Hybrid intelligent water Drops algorithm for examination timetabling problem

The field of wild fish classification faces many challenges such as the amount of training data, pose variation and uncontrolled environmental settings. This research work introduces a hybrid genetic algorithm (GA) that integrates the simulated annealing (SA) algorithm with a back-propagation algorithm (GSB classifier) to make the classification process. The algorithm is based on determining the suitable set of extracted features using color signature and color texture features as well as shape features. Four main classes of fish images have been classified, namely, food, garden, poison, and predatory. The proposed GSB classifier has been tested using 24 fish families with different species in each. Compared to the back-propagation (BP) algorithm, the proposed classifier has achieved a rate of 87.7% while the elder rate is 82.9%.

Section: Metaheuristic Algorithmmentioning

confidence: 99%

“…It tries preventing falling into local optima by allocating probabilities for failing movements [49]. Contrary to a simple local search, SA seems to have a greater function, because a worse solution with few possibilities is also accepted [44], [50], [51]. SA has been utilized by various people to solve difficult problems.…”

Section: Simulated Annealing Algorithmmentioning

confidence: 99%

Fish classification using extraction of appropriate feature set

Badawi

2022

“…Among algorithms that are based on water behavior [49], the great deluge (GD) algorithm was firstly proposed by Dueck in 1993 [50], GD uses an acceptance criterion for accepting the neighbor solutions. GD simulates the hill climber path in a great deluge while trying to maintain his feet dry.…”

Section: Great Deluge Algorithmmentioning

confidence: 99%

Cuckoo algorithm with great deluge local-search for feature selection problems

Alsmadi

Alzaqebah

Jawarneh

et al. 2022

Self Cite

Feature selection problem is concerned with searching in a dataset for a set of features aiming to reduce the training time and enhance the accuracy of a classification method. Therefore, feature selection algorithms are proposed to choose important features from large and complex datasets. The cuckoo search (CS) algorithm is a type of natural-inspired optimization algorithms and is widely implemented to find the optimum solution for a specified problem. In this work, the cuckoo search algorithm is hybridized with a local search algorithm to find a satisfactory solution for the problem of feature selection. The great deluge (GD) algorithm is an iterative search procedure, that can accept some worse moves to find better solutions for the problem, also to increase the exploitation ability of CS. The comparison is also provided to examine the performance of the proposed method and the original CS algorithm. As result, using the UCI datasets the proposed algorithm outperforms the original algorithm and produces comparable results compared with some of the results from the literature.

“…Artificial intelligence (AI) techniques have been used in many studies for imaging data acquisition, segmentation and diagnosis for COVID-19 [24]. Where these techniques are previously applied to other artificial intelligence problems and demonstrated their effectiveness in solving them [25]- [34] [35], [36]. Lockdowns are an effective strategy in slowing down the transmission of COVID-19.…”

Section: Introductionmentioning

confidence: 99%

Modified SEIR and machine learning prediction of the trend of the epidemic of COVID-19 in Jordan under lockdowns impact

Alsmadi

2022

Susceptible exposed infectious recovered (SEIR) is a fitting model for coronavirus disease (COVID-19) spread prediction. Hence, to examine the effect of different levels of social distancing on the spreading of the disease, a variable was introduced in the SEIR equations system used in this work. We also used an artificial intelligence approach using a machine learning (ML) method known as deep neural network. This modified SEIR model was applied on the available initial spread data until June 25th, 2021 for the Hashemite Kingdom of Jordan. Without lockdown in Jordan, the analysis demonstrates potential infection to roughly 3.1 million people during the peak of spread approximately 3 months, starting from the date of lockdown (March 21st). Conversely, the present partial lockdowns strategy by the Kingdom was expected to reduce the predicted number of infections to 0.5 million in 9 months period. The analysis also demonstrates the ability of stricter lockdowns to effectively flatten the graph curve of COVID-19 in Jordan. Our modified SEIR and deep neural network (DNN) model were efficient in the prediction of COVID-19 epidemic sizes and peaks. The measures taken to control the epidemic by the government decreased the size of the COVID-19 epidemic.