This research aims to model tourist visit data to West Nusa Tenggara Province (NTB) using a hybrid model, combining the dynamic neural network method as the core model with the wavelet method and fuzzy inference as tools to optimize the model. The model developed in this research is referred to as the Fuzzy Wavelet Dynamic Neural Networks (FW-DNN) Model. The FW-DNN model is a feed-forward dynamic neural network model that utilizes the Wavelet B-spline function as its activation function and TSK (Takagi-Sugeno-Kang) fuzzy inference as the method for information aggregation. The modeling results on both in-sample and out-sample data show that the proposed FW-DNN model is capable of representing the patterns in tourist visit data to NTB quite effectively. Similar results were also observed in the patterns of data for both domestic and international tourist visit numbers. Based on the root of mean square error (RMSE) indicator, the performance of the developed FW-DNN model for aggregated tourist visit data is 95185.09 for in-sample data and 22615.54 for out-sample data. Partial performance analysis of the FW-DNN model for international tourist visit data shows a value of 39848.94 for in-sample data and 5223.86 for out-sample data. Similarly, the FW-DNN model's performance for domestic tourist visit data is 39848.94 for in-sample data and 5223.86 for out-sample data. Practically, the results of this research can be input for the NTB Provincial government in determining tourism management and/or development policies, especially related to the provision of supporting facilities and infrastructure, or the private sector in an effort to optimize the carrying capacity and/or services for tourists visiting NTB.

Applying solar radiation as a renewable energy source using photovoltaic panels has problems, such as work efficiency decreasing when the photovoltaic cell temperature is above the working temperature, thus requiring a cooling method. This research examines the cooling effect of photovoltaic panels using water spray with various types and diameters to reduce the temperature and performance of photovoltaic panels, which was carried out experimentally with solar radiation at 08:00-15:00 local time. The research results show that the water spray cooling system can reduce the temperature of the photovoltaic panel from 61.96 to 36.51℃ and increase efficiency from 10.98 to 14.47% with variations in the full cone nozzle with a hole diameter of 2 mm. Full cone nozzles can provide the best cooling performance compared to hollow cone nozzles and flat fan nozzles due to the more even distribution of water spray on the surface of the photovoltaic panel. Using different nozzle diameters also influences cooling. Based on the research results, the water spray cooling system effectively increases the work efficiency of photovoltaic panels with a 2 mm total cone nozzle variation, producing the highest efficiency.

Selective laser sintering (SLS) is a typical procedure in powder-based 3D printing technology that produces items with great accuracy and precision. The powders used in SLS are granular and discontinuous, making them difficult to simulate using traditional computational techniques that rely on continuous methods, such as the finite element method (FEM) or finite difference (FD). This paper presents a system for accurately depicting the physical interactions of particles affected by a moving laser source using the discrete element method (DEM), performed numerically in Python. This DEM framework was used on polyamide 12 powder with various laser powers (2W, 4W, 5W) and scanning speeds (0.5m/s, 1m/s). The results and comparison with previous literature confirm that the DEM framework accurately depicts the temperature distribution in the laser-scanned powder bed. The effect of laser power and scan speed on fused surface size is explored and corroborated using previous studies, confirming the DEM's dependability and applicability for modelling powder-based additive manufacturing processes.

Rice, a global staple crop, plays a crucial role in feeding approximately half of the global population. Nevertheless, the persistent spread of diseases poses a significant threat to rice production. Therefore, accurately identifying rice diseases is of paramount practical importance. The proposed approach introduces an innovative hybrid architecture for image classification, harnessing the strengths of both Vision Transformers (ViT) and Convolutional Neural Networks (CNNs). This research investigates five primary diseases affecting rice crops: Blast, Brown Spot, Tungro, False smut, and Bacterial Sheath Blight. Approximately 8000 images of these specific rice leaf diseases were employed for training purposes in the study. What distinguishes this method is its unique integration of a CNN block within the transformer layers, deviating from the traditional ViT architecture. Vision Transformers (ViTs), recognized for their exceptional performance in image classification, excel in providing global insights through attention-based mechanisms. Nevertheless, their model complexity can obscure the decision-making process, and ambiguous attention maps can lead to erroneous correlations among image patches. The incorporation of CNNs in this approach serves to address these challenges by effectively capturing local patterns. This synergistic combination enhances the model's robustness to variations in input data, such as changes in scale, perspective, or context. With the utilization of the proposed hybrid ViT-CNN model architecture, the model achieves remarkable results, boasting 100 percent accuracy and top-5 accuracy, along with a precision of 93.84 percent. Through this hybrid model, we have obtained satisfactory outcomes, surpassing the performance of the latest transformer models in the realm of rice leaf disease identification.

The focal objective of optimizing drilling processes is to mitigate challenges tied to the operation. However, the triumph of mineral drilling relies on the availability of pertinent data to ensure effectiveness. For efficient and successful drilling, an optimization approach necessitates access to pertinent data, especially concerning the physicochemical properties of the rock and operational parameters of the machine. In this study, our focus is on optimizing specific energy, a critical metric for assessing mining drilling efficiency. This measure evaluates the energy used during drilling per unit volume of rock extracted. Considering the complexity of factors involved, treating the selection of the operational mode governing specific energy as a form of multi-criteria decision-making is justifiable. This method involves an in-depth analysis of the problem's underlying structure. Experimental measures were used to validate the proposed optimization approach. The paper delves into evaluating the differences in rankings derived from the TOPSIS and VIKOR methods. A ranking similarity coefficient is employed to compare the rankings against experimental values. Ultimately, the available choices are prioritized, and the most suitable operating mode for the drilling machine is determined. The study's comparative analysis using TOPSIS and VIKOR methodologies leads to the discovery of the best operational modes for drilling machines, highlighting the subtle differences in how well the two methods work. By using a ranking similarity coefficient, this study not only shows what each method's rankings mean in real life compared to experimental values, but it also gives a plan for improving the efficiency of drilling machines by carefully adjusting their parameters. Such insights contribute significantly to the field of drilling optimization, showcasing a methodical approach to energy conservation and operational efficiency.

The impact of technological developments has now led to a transformation in the preparation of financial statements. By applying machine learning, auditors can easily increase anomalies detection. The purpose of this study is to determine the effect of optimism, innovativeness, perceived usefulness, and perceived ease of use on auditors’ intention to use machine learning. Data were collected using an online questionnaire and analyzed using the Structural Equation Modeling-Partial Least Square (SEM-PLS). The sample in this study used a nonprobability sampling and has a sample size of 100 respondents from auditors who work in a Public Accounting Firm in DKI Jakarta and Tangerang areas. The results of testing this study using SmartPLS 4 are optimism has a significant effect on perceived usefulness and perceived ease of use, while innovativeness only has a significant effect on perceived ease of use. In addition, perceived ease of use has a significant effect on perceived usefulness. This study implies that auditors' perception of the usefulness can influence the intention to use machine learning. However, perceived ease of use does not affect the intention to use machine learning. Therefore, we suggest that audit firms could establish training programs to enhance digital skills for auditor.

When wireless nodes communicate without the use of infrastructure, the network is subject to security breaches. Mobile Adhoc Network (MANET) is one of the most vulnerable wireless networks in terms of security breaches. The most common types of security breaches are intruders and attackers, whose tasks are to reduce the internal performance of the network. Many research studies are focused on detecting and preventing these two security threads. This article focuses on intruder and black hole attackers and their communication. Several techniques were proposed for thwart the intruders and attackers in the Mobile Adhoc Network communication by using the modern technologies which are an additional load to the nodes operation and these techniques could not be able to predict the attacker before it was done. To achieve this goal, this article proposed the Watch Dog approach involves routing protocol to monitoring the forwarding time of all nodes in the transmission. Delays in forwarded time nodes could indicate an intruder, while discarding the forwarded node could indicate a black hole attacker. The proposed Watch Dog routing algorithm with classification technique was implemented with a network simulator with Adhoc On Demand Vector protocol named as WD-AODV, and the simulation results were compared to a modern techniques of Fuzzy Logic based AODV (FL-AODV), Machine Learning-based AODV (ML-AODV) and Artificial Intelligence based AODV (AI-AODV) routing protocol. The compared results of attack rates, attack detection time, Packet delivery ratio and End to End delay showed that the Watch Dog-based attacker and intruder detection methods perform better by more than 59%, with excellent performance factors of 69%.

The aim of the attempt is to build a mechanism for objective evaluation of the autonomous nervous system (ANS) for disease diagnosis at an early stage. With the experience of data collection from various control subjects, BARC has identified eight different pulse morphologies. A Peripheral Pulse Analyser (PPA) measures peripheral blood flow. Blood flow was measured in control subjects (100) and patients (100). The morphology of a person's pulse changes throughout time. Pulse morphologies vary according to age, disease, and other parameters. More than 8500 signals from 200 humans were tested. Various pattern-matching and classification techniques are given in this research to detect the existence of specific pulse shapes in obtained PPA signals. Peaks of PPA blood flow patterns are detected, and features are extracted from the sample pattern. Various machine learning (ML) algorithms are used to identify various pulse shapes depending on the parameters of extracted features. We observed that in one PPA signal of the duration of 300 seconds, 3 to 4 defined pulse morphologies out of 8 are available. Every pulse morphology is different from the others. After training, the system was able to detect pulse shapes to assess the ANS of the subject with more than 94% to 97% accuracy. The proposed system will assist the doctor in making a decision quickly based on a few processed parameters rather than assessing several individual parameters at a crucial time. The output of the system is the assessment report of ANS. This is an attempt to replace traditional Ayurvedic pulse examination methos for disease detection.

A problem of heat transfer by conduction, convection, and radiation has been studied for both steady and unsteady states. A numerical technique based on the finite difference method was adopted to solve the mathematical boundary value problem, which was created under some conditions with different values of physical parameters. The solution started with an unsteady state, reaching a steady state after many iterations. The effect of various parameters has been discussed for different temperatures of the parallel walls, and the governing equations have been established, which appear to be of the parabolic type. They were treated numerically using the Alternating Direction Implicit Method, which is considered good in stability with acceptable accuracy. Both cases for the steady and unsteady state, which usually arise in the discussion of fluid flow or heat transfer problems, are treated in this paper as one case dissimilar to the previous works, and this is the main goal of the present article.

Breast tumors have become one of the most frequent illnesses among women, with 287,850 new cases projected to be discovered in 2022. Of those, 43,250 women passed away from this malignancy. The mortality rate for cancer might be decreased through early detection. Despite this, employing mammography photographs to manually identify this kind of cancer is a challenging process that always demands an expert. In the literature, a number of AI-based (Artificial Intelligence) strategies have been proposed. However, they still deal with issues including irrelevant feature extraction, inadequate training models, and similarities between cancerous and non-cancerous areas. In order to identify breast cancer, this research suggested an SMO-MAFNet-Hybrid Alexnet model. The images in this study were first preprocessed to get rid of noise. After that, the multi-attention fusion network (MAFNet) is used to extract features. The Spider Monkey Optimization (SMO) method is utilized in this work to optimize the learning rate in MAFNet. Following feature extraction, classification is done using the AlexNet model. In this work, hybrid optimization, namely Ant Colony Optimization-Reptile Search Algorithm (ACO-RSA), is applied to fine-tune the hyperparameters in AlexNet classification. The suggested method was tested using the CBIS-DDSM (Curated breast imaging subset of Digital Database for Screening Mammography) dataset and demonstrated an accuracy of 98%, outperforming previous models.

In military defence and wildlife conservation operations, detecting camouflage in images poses a significant challenge. This research investigates the efficacy of deep learning techniques, including Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and Long Short-Term Memory (LSTM), in addressing this challenge. The study meticulously evaluates each model's performance using metrics such as average accuracy, validation accuracy, and loss measures across well-known benchmark datasets comprising camouflaged and non-camouflaged images. Notably, the CNN + ANN Pipeline model emerges as the most effective, achieving a remarkable average accuracy of 91.37%. This model, together with the standalone CNN, outperforms the ANN and LSTM models in terms of camouflage detection. The discoveries advance the state-of-the-art in image analysis while also having practical implications for real-world applications. In military settings, good camouflage detection can improve situational awareness and danger detection capabilities. Similarly, automated camouflage detection helps monitor and protect endangered species by detecting hidden creatures or potential threats. Overall, this study highlights the ability of deep learning techniques to greatly improve visual analytic tasks across a variety of domains.