Architecture Selection Research Articles

An Integrated Method for Selecting Architecture Alternatives and Reconfiguration Options Towards System-of-Systems Resilience

Delivering persistent values in a dynamic environment is a challenging but imperative capability for a system-of-systems (SoS). Practitioners in the SoS and defense domains are exploring the benefits of the operational-level reconfiguration strategies via new operational concepts such as mosaic warfare. However, an architecture design that allows reconfiguration is also a crucial task, but has not yet received adequate attention, not to mention accounting for the mutual impact between architecture design alternatives and reconfiguration options. Therefore, this paper proposes an integrated method that can select the architecture with a specific inherent structure in the design phase that supports dynamic reconfiguration during the operational phase. This method firstly builds a structural framework that connects architecture design and reconfiguration, and identifies the enablers for SoS architecture reconfiguration. After developing an SoS effectiveness evaluator, the method constructs an integrated multi-objective formulation for the initial architecture selection and reconfiguration process, and provides a solution algorithm based on a fast non-dominated sorting genetic algorithm. An application to an air and missile defense SoS illustrates the effectiveness of the proposed method. The generated Pareto optimal set of solutions that have non-dominated recoverability and survivability provide useful decision support for SoS composition and initial architecture configuration, based upon which an SoS can also respond effectively to disruptions by computing the reconfiguration decisions.

Machine Learning in Brain Tumor Diagnosis: Assessing the Efficacy of Diverse Methods

Background: Brain tumors constitute a critical and potentially life-threatening condition that requires accurate and timely diagnosis. In recent years, machine learning (ML) approaches have emerged as powerful tools for assisting radiologists and clinicians in identifying and classifying tumors on medical imaging. While numerous ML methods, including conventional machine learning algorithms and deep learning-based models, have been explored, a comprehensive analysis of their efficacy in detecting, segmenting, and classifying brain tumors remains essential. Methods: We conducted a systematic evaluation of diverse ML methods used in brain tumor diagnosis. We first identified and collated relevant studies from major scientific databases, focusing on image-based applications such as magnetic resonance imaging (MRI). The methods included pre-processing pipelines, feature extraction techniques, and both supervised and unsupervised learning approaches. We then compared these methods based on standard metrics, including accuracy, sensitivity, specificity, and F1-score, to gain insights into their relative performance. Furthermore, we applied representative algorithms (such as support vector machines, convolutional neural networks, and random forests) to an open-access brain tumor imaging dataset to evaluate their performance and compare empirical findings. Results: Results indicated that deep learning models, particularly convolutional neural networks, consistently outperformed traditional ML models across various performance metrics. In particular, automated feature extraction in deep learning approaches proved pivotal in capturing nuanced information such as tumor shape and heterogeneity. Conventional algorithms still demonstrated merit when dataset sizes were limited or when computational resources were constrained. Additionally, various data augmentation techniques improved the robustness and generalizability of ML models in situations with scarce annotated data. Conclusion: Our findings suggest that deep learning-based methods hold the greatest potential for accurate and efficient brain tumor diagnosis, particularly when coupled with robust datasets and high-quality imaging. Nonetheless, careful selection of model architecture, training strategies, and validation protocols remains paramount to ensure reliable clinical translation.

The effectiveness of fire detection with convolutional neural networks

The article presents problems related to the detection of fire phenomena using convolutional neural network techniques. The main issue described in the article focuses on determining the precision of flame detection depending on lighting conditions and the selection of CNN architecture. The types of neural networks tested are primarily SSD architectures, which, with their speed of operation and energy consumption, are the most common in mobile applications. The study shows which of the neural network architectures used have the highest average precision in detecting the fire phenomenon. The selection of networks under testing was analyzed in terms of the speed of the algorithm and its precision. Four pre-trained neural network models were used during the testing of two training bases. The complexity of each model directly affected the training time of the model, which oscillated between 2-8 [h], and the precision achieved.

An automated diagnosis & classification of dengue using advance artificial neural network

In this research, an advanced artificial neural network (ANN)-based approach for prognosis and classification of dengue disease is presented. Dengue diagnosis usually relies on clinical assessment; subsequently, there might be a high probability of misdiagnoses due to the complex hodgepodge of symptoms of dengue with other vector-borne diseases. It is needed to develop a system that can help doctors to identify dengue disease much faster than the manual system, which takes longer time and more cost to detect the diseases. Such a system may help users to take an early action before it becomes serious. The study involved three phases: pre-processing, neural network processing, and post-processing. In the pre-processing phase, data were gathered from three high-severity dengue outbreak sites in Pakistan (Benazir Bhutto Hospital, CITI Lab Rawalpindi, and Meo Hospital Lahore) where the dengue outbreak severity was high during the year of 2011. After cleaning and normalizing, 768 samples were obtained, split into 560 for training and 208 for testing. Nineteen critical parameters were selected with input from physicians, medical staff, and prior research. This study presents a supervised feed-forward neural network (FFNN) with two hidden layers, trained using backpropagation and optimized with the Levenberg-Marquardt algorithm, achieving nearly 100% accuracy, minimal runtime, and a very low MSE (0.00000000000032521). The model reached 100% sensitivity, 99.8% precision, and 98.7% specificity, surpassing prior results in dengue diagnosis. The findings support improved diagnostic accuracy and confidence, providing a framework for physicians. Key factors in achieving optimal results include careful selection of architecture, data normalization, parameter selection, and critical evaluation.

Trust driven On-Demand scheme for client deployment in Federated Learning

Containerization technology plays a crucial role in Federated Learning (FL) setups, expanding the pool of potential clients and ensuring the availability of specific subsets for each learning iteration. However, doubts arise about the trustworthiness of devices deployed as clients in FL scenarios, especially when container deployment processes are involved. Addressing these challenges is important, particularly in managing potentially malicious clients capable of disrupting the learning process or compromising the entire model. In our research, we are motivated to integrate a trust element into the client selection and model deployment processes within our system architecture. This is a feature lacking in the initial client selection and deployment mechanism of the On-Demand architecture. We introduce a trust mechanism, named “Trusted-On-Demand-FL”, which establishes a relationship of trust between the server and the pool of eligible clients. Utilizing Docker in our deployment strategy enables us to monitor and validate participant actions effectively, ensuring strict adherence to agreed-upon protocols while strengthening defenses against unauthorized data access or tampering. Our simulations rely on continuous user behavior datasets, deploying an optimization model powered by a genetic algorithm to efficiently select clients for participation. By assigning trust values to individual clients and dynamically adjusting these values, combined with penalizing malicious clients through decreased trust scores, our proposed framework identifies and isolates harmful clients. This approach not only reduces disruptions to regular rounds but also minimizes instances of round dismissal, Consequently enhancing both system stability and security.

Neural Architecture Selection as a Nash Equilibrium With Batch Entanglement.

Modeling the architecture search process on a supernet and applying a differentiable method to find the importance of architecture are among the leading tools for differentiable neural architectures search (DARTS). One fundamental problem in DARTS is how to discretize or select a single-path architecture from the pretrained one-shot architecture. Previous approaches mainly exploit heuristic or progressive search methods for discretization and selection, which are not efficient and easily trapped by local optimizations. To address these issues, we formulate the task of finding a proper single-path architecture as an architecture game among the edges and operations with the strategies "keep" and "drop" and show that the optimal one-shot architecture is a Nash equilibrium of the architecture game. Then, we propose a novel and effective approach for discretizing and selecting a proper single-path architecture, which is based on extracting the single-path architecture that associates the maximal coefficient of the Nash equilibrium with the strategy "keep" in the architecture game. To further improve the efficiency, we employ a mechanism of entangled Gaussian representation of mini-batches, inspired by the classic Parrondo's paradox. If some mini-batch formed uncompetitive strategies, the entanglement of mini-batches would ensure the games be combined and, thus, turn into strong ones. We conduct extensive experiments on benchmark datasets and demonstrate that our approach is significantly faster than the state-of-the-art progressive discretizing methods while maintaining competitive performance with higher maximum accuracy.

Implementation of Artificial Neural Networks on Field-Programmable Gate Arrays

Implementing Artificial Neural Networks (ANNs) on Field-Programmable Gate Arrays (FPGAs) provides a promising solution for achieving high-performance, low-latency, and energy-efficient computations in complex tasks. This paper investigates the methodology for mapping ANNs onto FPGAs, focusing on critical aspects such as architecture selection, hardware design, and optimization techniques. By harnessing the parallel processing capabilities and reconfigurability of FPGAs, neural network computations are significantly accelerated, making them ideal for real-time applications like image processing and embedded systems. The implementation process addresses key considerations, including fixed-point arithmetic, memory management, and dataflow optimization, while employing advanced techniques such as pipelining, quantization, and pruning. The research compares the accuracy and performance speedup of ANNs on CPUs versus FPGAs, revealing that FPGA-based simulations are 4680 times faster than CPU-based simulations using MATLAB, without compromising prediction accuracy.

Algoritma Deep Learning Untuk Pengenalan Gambar Jenis Daun

Image processing is a branch of informatics that deals with transforming one image into another using certain techniques. Deep learning algorithms have become one of the effective approaches to solving this problem. In this paper, we propose a deep learning algorithm that uses Convolutional Neural Networks (CNN) architecture to recognize leaf types based on a given leaf image. We outline the main steps in model development, including data pre-processing, CNN architecture selection, and model training. The experimental results show that the proposed deep learning algorithm can achieve a high level of accuracy in leaf-type image recognition. In this study, the CNN method is used to identify and classify objects in digital images, specifically leaves. The dataset used consists of 33 leaf classes, with a division of 16,500 data for training, 3,300 for validation, and 1,650 for testing. The training and validation processes were carried out in as many as 150 epochs, which resulted in the highest accuracy of 94% with the lowest loss of 0.28. While in the testing process, the accuracy value obtained reached 84%. The researched method, which integrates CNN with data augmentation and transfer learning, demonstrated superior performance with an accuracy of 94% in leaf type recognition. This outperforms other methods that rely solely on traditional CNN or do not utilize augmentation and transfer learning, which generally achieve lower accuracy rates. The combination of these techniques enables more robust feature extraction and better generalization, leading to more accurate and reliable classification results compared to other approaches.

Fast machine-learning-enabled size reduction of microwave components using response features

Achieving compact size has emerged as a key consideration in modern microwave design. While structural miniaturization can be accomplished through judicious circuit architecture selection, precise parameter tuning is equally vital to minimize physical dimensions while meeting stringent performance requirements for electrical characteristics. Due to the intricate nature of compact structures, global optimization is recommended, yet hindered by the excessive expenses associated with system evaluation, typically conducted through electromagnetic (EM) simulation. This challenge is further compounded by the fact that size reduction is a constrained problem entailing expensive constraints. This paper introduces an innovative method for cost-effective explicit miniaturization of microwave components on a global scale. Our approach leverages response feature technology, formulating the optimization problem based on a set of characteristic points derived from EM-analyzed responses, combined with an implicit constraint handling approach. Both elements facilitate handling size reduction by transforming it into an unconstrained problem and regularizing the objective function. The core search engine employs a machine-learning framework with kriging-based surrogates refined using the predicted improvement in the objective function as the infill criterion. Our algorithm is demonstrated using two miniaturized couplers and is shown superior over several benchmark routines, encompassing both conventional (gradient-based) and population-based procedures, alongside a machine learning technique. The primary strengths of the proposed framework lie in its reliability, computational efficiency (with a typical optimization cost ranging from 100 to 150 EM circuit analyses), and straightforward setup.

A statistical modelling approach to feedforward neural network model selection

Feedforward neural networks (FNNs) can be viewed as non-linear regression models, where covariates enter the model through a combination of weighted summations and non-linear functions. Although these models have some similarities to the approaches used within statistical modelling, the majority of neural network research has been conducted outside of the field of statistics. This has resulted in a lack of statistically based methodology, and, in particular, there has been little emphasis on model parsimony. Determining the input layer structure is analogous to variable selection, while the structure for the hidden layer relates to model complexity. In practice, neural network model selection is often carried out by comparing models using out-of-sample performance. However, in contrast, the construction of an associated likelihood function opens the door to information-criteria-based variable and architecture selection. A novel model selection method, which performs both input- and hidden-node selection, is proposed using the Bayesian information criterion (BIC) for FNNs. The choice of BIC over out-of-sample performance as the model selection objective function leads to an increased probability of recovering the true model, while parsimoniously achieving favourable out-of-sample performance. Simulation studies are used to evaluate and justify the proposed method, and applications on real data are investigated.

Selection of AI Architecture for Autonomous Vehicles Using Complex Intuitionistic Fuzzy Rough Decision Making

The advancement of artificial intelligence (AI) has become a crucial element in autonomous cars. A well-designed AI architecture will be necessary to attain the full potential of autonomous vehicles and will significantly accelerate the development and deployment of autonomous cars in the transportation sector. Promising autonomous cars for innovating modern transportation systems are anticipated to address many long-standing transporting challenges related to congestion, safety, parking, and energy conservation. Choosing the optimal AI architecture for autonomous vehicles is a multi-attribute decision-making (MADM) dilemma, as it requires making a complicated decision while considering a number of attributes, and these attributes can have two-dimensional uncertainty as well as indiscernibility. Thus, in this framework, we developed a novel mathematical framework “complex intuitionistic fuzzy rough set” for tackling both two-dimensional uncertainties and indiscernibility. We also developed the elementary operations of the deduced complex intuitionistic fuzzy rough set. Moreover, we developed complex intuitionistic fuzzy rough (weighted averaging, ordered weighted averaging, weighted geometric, and ordered weighted geometric) aggregation operators. Afterward, we developed a method of MADM by employing the devised operators and investigated the case study “Selection of optimal AI architecture for autonomous vehicles” to reveal the practicability of the devised method of MADM. Finally, to reveal the dominance and supremacy of our proposed work, a benchmark dilemma was used for comparison with various prevailing techniques.

Performance evaluation of containers for low-latency packet processing in virtualized network environments

Packet processing in current network scenarios faces complex challenges due to the increasing prevalence of requirements such as low latency, high reliability, and resource sharing. Virtualization is a potential solution to mitigate these challenges by enabling resource sharing and on-demand provisioning; however, ensuring high reliability and ultra-low latency remains a key challenge. Since bare-metal systems are often impractical because of high cost and space usage, and the overhead of virtual machines (VMs) is substantial, we evaluate the utilization of containers as a potential lightweight solution for low-latency packet processing. Herein, we discuss the benefits and drawbacks and encourage container environments in low-latency packet processing when the degree of isolation of customer data is adequate and bare metal systems are unaffordable. Our results demonstrate that containers exhibit similar latency performance with more predictable tail-latency behavior than bare metal packet processing. Moreover, deciding which mainboard architecture to use, especially the cache division, is equally vital as containers are prone to higher latencies on more shared caches between cores especially when other optimizations cannot be used. We show that this has a higher impact on latencies within containers than on bare metal or VMs, resulting in the selection of hardware architectures following optimizations as a critical challenge. Furthermore, the results reveal that the virtualization overhead does not impact tail latencies.

Dual-mask: Progressively sparse multi-task architecture learning

Multi-task architecture learning has achieved significant success by learning optimal sharing architectures for different tasks. However, previous works to learn branched architectures for different tasks can sometimes lead to unsatisfying multi-task performance, as not all detailed branches are relevant to a specific task. Task-relevant architectures can be sparse, including only partial channels or layers in the entire architecture (i.e., a sub-network). In addition, most previous works rely on a heuristic architecture selection procedure that could not support continuous architecture optimization. To this end, in this paper, we propose dual-mask, a progressively sparse multi-task architecture learning method. Starting with a task-free architecture, it identifies the informative features along two-level, channels and layers, for each task, while suppressing conflicting or noisy parts in a differentiable manner, so that better task-specific sub-networks are captured. Specifically, the channel and layer selection modules produce respective hybrid binary and real value masks, designed to pick salient channels and layers for each task, respectively. To jointly optimize masks with model parameters, we propose an importance-guided relaxation method for solving the stochastic binary optimization problem, after which the interference or noise parts can be pruned by masks. Additionally, a progressive training strategy with continuation is provided that gradually sparsity the task-specific sub-networks. Experiments show that dual-mask achieves superior performance than SOTA multi-task methods.

Transformers for Molecular Property Prediction: Lessons Learned from the Past Five Years.

Molecular Property Prediction (MPP) is vital for drug discovery, crop protection, and environmental science. Over the last decades, diverse computational techniques have been developed, from using simple physical and chemical properties and molecular fingerprints in statistical models and classical machine learning to advanced deep learning approaches. In this review, we aim to distill insights from current research on employing transformer models for MPP. We analyze the currently available models and explore key questions that arise when training and fine-tuning a transformer model for MPP. These questions encompass the choice and scale of the pretraining data, optimal architecture selections, and promising pretraining objectives. Our analysis highlights areas not yet covered in current research, inviting further exploration to enhance the field's understanding. Additionally, we address the challenges in comparing different models, emphasizing the need for standardized data splitting and robust statistical analysis.

Towards laryngeal cancer diagnosis using Dandelion Optimizer Algorithm with ensemble learning on biomedical throat region images

Laryngeal cancer exhibits a notable global health burden, with later-stage detection contributing to a low mortality rate. Laryngeal cancer diagnosis on throat region images is a pivotal application of computer vision (CV) and medical image diagnoses in the medical sector. It includes detecting and analysing abnormal or cancerous tissue from the larynx, an integral part of the vocal and respiratory systems. The computer-aided system makes use of artificial intelligence (AI) through deep learning (DL) and machine learning (ML) models, including convolution neural networks (CNN), for automated disease diagnoses and detection. Various DL and ML approaches are executed to categorize the extraction feature as healthy and cancerous tissues. This article introduces an automated Laryngeal Cancer Diagnosis using the Dandelion Optimizer Algorithm with Ensemble Learning (LCD-DOAEL) method on Biomedical Throat Region Image. The LCD-DOAEL method aims to investigate the images of the throat region for the presence of laryngeal cancer. In the LCD-DOAEL method, the Gaussian filtering (GF) approach is applied to eliminate the noise in the biomedical images. Besides, the complex and intrinsic feature patterns can be extracted by the MobileNetv2 model. Meanwhile, the DOA model carries out the hyperparameter selection of MobileNetV2 architecture. Finally, the ensemble of three classifiers such as bidirectional long short-term memory (BiLSTM), regularized extreme learning machine (ELM), and backpropagation neural network (BPNN) models, are utilized for the classification process. A comprehensive set of simulations is conducted on the biomedical image dataset to highlight the efficient performance of the LCD-DOAEL technique. The comparison analysis of the LCD-DOAEL method exhibited a superior accuracy outcome of 97.54% over other existing techniques.

A review of deep learning models and online healthcare databases for electronic health records and their use for health prediction

A fundamental obstacle to healthcare transformation continues to be the acquisition of knowledge and insightful data from complex, high dimensional, and heterogeneous biological data. As technology has improved, a wide variety of data sources, including omics data, imaging data, and health records, have been available for use in healthcare research contexts. Electronic health records (EHRs), which are digitalized versions of medical records, have given researchers a significant chance to create computational methods for analyzing healthcare data. EHR systems typically keep track of all the data relating to a patient’s medical history, including clinical notes, demographic background, and diagnosis details. EHR data can offer valuable insights and support doctors in making better decisions related to disease and diagnostic forecasts. As a result, several academics use deep learning to forecast diseases and track health trajectories in EHR. Recent advances in deep learning technology have produced innovative and practical paradigms for building end-to-end learning models. However, scholars have limited access to online HER databases, and there is an inherent need to address this issue. This research examines deep learning models, their architectures, and readily accessible EHR online databases. The goal of this paper is to examine how various architectures, models, and databases differ in terms of features and usability. It is anticipated that the outcomes of this review will lead to the development of more robust deep learning models that facilitate medical decision-making processes based on EHR data and inform efforts to support the selection of architectures, models, and databases for specific research purposes.

Continuous Glucose, Insulin and Lifestyle Data Augmentation in Artificial Pancreas Using Adaptive Generative and Discriminative Models.

Artificial pancreas requires data from multiple sources for accurate insulin dose estimation. These include data from continuous glucose sensors, past insulin dosage information, meal quantity and time and physical activity data. The effectiveness of closed-loop diabetes management systems might be hampered by the absence of these data caused by device error or lack of compliance by patients. In this study, we demonstrate the effect of output sequence length-driven generative and discriminative model selection in high quality data generation and augmentation. This novel generative adversarial network (GAN) based architecture automatically selects the generator and discriminator architecture based on the desired output sequence length. The proposed model is able to generate glucose, physical activity, meal information data for individual patients. The discriminative scores for Ohio T1DM (2018) dataset were 0.17 ±0.03 (Inputs: CGM, CHO, Insulin) and 0.15 ±0.02 (Inputs: CGM, CHO, Insulin, Heart Rate, Steps) and for Ohio T1D (2020) dataset was 0.16 ±0.02 (Inputs: CGM, CHO, Insulin) and 0.15 ±0.02 (Inputs: CGM, CHO, Insulin, acceleration). A mixture of generated and real data was used to test predictive scores for glucose forecasting models. The best RMSE and MARD achieved for OhioT1DM patients were 17.19 ±3.22 and 7.14 ±1.76 for PH=30 min with CGM, CHO, Insulin, heartrate and steps as inputs. Similarly, the RMSE and MARD for real+synthetic data were 15.63 ±2.57 and 5.86 ±1.69 respectively. Compared to existing generative models, we demonstrate that sequence length based architecture selection leads to better synthetic data generation for multiple output sequences (CGM, CHO, Insulin) and forecasting accuracy.

O-131 A novel approach to predicting the potential of a blastocyst using untargeted spectral analysis of spent culture medium and machine learning

Abstract Study question Is it possible to effectively predict negative outcomes of intrauterine embryo transfer using modified untargeted Raman spectroscopy of the spent culture medium? Summary answer The proposed spectroscopic approach, combined with machine learning methods, allows identifying a group of embryos that are almost unable to implant and develop ongoing pregnancy. What is known already Embryo deselection is usually based on the karyotype analysis of the embryo and originates from the assumption that an abnormal PGT result is associated with negative transfer outcomes. Embryo selection methods aimed at identifying the most capable for implantation embryo are based on morphological, morphometric, and metabolic approaches. However, due to the dependence of the phenomenon (pregnancy) on several factors, predicting the outcome of the transfer solely through variables derived from the embryo does not correspond to modern views on implantation. At the same time, predicting negative transfer outcomes through the information originating from the embryo appears quite rational. Study design, size, duration 424 samples of spent culture medium used, collected from microdrops with individually cultured blastocyst from the internal institutional biosamples repository. Medium samples were collected from July 1, 2021, to June 1, 2023. The class attribute for each sample was the absence or presence of ongoing pregnancy at the 12-14 week of gestational age. The positive class (ongoing pregnancy) proportion in the presented dataset is 33%, and the negative (no ongoing pregnancy) class proportion is 67%. Participants/materials, setting, methods The study material was spent culture medium from blastocysts with known transfer outcomes by the end of first trimester. All media samples were stored at -86 °С until the moment of spectroscopy. Before the study, samples were thawed at room temperature for 15 minutes. Untargeted Raman spectroscopy was done on a signal amplification substrate using a green laser (532 nm). The architecture selection and machine learning model training were performed using the Python library mcfly. Main results and the role of chance After building the model the following results for validation and test sets were obtained: So it is possible to identify a group of embryos that are almost incapable of producing ongoing pregnancy. This group constitutes about 40% of the total number of negative outcomes. The error of determining an embryo as being incapable for implantation and normal pregnancy development is about 6%, what is relatively low number. Limitations, reasons for caution The presented data are not multicenter; they were obtained from samples from one laboratory and using a limited set (only one manufacturer) of culture media. This may lead to reduced or nonexistent relevance of the model for data from other sources and conditions. Wider implications of the findings It is necessary to check the proposed method on an additional set of culture media from other manufactures and laboratories. This may lead to refining the parameters of the built neural network. The assumption of significant clinical value of the developed model needs to be checked through prospective testing. Trial registration number fpc-2023-ivf-01

Deep image clustering: A survey

Deep image clustering networks have the capability to categorize unlabeled images, thereby effectively utilizing them. This paper synthesizes recent researches about deep image clustering network and summarizes them within a general framework. Image Preprocessing part transforms collected images into a dataset accepted by the network, then Image Embedding part embeds images from the dataset into vectors which represents image features. After Feature Processing part further reduces the dimensionality or enhances these features, the following Feature Clustering part divides the images into several categories. Cluster Result Processing part treats the clustering outcomes to implement weighted, multi-view, subspace, multimodal, or self-supervised methods. Downstream Applications part employ the clustering results to address various real-world problems. The performance of common baseline clustering methods and several feature extraction architectures are also compared and analyzed. The results indicate that within deep image clustering networks, the choice of clustering algorithm has a relatively minor impact on clustering performance, whereas the selection of the feature extraction network architecture is decisive for clustering metrics. The choice of architecture should be customized based on the characteristics of the dataset. Finally, we provide suggestions for potential research directions in deep image clustering networks.

Deep neural network-based prediction of tsunami wave attenuation by mangrove forests

The goal of this research is to develop a model employing deep neural networks (DNNs) to predict the effectiveness of mangrove forests in attenuating the impact of tsunami waves. The dataset for the DNN model is obtained by simulating tsunami wave attenuation using the Boussinesq model with a staggered grid approximation. The Boussinesq model for wave attenuation is validated using laboratory experiments exhibiting a mean absolute error (MAE) ranging from 0.003 to 0.01. We employ over 40,000 data points generated from the Boussinesq numerical simulations to train the DNN. Efforts are made to optimize hyperparameters and determine the neural network architecture to attain optimal performance during the training process. The prediction results of the DNN model exhibit a coefficient of determination (R2) of 0.99560, an MAE of 0.00118, a root mean squared error (RMSE) of 0.00151, and a mean absolute percentage error (MAPE) of 3 %. When comparing the DNN model with three alternative machine learning models— support vector regression (SVR), multiple linear regression (MLR), and extreme gradient boosting (XGBoost)— the performance of DNN is superior to that of SVR and MLR, but it is similar to XGBoost.•High-accuracy DNN models require hyperparameter optimization and neural network architecture selection.•The error of DNN models in predicting the attenuation of tsunami waves by mangrove forests is less than 3 %.•DNN can serve as an alternate predictive model to empirical formulas or classical numerical models.