23 research outputs found
Impact of Salt and Alkali Stress on Forage Biomass Yield, Nutritive Value, and Animal Growth Performance: A Comprehensive Review
No full textThis review investigates the impact of saline and alkaline soils on forage biomass yield, nutritive value, and their subsequent effects on animal growth performance, which are critical for sustainable livestock production. Soil salinity and alkalinity, driven by environmental factors and human activities, significantly affect forage yield and quality, with notable consequences for ruminant nutrition. While some forage species exhibit enhanced crude protein (CP) content and improved leaf-to-stem ratios under salt stress, others suffer from reduced growth and biomass yield. Saline-affected forages are often characterized by lower acid detergent fiber (ADF) and neutral detergent fiber (NDF) levels, enhancing their digestibility and making them a potentially valuable feed resource. However, high salinity levels pose significant challenges to consistent forage production in arid and semi-arid regions. Cultivating salt-tolerant forage species has emerged as a promising solution, offering a sustainable approach to addressing the dual challenges of soil salinity and livestock feed shortages. This review emphasizes the need for further research on salinity tolerance mechanisms and the development of resilient forage varieties. By integrating salt-tolerant forages and adopting effective management practices, livestock producers can ensure a reliable and high-quality feed supply while enhancing the growth performance of ruminant animals in salt-affected areas
Feeding with a NaCl-Supplemented Alfalfa-Based TMR Improves Nutrient Utilization, Rumen Fermentation, and Antioxidant Enzyme Activity in AOHU Sheep: A Nutritional Simulation of Saline–Alkaline Conditions
No full textSaline–alkaline soils are becoming prevalent across the globe, decreasing the availability of forage for animals and threatening sustainable animal production. This study evaluated the effects of a NaCl-supplemented alfalfa-based total mixed ration, simulating saline–alkaline soil conditions, on intake, the utilization of nutrients, antioxidant levels, and rumen fermentation. A 60-day feeding trial with 24 AOHU lambs (Australian White × Hu) compared a control diet (0.43% NaCl) with the NaCl-supplemented group (1.71% NaCl). Digestibility trials were conducted in metabolic cages for the collection of total feces and urine. Blood samples were taken at 0, 30, and 60 days for serum analysis, and slaughter samples (liver, kidney, rumen tissue, and rumen fluid) were taken for physiological, biochemical, and histological evaluation. The NaCl alfalfa-based TMR markedly increased liver and kidney weights. The rumen muscle layer thickened in the NaCl group. The ruminal ammonia nitrogen (NH3-N), ruminal microbial crude protein (MCP) synthesis, and glucogenic/branched-chain VFAs increased, indicating enhanced proteolysis, microbial protein synthesis, and energetically efficient fermentation. Serum total protein and albumin also rose over time in the NaCl group, reflecting increased nitrogen retention, while superoxide dismutase and glutathione peroxidase activity rose considerably by day 60, reflecting increased antioxidant defense. Furthermore, nitrogen intake, digestibility, and retention were improved in the NaCl group along with augmented digestible and metabolizable energy (28.47 vs. 13.93 MJ/d and 24.68 vs. 11.58 MJ/d, respectively) and gross energy digestibility (78.13% vs. 67.10%). Although NaCl-based alfalfa TMR cannot fully emulate naturally salt-stressed forages, these results indicate that the NaCl alfalfa-based diets improved rumen fermentation, energy yields, and antioxidant enzyme activity without impairing electrolyte balance. These findings suggest that NaCl-supplemented alfalfa-based TMRs, with a salt content comparable to that of alfalfa hay grown under saline–alkaline conditions, could support environmentally sustainable meat production in salt-stressed regions
AN EFFICIENT DEEP LEARNING APPROACH FOR GROUND POINT FILTERING IN AERIAL LASER SCANNING POINT CLOUDS
No full textGround surface extraction is one of the classic tasks in airborne laser scanning (ALS) point cloud processing that is used for three-dimensional (3D) city modelling, infrastructure health monitoring, and disaster management. Many methods have been developed over the last three decades. Recently, Deep Learning (DL) has become the most dominant technique for 3D point cloud classification. DL methods used for classification can be categorized into end-to-end and non end-to-end approaches. One of the main challenges of using supervised DL approaches is getting a sufficient amount of training data. The main advantage of using a supervised non end-to-end approach is that it requires less training data. This paper introduces a novel local feature-based non end-to-end DL algorithm that generates a binary classifier for ground point filtering. It studies feature relevance, and investigates three models that are different combinations of features. This method is free from the limitations of point clouds’ irregular data structure and varying data density, which is the biggest challenge for using the elegant convolutional neural network. The new algorithm does not require transforming data into regular 3D voxel grids or any rasterization. The performance of the new method has been demonstrated through two ALS datasets covering urban environments. The method successfully labels ground and non-ground points in the presence of steep slopes and height discontinuity in the terrain. Experiments in this paper show that the algorithm achieves around 97% in both F1-score and model accuracy for ground point labelling
Automated Web-Based Malaria Detection System with Machine Learning and Deep Learning Techniques
No full textMalaria parasites pose a significant global health burden, causing widespread suffering and mortality. Detecting malaria infection accurately is crucial for effective treatment and control. However, existing automated detection techniques have shown limitations in terms of accuracy and generalizability. Many studies have focused on specific features without exploring more comprehensive approaches. In our case, we formulate a deep learning technique for malaria-infected cell classification using traditional CNNs and transfer learning models notably VGG19, InceptionV3, and Xception. The models were trained using NIH datasets and tested using different performance metrics such as accuracy, precision, recall, and F1-score. The test results showed that deep CNNs achieved the highest accuracy -- 97%, followed by Xception with an accuracy of 95%. A machine learning model SVM achieved an accuracy of 83%, while an Inception-V3 achieved an accuracy of 94%. Furthermore, the system can be accessed through a web interface, where users can upload blood smear images for malaria detection
Time to Recovery and Its Predictors among Children 6–59 Months Admitted with Severe Acute Malnutrition to East Amhara Hospitals, Northeast Ethiopia: A Multicenter Prospective Cohort Study
No full textBackground. Malnutrition has been among the most common public health problems in the world, especially in developing countries including Ethiopia. Even though the Ethiopian government launched stabilization centers in different hospitals, there are limited data on how long children will stay in treatment centers to recover from severe acute malnutrition. This study aimed to assess the time to recovery and its predictors among children 6–59 months with severe acute malnutrition admitted to public hospitals in East Amhara, Northeast Ethiopia. Methods. Institution-based, prospective cohort study was conducted in seven public hospitals in East Amhara and a total of 341 children were included in the study. The results were determined by Kaplan–Meier procedure, log-rank test, and Cox-regression to predict the time to recovery and to identify the predictors of recovery time. Variables having P value ≤0.2 during binary analysis were entered into multivarable Cox proportional hazards regression analysis. P value <0.05 was considered statistically significant. Results. The nutritional recovery rate was 6.9 per 100 person-days with a median nutritional recovery time of 11 days (an interquartile range of 6). The independent predictors like using NG tube for feeding (AHR = 0.44, 95% CI: 0.27–0.71), not entering phase 2 on day 10 (AHR = 0.19, 95% CI: 0.12–0.29), and being admitted to referral hospitals (AHR = 0.52 95% CI: 0.37–0.73) were associated with longer periods of nutritional recovery time. Conclusion. Both the recovery rate and the recovery time were within the acceptable minimum standards. But, special attention has to be given to children who failed to enter phase 2 on day 10, for those who needed NG tube for feeding, and for those admitted to referral hospitals during inpatient management
Automatic Identification of Amharic Text Idiomatic Expressions Using a Deep Learning Approach
No full textNatural Language Processing (NLP) is a tract of artificial intelligence and linguistics devoted to making computers understand the statements or words written in human languages. Amharic, the most widely spoken language in Ethiopia, uses a lot of idiomatic expressions and proverbs to emphasize the message of the text. The meaning of an idiomatic phrase cannot be inferred from individual words. Developing a model to identify Amharic idiomatic terms is helpful for different NLP applications like machine translation, sentiment analysis, spam classification, intent recognition, and so on. Few studies have been conducted to identify idiomatic expressions using K-Nearest Neighbors (KNN) and Convolutional Neural Network (CNN) algorithms for the Amharic language. The KNN model was designed to identify only dual-word idioms by neglecting idioms with three or more words, and this study didn’t use the n-gram technique to identify idioms found in a sentence or paragraph. Like the former model, the CNN model did not use the n-gram technique, and the testing accuracy was not greater than 80%. Due to this gap, we need to develop a deep learning model that identifies Amharic idioms constructed from two or more words. To identify idioms found in a sentence or paragraph, we used the n-gram method to divide the sentence or the paragraph into phrases for enhancing the previous works. For designing our model, we used 4053 idiomatic phrases and 4051 literal Amharic phrases. After the data were collected, text preprocessing techniques were applied to the collected data, and FastText and Word2Vec models were used for word embedding purposes. We conducted experiments with 70:30 and 80:20 data split ratios with FastText and Word2Vec word embedding models along with long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM) with and without attention layer algorithms. Among those experiments, the highest accuracy of 98.95% was attained using an 80:20 train-test split ratio, Adamax optimizer, 64 batch sizes, and a 0.001 learning rate by using Bi-LSTM with an attention layer and FastText word embedding model
A Two-Step Feature Extraction Algorithm: Application to deep learning for point cloud classification
No full textMost deep learning (DL) methods that are not end-to-end use several multi-scale and multi-type hand-crafted features that make the network challenging, more computationally intensive and vulnerable to overfitting. Furthermore, reliance on empirically-based feature dimensionality reduction may lead to misclassification. In contrast, efficient feature management can reduce storage and computational complexities, builds better classifiers, and improves overall performance. Principal Component Analysis (PCA) is a well-known dimension reduction technique that has been used for feature extraction. This paper presents a two-step PCA based feature extraction algorithm that employs a variant of feature-based PointNet (Qi et al., 2017a) for point cloud classification. This paper extends the PointNet framework for use on large-scale aerial LiDAR data, and contributes by (i) developing a new feature extraction algorithm, (ii) exploring the impact of dimensionality reduction in feature extraction, and (iii) introducing a non-end-to-end PointNet variant for per point classification in point clouds. This is demonstrated on aerial laser scanning (ALS) point clouds. The algorithm successfully reduces the dimension of the feature space without sacrificing performance, as benchmarked against the original PointNet algorithm. When tested on the well-known Vaihingen data set, the proposed algorithm achieves an Overall Accuracy (OA) of 74.64% by using 9 input vectors and 14 shape features, whereas with the same 9 input vectors and only 5PCs (principal components built by the 14 shape features) it actually achieves a higher OA of 75.36% which demonstrates the effect of efficient dimensionality reduction. Optical and Laser Remote Sensin
Isolation of Leishmania tropica from an Ethiopian cutaneous leishmaniasis patient
No full textCutaneous leishmaniasis (CL) in the Old World is caused mainly by three species of Leishmania: L. major, L. tropica and L. aethiopica, and sporadically by L. infantum and L. donovani. In Ethiopia, zoonotic cutaneous leishmaniasis, caused by L. aethiopica, is a major public health problem affecting thousands of people in the highlands. By contrast, little is known about the existence and epidemiology of CL due to L. tropica. In this report, we provide the first well-documented case of CL in Ethiopia caused by L. tropica. The patient acquired the infection in Awash valley of the Ethiopian Rift Valley (northeastern Ethiopia), where Phlebotomus sergenti and P saevus have previously been found infected by L. tropica. Using the isoenzyme electrophoresis technique, the isolate was found to belong to a variant of L. tropica zymodeme MON-71, one of the new zymodemes found in Ethiopia from P sergenti in the same region so far. The epidemiological implications of the finding are discussed. (c) 2005 Royal Society of Tropical Medicine and Hygiene. Published by Elsevier Ltd. All rights reserve
Time to Recovery and Its Predictors among Children 6–59 Months Admitted with Severe Acute Malnutrition to East Amhara Hospitals, Northeast Ethiopia: A Multicenter Prospective Cohort Study
No full textBackground. Malnutrition has been among the most common public health problems in the world, especially in developing countries including Ethiopia. Even though the Ethiopian government launched stabilization centers in different hospitals, there are limited data on how long children will stay in treatment centers to recover from severe acute malnutrition. This study aimed to assess the time to recovery and its predictors among children 6–59 months with severe acute malnutrition admitted to public hospitals in East Amhara, Northeast Ethiopia. Methods. Institution-based, prospective cohort study was conducted in seven public hospitals in East Amhara and a total of 341 children were included in the study. The results were determined by Kaplan–Meier procedure, log-rank test, and Cox-regression to predict the time to recovery and to identify the predictors of recovery time. Variables having P value ≤0.2 during binary analysis were entered into multivarable Cox proportional hazards regression analysis. P value <0.05 was considered statistically significant. Results. The nutritional recovery rate was 6.9 per 100 person-days with a median nutritional recovery time of 11 days (an interquartile range of 6). The independent predictors like using NG tube for feeding (AHR = 0.44, 95% CI: 0.27–0.71), not entering phase 2 on day 10 (AHR = 0.19, 95% CI: 0.12–0.29), and being admitted to referral hospitals (AHR = 0.52 95% CI: 0.37–0.73) were associated with longer periods of nutritional recovery time. Conclusion. Both the recovery rate and the recovery time were within the acceptable minimum standards. But, special attention has to be given to children who failed to enter phase 2 on day 10, for those who needed NG tube for feeding, and for those admitted to referral hospitals during inpatient management
Biochemical profiles of patients with COVID-19 during the first and second waves in Ethiopia
No full textCoronavirus disease 2019 (COVID-19) is a highly infectious disease caused by severe acute respiratory syndrome coronavirus 2. Nasopharyngeal swabs (NP swabs) were used for patients with COVID-19 who demonstrated serious clinical symptoms and disturbances in biochemical parameters. The biochemical profiles of these patients remain ambiguous and differ from wave to wave of COVID-19 infections. Herein, we conducted a multicenter retrospective cohort study with 538 patients with COVID-19 at six COVID-19 treatment centers in Ethiopia. Professional data collectors collected the data. Descriptive statistics were used to summarize the data, and independent t-tests and chi-square tests were used to assess the relationships between the continuous and categorical variables across waves, respectively. In total, 240 and 298 patients were included from the first and second waves, respectively. Men and individuals aged 53–69 years were more likely to be infected in each wave. The mean alkaline phosphatase (p < 0.001) and sodium levels (p = 0.035) significantly differed between patients across the two waves of COVID-19; the significant difference in the alkaline phosphatase levels of patients between the two waves was −45.425. All the symptoms of COVID-19 were significantly (p < 0.05) associated with the waves of the pandemic. Patients in both waves had no chronic disease comorbidities. This study showed that the mean alkaline phosphatase and sodium levels differed significantly across the first two waves of the pandemic at six COVID-19 treatment centers in Ethiopia while all clinical symptoms of COVID-19 were associated with the first two waves of the pandemic
