---

Aim: The main aim of this study was to assess the efficacy of two important signal processing approaches i.e., wavelet transform and ensemble empirical mode decomposition (EEMD) on the performance of convolutional neural network (CNN).
Materials & Methods: The study was performed in two watersheds i.e., Kasilian and Bar-Erieh watersheds. In the first step, the CNN based runoff modeling was done in its single form i.e., using the original data as input. In the next step the input data was decomposed into several different sub-components i.e., approximation and details using Wavelet transform and Intrinsic Mode Functions (IMFs) using EEMD. Then the decomposed data were imported to the CNN model as input and combined Wavelet-CNN and EEMD-CNN models were provided.
Findings: The results showed that CNN in its single form could not estimate the one day ahead runoff with an acceptable accuracy. CNN in its original form had a moderate performance (with NRMSE of 83 and 66%). However, application of Wavelet transform and EEMD in combination with CNN produced acceptable results. It was shown that Wavelet transform had a higher impact (with NRMSE of 48 and 26%) on the performance of CNN in comparison to EEMD (with NRMSE of 52 and 61%).
Conclusion: This study showed that signal processing approaches can enhance the ability of deep learning methods such as CNN in predicting runoff values for one day ahead. However, the impact of signal processing methods on the performance of deep learning methods are not equal.
 

---

Aims: A new generation of building materials is produced using computing and digital methods. Recombinant building materials have created new perspectives. The main purpose of research is to study, analyze and prioritize the computing of new materials in accordance with environment. The practical purpose of the research is to explain the concept and present strategies based on the use of appropriate materials to achieve the model of "healthy city".
Methods: It is qualitative-quantitative research in terms of methodology. Qualitative steps lead to the explanation of the conceptual framework of the research, and quantitative steps lead to prioritization of the strategies base on online questionnaire. Kappa coefficient has been used to confirm the reliability. A total of 386 questionnaires were collected and the results were analyzed using Spearman correlation.
Findings: Among the ten items extracted about the new materials used, four items with a high degree of significance were obtained: 1- Exposure to direct sunlight, 2- Material health (MSDS), 3- Ease of replacement and replacement, and 4- Degree of moisture absorption, respectively. 
Conclusion: The increasing risk of pandemics shows that the concept of the healthy city is not possible without the computing of new materials; an interdisciplinary field that requires a combined approach of green chemistry, biocomputing and materials-based computing. Computing new materials is an effective way to achieve the healthy city which is in need of "environmental education" and the "healthy city management" skill development.

---

Aims: This study aimed to propose an effective model for estimating soil moisture by integrating the optical trapezoid method with a deep learning Long Short-Term Memory (LSTM) model. The performance of the proposed model was compared with two other methods, i.e., Partial Least Squares (PLS) regression and Group Method of Data Handling (GMDH) multivariate neural network.
Materials & Methods: This study combined the optical trapezoid method with deep learning models to propose an effective model for soil moisture estimation in the Maragheh watershed. A total of 499 in-situ soil moisture data were collected. Relative moisture content was calculated using the optical trapezoid method and imported into the LSTM model, along with other inputs such as spectral indices and DEM-based derived variables. The performance of the mentioned models was assessed both with and without the optical trapezoid method to evaluate its efficacy on the performance of AI models.
Findings: The results demonstrate that the combined model of deep learning LSTM and the optical trapezoid method achieves satisfactory performance, with an R² of 0.95 and a RMSE of 1.7%. The PLS and GMDH methods performed moderately, both without the involvement of the optical trapezoid method and in the combined mode.
Conclusion: This study shows that the optical trapezoid method can improve the performance of deep-learning models in estimating soil moisture. However, considering the significant difference in computational costs among these models, choosing the appropriate model depends on the user's objectives and desired level of accuracy and precision.
 

---

---

Aims: In the indoor space, the temperature and relative humidity are often controlled and even without the use of heating and cooling systems, the temperature and relative humidity changes in the indoor space are less than the outdoor space. Buildings are relatively protected against pollutants of external origin. The main problem of the research is to analyze and investigate the environmental effects of exposure to particles and gases that are released or produced inside the house; And especially the effect of these pollutants on the health of residents.

Methods: The research method of this study is based on logical reasoning. The scientific foundations of the subject are analyzed with a quasi-experimental approach, and the results are presented with the combined modeling method. In terms of methodology, in this research, chemical reactions carried out in indoor spaces are investigated. In this direction, the mechanisms and kinetics of reactions, the characteristics of different surfaces and the effect of factors such as light and temperature
will be investigated.

Findings: A healthy environment is a prerequisite for a healthy life for residents; This is as important in closed spaces as in open and semi-open spaces. Research
findings emphasize the special importance of micropollutants and their impact on residents' health.

Conclusion: Clarifying the importance and role of building materials in indoor air health is one of the most important achievements of this research. An achievement that above all emphasizes the importance of environmental education in promoting healthy buildings, bio-computing and the use of environmentally friendly materials.

---

Since 2010, deep learning has been further developed, and the concept of multi-modality has penetrated into all walks of life. However, it has not been fully researched and applied in college English teaching, so this study modeled and practiced the multimodal teaching method of college English under the deep learning mode and its application. The definitions of modality and medium are first introduced, and then the definition of multimodality in this study is clarified. Then the classification of multimodal transport is expounded. The random forest algorithm is chosen as the main algorithm of this research, and a dynamic multimodal model is established. After that, there was a collaboration with a university and sophomore students were selected for practice. After processing and analyzing the collected data, it was found that in the data sample of 268 students, the number of students who did not study independently accounted for 24%, which indicates that most college students lack interest in learning English. Preliminary tests were also conducted on students' English proficiency throughout the year, and the results showed that the students' English proficiency was at a pass level and the overall English proficiency was weak. Reassessment of students' English proficiency showed that the actual teaching effect of each English proficiency was greater than 85%, and the effectiveness of English teaching in the selected universities was significantly improved. The average score improved by 8 points, indicating that multimodal teaching is scientifically effective
After a semester of multimodal teaching, the English teaching effectiveness of the university selected in this article has significantly improved. The research results indicate that the development of deep computer learning has introduced multimodal concepts into the teaching field, which is very suitable for assisting language learning based on its own advantages.
After a semester of multimodal teaching, the English teaching effectiveness of the university selected in this article has significantly improved. The research results indicate that the development of deep computer learning has introduced multimodal concepts into the teaching field, which is very suitable for assisting language learning based on its own advantages.

---

Cancer is one of the leading causes of death worldwide. Breast cancer is the most common cancer among women and causes a high number of annual deaths. The most reliable method for successful cancer management is accurate and early diagnosis. On the other hand, the lack of timely diagnosis leads to the spread of cancer in the body, making it difficult to treat and control. The gold standard method for breast cancer diagnosis is biopsy. Usually, visual inspection and manual assesement are used to diagnose cancer, where the pathologist examines the histopathology slides under a microscope which is error-prone and time- consuming procedure and requires years of expertise. Therefore, computer-aided diagnosis is essential to help physicians improve the efficiency of interpreting medical images. In this study, we use deep learning models, especially convolutional neural networks (CNNs) to detect whether or not histopathological images are cancerous. The AUC, Precision and F1-score obtained using the pre-trained Incetion-V3 deep neural network are 98.36%, 95.28% and,97.25% respectively, and the same parameters for the pre-trained ResNet-18 deep neural network are equal to 97.90 %, 97.46% and 98.22%. The presented models are able to provide reliable diagnosis results for different morphologies of breast tissues.
 

---

Blood pressure monitoring is a vital component of maintaining overall health. High blood pressure values, as a risk factor, can lead to heart attacks, strokes, and heart and kidney failures. Similarly, low blood pressure values can also be dangerous, causing dizziness, weakness, fainting, and impaired oxygen delivery to organs, resulting in brain and heart damage. Consequently, continuous monitoring of blood pressure levels in high-risk individuals is very important. A Holter blood pressure monitoring device is prescribed for many patients due to its ability to provide long-term and valuable blood pressure data. The pursuit of software techniques and the development of cuffless blood pressure measurement devices, while ensuring patient comfort and convenience, are among the significant challenges that researchers are focusing on. In this study, a deep learning framework based on the UNet network is proposed for continuous blood pressure estimation from photoplethysmography signals. The proposed model was evaluated on the UCI database, involving 942 patients under intensive care, and achieved mean absolute errors of 8.88, 4.43, and 3.32, with standard deviations of 11.01, 6.18, and 4.15, respectively, for systolic, diastolic, and mean arterial blood pressure values. According to the international BHS standard, the proposed method meets grade A criteria for diastolic and mean blood pressure estimations and grade C for systolic blood pressure estimation. The results of this study demonstrate that the suggested deep learning framework has the necessary potential for blood pressure estimation from PPG signals in real-world applications.
 

---

Plant pests and diseases are categorized as one major group threatening to food security. In large farms, accurate and timely human diagnosis is not possible due to time consuming and possible misdiagnosis. Therefore, for immediate, automatic, appropriate and accurate detection of agricultural pests, the use of image processing and artificial intelligence, including deep learning can be very useful. In this study, convolutional neural network models have been developed to identify three common citrus pests in northern Iran such as citrus leafminer, sooty mold and pulvinaria using images of infected leaves, through deep learning methods. For this purpose, Resnet50 and VGG16 architectures are trained as well-known convolutional neural networks, applying the transfer learning method on 1774 images of infected citrus leaves, accumulated from natural and field conditions. In the training phase, data augmentation is used to increase the number of training samples, and to improve the generalizability of the classifiers. For experimental analysis, cross validation strategy is used to evaluate the accuracy of the convolutional neural network. In this strategy, all images are tested without any overlap between training and test sets. Based on the results, the accuracies of Resnet 50 and VGG 16 models are evaluated as 96.05 and 89.34%, respectively. Hence, the Resnet 50 model can convert the above method into a very suitable early warning or consulting system.
 

---

---

   Civil structures may experience unexpected loads and consequently damages during their life cycle. Damage identification has been a challenging inverse problem in structural health monitoring. The main difficulty is characterizing the unknown relation between the measurements and damage patterns. Such damage indicators would ideally be able to identify the existence, location, and severity of damages. In order to solve such problems, biologically inspired soft-computing techniques have gained traction. The most widely used soft-computing method, called neural networks is designed such that it can learn from data without a need of feature design process. Damage pattern can be detected using neural network. A deep unsupervised neural network can recognize patterns and extract features from data. In this paper a methodology is described for global and local health condition assessment of structural systems using vibration response of the structure. The model incorporates Fast Fourier Transform and unsupervised deep Boltzmann machine to extract features from the frequency domain of the recorded signals. Restricted boltzmann machine is a shallow neural network with two layer. First layer of restricted boltzmann machine called input layer and second layer of restricted boltzmann machine called hidden layer.Deep Boltzmann machine created by setting some restricted Boltzmann machine sequentional. Hidden layer of each restricted boltzmann machine is input layer of next restricted boltzmann machine. Each layer of restricted Boltzmann machine extract features form input data Recorded data divided to smaller vectors. Fast fourier transformation used to transform divided vectors into frequency domain.  A benefit of the proposed model is that it does not require costly experimental results to be obtained from a scaled version of the structure to simulate different damage states of the structure and only vibration response of the healthy structure is needed to training deep neural network. The input consists of a set of records obtained from the healthy state of the structure and another set of records with unknown health states. The model extracts information from both healthy and unknown sets to determine the health states of the unknown set. The healthy records are low intensity vibrations of the structure at least in one planar direction in the healthy state in the form of time series signals and The unknown records are low intensity vibrations of the structure on unknown state of health. Ambient vibrations can be due to wind, traffic, or human/pedestrian activities. An appropiate health index is defined and calculated for each part of the structure. The value of this index is between 0 and 1. The closer the value is to 1 the healthier the structure. To evaluate the efficiency of the proposed method a building structures with 35 story has been simulated in OPENSEES. Data collection should be selected appropriately to prevent errors. Obtained result demonstrate that proposed method has about 95 percent efficiency to predict damages and their severity. Different damage state put on due to three earthquakes with different severity. Structural health index calculated after each earthquake. Calculated structural health index demonstrate efficieency of proposed method for detecting damages and severity of damages.

---

^{The human hand is one of the most complex organs of the human body, capable of performing skilled tasks. Manipulation, especially grasping is a critical ability for robots. However, grasping objects by a robot hand is a challenging issue. Many researchers have used deep learning and computer vision methods to solve this problem. This paper presents a humanoid 5-degree-of-freedom robot hand for grasping objects. The robotic hand is made using a 3D printer and 5 servo motors are used to move the fingers. In order to simplify the robotic hand, a tendon-based transmission system was chosen that allows the robot's fingers to flexion and extension. The purpose of this article is to use deep learning algorithm to grasping different objects semi-automatically. In this regard, a convolutional neural network structure is trained with more than 600 images. These images were collected by a camera mounted on the robot's hand. Then, the performance of this algorithm is tested on different objects in similar conditions. Finally, the robot hand is able of successfully grasping with 85% accuracy.}
 

---

Friction angle of soil is a critical parameter in the geotechnical engineering and has a direct impact on the design of various structures, such as retaining walls, slopes, and piles. This parameter plays a crucial role in determining the overall safety and performance of these structures, making it a key player in the geotechnical analysis and design. In recent years, there have been some impressive advancements in the field of artificial neural networks and deep learning models. These advancements have transformed these models into the highly effective tools for predicting the properties and behavior of soil. By using a powerful deep learning model, it is now possible to save a considerable amount of time and money when it comes to estimating and predicting soil properties. In this particular study, a convolutional neural network was developed to predict the peak friction angle of Firuzkuh sand using some soil images and the dry density as the input parameters. The network itself consisted of five consecutive convolutional layers, as well as a pyramid pooling module that utilized four different pooling sizes arranged in parallel. In addition, two fully connected layers were incorporated into the network's design, which enabled it to satisfactorily process the input parameters of the images and the dry densities with respect to the speed and precision. This network converts the soil image into a scalar (number) by using these 5 convolutional layers, the pyramid pooling module and a fully connected layer. Then, this scalar is concatenated with the dry density of the soil, is passed through a fully connected layer, and the peak friction angle of the soil is obtained as an output. For data generation, a total of ten samples of Firuzkuh sand were prepared. These samples had different gradation curves, which are referred to as S1 to S10 specimens. Each soil specimen was compacted at three different dry densities. The peak friction angle associated with the 30 different densities for the 10 different particle size distributions (S1 to S10 specimens) was determined using the direct shear test apparatus. The direct shear test box was 100 ×100 × 25 mm in size. For network training and testing, the soil specimens were spread on a flat surface and 50 photos in different light environments with varying distances of the camera from the soil surface, were taken from each specimen. Since in the network training process, three dry densities were considered for each sample, a total of 1500 images were prepared for the network database. Of these, 1125 photos were used for training and 375 photos were saved for testing the network. The network was trained for 1000 epochs on the training data, and the mean square error after 1000 epochs was reduced to 1.84. The outcome of the assessment conducted on the designed convolutional neural network in this study, using 375 test data, revealed that the network can predict the peak friction angle of Firuzkuh sand by incorporating the image and dry density of the soil as input variables. The total normalized relative error was 3.0%, while the maximum normalized relative error was 10%. This indicates that the network has the ability to quickly predict the peak friction angle of the Firuzkuh sand with a good accuracy.

---

Civil structures inevitably undergo damage over time due to various reasons such as environmental changes, material aging, load variations, and insufficient maintenance. Monitoring these structures, especially aging ones, is crucial to detect damage early on and implement suitable retrofitting measures, ensuring their continued safe and reliable operation without unexpected failures. Consequently, there has been significant research in this field, focusing on damage detection in both simple and complex structures. Health monitoring of highway bridges is essential for achieving a reliable transportation system. The vibration-based damage detection method uses changes in the vibrational properties of structures to detect damages and ensure a healthy state. In this study, the absolute value of the modal flexibility damage index and the modal strain energy damage index simultaneously are utilized to prevent unsafe decisions.
These absolute values of modal strain energy and flexibility damage indexes are utilized as the bases for training deep neural networks (DNNs). These indexes are applied to provide safe decisions and reliable damage evaluation in steel girder of the highway bridges. The convolution neural network (CNN) is utilized for damage quantification estimation. The CNN is one of the deep learning models that can currently be applied in 2D dominant approaches, such as pattern recognition and speech recognition. In addition, these networks can utilize the 1D time domain and vibrational signal data via the convolutional layer. The initial stage of CNN model comprises combined convolutional and pooling layers that apply different filters to extract features. Following this, fully connected layers, similar to a hidden layer of a multilayer perceptron are incorporated. Ultimately, these layers are classified together with a softmax layer. The convolution layer acts as a filter that convolutes the input layer with a set of weights, adding bias and applying an activation function to the outcome. Gradient descent momentum methods (SGDM) can be employed to optimize the parameters in CNN network architecture. SGDM estimates the gradient with high velocity in any dimension. This method mitigates issues such as jittering and saddle points by utilizing high-velocity inconsistent gradient dimensions and the SGD gradients, respectively. Additionally, when the Current gradient approaches zero, the SGDM provides some momentum.
The convolution neural network is trained to utilize damage indexes obtained from numerical simulation of the validated finite element model of the bridge. The damage indexes as the inputs for the neural network, which are achieved from different damage scenarios. Once network training and validation are completed, a well-trained neural network is used to detect, localize, and quantify the intensity of unknown damages. The proposed method overcomes previous damage detection problems such as false positive indications, the unreliability of a single damage index, and insufficient precision in determining the intensity.  The results revealed that the presented method, based on the dual updated damage indexes and CNN, practically and accurately identified unspecified single damages' location and severity in multi-span beams. The new training method of deep neural network systems overcomes some shortcomings in ANN. Moreever, this deep neural network training scheme can reduce the need for huge amounts of input data and enhance the accuracy of network training. The method is capable in predicting single damage scenarios in steel beam.   

 

---

The warming of the urban environment is one of the consequences of unsustainable growth. This research aims to investigate the possibility of modeling the effect of the structural parameters on the city’s surface temperature in the summer season in Tehran. For this purpose, the Landsat-8 image taken in 2018 was used to calculate the surface temperature. In order to determine the study units in this research, the segmentation method was used on the Sentinel-2 image of 2018, and the ratio of the vegetation cover and the separation of built-up areas from non-built-up ones were extracted using this image. The multi-layer perceptron neural network and the convolutional neural network methods were used to model the effect of urban structural parameters on the surface temperature during the summer. The results obtained from random forest feature selection  for the summer indicates that the presence of vegetation and urban uses that include residential and industrial areas, the presence of mixed residential/commercial/administrative areas, and the presence of vegetation affect changes in the urban surface temperature. Further, the information layers of road and population density in this season have an effect on the changing temperature of the earth's surface. Additionally, the results obtained through modeling and t-test of paired samples demonstrate the superiority of the convolutional neural network method, with a root mean square error of 0.61, determination coefficient of 0.62, and 17.75% estimation error, compared to the multi-layer perceptron model, which had 0.82 root mean square error, 0.26 determination coefficient, and 23.34% estimation error.
 

---