Artículos Científicos
Permanent URI for this collection
Browse
Browsing Artículos Científicos by Author "Abdulsahib, Ghaida Muttashar"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item A Classification Algorithm-Based Hybrid Diabetes Prediction Model(Frontiers Media S.A., 2022) Edeh, Michael Onyema; Khalaf, Osamah Ibrahim; Tavera, Carlos Andrés; Tayeb, Sofiane; Ghouali, Samir; Abdulsahib, Ghaida Muttashar; Richard Nnabu, Nneka Ernestina; Louni, AbdRahmaneDiabetes is considered to be one of the leading causes of death globally. If diabetes is not treated and detected early, it can lead to a variety of complications. The aim of this study was to develop a model that can accurately predict the likelihood of developing diabetes in patients with the greatest amount of precision. Classification algorithms are widely used in the medical field to classify data into different categories based on some criteria that are relatively restrictive to the individual classifier, Therefore, four machine learning classification algorithms, namely supervised learning algorithms (Random forest, SVM and Naïve Bayes, Decision Tree DT) and unsupervised learning algorithm (k-means), have been a technique that was utilized in this investigation to identify diabetes in its early stages. The experiments are per-formed on two databases, one extracted from the Frankfurt Hospital in Germany and the other from the database. PIMA Indian Diabetes (PIDD) provided by the UCI machine learning repository. The results obtained from the database extracted from Frankfurt Hospital, Germany, showed that the random forest algorithm outperformed with the highest accuracy of 97.6%, and the results obtained from the Pima Indian database showed that the SVM algorithm outperformed with the highest accuracy of 83.1% compared to other algorithms. The validity of these results is confirmed by the process of separating the data set into two parts: a training set and a test set, which is described below. The training set is used to develop the model's capabilities. The test set is used to put the model through its paces and determine its correctness.Item A depth-controlled and energy-efficient routing protocol for underwater wireless sensor networks(2022-09) Lilhore, Umesh Kumar; Khalaf, Osamah Ibrahim; Simaiya, Sarita; Tavera Romero, Carlos Andrés; Abdulsahib, Ghaida Muttashar; Poongodi M.; Kumar, DineshUnderwater wireless sensor network attracted massive attention from researchers. In underwater wireless sensor network, many sensor nodes are distributed at different depths in the sea. Due to its complex nature, updating their location or adding new devices is pretty challenging. Due to the constraints on energy storage of underwater wireless sensor network end devices and the complexity of repairing or recharging the device underwater, this is highly significant to strengthen the energy performance of underwater wireless sensor network. An imbalance in power consumption can cause poor performance and a limited network lifetime. To overcome these issues, we propose a depth controlled with energy-balanced routing protocol, which will be able to adjust the depth of lower energy nodes and be able to swap the lower energy nodes with higher energy nodes to ensure consistent energy utilization. The proposed energy-efficient routing protocol is based on an enhanced genetic algorithm and data fusion technique. In the proposed energy-efficient routing protocol, an existing genetic algorithm is enhanced by adding an encoding strategy, a crossover procedure, and an improved mutation operation that helps determine the nodes. The proposed model also utilized an enhanced back propagation neural network for data fusion operation, which is based on multi-hop system and also operates a highly optimized momentum technique, which helps to choose only optimum energy nodes and avoid duplicate selections that help to improve the overall energy and further reduce the quantity of data transmission. In the proposed energy-efficient routing protocol, an enhanced cluster head node is used to select a strategy that can analyze the remaining energy and directions of each participating node. In the simulation, the proposed model achieves 86.7% packet delivery ratio, 12.6% energy consumption, and 10.5% packet drop ratio over existing depth-based routing and energy-efficient depth-based routing methods for underwater wireless sensor network.