Data were pooled via random-effects model and are presented as standardised mean differences (SMD) with 95% confidence intervals (CI) for each effect size. Key results HDEP and EM showed a significant increase in the SMD of 11.3% (95% CI: 0.037–0.118, P = 0.003) and 22.5 g egg/hen.day (95% CI: 0.095–0.356, P < 0.001) respectively. Subgroup analysis showed that EST, EM, HDEP and FCR were improved in laying hens that received a yeast-based diet at <5 g/kg feed, compared with the group that received a yeast-based diet at >5 g/kg feed. The results indicated that trial country was a predictor of FI, FCR, EM, HDEP and EST in layers fed yeast-based rations. Conclusion These results suggest that feeding probiotic-yeast at <5 g/kg feed improved FCR, HDEP and EM in laying hens. Implications The results of the present meta-analysis will help poultry nutritionists develop the guidelines for standardising the experimental designs of future experiments on the use of probiotic yeast to enhance the productivity of laying hens.

Production, nitrogenous compounds in manure and serum chemistry of laying hens provided multi-species (Lactobacillus spp.) probiotics

Context A practical, low-cost suggestion for industry to reduce ammonia (NH3) in layer houses is use of Lactobacillus species (L. rhamnosus, L. paracasei and L. plantarum) in drinking water or feed. Thus, we investigated their short-term (8 weeks) use in young layers. Aim A combination of species of Lactobacillus (L. rhamnosus, L. paracasei and L. plantarum at 1.0 × 1012 CFU/kg feed) was provided for laying hens in order to investigate effects on production, nitrogenous compounds in manure, serum chemistry and uric acid in the liver. Method Ninety-six White Leghorns (32 weeks old) were randomly assigned to a control diet (commercial feed) or a diet containing commercial feed + probiotics (g/kg feed: L. rhamnosus 1.667, L. paracasei 0.667 and L. plantarum 0.740) and fed for an additional 8 weeks. Key results No significant major effects were observed among diets on bodyweight, feed intake, egg production or feed conversion ratio. Numerical reductions were noted for feed intake (10%) and feed conversion ratio (9%) at Week 2 for layers receiving probiotics as compared to the control. Ammonia, ammonium-nitrogen (N), total Kjeldahl N and total N in manure were not changed significantly by probiotics, nor did probiotics significantly affect the serum profile (ammonia, uric acid, total protein, albumin and creatine kinase) or uric acid in the liver. There was a numerical but non-significant increase in creatine kinase (11%) after 8 weeks in serum of hens receiving probiotics; likewise, there was a non-significant 8% increase in uric acid concentration in the liver of hens receiving probiotics at the end of the experimental period. Conclusion The probiotics (L. rhamnosus, L. paracasei and L. plantarum at 1.0 × 1012 CFU/kg feed) used in this study did not significantly reduce N-containing compounds in manure of 32–40-week-old layers. Implications Age, different types of layers (and broilers) and mode of administration or concentration of probiotics play important roles in outcomes. Extensive collaborative studies are needed to provide definitive answers for use of probiotics in layer (as well as broiler) feed for reduction of N-containing compounds in poultry houses.

An optimization method for failure analysis in beam like structures

Abstract Industrial revolution plays a major role in the economy of a nation. To have an uninterrupted support from any of the industries, a regular structural health monitoring is very much essential. Again, the online monitoring is preferred over any of the conventional approach. In the recent past many researchers work on the failure analysis of online structural health monitoring. Though visual inspection can’t give better results in many aspects, so it is better to work on a method which can give better results with better accuracy and should be with less time consuming. In this present work we focus on inverse problems for the determination of crack parameters in the form of its location and severity. Basically, the present work is limited to, the failure analysis of a beam like structure. We have considered a cantilever beam for the analysis. The research work has been conducted in two phases. In the first phase the theoretical investigation of the structure has been performed through a numerical method called finite element analysis (FEA), which is comprised of different matrices such as mass matrix and the element stiffness matrix based on the material properties as well as loading conditions. The analysis has been performed with and without the presence of the crack parameters, which leads to give a result of different natural frequencies at different modes of free vibration. The results of natural frequency create a platform to identify unhealthy structures. In the second phase, the main objective of the findings in which the theoretical results have been trained to get the crack parameters as crack depth and crack location. Out of the several inverse techniques we choose the Extreme Learning Machine (ELM) as the best method for this proposed work. ELM is a non-iterative single layer feed forward neural network (NN) system in which the weights and biases (parameters of the hubs) are set haphazardly and require not to be tuned amid the fair treatment. The weights (output) of the network are determined analytically through simple generalized Moore Penrose pseudo inverse operation. It is observed that the ELM gives a better result with better accuracy with less computation time. The robustness of the proposed work has been verified through a comparison study

Comparative Laying Performance, Egg Quality, Fertility and Hatchability of Guinea Fowl with Tilili, Horro and Potchefstroom Koekoek Chicken Breeds

A study was conducted to compare laying performance, fertility, hatchability, and egg quality of guinea fowl (GF) with Horro (HR) and Tilili (TL) local chicken and Potchefstroom Koekoek (PK) exotic chicken. Forty five layers from each genotype and 6 cocks from each chicken genotype and 9 cocks from GF were used in 3 replications in a completely randomized design. Commercial layer feed was used ad libitum for the study that lasted 29 weeks. Daily DM intake per hen was 85, 114, 103 and 137 g (SEM = 3.1) for GF, HR, TL and PK, respectively, and was in the order of GF HR > TL > GF. Average egg weight was higher for PK eggs (46.4 g), intermediate for HR (43.5 g) and TL (42.3 g), and lowest for GF (35.9 g). Eggshell weight and thickness were higher for GF than chicken genotypes. Haugh unit was similar among genotypes. Such differences among poultry genotypes could be reflection of previous selection and breeding interventions, which are apparently more in chicken genotypes than GF. A possible more stressful condition of the confined environment for GF versus chicken genotypes could have also contributed to such differences. This study highlighted the need of implementing future selection and breeding schemes to improve the performance of GF and TL birds to the level achieved by other genotypes.

Modeling of Chromium (VI) adsorption on limonia acidissima hull powder using Artificial Neural Network (ANN) approach

Batch experiment was carried out for the removal of Chromium (VI) from aqueous solution to get experimental data to which an Artificial Neural Network (ANN) model was developed using 16 experimental data points (for testing) and 36 experimental data points (for training). A single layer feed forward back propagation was used to get minimum mean square error with eleven neurons in hidden layer. To develop ANN model, a tan sigmoid transfer function for input and purelin for output layers were used. The optimized process parameters viz., adsorbent dosage, pH and initial concentration of chromium (VI) were obtained along with the maximum percentage removal of Chromium (VI). The predicted ANN model data were in perfect match with the experimental data based on the regression coefficient R2 of 0.995. The optimized parameters along with maximum percentage removal of chromium (VI) were achieved by means of pattern search method in Genetic Algorithm.

Free-choice Feeding of Three Different Dietary Calcium Sources and their Influence on Egg Quality Parameters of Commercial Layers

Purpose: The study reported herein was conducted to determine the effects of choice feeding three different calcium (Ca) sources on external and internal egg quality parameters of commercial layers. Research Method: Three dietary Ca sources (oyster shells, limestone and bone meal) were choice fed ad libitumly along with a commercial layer feed. The birds fed only the commercial layer diet was used as the control. The experiment was conducted as a complete randomized design. A total of 128, 55 weeks old Hy-line white layer hens (1500 ±21g) were assigned into 16 cages of 8 birds each. Four replicate cages were randomly assigned to each of the four dietary treatments. Bird’s performances were tested weekly. Twenty eggs from each treatment were collected weekly over five weeks period and were assessed for shell and internal quality parameters. Findings: Daily Ca intakes of birds affected significantly (P<0.05) by the Ca source. The birds fed oyster shells and limestone showed the highest (P<0.05) daily Ca intakes. Feeding bone meal significantly (P<0.05) reduced damaged shell percentage. Weekly body weight gain, weekly egg production and feed conversion ratio among treatments were similar (P>0.05). Dietary supplementation of Ca significantly (P<0.05) improved the egg weight. Shape index and shell ratios among treatments were similar (P>0.05). Feeding bone meal significantly (P<0.05) improved unit surface shell weight (USSW) and the shell thickness. Calcium supplementation had no effect (P>0.05) on albumen and yolk quality parameters of eggs. Originality/value: The present study concluded that feeding bone meal to commercial layers improves USSW, shell thickness thereby reducing egg damages. Calcium source has no influence in improving internal quality parameters of chicken eggs.

Brassica napus and Brassica juncea extruded-expelled cake and solvent-extracted meal as feedstuffs for laying hens: Lay performance, egg quality, and nutrient digestibility

Two experiments evaluated feeding Brassica (B.) napus (canola) or B. juncea co-products to brown-shelled egg laying hens. In Exp. 1, diets including 20% B. napus or B. juncea extruded-expelled cakes (NC, JC) or solvent-extracted meals (NM, JM) compared to a control diet with no Brassica co-products, were fed to 120 hens (4 hens/cage, n = 6) for 36 wk. In Exp. 2, DM, gross energy, CP and amino acid (AA) retention/digestibility was determined by feeding diets containing 30% B. napus or B. juncea cakes or meals and basal diet to 240 hens (8 hens/pair of cages, n = 6) for 7 d. Cakes averaged 40 g/kg lower moisture, 28 g/kg lower CP, and 84 g/kg greater fat content compared with meals. In Exp. 1, there was no effect of diet on lay percentage or BW throughout the experiment. Feed consumption was 3.5 g/d lower in layers fed JM compared with controls and egg: feed was reduced by 14 mg egg/g feed in layers fed JC (P < 0.01). Although eggs from layers fed NM were 0.7 g heavier than controls, eggs from layers fed NC, JM or JC were 1.4 g lighter than controls (P < 0.01). Eggs from layers fed Brassica diets contained a greater proportion (1.6%-points) of monounsaturated fatty acids compared with controls (P < 0.01). Eggs from layers fed B. juncea had a relatively greater proportion (0.2%-points) of C18:3 (n3) compared with those of layers fed B. napus diets (P < 0.01). Feeding Brassica diets reduced digestibility of DM (5%-points), gross energy (7%-points) and CP (4%-points) vs. basal (P < 0.01). The digestibility of indispensable AA except tryptophan, was reduced feeding Brassica diets vs. basal (P < 0.01). We concluded that feeding B. napus and B. juncea extruded-expelled cakes and solvent-extracted meal at 20% of diets to hens supported acceptable lay performance and egg quality over a 36 wk production cycle. Digestibility data indicated that indispensable AA in Brassica co-products had moderately high (75 to 85%) apparent ileal digestibility.

Docosahexaenoic Acid Included in Layer Feed as an Unextracted Aurantiochytrium limacinum Biomass Is Efficiently Transferred to Eggs When Provided in Mash or Pellet Form

SUMMARY Pelleting is commonly used in the production of poultry feed as it can reduce waste, kill pathogenic bacteria, and improve productivity. However, high temperatures used during production can negatively impact some feed ingredients. Omega-3 long-chain polyunsaturated fatty acid (n-3 LC-PUFA)-rich ingredients are often added to poultry feed to increase the n-3 LC-PUFA concentration of meat and eggs, adding value due to the health benefits associated with n-3 LC-PUFA consumption. Fish oils have traditionally been used for this purpose, but the n-3 LC-PUFA they contain are susceptible to oxidation, which can result in rancidity in enriched poultry products. Alternatively, protists that are primary producers of n-3 LC-PUFA are used. When provided in an unextracted form, these organisms could potentially protect the n-3 LC-PUFA they contain from oxidation. Aurantiochytrium limacinum is a marine protist, rich in docosahexaenoic acid (DHA), an n-3 LC-PUFA associated with various health benefits. We supplemented layer feed with A. limacinum and investigated the effect of pelleting on the recovery of DHA from feed and the efficiency of DHA transfer from feed to eggs. Pelleting did not decrease the concentration of DHA in feed. Also, no differences were observed between the groups fed mash or pelleted feeds in terms of the level of DHA enrichment of eggs. These results indicate that DHA, in the form of an A. limacinum biomass, is resistant to pelleting conditions and can be used as an ingredient in pelleted poultry diets to increase the DHA concentration of poultry products.

Crecimiento de larvas de mosca soldado alimentadas con gallinaza, porcinaza y alimento para ponedoras

En esta investigación se estudió el efecto de la gallinaza, porcinaza y alimento para ponedoras, sobre el crecimiento de larvas de mosca soldado; este último evaluado a través del cambio del peso, ancho y largo de las larvas. Los datos fueron analizados mediante modelos mixtos de coeficientes aleatorios, puesto que las variables fueron analizadas en el tiempo y se producen datos longitudinales. Se analizó el crecimiento de las larvas durante cuatro semanas y se observó que la alimentación con porcinaza produce larvas con menor desempeño en peso, largo y ancho, comparado con las alimentadas con gallinaza y alimento para ponedoras, los cuales no presentan diferencias significativas, lo que indica que la gallinaza y el alimento para ponedoras son más eficientes en términos de crecimiento. Es importante seguir realizando experimentos que evidencien que la gallinaza y el alimento para ponedoras son más apropiados para el crecimiento de las larvas de mosca soldado.

Elimination of micropollutants in four test-scale constructed wetlands treating combined sewer overflow: Influence of filtration layer height and feeding regime

Municipal wastewater can contain large amounts of organic micropollutants. Some of these substances are harmful to the environment, even at low concentrations, e.g. when being discharged untreated into surface water bodies in case of combined sewer overflows (CSOs) during or after heavy rainfall events. Constructed wetlands can be very effective in treating CSOs. To date, there have only been few investigations about the retention of micropollutants using retention soil filters (RSFs), which basically are vertical flow constructed wetlands with an additional retention area. Thus, focus of this study was set on the interaction between dry periods, loading events, filter operation time, and the resulting removal of micropollutants originating from CSOs. The removal of 1-H-benzotriazole, carbamazepine, diclofenac, metoprolol, sulfamethoxazole and bisphenol A was examined in four test-scale RSFs. Removal efficiencies of approximately 70% were found for metoprolol. 1-H-benzotriazole, diclofenac and bisphenol A were removed moderately between 30 and 40%. For carbamazepine and sulfamethoxazole, negative retention rates were found. No significant correlations were found between removal efficiencies and the length of the antecedent dry period and/or filter operation time. However, the study showed that removal efficiencies depend strongly on respective inflow concentrations. Thickness of the filter layer seems to have an influence as well; does not lead to uniform results, though.

Multi Layer Feed Forward Neural Network Knowledge Base to Future Stock Market Prediction

Stock price prediction is always a most challenging task. Artificial Neural Network prediction clears the stock price prediction challenge by forming the training set. By using the past information as the network input, one can predict the expected output of the network. In order to predict the expected result as the accurate we add multi-layer perceptron to the knowledge set we formed from the past historical data available in the nifty NSE and Sensex BSE. This paper proves that proposing the learning knowledge set using multilayer neural network will predict the accurate closing price of future stock in stock market.

Analysis of PLA Geometric Properties Processed by FFF Additive Manufacturing: Effects of Process Parameters and Plate-Extruder Precision Motion.

The evolution of fused filament fabrication (FFF) technology, initially restricted to the manufacturing of prototypes, has led to its application in the manufacture of finished functional products with excellent mechanical properties. However, FFF technology entails drawbacks in aspects, such as dimensional and geometric precision, and surface finish. These aspects are crucial for the assembly and service life of functional parts, with geometric qualities lagging far behind the optimum levels obtained by conventional manufacturing processes. A further shortcoming is the proliferation of low cost FFF 3D printers with low quality mechanical components, and malfunctions that have a critical impact on the quality of finished products. FFF product quality is directly influenced by printer settings, material properties in terms of cured layers, and the functional mechanical efficiency of the 3D printer. This paper analyzes the effect of the build orientation (Bo), layer thickness (Lt), feed rate (Fr) parameters, and plate-extruder movements on the dimensional accuracy, flatness error, and surface texture of polylactic acid (PLA) using a low cost open-source FFF 3D printer. The mathematical modelling of geometric properties was performed using artificial neural networks (ANN). The results showed that thinner layer thickness generated lower dimensional deviations, and feed rate had a minor influence on dimensional accuracy. The flatness error and surface texture showed a quasi-linear behavior correlated to layer thickness and feed rate, with alterations produced by 3D printer malfunctions. The mathematical models provide a comprehensive analysis of the geometric behavior of PLA processing by FFF, in order to identify optimum print settings for the processing of functional components.

Experimental studies and neural network modeling of the removal of trichloroethylene vapor in a biofilter

In this study, bamboo carrier based lab scale compost biofilter was evaluated to treat synthetic waste air containing trichloroethylene (TCE) under continuous operation mode. The effect of inlet TCE concentration and gas flow rate and its removal was investigated. Maximum TCE removal efficiency was found to be 89% under optimum conditions of inlet 0.986 g/m3 TCE concentration corresponding to a loading rate of 43 g/m3 h and 0.042 m3/h gas flow rate at empty bed residence time (EBRT) of 2 min. For the first time, Artificial Neural Network (ANN) was applied to predict the performance of the compost biofilter in terms of TCE removal. The ANN model used a three layer feed forward based Levenberg-Marquardt algorithm, and its topology consisted of 3-25-1 as the optimum number for the three layers (input, hidden and output). An excellent match between the experimental and ANN predicted the value of TCE removal was obtained with a coefficient of determination (R2) value greater than 0.99 during the model training, validation, testing and overall. Furthermore, statistical analysis of the ANN model performance mediated its prediction accuracy of the bioreactor to treat TCE contaminated systems.

Enhanced Classifier Accuracy in Liver Disease Diagnosis using a Novel Multi Layer Feed Forward Deep Neural Network

Classification techniques are often used for predicting Liver diseases and assist doctors in early detection of liver diseases. As per studies in the past and our experiments, conventional classification algorithms are found to be less accurate in predicting liver diseases. Therefore, there is a need for sophisticated classifiers in this area. For many medical applications, including Liver Diseases, Deep Neural Networks (DNNs) are used but the accuracies are not satisfactory. Deep Neural Network training is a time taking procedure, particularly if the hidden layers and nodes are more. Most of the times it leads to over fitting and the classifier does not perform well on unseen data samples .We, in this paper, tuned a Multi Layer Feed Forward Deep Neural Network (MLFFDNN) by fitting appropriate number of hidden layer and nodes, dropout function after each hidden layer to avoid over fitting, loss functions, bias, learning rate and activation functions for more accurate liver disease predictions. We used a balanced data set containing 882 samples. The data is collected from north coastal districts of Andhra Pradesh hospitals, India. The training process is carried out for 400 epochs and finally It is .observed that our model exhibited 98% accuracy at epoch 363 which is more than the performance of Neural Network models tuned till now by machine learning researchers and also some regularly used classification algorithms like Support Vector Machines (SVM), Naive Bayes (NB), C4.5 Decision Tree, Random Belief Networks and Alternating Decision Trees (ADT) .

Leakage Current Prediction of Composite Insulator using Artificial Neural Network

The uninterrupted power supply is one of the main concerns for the power utility which is often adversely affected by the flashover of the outdoor insulators. The main cause of the flashover of outdoor insulator is the contaminated pollution on its surface which is more severe for the insulators located nearer to the seashore. At such sites, insulators have to be washed regularly to avoid flashover which is an expensive and time-consuming process. So it is required to optimize the washing schedule. When the contamination is severe on the surface of the insulator, it allows the flow of the leakage current (LC) which turns into the flashover. The LC is a good indication for predicting the flashover. LC measurement and instrumentation system in real tower insulator is complex and expensive. In this paper, a prediction method is developed which predicts the LC at the level of starting of the arc which may turns into a flashover. An artificial neural network based model is developed which predicts the leakage current for the different polluted condition and humidity level. An experimental setup is prepared and subsequently data is taken to acquire LC on different relative humidity and equivalent salt deposit density (ESDD). Subsequently, a neural network model is constructed with the experimental data to predict LC. A single layer feed forward network based a predictive model performs LC prediction with the average error of 5.46% from the real values which is acceptable in case of alarming situations.

Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks.

Polysomnography (PSG) scoring is labor intensive and suffers from variability in inter- and intra-rater reliability. Automated PSG scoring has the potential to reduce the human labor costs and the variability inherent to this task. Deep learning is a form of machine learning that uses neural networks to recognize data patterns by inspecting many examples rather than by following explicit programming. A sleep staging classifier trained using deep learning methods scored PSG data from the Sleep Heart Health Study (SHHS). The training set was composed of 42 560 hours of PSG data from 5213 patients. To capture higher-order data, spectrograms were generated from electroencephalography, electrooculography, and electromyography data and then passed to the neural network. A holdout set of 580 PSGs not included in the training set was used to assess model accuracy and discrimination via weighted F1-score, per-stage accuracy, and Cohen's kappa (K). The optimal neural network model was composed of spectrograms in the input layer feeding into convolutional neural network layers and a long short-term memory layer to achieve a weighted F1-score of 0.87 and K = 0.82. The deep learning sleep stage classifier demonstrates excellent accuracy and agreement with expert sleep stage scoring, outperforming human agreement on sleep staging. It achieves comparable or better F1-scores, accuracy, and Cohen's kappa compared to literature for automated sleep stage scoring of PSG epochs. Accurate automated scoring of other PSG events may eventually allow for fully automated PSG scoring.

Effect Adding Petroselium sativam L to the Diet of layer Chicken for Reduce Fecal Bacterial Load

The present study was undertaken to assessment adding herbal preparation(Petroselium sativam L) in different series of doses 0.25%, 0.75 % and 0.125 % in chicken of layer feed breed on the total fecal bacterial count, as well as the count of coliform bacteria and the count of lactobacilli bacteria.Methods: The study was carried out in 35 weeks old Isa Brown breed(72 birds) with 18 birds per group for 3 replicate 6 birds in each. Control group T1was fed only with the ordinary feeding without any addition of herbs while in the treatment groups T2, T3 and T4, different levels of herbal preparation were added with ordinary feed of birds as mentioned above. The assessment of these experiments was carried out for 21 days and a sample composed of Six birds from each group were selected and the data collected from each birdResults: All groups showed a significant reduction (p < 0.05) in both of total fecal bacterial count and faecal coliform count and the differences were more apparent in the T4 as it compared to control group also a significant increment (p<0.05) was showed in lactobacilli count in all the groups with more ever increment in T4 when compared with control one.Conclusion: It can be concluded that the herb Petroselium sativam L supplementation at 0.25%, 0.75% and 0.125 % level to the layer diet causes a definite reduction in the faecal total bacterial count and faecal coliform count and increment of lactobacilli count specially at 0.125% level which recorded best value.

A State of Health Estimation Framework for Lithium-Ion Batteries Using Transfer Components Analysis

As different types of lithium batteries are increasingly employed in various devices, it is crucial to predict the state of health (SOH) of lithium batteries. There are plenty of methods for SOH estimation of a lithium-ion battery. However, existing technologies often have computational complexity. Furthermore, it is difficult to use least the previous 30% of data of the battery degradation process to predict the SOH variation of the entire degradation process. To address this problem, in this paper, the SOH of the target battery is estimated based on the transfer of different battery data sets. Firstly, according to importance sampling (IS), valid features are extracted from cycles of charging voltage in both the source and target battery. Secondly, transfer component analysis (TCA) is used to map the source data set to the target data set. Moreover, an extreme learning machine (ELM) algorithm is employed to train a single hidden layer feed forward neural network (SLFN) for its fast training speed and facile to set up. Finally, validation experiments and the comparisons on the results are conducted. The results showed that the proposed framework has a good capability of predicting the SOH of lithium batteries.