Hepatitis C Stage Classification with hybridization of GA and Chi2 Feature Selection

Umar, Rukayya,Adeshina, Steve,Boukar, Moussa Mahamat International Journal of Computer ScienceNetwork S 2022 International journal of computer science and netw Vol.22 No.1

In metaheuristic algorithms such as Genetic Algorithm (GA), initial population has a significant impact as it affects the time such algorithm takes to obtain an optimal solution to the given problem. In addition, it may influence the quality of the solution obtained. In the machine learning field, feature selection is an important process to attaining a good performance model; Genetic algorithm has been utilized for this purpose by scientists. However, the characteristics of Genetic algorithm, namely random initial population generation from a vector of feature elements, may influence solution and execution time. In this paper, the use of a statistical algorithm has been introduced (Chi2) for feature relevant checks where p-values of conditional independence were considered. Features with low p-values were discarded and subject relevant subset of features to Genetic Algorithm. This is to gain a level of certainty of the fitness of features randomly selected. An ensembled-based learning model for Hepatitis has been developed for Hepatitis C stage classification. 1385 samples were used using Egyptian-dataset obtained from UCI repository. The comparative evaluation confirms decreased in execution time and an increase in model performance accuracy from 56% to 63%.

Efficiency of SNP and SSR-Based Analysis of Genetic Diversity, Population Structure, and Relationships among Cowpea (Vigna unguiculata (L.) Walp.) Germplasm from East Africa and IITA Inbred Lines

Belayneh Ayalew Desalegne, Kifle Dagne, Gedil Melaku, Boukar Ousmane, 한국작물학회 2017 Journal of crop science and biotechnology Vol.20 No.2

The extent of genetic diversity and relatedness of cowpea germplasm from East Africa are poorly understood. A set of 13 microsatellites (SSR) and 151 single nucleotide olymorphisms (SNPs) markers were applied to assess the levels of genetic diversity in a sample of 95 accessions of local cowpea germplasm and inbred lines of Vigna unguiculata. The average genetic diversity (D), as quantified by the expected heterozygosity, was higher for SSR loci (0.52) than for SNPs (0.34). The polymorphic information content was 0.48 for SSR and 0.28 for SNP while the fixation index was 0.095 for SSR and 0.15 for SNPs showing moderate differentiation and high gene flow among cowpea accessions from East African countries. The results of data analysis of both SSR and SNP markers showed similar clustering patterns suggesting a substantial degree of association between origin and genotype. Principal coordinate analysis (PCoA) with SSR and SNP markers showed that accessions were grouped into two and three broad groups across the first two axes, respectively. Our study found that SNP markers were more effective than SSR in determining the genetic relationship among East African local cowpea accessions and IITA inbred lines. Based on this analysis, five local cowpea accessions Tvu-13490, Tvu-6378, Tvu-13448, Tvu-16073, and 2305675 were identified to be tightly clustered sharing several common alleles with the drought tolerant variety Danila when analyzed with SSR and SNP markers. The findings will assist and contribute to future genetic diversity studies aimed at the genetic improvement of local Eastern Africa cowpea accessions for improved overall agronomic performance in general and breeding for drought tolerant in particular.

A Multi-Indexes Based Technique for Resolving Collision in a Hash Table

Yusuf, Ahmed Dalhatu,Abdullahi, Saleh,Boukar, Moussa Mahamat,Yusuf, Salisu Ibrahim International Journal of Computer ScienceNetwork S 2021 International journal of computer science and netw Vol.21 No.9

The rapid development of various applications in networking system, business, medical, education, and other domains that use basic data access operations such as insert, edit, delete and search makes data structure venerable and crucial in providing an efficient method for day to day operations of those numerous applications. One of the major problems of those applications is achieving constant time to search a key from a collection. A number of different methods which attempt to achieve that have been discovered by researchers over the years with different performance behaviors. This work evaluated these methods, and found out that almost all the existing methods have non-constant time for adding and searching a key. In this work, we designed a multi-indexes hashing algorithm that handles a collision in a hash table T efficiently and achieved constant time O(1) for searching and adding a key. Our method employed two-level of hashing which uses pattern extraction h₁(key) and h₂(key). The second hash function h₂(key) is use for handling collision in T. Here, we eliminated the wasted slots in the search space T which is another problem associated with the existing methods.

Remote Sensing Image Classification for Land Cover Mapping in Developing Countries: A Novel Deep Learning Approach

Lynda, Nzurumike Obianuju,Nnanna, Nwojo Agwu,Boukar, Moussa Mahamat International Journal of Computer ScienceNetwork S 2022 International journal of computer science and netw Vol.22 No.2

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

Genotype × environment interactions of yield of cowpea (Vigna unguiculata (L.) Walp) inbred lines in the Guinea and Sudan Savanna

Emmanuel Yaw Owusu,Isaac Kodzo Amegbor,Haruna Mohammed,Francis Kusi,Ibrahim Atopkle,Emmanuel Kofi Sie,Memunatu Ishahku,Muktaru Zakaria,Sumani Iddrisu,Haruna Ali Kendey,Ousmane Boukar,Christian Fatokun 한국작물학회 2020 Journal of crop science and biotechnology Vol.23 No.5

The variable cowpea productivity across diff erent environments demands evaluating the performance of genotypes in a breeding program prior to their release. The aim of this study was to assess yield stability of eight cowpea advanced breeding lines selected from participatory varietal selection in multilocational trials, and to identify mega-environments for cowpea production in Ghana. The genotypes were evaluated across fi ve environments in 2016 and 2017 in randomized complete block design with three replications. The GEA-R version 4.0 software was used for genotype main eff ect plus genotype by environment interaction (GGE) biplot analyses. Analysis of variance (PROC GLM of SAS using a RANDOM statement with the TEST option) detected signifi cant variations for location, year, genotype, environment, and their interactions. The results showed that the yield performances of the cowpea genotypes were highly infl uenced by genotype × environment interaction eff ects. The principal component 1 (PC1) and PC2 were signifi cant components which accounted for 46.75% and 22.84% of GGE sum of squares, respectively. We showed for the fi rst time, two mega-environments for cowpea production and testing in the major cowpea production agro-ecologies in Ghana. The genotypes SARI-6-2-6 and IT07K-303-1 were adapted to Damongo, Nyankpala, and Tumu, whereas SARI-2-50-80 was adapted to Yendi and Manga. The best ranking location was Damongo followed by Tumu, and Nyankpala. The high-yielding genotypes, IT86D-610, IT10K-837-1, IT07K-303-1, and SARI-2-50-80 had signifi cant higher grain yields than the check (Bawutawuta) and were recommended for release as cultivars (or as breeding lines) to boost cowpea production in Ghana.