Fish species recognition using transfer learning techniques

Marine species recognition is the process of identifying various species that help in population estimation and identifying the endangered types for taking further remedies and actions. The superior performance of deep learning for classification is due to the property of estimating millions of parameters that have to be extracted from many annotated datasets. However, many types of fish species are becoming extinct, which may reduce the number of samples. The unavailability of a large dataset is a significant hurdle for applying a deep neural network that can be overcome using transfer learning techniques. To overcome this problem, we propose a transfer learning technique using a pre-trained model that uses underwater fish images as input and applies a transfer learning technique to detect the fish species using a pre-trained Google Inception-v3 model. We have evaluated our proposed method on the Fish4knowledge(F4K) dataset and obtained an accuracy of 95.37%. The research would be helpful to identify fish existence and quantity for marine biologists to understand the underwater environment to encourage its preservation and study the behavior and interactions of marine animals.

A particle swarm optimization levy flight algorithm for imputation of missing creatinine dataset

Clinicians could intervene during what may be a crucial stage for preventing permanent kidney injury if patients with incipient Acute Kidney Injury (AKI) and those at high risk of developing AKI could be identified. This paper proposes an improved mechanism to machine learning imputation algorithms by introducing the Particle Swarm Levy Flight algorithm. We improve the algorithms by modifying the Particle Swarm Optimization Algorithm (PSO), by enhancing the algorithm with levy flight (PSOLF). The creatinine dataset that we collected, including AKI diagnosis and staging, mortality at hospital discharge, and renal recovery, are tested and compared with other machine learning algorithms such as Genetic Algorithm and traditional PSO. The proposed algorithms' performances are validated with a statistical significance test. The results show that SVMPSOLF has better performance than the other method. This research could be useful as an important tool of prognostic capabilities for determining which patients are likely to suffer from AKI, potentially allowing clinicians to intervene before kidney damage manifests.

The extraction of beautiful sound patterns from Sunthorn Phu’s poem using machine learning technique and internal rhyme rule

The melodious poems have been written from the distinctive features of poetry or based on each country's typical style. Especially, Thai poems which composed by the use of specific forming, such as Internal Rhyme to develop melodiousness. The most attractive and well-known poems were composed by a genius Thai poet named Sunthorn Phu. He is a role model for Thai poets. UNESCO honored him as the world’s great poet and the best role model in poetry works. In this article, we proposed extracting 15,796 sentences (Waks) of the beautiful sound patterns of Phra Aphai Mani’s tales by machine learning technology in conjunction with the rules of internal Rhyme Klon-Suphap by using the Apriori Algorithm. The extraction of vowel rhymes separated by a group of Waks including 1) Poem Wak No. 1; 2) Poem Wak No. 2; 3) Poem Wak No. 3; and 4) Poem Wak No. 4. In this article, “Wak” means sentence. The created tool can extract the internal rhyme patterns and the 25 popular pattern vowels. The popular pattern illustrates the melodiousness of the Poem and sets up a standard of how to melodiously compose a poem. Then, the evaluation of the experiments was done by using 144 Waks selected from the extraction of the beautiful patterns and evaluated by the consistency score from 3 experts. The average accuracy score resulted in 95.30%.

Lung cancer medical images classification using hybrid CNN-SVM

Lung cancer is one of the leading causes of death worldwide. Early detection of this disease increases the chances of survival. Computer-Aided Detection (CAD) has been used to process CT images of the lung to determine whether an image has traces of cancer. This paper presents an image classification method based on the hybrid Convolutional Neural Network (CNN) algorithm and Support Vector Machine (SVM). This algorithm is capable of automatically classifying and analyzing each lung image to check if there is any presence of cancer cells or not. CNN is easier to train and has fewer parameters compared to a fully connected network with the same number of hidden units. Moreover, SVM has been utilized to eliminate useless information that affects accuracy negatively. In recent years, Convolutional Neural Networks (CNNs) have achieved excellent performance in many computer visions tasks. In this study, the performance of this algorithm is evaluated, and the results indicated that our proposed CNN-SVM algorithm has been succeed in classifying lung images with 97.91% accuracy. This has shown the method's merit and its ability to classify lung cancer in CT images accurately.

Post-Stroke identification of EEG signals using recurrent neural networks and long short-term memory

Stroke often causes disability, so patients need rehabilitation for recovery. Therefore, it is necessary to measure its effectiveness. An Electroencephalogram (EEG) can capture the improvement of activity in the brain in stroke rehabilitation. Therefore, the focus is on the identification of several post-rehabilitation conditions. This paper proposed identifying post-stroke EEG signals using Recurrent Neural Networks (RNN) to process sequential data. Memory control in the use of RNN adopted Long Short-Term Memory. Identification was provided out on two classes based on patient condition, particularly "No Stroke" and "Stroke". EEG signals are filtered using Wavelet to get the waves that characterize a stroke. The four waves and the average amplitude are features of the identification model. The experiment also varied the weight correction, i.e., Adaptive Moment Optimization (Adam) and Stochastic Gradient Descent (SGD). This research showed the highest accuracy using Wavelet without amplitude features of 94.80% for new data with Adam optimization model. Meanwhile, the feature configuration tested effect shows that the use of the amplitude feature slightly reduces the accuracy to 91.38%. The results also show that the effect of the optimization model, namely Adam has a higher accuracy of 94.8% compared to SGD, only 74.14%. The number of hidden layers showed that three hidden layers could slightly increase the accuracy from 93.10% to 94.8%. Therefore, wavelets as extraction are more significant than other configurations, which slightly differ in performance. Adam's model achieved convergence in earlier times, but the speed of each iteration is slower than the SGD model. Experiments also showed that the optimization model, number of epochs, configuration, and duration of the EEG signal provide the best accuracy settings.

A novel edge detection method based on efficient gaussian binomial filter

Most basic and recent image edge detection methods are based on exploiting spatial high-frequency to localize efficiency the boundaries and image discontinuities. These approaches are strictly sensitive to noise, and their performance decrease with the increasing noise level. This research suggests a novel and robust approach based on a binomial Gaussian filter for edge detection. We propose a scheme-based Gaussian filter that employs low-pass filters to reduce noise and gradient image differentiation to perform edge recovering. The results presented illustrate that the proposed approach outperforms the basic method for edge detection. The global scheme may be implemented efficiently with high speed using the proposed novel binomial Gaussian filter.

Optimized COCOMO parameters using hybrid particle swarm optimization

Software effort and cost estimation are crucial parts of software project development. It determines the budget, time, and resources needed to develop a software project. The success of a software project development depends mainly on the accuracy of software effort and cost estimation. A poor estimation will impact the result, which worsens the project management. Various software effort estimation model has been introduced to resolve this problem. COnstructive COst MOdel (COCOMO) is a well-established software project estimation model; however, it lacks accuracy in effort and cost estimation, especially for current projects. Inaccuracy and complexity in the estimated effort have made it difficult to efficiently and effectively develop software, affecting the schedule, cost, and uncertain estimation directly. In this paper, Particle Swarm Optimization (PSO) is proposed as a metaheuristics optimization method to hybrid with three traditional state-of-art techniques such as Support Vector Machine (SVM), Linear Regression (LR), and Random Forest (RF) for optimizing the parameters of COCOMO models. The proposed approach is applied to the NASA software project dataset downloaded from the promise repository. Comparing the proposed approach has been made with the three traditional algorithms; however, the obtained results confirm low accuracy before hybrid with PSO. Overall, the results showed that PSOSVM on the NASA software project dataset could improve effort estimation accuracy and outperform other models.

ModCOVNN: a convolutional neural network approach in COVID-19 prognosis

COVID-19 is a devastating pandemic in the history of humankind. It is a highly contagious flu that can spread from human to human. For being so contagious, detecting patients with it and isolating them has become the primary concern for healthcare professionals. However, identifying COVID-19 patients with a Polymerase chain reaction (PCR) test can sometimes be problematic and time-consuming. Therefore, detecting patients with this virus from X-ray chest images can be a perfect alternative to the de-facto standard PCR test. This article aims at providing such a decision support system that can detect COVID-19 patients with the help of X-ray images. To do that, a novel convolutional neural network (CNN) based architecture, namely ModCOVNN, has been introduced. To determine whether the proposed model works with good efficiency, two CNN-based architectures – VGG16 and VGG19 have been developed for the detection task. The experimental results of this study have proved that the proposed architecture has outperformed the other two models with 98.08% accuracy, 98.14% precision, and 98.4% recall. This result indicates that proper detection of COVID-19 patients with the help of X-ray images of the chest is possible using machine learning methods with high accuracy. This type of data-driven system can help us to overcome the current appalling situation throughout the world.

Identification of wood defect using pattern recognition technique

This study proposed a classification model for timber defect classification based on an artificial neural network (ANN). Besides that, the research also focuses on determining the appropriate parameters for the neural network model in optimizing the defect identification performance, such as the number of hidden layers nodes and the number of epochs in the neural network. The neural network's performance is compared with other standard classifiers such as Naïve Bayes, K-Nearest Neighbours, and J48 Decision Tree in finding their significant differences across the multiple timber species. The classifier's performance is measured based on the F-measure due to the imbalanced dataset of the timber species. The experimental results show that the proposed classification model based on the neural network outperforms the other standard classifiers in detecting many types of defects across multiple timber species with an F-measure of 84.01%. This research demonstrates that ANN can accurately classify the defects across multiple species while defining appropriate parameters (hidden layers and epochs) for the neural network model in optimizing defect identification performance.

A hybrid ensemble deep learning approach for reliable breast cancer detection

Among the cancer diseases, breast cancer is considered one of the most prevalent threats requiring early detection for a higher recovery rate. Meanwhile, the manual evaluation of malignant tissue regions in histopathology images is a critical and challenging task. Nowadays, deep learning becomes a leading technology for automatic tumor feature extraction and classification as malignant or benign. This paper presents a proposed hybrid deep learning-based approach, for reliable breast cancer detection, in three consecutive stages: 1) fine-tuning the pre-trained Xception-based classification model, 2) merging the extracted features with the predictions of a two-layer stacked LSTM-based regression model, and finally, 3) applying the support vector machine, in the classification phase, to the merged features. For the three stages of the proposed approach, training and testing phases are performed on the BreakHis dataset with nine adopted different augmentation techniques to ensure generalization of the proposed approach. A comprehensive performance evaluation of the proposed approach, with diverse metrics, shows that employing the LSTM-based regression model improves accuracy and precision metrics of the fine-tuned Xception-based model by 10.65% and 11.6%, respectively. Additionally, as a classifier, implementing the support vector machine further boosts the model by 3.43% and 5.22% for both metrics, respectively. Experimental results exploit the efficiency of the proposed approach with outstanding reliability in comparison with the recent state-of-the-art approaches.