Search

The fast and nondestructive identification of mobile phone cases is a crucial task for law enforcement personnel in the field of forensic science. Attenuated total reflection-Fourier transform infrared spectroscopy (ATR-FTIR) has been employed in conjunction with feature extraction and deep learning algorithms to develop a method for distinguishing mobile phone cases. As preprocessing steps, multivariate scatter correction and standard normal variate were performed. Feature variables were extracted using the competitive adaptive reweighted sampling and shuffled frog leaping algorithm. Several supervised pattern recognition methods, namely ResNet50, VGG16, and multilayer perceptron (MLP), were utilized for constructing classifiers. The results indicated that the model's performance based on multivariate scattering correction (MSC) with competitive adaptive re-weighted sampling (CARS) surpassed that of other approaches. Notably, the ResNet50 model exhibited superior discriminative ability compared to the VGG16 and MLP models, achieving 100% accuracy in the differentiation of all samples. This designed method represents a potentially rapid and nondestructive approach for identifying mobile phone cases in forensic science. [ABSTRACT FROM AUTHOR]

Background: Pulmonary tuberculosis (PTB) is a prevalent chronic disease associated with a significant economic burden on patients. Using machine learning to predict hospitalization costs can allocate medical resources effectively and optimize the cost structure rationally, so as to control the hospitalization costs of patients better. Methods: This research analyzed data (2020–2022) from a Kashgar pulmonary hospital's information system, involving 9570 eligible PTB patients. SPSS 26.0 was used for multiple regression analysis, while Python 3.7 was used for random forest regression (RFR) and MLP. The training set included data from 2020 and 2021, while the test set included data from 2022. The models predicted seven various costs related to PTB patients, including diagnostic cost, medical service cost, material cost, treatment cost, drug cost, other cost, and total hospitalization cost. The model's predictive performance was evaluated using R-square (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) metrics. Results: Among the 9570 PTB patients included in the study, the median and quartile of total hospitalization cost were 13,150.45 (9891.34, 19,648.48) yuan. Nine factors, including age, marital status, admission condition, length of hospital stay, initial treatment, presence of other diseases, transfer, drug resistance, and admission department, significantly influenced hospitalization costs for PTB patients. Overall, MLP demonstrated superior performance in most cost predictions, outperforming RFR and multiple regression; The performance of RFR is between MLP and multiple regression; The predictive performance of multiple regression is the lowest, but it shows the best results for Other costs. Conclusion: The MLP can effectively leverage patient information and accurately predict various hospitalization costs, achieving a rationalized structure of hospitalization costs by adjusting higher-cost inpatient items and balancing different cost categories. The insights of this predictive model also hold relevance for research in other medical conditions. [ABSTRACT FROM AUTHOR]

Landslide disasters, due to their widespread distribution and clustered occurrences, pose a significant threat to human society. Rainfall is considered a primary triggering factor, and the frequent clustering of landslides underscores the importance of early warning systems for regional landslide disasters in preventing and mitigating rainfall-induced landslides. Research on early warning models is crucial for accurately predicting rainfall-induced landslides. However, traditional models face challenges such as the complexity of landslide causes, insufficient data, and limited analysis methods, resulting in low accuracy and inadequate precision. This study focuses on Fujian Province, China, proposing a four-step process for building a regional landslide early warning model based on machine learning. The process includes data integration and cleaning, sample set construction, model training and validation, and practical application. By integrating and cleaning the latest and most detailed data, a training sample set (15,589 samples) for the regional landslide disaster early warning model is established. Three machine learning algorithms--Random Forest, Multilayer Perceptron, and Convolutional Neural Network--are employed and compared, the evaluation results indicated that the RF-based warning model achieved an accuracy of 0.930-0.957 and an AUC value of 0.955. The CNNbased warning model demonstrated an accuracy of 0.945-0.948 with an AUC value of 0.940. The MLP-based warning model achieved an accuracy of 0.930-0.953 and an AUC value of 0.930. The results showed comparable accuracy metrics among the three models, with RF exhibiting a significant advantage in AUC values. Finally, the models are applied to the regional landslide disasters induced by heavy rainfall in Fujian Province on 5 August 2021. The results showed that in the binary classification warning strategy, the accuracy of the Random Forest and Convolutional Neural Network was 92.9%, while that of the Multilayer Perceptron was 85.8%, all performing well. In the multi-classification hierarchical warning strategy, the Random Forest excelled, while the performance of the Convolutional Neural Network and Multilayer Perceptron was relatively limited. The findings of this study Frontiers in Earth Science 01 frontiersin.org Liu et al. 10.3389/feart.2024.1419421 contribute to valuable attempts in landslide disaster warning model research, with anticipated further improvements through the gradual accumulation of samples and practical application verification. [ABSTRACT FROM AUTHOR]

Head pose estimation methods can be generally classified into two categories: model-based and appearance-based methods. The model-based approach relies on facial landmarks for three-dimensional reconstruction, aiming to achieve high-precision results. However, this method is heavily dependent on the accuracy of these landmarks. The appearance-based approach utilizes images as input and employs feature extraction and calculations to generate outcomes. While the appearance-based method boasts greater robustness, its accuracy falls short of the former. In this paper, a new and effective hybrid method is proposed. This hybrid approach combines the strengths of both methods. Unlike the conventional model-based methods, the proposed method regards the facial landmarks in 2D images as a sequence of neural network inputs and then obtains the head pose estimation results for users by neural network regression. The proposed method solves the fuzzy rotation labeling problem by using a rotation matrix representation, introducing a 6D rotation matrix representation as an intermediate state of the rotation matrix to achieve effective direct regression. Introducing face processing enhances the robustness of the model in cross-dataset scenarios. The proposed method achieves remarkable results based on imprecise face recognition and a simplistic model. The proposed method can be divided into three parts. First, the proposed method applies face processing on the input image; second, the method detects facial landmarks; and third, it converts these facial landmarks into sequences and obtains the 6D rotation representation of the head pose by regression. Extensive experiments on the publicly available BIWI, PRIMA, and DrivFace datasets show that this method is functional and performs better than other state-of-the-art methods. Compared to other methods, this approach demonstrates an average performance improvement of at least 10% across the dataset. [ABSTRACT FROM AUTHOR]

In large indoor environments, accurate positioning and tracking of people and autonomous equipment have become essential requirements. The application of increasingly automated moving transportation units in large indoor spaces demands a precise knowledge of their positions, for both efficiency and safety reasons. Moreover, satellite-based Global Positioning System (GPS) signals are likely to be unusable in deep indoor spaces, and technologies like WiFi and Bluetooth are susceptible to signal noise and fading effects. For these reasons, a hybrid approach that employs at least two different signal typologies proved to be more effective, resilient, robust, and accurate in determining localization in indoor environments. This paper proposes an improved hybrid technique that implements fingerprinting-based indoor positioning using Received Signal Strength (RSS) information from available Wireless Local Area Network (WLAN) access points and Wireless Sensor Network (WSN) technology. Six signals were recorded on a regular grid of anchor points covering the research surface. For optimization purposes, appropriate raw signal weighing was applied in accordance with previous research on the same data. The novel approach in this work consisted of performing a virtual tessellation of the considered indoor surface with a regular set of tiles encompassing the whole area. The optimization process was focused on varying the size of the tiles as well as their relative position concerning the signal acquisition grid, with the goal of minimizing the average distance error based on tile identification accuracy. The optimization process was conducted using a standard Quantum Particle Swarm Optimization (QPSO), while the position error estimate for each tile configuration was performed using a 3-layer Multilayer Perceptron (MLP) neural network. These experimental results showed a 16% reduction in the positioning error when a suitable tile configuration was calculated in the optimization process. Our final achieved value of 0.611 m of location incertitude shows a sensible improvement compared to our previous results. [ABSTRACT FROM AUTHOR]

It is known that the determination of the good-dice-in-bad-neighborhoods (GDBNs) has been regarded as an effective technique to reduce the value of the defect parts per million (DPPM) by identifying and rejecting the suspicious dice even though they are good in testing. Instead of examining eight immediate neighbors in a small-sized $3\times 3$ window or exploiting simple linear regression, a large-sized window can be used to recognize the broad-sighted neighborhoods and accurately infer the suspiciousness level for any given die. In this paper, the artificial neural networks (ANN)-based method can be proposed to solve the GDBN identification. Furthermore, two enhanced techniques can be further presented to improve the inference accuracy of the original ANN-based method by considering the variation of the time-dependent wafer patterns and the wafer-to-wafer relationship between two adjacent wafers. After applying the two enhanced techniques, the business profits can be improved in the new ANN-based method. Various experiments on two datasets clearly reveal the superiority of the proposed ANN-based method over the other existing methods. In addition to the reduction of the DPPM value, the new ANN-based method can achieve the 1.5X–2X better reduction in the cost of the return merchandise authorization (RMA). On the other hand, the experimental results show that the similar result can also be obtained in the other lower-yield products. By using the new ANN-based method, the relationships on bad dice cross wafers can be captured and the highly-accurate inference results can be simultaneously maintained. [ABSTRACT FROM AUTHOR]

Addressing the issues of prolonged training times and low recognition rates in large model applications, this paper proposes a weight training method based on entropy gain for weight initialization and dynamic adjustment of the learning rate using the multilayer perceptron (MLP) model as an example. Initially, entropy gain was used to replace random initial values for weight initialization. Subsequently, an incremental learning rate strategy was employed for weight updates. The model was trained and validated using the MNIST handwritten digit dataset. The experimental results showed that, compared to random initialization, the proposed initialization method improves training effectiveness by 39.8% and increases the maximum recognition accuracy by 8.9%, demonstrating the feasibility of this method in large model applications. [ABSTRACT FROM AUTHOR]

This study examines the correlation between physical exercise habits and mental health outcomes in adolescents using a regression-based Multilayer Perceptron (MLP) model. By utilizing a substantial dataset, the model successfully captures intricate, non-linear connections between several exercise-related characteristics and mental health scores. The MLP model exhibited robust prediction accuracy, characterized by elevated R² values and diminished MSE, underscoring its promise for practical implementations. By integrating big data, a thorough analysis was conducted, which demonstrated that engaging in regular physical activity is a substantial indicator of mental wellbeing. The results emphasize the significance of engaging in physical activity to enhance mental well-being and showcase the effectiveness of machine learning and big data in health evaluations. Subsequent research could investigate the integration of supplementary lifestyle elements and more sophisticated deep learning architectures to further improve prediction abilities. [ABSTRACT FROM AUTHOR]

This study uses artificial neural networks (ANNs) to examine the intricate relationship between air pollutants, meteorological factors, and respiratory disorders. The study investigates the correlation between hospital admissions for respiratory diseases and the levels of PM10 and SO2 pollutants, as well as local meteorological conditions, using data from 2017 to 2019. The objective of this study is to clarify the impact of air pollution on the well-being of the general population, specifically focusing on respiratory ailments. An ANN called a multilayer perceptron (MLP) was used. The network was trained using the Levenberg–Marquardt (LM) backpropagation algorithm. The data revealed a substantial increase in hospital admissions for upper respiratory tract diseases, amounting to a total of 11,746 cases. There were clear seasonal fluctuations, with fall having the highest number of cases of bronchitis (N = 181), sinusitis (N = 83), and upper respiratory infections (N = 194). The study also found demographic differences, with females and people aged 18 to 65 years having greater admission rates. The performance of the ANN model, measured using R2 values, demonstrated a high level of predictive accuracy. Specifically, the R2 value was 0.91675 during training, 0.99182 during testing, and 0.95287 for validating the prediction of asthma. The comparative analysis revealed that the ANN-MLP model provided the most optimal result. The results emphasize the effectiveness of ANNs in representing the complex relationships between air quality, climatic conditions, and respiratory health. The results offer crucial insights for formulating focused healthcare policies and treatments to alleviate the detrimental impact of air pollution and meteorological factors. [ABSTRACT FROM AUTHOR]

In this paper, we experimentally illustrate the effectiveness of neural networks (NNs) as non-linear equalisers for multilevel pulse amplitude modulation (PAM-M) transmission over an optical wireless communication (OWC) link. In our study, we compare the bit-error-rate (BER) performances of two decision feedback equalisers (DFEs)—a multilayer-perceptron-based DFE (MLPDFE), which is the NN equaliser, and a transversal DFE (TRDFE)—under two degrees of non-linear distortion using an eye-safe 850 nm single-mode vertical-cavity surface-emitting laser (SM-VCSEL). Our results consistently show that the MLPDFE delivers superior performance in comparison to the TRDFE, particularly in scenarios involving high non-linear distortion and PAM constellations with eight or more levels. At a forward error correction (FEC) threshold BER of 0.0038, we achieve bit rates of ~28 Gbps, ~29 Gbps, ~22.5 Gbps, and ~5 Gbps using PAM schemes with 2, 4, 8, and 16 levels, respectively, with the MLPDFE. Comparably, the TRDFE yields bit rates of ~28 Gbps and ~29 Gbps with PAM-2 and PAM-4, respectively. Higher PAM levels with the TRDFE result in BERs greater than 0.0038 for bit rates above 2 Gbps. These results highlight the effectiveness of the MLPDFE in optimising the performance of SM-VCSEL-based OWC systems across different modulation schemes and non-linear distortion levels. [ABSTRACT FROM AUTHOR]

An efficient credit risk management model is a promising technique that provides Financial Institutions or Banks the ability to determine a creditworthy customer from a non-worthy customer. The fact remains that no country’s economy can survive or improve without credit using historically available data. This paper presents an evaluation of several gradient descent techniques, and metaheuristic optimization algorithms implemented in Machine Learning and Multi-layer perceptron for better credit risk prediction. It also handles imbalanced dataset using smote Edited Nearest Neighbour. The study provided various architectures and advantages of the algorithms while addressing how the limitations can be improved to build a better credit risk model and improve model accuracy. The study showed MLP WOA achieved accuracy of 98.56% based on Adam gradient descent to achieve faster convergence and exploration compared to MLP PSO with 98.39%. [ABSTRACT FROM AUTHOR]

Methaheuristics (MHs) are techniques widely used for solving complex optimization problems. In recent years, the interest in combining MH and machine learning (ML) has grown. This integration can occur mainly in two ways: ML-in-MH and MH-in-ML. In the present work, we combine the techniques in both ways—ML-in-MH-in-ML, providing an approach in which ML is considered to improve the performance of an evolutionary algorithm (EA), whose solutions encode parameters of an ML model—artificial neural network (ANN). Our approach called TS in EA in ANN employs a reinforcement learning neighborhood (RLN) mutation based on Thompson sampling (TS). TS is a parameterless reinforcement learning method, used here to boost the EA performance. In the experiments, every candidate ANN solves a regression problem known as protein structure prediction deviation. We consider two protein datasets, one with 16,382 and the other with 45,730 samples. The results show that TS in EA in ANN performs significantly better than a canonical genetic algorithm (GA in ANN) and the evolutionary algorithm without reinforcement learning (EA in ANN). Analyses of the parameter's frequency are also performed comparing the approaches. Finally, comparisons with the literature show that except for one particular case in the largest dataset, TS in EA in ANN outperforms other approaches considered the state of the art for the addressed datasets. [ABSTRACT FROM AUTHOR]

This paper examines the predictability of the changes in Brent oil futures prices using a multilayer perceptron artificial neural network that exploits the information contained in the largest possible set of economic indicators. Feature engineering is employed to identify the most important predictors of the change in Brent oil futures prices. We find that oil‐market‐specific variables are important predictors. Our findings also suggest that forecasts of the change in the Brent oil futures prices from the multilayer perceptron that exploits the informational content of all and oil‐market‐specific predictors exhibit higher statistical forecast accuracy than the random walk. Tests of forecast optimality indicate that the forecasts generated using oil‐market‐specific predictors are optimal. We discuss the policymaking and practical relevance of our results. [ABSTRACT FROM AUTHOR]

A wireless Sensor Network (WSN) is made up of many sensor nodes which gather and transmit data to a central location. The limited resources of the nodes create significant security challenges when deploying and communicating WSNs. The detection of unauthorized access is a crucial aspect of enhancing the security measures of WSNs. The utilization of network intrusion detection systems (IDS) has become an essential aspect of any communication network, as they offer valuable services to the network. Several studies in the field of machine learning have been conducted to explore the potential of utilizing this technology for intrusion detection in WSNs, yielding promising outcomes. These efforts still need to be more precise and efficient against network traffic unbalanced data issues. The paper presents a new model for detecting intrusion attacks that utilize a hybrid multilayer perceptron (MLP) and CatBoost classifier, as well as feature selection techniques. The proposed approach aims for good performance in identifying different forms of threats. The system performs data preprocessing on various datasets and reduces the dataset size using a feature selection algorithm. Pelican Optimization Algorithm (POA) has been proposed for tuning the hyper-parameters of the classifier designs and selecting the relevant features from the dataset. The CSE-CIC-IDS2018, AWID, and UNSW-NB15 databases reutilized for conducting performance evaluations on the proposed framework. The tests included accuracy, precision, recall, FAR, DR and complexity time. The proposed model has a low FPR and high accuracy in binary classification, as shown. [ABSTRACT FROM AUTHOR]

The subject of predicting global crude oil prices is well recognized in academic circles. The notion of hybrid modeling suggests that the integration of several methodologies has the potential to optimize advantages while reducing limitations. Consequently, hybrid techniques are extensively used in contemporary research. In this paper, a novel decompose-ensemble prediction approach is proposed by integrating various optimization algorithms, namely biography-based optimization (BBO), backtracking search algorithm (BSA), teaching-learning-based algorithm (TLBO), cuckoo optimization algorithm (COA), multi-verse optimization (MVO), and multilayer perceptron (MLP). Furthermore, the aforementioned approaches, namely BBO-MLP, BSA-MLP, and TLBO-MLP, include the de-compose-ensemble technique into the individual artificial intelligence model in order to enhance the accuracy of predictions. In order to validate the findings, the forecast is conducted using the authoritative data on oil prices. This study will use three primary indicators, including EMA 20, EMA 60, EMA 100, ROC, and AUC assessments, to assess and evaluate the efficacy of the five methodologies under investigation. The below findings are derived from the conducted research: Based on the achieved AUC values of 0.9567 and 0.9429, it can be concluded that using a multi-verse optimization technique is considered the most suitable strategy for effectively handling the dataset pertaining to crude oil revenue. The next four approaches likewise have a significant AUC value, surpassing 0.8. The AUC values for the BBO- MLP, BSA-MLP, TLBO-MLP, and COA-MLP approaches were obtained as follows: (0.874 and 0.792) for training and testing stages, (0.809 and 0.792) for training and testing stages, (0.9353 and 0.9237) for training and testing stages, and (0.9092 and 0.8927) for training and testing stages, respectively. This model has the potential to contribute to the resolution of default probability and is very valuable to the credit card industry. Broadly speaking, this novel forecasting approach serves as a notable predictor of crude oil prices. [ABSTRACT FROM AUTHOR]

This study focused on assessing the financial efficiency of investing in a horizontal shower heat exchanger. The analysis was based on net present value (NPV). The research also examined the possibility of using artificial neural networks and SHapley Additive exPlanation (SHAP) analysis to assess the profitability of the investment and the significance of individual parameters affecting the NPV of the project related to installing the heat exchanger in buildings. Comprehensive research was conducted, considering a wide range of input parameters. As a result, 1,215,000 NPV values were obtained, ranging from EUR −1996.40 to EUR 36,933.83. Based on these values, artificial neural network models were generated, and the one exhibiting the highest accuracy in prediction was selected (R2 ≈ 0.999, RMSE ≈ 57). SHAP analysis identified total daily shower length and initial energy price as key factors influencing the profitability of the shower heat exchanger. The least influential parameter was found to be the efficiency of the hot water heater. The research results can contribute to improving systems for assessing the profitability of investments in shower heat exchangers. The application of the developed model can also help in selecting appropriate technical parameters of the system to achieve maximum financial benefits. [ABSTRACT FROM AUTHOR]

Accurately estimating the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for maintaining the safe and stable operation of rechargeable battery management systems. However, this task is often challenging due to the complex temporal dynamics. Recently, attention-based networks, such as Transformers and Informer, have been the popular architecture in time series forecasting. Despite their effectiveness, these models with abundant parameters necessitate substantial training time to unravel temporal patterns. To tackle these challenges, we propose a straightforward MLP-Mixer-based architecture named "Intra–Inter Patch Mixer" (IIP-Mixer), which leverages the strengths of multilayer perceptron (MLP) models to capture both local and global temporal patterns in time series data. Specifically, it extracts information using an MLP and performs mixing operations along both intra-patch and inter-patch dimensions for battery RUL prediction. The proposed IIP-Mixer comprises parallel dual-head mixer layers: the intra-patch mixing MLP, capturing local temporal patterns in the short-term period, and the inter-patch mixing MLP, capturing global temporal patterns in the long-term period. Notably, to address the varying importance of features in RUL prediction, we introduce a weighted loss function in the MLP-Mixer-based architecture, marking the first time such an approach has been employed. Our experiments demonstrate that IIP-Mixer achieves competitive performance in battery RUL prediction, outperforming other popular time series frameworks, such as Informer and DLinear, with relative reductions in mean absolute error (MAE) of 24% and 10%, respectively. [ABSTRACT FROM AUTHOR]

A technique is proposed to detect the presence of the multipath effect in Global Navigation Satellite Signal (GNSS) signals using a convolutional neural network (CNN) as the building block. The network is trained and validated, for a wide range of C / N 0 values, with a realistic dataset constituted by the synthetic noisy outputs of a 2D grid of correlators associated with different Doppler frequencies and code delays (time-domain dataset). Multipath-disturbed signals are generated in agreement with the various scenarios encompassed by the adopted multipath model. It was found that pre-processing the outputs of the correlators grid with the two-dimensional Discrete Fourier Transform (frequency-domain dataset) enables the CNN to improve the accuracy relative to the time-domain dataset. Depending on the kind of CNN outputs, two strategies can then be devised to solve the equation of navigation: either remove the disturbed signal from the equation (hard decision) or process the pseudoranges with a weighted least-squares algorithm, where the entries of the weighting matrix are computed using the analog outputs of the neural network (soft decision). [ABSTRACT FROM AUTHOR]

Airline rescheduling can minimize the number of abnormal flights and their subsequent adverse effects during the flight-plan execution process. The current subjective manual rescheduling method has a low efficiency and does not consider uncontrollable factors. The traditional machine learning-based methods require massive training data, which are not applicable to some few sample's factors. In this study, we firstly addressed the factors that influence airline rescheduling. A set of airline rescheduling indicators was determined as the inputs of a multilayer perceptron model. Then, an airline rescheduling algorithm, namely MAML–SGD was proposed to solve the mentioned model constraint with few samples. Compared with the identification model that uses an SGD algorithm to iteratively update parameters, this proposed algorithm can maintain the stability of the gradient descent during the training and testing processes of the model. Finally, by using historical data from Guangzhou Baiyun International Airport and Urumqi Diwopu International Airport, the airline rescheduling accuracy of the model reached 97%, which was markedly higher than the results obtained by traditional machine learning models such as SVM. [ABSTRACT FROM AUTHOR]

(1) Background: This study aims to investigate the correlation between heart rate variability (HRV) during exercise and recovery periods and the levels of anxiety and depression among college students. Additionally, the study assesses the accuracy of a multilayer perceptron-based HRV analysis in predicting these emotional states. (2) Methods: A total of 845 healthy college students, aged between 18 and 22, participated in the study. Participants completed self-assessment scales for anxiety and depression (SAS and PHQ-9). HRV data were collected during exercise and for a 5-min period post-exercise. The multilayer perceptron neural network model, which included several branches with identical configurations, was employed for data processing. (3) Results: Through a 5-fold cross-validation approach, the average accuracy of HRV in predicting anxiety levels was 89.3% for no anxiety, 83.6% for mild anxiety, and 74.9% for moderate to severe anxiety. For depression levels, the average accuracy was 90.1% for no depression, 84.2% for mild depression, and 82.1% for moderate to severe depression. The predictive R-squared values for anxiety and depression scores were 0.62 and 0.41, respectively. (4) Conclusions: The study demonstrated that HRV during exercise and recovery in college students can effectively predict levels of anxiety and depression. However, the accuracy of score prediction requires further improvement. HRV related to exercise can serve as a non-invasive biomarker for assessing psychological health. [ABSTRACT FROM AUTHOR]

The soil water retention curve (SWRC) provides information for a wide range of geoenvironmental problems, such as analyses of transient two-phase flow, the bearing capacity and shear strength of unsaturated soils. Many past studies have shown experimentally the effects of stress on the SWRC. Unfortunately, direct stress-dependent water retention measurements are relatively time-consuming and generally require special equipment and a certain level of expertise. This study primarily aimed to develop a novel predictive framework within the context of soft computing to capture the dependency of the SWRC on several variables, with an emphasis on stress and soil type. To achieve this, the three shape parameters of van Genuchten's water retention model were estimated using a comprehensive database of 102 SWRC tests retrieved from the literature. In this study, 60% of the datasets were employed for model training, with an additional 20% being designated for validation, while the remaining 20% were set aside for testing the model's performance. The data were analyzed using two machine learning techniques: the group method of data handling and multi-layer perceptron approaches. Results showed excellent performance of the two methods. A sensitivity analysis was conducted to explore the relative significance of the different variables. Interestingly, net stress was found to be almost as significant as soil type. The introduced artificial intelligence based predictive framework provided a very effective method of integrating theory and practice. [ABSTRACT FROM AUTHOR]

DRAM memory controller plays a critical role in maximizing the performance of high bandwidth memory by efficiently managing data transfers between the CPU and the memory modules. Thus, they are suitable for low-power data-intensive applications. However, the complexity of DRAM command scheduling combined with tag management overheads in the cache makes the design of in-package cache controllers significantly challenging. Traditional memory controllers often face challenges with static, inflexible access scheduling designed for general applications, leading to suboptimal performance in dynamic environments. On the other hand, while some advanced controllers employing reinforcement learning offer adaptability to workload fluctuations, they tend to introduce hardware complexity and incur longer training latencies. Our approach aims to design low-power and efficient DRAM cache controllers using a machine learning model that dynamically adjusts to workload changes with optimized hardware efficiency and reduced training time. Therefore, we propose a machine learning approach to design low-power and efficient DRAM cache controllers that will leverage the trained model to produce optimal cache command schedules at runtime. The model considers several conditions for each request queue and chooses the best response among the options. The simulation results show the superiority of our proposed design over the previous algorithms in a set of twelve data-intensive applications; our model is able to improve the performance by up to 40% in some cases and an average of 15% in performance and 10% in power consumption. [ABSTRACT FROM AUTHOR]

The objective and automatic detection of the sleep–wake cycle (SWC) stages is essential for the investigation of its physiology and dysfunction. Here, we propose a machine learning model for the classification of SWC stages based on the measurement of synchronization between neural oscillations of different frequencies. Publicly available electrophysiological recordings of mice were analyzed for the computation of phase–amplitude couplings, which were then supplied to a multilayer perceptron (MLP). Firstly, we assessed the performance of several architectures, varying among different input choices and numbers of neurons in the hidden layer. The top performing architecture was then tested using distinct extrapolation strategies that would simulate applications in a real lab setting. Although all the different choices of input data displayed high AUC values (>0.85) for all the stages, the ones using larger input datasets performed significantly better. The top performing architecture displayed high AUC values (>0.95) for all the extrapolation strategies, even in the worst-case scenario in which the training with a single day and single animal was used to classify the rest of the data. Overall, the results using multiple performance metrics indicate that the usage of a basic MLP fed with highly descriptive features such as neural synchronization is enough to efficiently classify SWC stages. [ABSTRACT FROM AUTHOR]

Groundwater contamination source recognition is an important prerequisite for subsequent remediation efforts. To overcome the limitations of single inversion methods, this study proposed a two-stage inversion framework by integrating two primary inversion approaches—simulation-optimization and simulation-data assimilation—thereby enhancing inversion accuracy. In the first stage, the ensemble smoother with multiple data assimilation method (a type of simulation-data assimilation) conducted a global broad search to provide better initial values and ranges for the second stage. In the subsequent stage, a collective decision optimization algorithm (a type of simulation-optimization) was used for a refined deep search, further enhancing the final inversion accuracy. Additionally, a deep learning method, the multilayer perceptron, was utilized to establish a surrogate of the simulation model, reducing computational costs. These theories and methods were applied and validated in a hypothetical scenario for the synchronous identification of the contamination source and boundary conditions. The results demonstrated that the proposed two-stage inversion framework significantly improved search accuracy compared to single inversion methods, with a mean relative error and mean absolute error of just 4.95% and 0.1756, respectively. Moreover, the multilayer perceptron surrogate model offered greater approximation accuracy to the simulation model than the traditional shallow learning surrogate model. Specifically, the coefficient of determination, mean relative error, mean absolute error, and root mean square error were 0.9860, 9.72%, 0.1727, and 0.47, respectively, highlighting its significant advantages. The findings of this study can provide more reliable technical support for practical case applications and improve subsequent remediation efficiency. [ABSTRACT FROM AUTHOR]

Purpose – The study aims to explore how integrating recent fundamental values (RFVs) from conventional accounting studies enhances the accuracy of a machine learning (ML) model for predicting stock return movement in Indonesia. Design/methodology/approach – The study uses multilayer perceptron (MLP) analysis, a deep learning model subset of the ML method. The model utilizes findings from conventional accounting studies from 2019 to 2021 and samples from 10 firms in the Indonesian stock market from September 2018 to August 2019. Findings – Incorporating RFVs improves predictive accuracy in the MLP model, especially in long reporting data ranges. The accuracy of the RFVs is also higher than that of raw data and common accounting ratio inputs. Research limitations/implications – The study uses Indonesian firms as its sample. We believe our findings apply to other emerging Asian markets and add to the existing ML literature on stock prediction. Nevertheless, expanding to different samples could strengthen the results of this study. Practical implications – Governments can regulate RFV-based artificial intelligence (AI) applications for stock prediction to enhance decision-making about stock investment. Also, practitioners, analysts and investors can be inspired to develop RFV-based AI tools. Originality/value – Studies in the literature on ML-based stock prediction find limited use for fundamental values and mainly apply technical indicators. However, this study demonstrates that including RFV in the ML model improves investors’ decision-making and minimizes unethical data use and artificial intelligence-based fraud.

Abstract Background Pulmonary tuberculosis (PTB) is a prevalent chronic disease associated with a significant economic burden on patients. Using machine learning to predict hospitalization costs can allocate medical resources effectively and optimize the cost structure rationally, so as to control the hospitalization costs of patients better. Methods This research analyzed data (2020–2022) from a Kashgar pulmonary hospital’s information system, involving 9570 eligible PTB patients. SPSS 26.0 was used for multiple regression analysis, while Python 3.7 was used for random forest regression (RFR) and MLP. The training set included data from 2020 and 2021, while the test set included data from 2022. The models predicted seven various costs related to PTB patients, including diagnostic cost, medical service cost, material cost, treatment cost, drug cost, other cost, and total hospitalization cost. The model’s predictive performance was evaluated using R-square (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) metrics. Results Among the 9570 PTB patients included in the study, the median and quartile of total hospitalization cost were 13,150.45 (9891.34, 19,648.48) yuan. Nine factors, including age, marital status, admission condition, length of hospital stay, initial treatment, presence of other diseases, transfer, drug resistance, and admission department, significantly influenced hospitalization costs for PTB patients. Overall, MLP demonstrated superior performance in most cost predictions, outperforming RFR and multiple regression; The performance of RFR is between MLP and multiple regression; The predictive performance of multiple regression is the lowest, but it shows the best results for Other costs. Conclusion The MLP can effectively leverage patient information and accurately predict various hospitalization costs, achieving a rationalized structure of hospitalization costs by adjusting higher-cost inpatient items and balancing different cost categories. The insights of this predictive model also hold relevance for research in other medical conditions.

Host-pathogen interactions (HPIs) are vital in numerous biological activities and are intrinsically linked to the onset and progression of infectious diseases. HPIs are pivotal in the entire lifecycle of diseases: from the onset of pathogen introduction, navigating through the mechanisms that bypass host cellular defenses, to its subsequent proliferation inside the host. At the heart of these stages lies the synergy of proteins from both the host and the pathogen. By understanding these interlinking protein dynamics, we can gain crucial insights into how diseases progress and pave the way for stronger plant defenses and the swift formulation of countermeasures. In the framework of current study, we developed a web-based R/Shiny app, Deep-HPI-pred, that uses network-driven feature learning method to predict the yet unmapped interactions between pathogen and host proteins. Leveraging citrus and CLas bacteria training datasets as case study, we spotlight the effectiveness of Deep-HPI-pred in discerning Protein-protein interaction (PPIs) between them. Deep-HPI-pred use Multilayer Perceptron (MLP) models for HPI prediction, which is based on a comprehensive evaluation of topological features and neural network architectures. When subjected to independent validation datasets, the predicted models consistently surpassed a Matthews correlation coefficient (MCC) of 0.80 in host-pathogen interactions. Remarkably, the use of Eigenvector Centrality as the leading topological feature further enhanced this performance. Further, Deep-HPI-pred also offers relevant gene ontology (GO) term information for each pathogen and host protein within the system. This protein annotation data contributes an additional layer to our understanding of the intricate dynamics within host-pathogen interactions. In the additional benchmarking studies, the Deep-HPI-pred model has proven its robustness by consistently delivering reliable results across different host-pathogen systems, including plant-pathogens (accuracy of 98.4% and 97.9%), human-virus (accuracy of 94.3%), and animal-bacteria (accuracy of 96.6%) interactomes. These results not only demonstrate the model's versatility but also pave the way for gaining comprehensive insights into the molecular underpinnings of complex host-pathogen interactions. Taken together, the Deep-HPI-pred applet offers a unified web service for both identifying and illustrating interaction networks. Deep-HPI-pred applet is freely accessible at its homepage: https://cbi.gxu.edu.cn/shiny-apps/Deep-HPI-pred/ and at github: https://github.com/tahirulqamar/Deep-HPI-pred.