Tutorial: Artificial neural networks to analyze single-case experimental designs.

Mercury is a highly poisonous metal which is mostly found in environment. It is considered at the top of the parameters of water quality that requires investigations for planning and management. To understand the status of mercury in the groundwater of Naameh Landfill, Artificial Neural Network (ANN) models were used as indicators of water quality and for the prediction of Mercury. Two types of feed forward networks have been used including multilayer perceptron (MLP) and radial basis function (RBF). A number of different MLP neural networks algorithms and RBF networks trained and developed with reference to pH, EC, TDS, TON, calcium and magnesium to predict Mercury concentration in groundwater. Six scenarios were used to train MLP and RBF networks for choosing the best-fit model for predicting water quality parameters in groundwater of Naameh Landfill. The performances of MLP and RBF models were evaluated by utilizing the coefficient of determination (R2). The results showed that the computed values of R2 for MLP and RBF were 0.791 and 0.881respectively. In addition, the prediction results showed that both types of networks are very good for predicting Mercury concentration in the ground water of our study area. Moreover, the results showed that there are mercury residues for 2 years ahead even if there is no discharge in this place. As a matter of fact, there are no studies that encompass status of heavy metals in municipal solid waste landfills in Lebanon or neighboring countries using ANN models. Thus, this study can be described as unique as it demonstrated a 9 year groundwater data (2011-2019), presented data and projected data for two upcoming years. This is crucial especially in the continual waste crisis that Lebanon is facing and the absence of sustainable disposal practices. This data is a rigid base and a solid reference for developing adequate solutions to prevent future contamination of groundwater with its associated negative impacts on the health and wellbeing of individuals.

Burnup characteristics and performance of boron nitride and boron coated urania and urania-gadolinia fuels

Rutherford backscattering (RBS) is a nondestructive, fully quantitative technique for accurately determining the compositional depth profile of thin films. The inverse RBS problem, which is to determine from the data the corresponding sample structure, is, however, in general ill posed. Skilled analysts use their knowledge and experience to recognize recurring features in the data and relate them to features in the sample structure. This is then followed by a detailed quantitative analysis. We have developed an artificial neural network (ANN) for the same purpose, applied to the specific case of Ge-implanted Si. The ANN was trained with thousands of constructed spectra of samples for which the structure is known. It thus learns how to interpret the spectrum of a given sample, without any knowledge of the physics involved. The ANN was then applied to experimental data from samples of unknown structure. The quantitative results obtained were compared with those given by traditional analysis methods and are excellent. The major advantage of ANNs over those other methods is that, after the time-consuming training phase, the analysis is instantaneous, which opens the door to automated on-line data analysis. Furthermore, the ANN was able to distinguish two different classes of data which are experimentally difficult to analyze. This opens the door to automated on-line optimization of the experimental conditions.

Single‐case experimental designs (SCEDs) may offer a reliable and internally valid way to evaluate technology‐enhanced learning (TEL). A systematic review was conducted to provide an overview of what, why and how SCEDs are used to evaluate TEL. Accordingly, 136 studies from nine databases fulfilling the inclusion criteria were included. The results showed that most of the studies were conducted in the field of special education focusing on evaluating the effectiveness of computer‐assisted instructions, video prompts and mobile devices to improve language and communication, socio‐emotional, skills and mental health. The research objective of most studies was to evaluate the effects of the intervention; often no specific justification for using SCED was provided. Additionally, multiple baseline and phase designs were the most common SCED types, with most measurements in the intervention phase. Frequent data collection methods were observation, tests, questionnaires and task analysis, whereas, visual and descriptive analysis were common methods for data analysis. Nearly half of the studies did not acknowledge any limitations, while a few mentioned generalization and small sample size as limitations. The review provides valuable insights into utilizing SCEDs to advance TEL evaluation methodology and concludes with a reflection on further opportunities that SCEDs can offer for evaluating TEL. Practitioner notes What is already known about this topic SCEDs use multiple measurements to study a single participant over multiple conditions, in the absence and presence of an intervention SCEDs can be rigorous designs for evaluating behaviour change caused by any intervention, including for testing technology‐based interventions. What this paper adds Reveals patterns, trends and gaps in the use of SCED for TEL. Identifies the study disciplines, EdTech tools and outcome variables studied using SCEDs. Provides a comprehensive understanding of how SCEDs are used to evaluate TEL by shedding light on methodological techniques. Enriches insights about justifications and limitations of using SCEDs for TEL. Implications for practice and/or policy Informs about the use of the rigorous method, SCED, for evaluation of technology‐driven interventions across various disciplines. Contributes therefore to the quality of an evidence base, which provides policymakers, and different stakeholders a consolidated resource to design, implement and decide about TEL.

In order to enhance the acoustical performance of gun mufflers, a multi-chamber muffler internally inserting with expansion cones and perforated tubes ducts is presented. Because of the complicated geometry of gun muffler, traditional analytic method used in predicting a muffler’s acoustical performance is difficult; therefore, a finite element method using the COMSOL software is adopted to predict the gun muffler’s sound transmission loss. Moreover, because an objective function (or fitness function) is needed during the optimization process, a simplified mathematical model using Artificial Neural Network (ANN) is used. Here, a polynomial objective function is established by inputting the muffler’s geometric design parameters and the related simulated Sound Transmission Loss (STL) (run on the COMSOL) via the Artificial Neural Network. Furthermore, Genetic Algorithm (GA), an optimizer, is linked to the simplified mathematical model to maximize the gun muffler’s acoustical performance. To pursue a maximal STL at the targeted tones, the geometric parameters of cone’s horizontal length (L1) and first cone’s span (L2) is optimally adjusted. Results demonstrates the STL of gun muffler at the specified frequencies of 1000, 2000, and 4000 Hz can be improved from 15.8 dB, 72.6 dB, 184.8 dB to 18.2 dB, 112.6 dB, and 416.3 dB, respectively. The paper aims to provide an optimal design method of gun muffler using Finite Element Method (FEM), Artificial Neural Network, and Genetic Algorithm. Consequently, the simulated results reveal that the optimally shaped gun muffler can efficiently depress the gun’s shooting noise.

<span>An extensive review of the artificial neural network (ANN) is presented in this paper. Previous studies review the artificial neural network (ANN) based on the approaches (algorithms) used or based on the types of the artificial neural network (ANN). The presented paper reviews the ANN based on the goal of the ANN (methods, and layers), which become the main objective of this paper. As a famous artificial intelligent model, ANN mimics the human nervous system in handling the information transmited by different nodes (also known as neurons) in this model. These nodes are stacked in layers and work collectively to bring about solution to complex problems. Numerous structures exist for ANN and each of these structures is designed to addressa a specific task. Basically, the ANN architecture is comprised of 3 different layers wherein the first layer rpresents the input layer that consist of several input nodes that represent the input parameterfor the model. The hidden layer is te second layer and consists of a hidden layer of neurons. The neurons in this layer are directly connected to the neurons in the output layer. The third layer is the output layer which is the models’ response layer. The output layer neurons have the activation functions for the calculation of the ANN final output. The connection between the nodes in the ANN model is mediated by synaptic weights. This paper is a comprehensive study of ANN models and their layers.</span>

Wind power plays a vital role in the electricity generation of many countries, including Ethiopia. It serves as a valuable complement to hydropower during the dry season, and its affordability is crucial for the growth of industrial centers. However, accurately estimating wind energy poses significant challenges due to its random nature, severe variability, and dependence on wind speed. Numerous techniques have been employed to tackle this problem, and recent research has shown that Artificial Neural Network (ANN) models excel in prediction accuracy. This study aims to assess the effectiveness of different ANN network types in estimating the monthly average daily wind power at Adama Wind Farm I. The collected data was divided into three sets: training (70%), testing (15%), and validation (15%). Four network types, namely Feedforward Backpropagation (FFBP), Cascade Feedforward Backpropagation (CFBP), Error Backpropagation (EBP), and Levenberg–Marquardt (LR), were utilized with seven input parameters for prediction. The performance of these networks was evaluated using Mean Absolute Percentage Error (MAPE) and R-squared (R2). The EBP network type demonstrated exceptional performance in estimating wind power for all wind turbines in Groups GI, GII, and GIII. Additionally, all proposed network types achieved impressive accuracy levels with MAPE ranging from 0.0119 to 0.0489 and R2 values ranging from 0.982 to 0.9989. These results highlight the high predictive accuracy attained at the study site. Consequently, we can conclude that the ANN model’s network types were highly effective in predicting the monthly averaged daily wind power at Adama Wind Farm I. By leveraging the power of ANN models, this research contributes to improving wind energy estimation, thereby enabling more reliable and efficient utilization of wind resources. The findings of this study have practical implications for the wind energy industry and can guide decision-making processes regarding wind power generation and integration into the energy mix.

The attack that occurred recently involved the utilization of malicious software, commonly referred to as malware, along with advanced techniques such as machine learning, specifically deep learning, code transformation, and polymorphism. This makes it harder for cyber experts to detect malware using traditional analysis methods. In view of the low accuracy and high false positive rate of traditional malware detection methods, this research proposes a fine-tuned deep learning model with a novel dataset that is compared with ANN, Support Vector Machine (SVM), random forest (RF), K-Nearest Neighbourhood (KNN) classifiers. Converting a malware code into an image could allow users to effectively identify the presence of malware, even if the original code is modified by the creator. This is due to the fact that the attributes of images remain unchanged, allowing for reliable identification. So, researchers used deep learning technology to detect malware, like detecting malaria from red blood cells. The deep learning model found that a more detailed analysis of malware data sets, focusing on RGB and greyscale images, is needed. These data sets currently rely on publicly available data, but the accuracy of the traditional model could be a lot higher. It also produces many false positive results. The main goal is to create a new data set and model using malware images to identify and categorize malware using deep learning without relying on existing image detection and transfer learning models. The researcher adjusted different hyper parameters, like the number of neurons, filters, stride, hidden units, layers, learning rate, batch size, activation function, optimizer, and epochs. Identifying and correcting issues in models, improving their clarity, stability, and fairness, as well as debugging and monitoring them, is a challenging task. To eliminate this obstacle, assess the model's behaviour and performance by employing various methods such as logging, profiling, testing, visualization, and model clarity. To overcome the challenges posed by the electricity shutdown, we utilized Google's cloud-based GPU and Python 3.7 language to conduct the experiment and train the model. Kali Linux is an operating system that can automatically encrypt file systems and has a lower chance of crashing the system due to malware in a virtual sandbox. The researcher used techniques like early stopping and cross-validation to prevent over fitting and assess generalization in addition to monitoring and evaluating the model's behaviour and performance. The researcher used different methods like L1 and L2 regularization, dropout, and batch normalization to improve the model's performance and avoid over fitting. The binary portable executable (PE) malware dataset is collected from Kaggle, Malimg, Virusshare, Malvis, MS Big2015, and VX-underground and finally converted to greyscale and RGB images to create a novel dataset to fill the lack of image dataset. The raw dataset was then rescaled to a 128x128 greyscale and RGB (red, green, blue) image and flattened to 1024-byte vector images input into convolution neural network (CNN) interpolation to extract features for malware detection. The newly acquired dataset is utilized as an input for the innovative DL algorithms in order to create a tailor-made model capable of accurately predicting malware. The findings in this customized CNN model by fine-tuning hyper-parameters with the three-channel RGB dataset outperformed a greyscale dataset with an accuracy of 98.7% and error rate of 1.3% in current malware compared with other artificial neural network (ANN), ML algorithms such as Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and also Random Forest (RF) models. The proposed approach is compatible with all operating systems (Windows, Linux, and Mac) and can identify different types of malwares, such as packed, polymorphic, obfuscated, metamorphic, or variations of a malware family. There are some limitations to the shortage of malware image datasets and computational costs for fine-tuning hyper parameters in the whole model. Furthermore, the proposed approach detects malware and groups it into families without using common techniques like disassembly, decompilation, de-obfuscation, or running malicious code in a virtual environment.

The precise assessment and evaluation of global solar radiation (GSR) is crucial for designing effective solar energy systems. However, in developing countries like Ethiopia, the cost and maintenance of measuring devices are inadequate. As a result, researchers have explored alternative methods such as empirical models to estimate GSR. This article proposes using artificial neural networks (ANN) to predict daily and monthly averaged horizontal GSR (HGSR) around Fiche town of Ethiopia, using various network types. The input variables were divided into training (70%) and testing (30%) sets to evaluate the network types, with the sigmoid function used as the activation function at the hidden layer and a linear function for the output layer. The predicted mean daily and monthly HGSR ranges from 3.282 kWh/m2/day to 6.967 kWh/m2/day and 4.628 kWh/m2 to 6.613 kWh/m2 respectively. The values obtained were compared to those provided by NASA observation data and were found to be within acceptable limits. Statistical metrics of MAPE, MSE, and RMSE show that CFBP, FFBP, LR, and EBP are better network types for estimating mean daily HGSR, while EBP, FFBP, CFBP, and LR are better for estimating mean monthly HGSR. Overall, all network types of ANN accurately predicted the mean daily and monthly HGSR. In general, the findings of this study indicated that the location had promising solar energy for producing electricity and for various uses.

In the present study, deep learning neural network model has been employed in many engineering problems including heat transfer prediction. The main consideration of this document is to predict the performance of the boiling heat transfer in helical coils under terrestrial gravity conditions and compare with actual experimental data. Total of 877 data sample has been used in the present neural model. Artificial new Neural Network (ANN) model developed in Python environment with Multi-layer Perceptron (MLP) using four parameters (helical coils dimensions, mass flow rate, heating power, inlet temperature) and one parameter (outlet temperature) has been used in the input layer and output layer in order. Levenberg-Marquardt (LM) algorithm using L2 Regularization to find out the optimal model. A typical feed-forward neural network model composed of three layers, with 30 numbers of neurons in each hidden layer, has been found as optimal based on statistical error analysis. The 4-30-30-1 neural model predicts the characteristics of the helical coil with the accuracy of 98.16 percent in the training stage and 96.68 percent in the testing stage. The result indicated that the proposed ANN model successfully predicts the heat transfer performance in helical coils and can be applied for others operation concerned with heat transfer prediction for future works

The quality of the nasopharyngeal carcinoma (NPC) treatment plans evaluation using three types of artificial neural networks (ANNs) are instructed by three different training algorithms. Three ANNs including Elman (ANN-E), feed-forward (ANN-FF), and pattern recognition (ANN-PR) were trained by using three different models, that is, leave-one-out (Train-loo), random selection (Train-random), and user defined (Train-user) method. One hundred sets of NPC treatment plans were collected as the input data of the neural networks. The conformal index (CI) and homogeneity index (HI) were used as the characteristic values and also to train the neurons. Four grades (A, B, C, and D) were classified in degrading order. The over-training issue is considered between the train data and the number of neurons. The receiver operating characteristic (ROC) curves were obtained to evaluate the performed accuracies. The optimal numbers of neurons for ANN-E, ANN-FF, and ANN-PR, in the loo method are 6, 24, and 9; in the random-selection method, they are 26, 22, and 4; and in the user-defined method they are 12, 8, and 11 neurons, respectively. The optimal size of train data is 92% of total inputs in the cases of ANN-E and ANN-FF and 76% in the case of ANN-PR. The networks with higher accuracy are ANN-PR-loo (93.65 ± 3.60%), ANN-FF-loo (88.05 ± 5.84%), and ANN-E-loo (87.55 ± 5.86%), respectively. The networks with shorter training time are ANN-PR-random (0.55 ± 0.11 s), ANN-PR-user (0.59 ± 0.08 s), and ANN-PR-user (1.07 ± 0.16 s), respectively. The ROC curves show that the ANN-PR-loo approach has the highest sensitivity, which is 99%. ANN-PR-loo reduces the amount of trail-and-error during the iterative process of generating inverse treatment plans. It is concluded that the ANN-PR-loo is an excellent model among the three for classifying the quality of treatment plans for NPC. Key words: Artificial neural networks (ANNs), dose-volume histogram (DVH), intelligence system, nasopharyngeal carcinoma (NPC).

Unlike calculation of scour depth around of a single pier, estimation of scour depth around group piers is a complex problem. In this research, four types of artificial neural networks (ANNs) were applied multi layer perceptron (MLP), radial basis function (RBF), neuro fuzzy inference system (ANFIS), and support vector machine (SVM). The inputs of ANNs were coordinates of considered points in the channel (X, Y), size of pier, flow depth, flow discharge, flow velocity, and critical velocity for inception of sediment transport. The trained methods were momentum and Levenberg–Marquardt (LM) training methods. Also, genetic algorithm (GA) was applied for optimization of MLP and RBF. Two group piers were used (three circular piers and three square piers) in a channel with stable flow conditions, scouring of clear water, and uniform bed particles (with D50 = 1.31 mm). Outputs of different ANNs (scour depth) were compared with observed data using of performance criteria correlation coefficient (R), mean square error (MSE), and mean absolute error (MAE). For circular piers, between square piers and behind of gear square pier, the best ANN is RBF-GA, while in front of first square pier, the best ANN is MLP-GA. The best ANNs have two hidden layers, and their training method is the Levenberg–Marquardt (LM). The values of R, MSE, and MAE of RBF-GA are 0.997, 1.66 mm2, and 0.9 mm, and the values of R, MSE, and MAE of MLP-GA are 0.997, 2.55 mm2, and 1.16 mm. Also, the sensitive analysis shows that threshold velocity (Uc) is the most effective factor on scour depth

Factors Affecting Performance of Parametric and Non-parametric Models for Daily Traffic Forecasting

Cabreira, A. G., Tripode, M., and Madirolas, A. 2009. Artificial neural networks for fish-species identification. – ICES Journal of Marine Science, 66: 1119–1129. Acoustic fish detection is a valuable tool for the continuous monitoring of fish schools. However, changes in species composition or mixed multispecies situations still complicate the analysis of acoustic data. Validation of echo recordings is usually accomplished by trawling, but only at point locations. However, species proportions and size distributions in the catch can be biased because of gear selectivity and fish avoidance. In this paper, techniques involving training and testing of artificial neural networks (ANNs) are applied for the automatic recognition and classification of digital echo recordings of schools in the Southwest Atlantic. Energetic, morphometric, and bathymetric school descriptors were extracted from the echo-recordings as the input for the ANNs. Several pelagic and demersal fish species known to aggregate into schools were considered, including anchovy, rough scad, longtail hoki, sprat, and blue whiting. Different types of ANNs were tested. Best performances were obtained by levelling the input data (number of schools) per species. Correct classification rates up to 96% were obtained, depending on the species, type of network, and the number of school descriptors utilized. Some of these species inhabit areas geographically distant from each other. Hence, the contribution of the school position as a descriptor was investigated. By deleting the geographical location of the schools from the ANN input data, the average performance decreased to some extent but was still satisfactory, proving the networks were able usually to recognize fish species based only on the intrinsic characteristics of the school. The results have encouraged further testing of this method as a useful tool for scrutinizing echograms.

Making Artificial Brains: Components, Topology, and Optimization.