Performance Evaluation Metrics Research Articles

A systematic survey of fuzzy deep learning for uncertain medical data

Intelligent medical industry is in a rapid stage of development around the world, followed by are the expanding market size and basic theories of intelligent medical diagnosis and decision-making. Deep learning models have achieved good practical results in medical domain. However, traditional deep learning is almost calculated and developed by crisp values, while imprecise, uncertain, and vague medical data is common in the process of diagnosis and treatment. It is important and significant to review the contributions of fuzzy deep learning for uncertain medical data, because fuzzy deep learning that originated from fuzzy sets, can effectively deal with uncertain and inaccurate information, providing new viewpoints for alleviating the presence of noise, artifact or high dimensional unstructured information in uncertain medical data. Therefore, taking focus on the intersection of both different fuzzy deep learning models and several types of uncertain medical data, the paper first constructs four types of frameworks of fuzzy deep learning models used for uncertain medical data, and investigates the status from three aspects: fuzzy deep learning models, uncertain medical data and application scenarios. Then the performance evaluation metrics of fuzzy deep learning models are analyzed in details. This work has some original points: (1) four types of frameworks of applying fuzzy deep learning models for uncertain medical data are first proposed. (2) Seven fuzzy deep learning models, five types of uncertain medical data, and five application scenarios are reviewed in details, respectively. (3) The advantages, challenges, and future research directions of fuzzy deep learning for uncertain medical data are critically analyzed, providing valuable suggestions for further deep research.

Prediction and analysis of relative error in electric vehicle charging stations based on an improved ConvFormer model

In order to address the issue of metering inaccuracies in charging stations that directly affect the development of electric vehicles, a prediction method for the relative error of charging stations based on the ConvFormer model is proposed. The model combines Convolutional Neural Networks (CNN) with Transformer models in parallel, significantly improving the prediction accuracy. First, charging station data is preprocessed using forward interpolation and normalization methods, and the dataset is transformed into a dataset of input relative errors. Then, a neural network with an improved unidirectional convolutional and attention combination for time-series forecasting is constructed, and common regression performance evaluation metrics, MAE (Mean Absolute Error) and MSE (Mean Squared Error), are selected for evaluation. Finally, based on seven days of charging station data, the relative error of charging stations for the next 24 h is predicted, and compared to traditional Transformer and LSTM (Long Short-Term Memory) time-series models. The results show that the improved model yields the lowest values for both MAE and MSE, with a 47.30 % reduction in MAE compared to the Transformer model and a 38.06 % reduction compared to LSTM, and a 66.94 % reduction in MSE compared to the Transformer model and approximately 62.32 % reduction compared to LSTM.

Argo data anomaly detection algorithm based on selective ensemble of fuzzy clustering

Abstract Argo profiling float data is a crucial data source for fundamental research and predictive forecasting operations in oceanography and environmental science. However, compiling and organizing such datasets demands considerable time and human resources. Therefore, the quest for effective methods of detecting anomalies in Argo data is of paramount importance. In this regard, we propose three improvement strategies within the stacking ensemble framework: preserving the original training set, weighting base model outputs, and combining the two former methods. The aim is to explore implicit relationships within the data, enhance model prediction diversity, and improve Accuracy. Additionally, in the selection of base models, to address the challenge of conventional clustering-based ensemble algorithms in achieving high levels of both diversity and accuracy among base learners, we introduce a selective ensemble method based on C-means clustering. This method selects base learners for the ensemble based on weighted scores derived from membership and performance evaluation metrics. Both of these enhancement approaches demonstrate effective application and improved detection performance when applied to Argo data.

Lure: A simulator for networks of batteryless intermittent nodes

The emerging paradigm of batteryless intermittent sensor networks (BISNs) presents new challenges for researchers of low-power wireless systems and protocols. The nature of these challenges exacerbates the difficulty of evaluating networks of physical sensor nodes, making simulation an even more important component in evaluating performance metrics, such as communication throughput and delay, for BISN designs. To our knowledge, existing simulators and analytical models do not meet the unique needs of BISN research; therefore, we have created a new open-source BISN simulator named Lure. Lure is designed from the ground-up for simulation of batteryless intermittent systems and networks. Written in Python, Lure is powerful, flexible, highly configurable, and supports rapid prototyping of new protocols, systems, and applications, with a low learning curve. In this paper, we present Lure and validate it with experimental data to show that Lure can accurately reflect the reality of BISNs. We then demonstrate the process of applying Lure to research questions in select case studies.

Chemical approaches for the biomass valorisation: a comprehensive review of pretreatment strategies.

The most abundant natural renewable resource in the world, lignocellulosic biomass (LCB), has the potential to be exploited as a substitute green feedstock for the synthesis of various chemicals, materials, and biofuels. The annual global production of 13 billion tonnes of LCB offers an opportunity to cater to the increasing energy and materials requirement of process industries and also restricts the discharge of greenhouse gases. Although LCB is enriched with valuable ingredients such as cellulose, lignin, and hemicellulose, its recalcitrant nature limits its efficient utilisation. These components of LCB are strongly interlinked with each other, which resists their isolation and conversion valorisation into useful products. To disrupt the complicated structure of LCB and to isolate the lignocellulosic components in pure form, pretreatment is a crucial process in the bio-refinery, ensuring the economic feasibility of downstream processes. This review provides an outline of the structure, composition, and various sources of LCB; and the necessity of the pretreatment. Moreover, this article provides an in-depth analysis of the underlying mechanisms, advantages, and limitations of various pretreatment methods, such as physical, chemical, biological, and physicochemical. Further, the impact of chemical pretreatment techniques on the physicochemical characteristics of the material that is extracted from the biomass is also covered in detail through the rigorous evaluation of performance metrics, including substrate digestibility, sugar yield, inhibitor production, and energy requirements. This review provides a balanced and comprehensive overview of the state-of-the-art pretreatment strategies and their impact on biomass valorisation that will be useful to the scientists, engineers, and policy makers interested in biomass conversion technologies.

Perfect vortex Laguerre-Gauss beams as a carrier in the MMF/FSO communication system

This paper presents a novel, to the best of our knowledge, high-speed transmission system that integrates a new structured light beam, specifically the perfect vortex Laguerre-Gaussian (PVLG) beam, with an optical code division multiple access (OCDMA) system utilizing a premutation vector (PV) code. The PVLG beams are distinguished by their unique shape, which remains nearly invariant during propagation regardless of the azimuthal order of the orbital angular momentum (OAM), facilitating the multiplexing of multiple OAM beams within the same spatial area. Additionally, the system employs hybrid multimode fiber (MMF) and free space optics (FSO) channels, with consideration of foggy weather conditions in the FSO channel. A comparative analysis between the performance of PVLG beams and standard LG beams is conducted. Performance evaluation metrics include the Q-factor, bit error rate (BER), and eye diagrams, providing comprehensive insights into received signal quality. The results demonstrate that the system utilizing PVLG beams outperforms the one using standard LG beams. Specifically, the system achieves a maximum MMF length of 0.35 km with a BER of approximately 10−4 and a Q-factor of around three when the MMF cable channel is used only. For the FSO channel, the achievable ranges are 1.1 km, 0.7 km, and 0.35 km under low fog (LF), medium fog (MF), and high fog (HF) conditions, respectively, maintaining the same BER and Q-factor values. Moreover, the hybrid MMF/FSO channel extends the transmission range to 1.2 km under LF conditions and to 0.45 km under HF conditions, with consistent BER and Q-factor values. Each of the four PVLG beams carries 40 Gbps, resulting in a total transmission capacity of 160 Gbps. Thus, the proposed system is well positioned to meet the high-speed data transmission demands of next-generation 6G networks.

A high-level simulator for Network-on-Chip

This study presents a high-level simulator for Network-on-Chip (NoC), designed for many-core architectures, and integrated with the PlatEMO platform. The motivation for developing this tool arose from the need to evaluate the behavior of application mapping algorithms and the routing, both aspects are essential in the implementation and design of NoC architectures. This analysis underscored the importance of having effective NoC simulators as tools that allow for studying and comparing various network technologies while ensuring a controlled simulation environment. During this investigation and evaluation, some simulators, such as Noxim, NoCTweak, and NoCmap, among others, offered configurable parameters for application traffic, options to synthetically define topology and packet traffic patterns. Additionally, they include mapping options that optimize latency and energy consumption, routing algorithms, technological settings such as the CMOS process, and measurement options for evaluating performance metrics such as throughput and power usage. However, while these simulators meet detailed technical demands, they are mostly restricted to analyzing the low-level elements of the architecture, thus hindering quick and easy under- standing for non-specialists. This insight underscored the challenge in developing a tool that balances detailed analysis with a comprehensive learning perspective, considering the specific restrictions of each simulator analyzed. Experiments demonstrated the proposed simulator efficacy in handling algorithms like GA, PSO, and SA variant, and, surprisingly, revealed limitations of the XY algorithm in Mesh topologies, indicating the need for further investigation to confirm these findings. Future work will expand the simulator functionalities, incorporating a broader range of algorithms and performance metrics, to establish it as an indispensable tool for research and development in NoCs.

Identifying critical nodes in interdependent networks by GA-XGBoost

Once a critical node is destroyed, the interdependent network is prone to experience severe cascading failure. Due to the coupling, traditional methods are challenging to apply to interdependent networks. Here, we propose a novel comprehensive model based on machine learning. The main work of this data-driven approach is to train the model on a small set of nodes (5 % of the graph) and do the critical node identification on the rest. We collect node centrality indicators to describe the node features and provide informative input data from different dimensions. The uniform node sampling is improved to cluster oversampling, which combines K-means and Synthetic Minority Over-sampling Technique (SMOTE) to select and recreate uniformly distributed training samples. We optimize the XGBoost based on the Genetic algorithm (GA) to overcome the instability of manual parameters. Kendall's τ correlation coefficient, Jaccard similarity coefficient, R2, and RMSE are used as the model performance evaluation metrics. Experiment results confirm that the proposed GA-XGBoost model outperforms others, demonstrating higher adaptability and stability in various situations. The heuristic algorithm-optimized machine learning model offers a viable solution for identifying critical nodes in interdependent networks, which is of great significance for controlling virus propagation and preventing failures.

The impact of clock timing on VDT visual search performance under time constraint.

Conducting Visual Display Terminal (VDT) visual search tasks under time constraint has broad applications in fields such as security checks, medical diagnostics, and rescue operations. While excessive time pressure can impair performance, moderate time pressure can motivate individuals to complete tasks and increase productivity. Investigating the positive impact of time pressure on visual search tasks has become a crucial area of study. Clock timing plays a vital role in the visual interface, influencing the perception of time pressure and impacting visual search performance. However, existing research has paid little attention to the induction of time pressure and the impact of clock timing in VDT visual interfaces on visual search performance. Hence, the objective of this study is to investigate the impact of clock timing on VDT visual search performance under time constraint. The content of the experimental tasks was determined through a pilot experiment. The formal experiment was conducted in two phases over six sessions. Participants were tasked with locating the letter "E" embedded within the distractor letter "F," displayed with a clock area above the interface. The first phase of experiments included conditions of no clock, 4-min clock timing, and 4-min countdown clock timing. In the second phase of the experiment, the clock display method was a countdown clock, with three experiments conducted featuring long time, medium time, and short time. Search speed and accuracy were used as primary performance evaluation metrics to examine the impact of clock timing methods and duration on visual search performance. Twenty-one undergraduate students participated in the formal experiment. In the first phase of experiments, participants demonstrated significantly faster reaction times (RTs) in tasks where a clock display was present compared to tasks without (ANOVA, F(2, 60) = 4.588, P = 0.014). However, there were no significant differences in accuracy rates across different timing conditions (ANOVA, F(2, 60) = 0.146, P = 0.865), and no significant correlation between RTs and accuracy was found (Kendall's R = 0.11, P = 0.914). During the second phase, RTs decreased significantly as time constraints became more stringent (ANOVA, F(2, 60) = 7.564, P < 0.05). Conversely, accuracy rates decreased significantly under shorter time constraints (ANOVA, F(2, 60) = 4.315, P < 0.05), with a negative correlation observed between RTs and accuracy (Kendall's R = 0.220, P < 0.01). Compared to conditions without clock displays, having clock displays significantly improved the speed of the visual search task, although the difference in accuracy was not statistically significant. In the context of shorter clock countdown limits, Shorter timing constraints resulted in faster search speeds but also led to reduced accuracy and increased fatigue. Overall, a correlation exists between search speed and accuracy in visual tasks, where higher speed often correlates with lower accuracy. These findings provide valuable insights into clock timing design for visual search interfaces under time pressure.

Arctic tern-optimized weighted feature regression system for predicting bridge scour depth

This paper presents a pioneering artificial intelligence (AI) solution – the Arctic Tern-Optimized Weighted Feature Least Squares Support Vector Regression (ATO-WFLSSVR) system to aid civil engineers in accurately predicting scour depth at bridges. This prediction system amalgamates the strengths of hybrid models by uniting a metaheuristic optimization algorithm with weighted features and least squares support vector regression (WFLSSVR). The metaheuristic algorithm concurrently optimizes all hyperparameters of constituent WFLSSVR models, resulting in a highly effective system. Validation involves a comprehensive assessment using two case studies, which include datasets of scour depths across various complexities and pier foundation types. Comparative analyses against single AI models, conventional ensemble models, hybrid techniques, and empirical methods demonstrate that ATO-WFLSSVR's reliability outperforms others in performance evaluation metrics. Specifically, for the field dataset, ATO-WFLSSVR achieves MAPE and R values of 20.92% and 0.9435, respectively, and for scour depth data at complex pier foundations, it records MAPE and R values of 6.49% and 0.9384, respectively. The automated predictive analytics underscore the robustness, efficiency, and stability of ATO-WFLSSVR compared to existing methods. This study's notable contributions include the development of an innovative optimization algorithm named Arctic Terns Optimizer (ATO), proficiency in solving high-dimensional optimization problems, and the creation of a user-friendly graphical interface system, a promising tool for civil engineers to estimate scour depth at bridges. Further testing and evaluation of ATO-WFLSSVR across diverse datasets encompassing more complex scenarios are recommended. The data and source code for this study are currently accessible at https://www.researchgate.net/profile/Jui-Sheng-Chou/publications.

Improvement of Air Compressor Cooling with Intercooler Fine Pruning

An intercooler serves as a heat exchanger between the several stages of the working compressor, assisting in the transmission of thermal energy between fluids of varying temperatures. This article is about the experimental analysis of the effectiveness of an intercooler. Multiple variables oversee the performance evaluation under different circumstances. Standard operational values are used to calculate performance evaluation metrics such as total heat transfer coefficient and others. Heat rejection of intercoolers has been enhanced from 61% to 65% by the variation of different fin lengths. Furthermore, the recently added intercooler's isothermal efficiency, which reached an astounding 56.5% significantly, outperformed the earlier unit. This serves to highlight how well the intercooler design was modified. Furthermore, the effectiveness of the Intercooler was assessed considering the circumstances during operation. The intercooler fin is primarily concerned with the performance of the air compressor. This work analyses the many characteristics of fin length, fin number, and fin diameter. When compared to the existing intercooler, this modified intercooler has a high performance

Developing an Emotional Labor Scale for Employees in the Service Industry

Purpose: This research aims to develop an emotional labor scale and examine the consistency of the emotional labor measurement model with empirical data. The study focuses on individuals with long-term work experience and incorporates cross-cultural perspectives to address gaps in current research. Additionally, it seeks to create a standardized model for measuring and evaluating emotional labor that is applicable to contemporary work environments. Methodology: The population is front-service employees of hotels in Chonburi Province, and the sample consists of 280 front-service employees of hotels in Pattaya City, Chonburi Province. The research methodology for developing the emotional labor scale in this phase is quantitative research, using confirmatory factor analysis to examine the consistency of the emotional labor measurement model. Findings: The results of the model fit analysis and quality assessment of the CFA model found that the RMSEA (Root Mean Square Error of Approximation) was 0.217, indicating a lack of fit between the model and data. The CFI (Comparative Fit Index) was 0.591. The TLI (Tucker-Lewis Index) was 0.442. Finally, the IFI (Incremental Fit Index) was 0.595. Based on the presented indices, this model has a poor fit with the data. The RMSEA, CFI, TLI, and IFI values are lower than the recommended criteria, indicating a discrepancy between the model and data. Unique Contribution to Theory, Policy and Practice: These findings suggest that current emotional labor measurement models may not accurately capture the experiences of workers across different cultures and with varying lengths of work experience. Policymakers and organizations should consider developing more nuanced and culturally sensitive approaches to assess and manage emotional labor in the workplace. This could involve creating tailored training programs, revising performance evaluation metrics, and implementing supportive policies that acknowledge the complexity of emotional labor across diverse work environments.

CDTFAFN: A novel coarse-to-fine dual-scale time-frequency attention fusion network for machinery vibro-acoustic fault diagnosis

When the machinery device operates abnormally, it is not sufficient for fault detection only via extracting fault features from a single sensor due to the latent fault information may be scattered across multiple sensors. Multi-sensory fusion techniques with deep learning framework have attracted increasing attention from researchers due to the exploiting and integration of fault information between multiple sensors. Nevertheless, there are two remaining shortcomings in most existing multi-sensory fusion technologies. (1) Most existing fusion methods merely concentrate on conducting multi-sensory information fusion from time-domain or frequency-domain to achieve fault diagnosis, which are often unsatisfactory in the face of strong noise environments. (2) The collaborative fusion between several vibration sensors is generally considered in the past works, whereas the complementary information fusion between multi-sensory vibro-acoustic heterogeneous data are rarely studied. To address these deficiencies, this paper proposes a novel coarse-to-fine dual-scale time-frequency attention fusion network (CDTFAFN) for machinery fault diagnosis, which not only adequately considers the complementary information fusion of vibro-acoustic signal, but also has robust feature learning capabilities in a noisy scenario. Firstly, the signal-to-image encoding unit (SIEU) containing the improved constant-Q non-stationary Gabor transform (ICQ-NSGT) is introduced to convert the collected raw vibro-acoustic heterogeneous signal into time-frequency representation (TFR) and achieve the coarse-grained feature fusion. Secondly, the time-frequency attention feature fusion unit (TFA-FFU) is designed to concurrently learn the fine-grained features at two scales from the low-level fused features which are meaningful for fault diagnosis. Finally, the coarse-to-fine features are sequentially concatenated and fed into softmax classifier to preferably promote the network learning performance and automatically implement fault classification. The performance of the proposed approach is validated against those state-of-the-art results on two groups of multi-sensory vibro-acoustic data in different experimental platforms. Experiment results show that the proposed method with the diagnosis accuracy of 99 % above outperforms other several representative fusion technologies (i.e., 2MNet, MFF-GBFD, MSCNN-BiLSTM, MFAN-VAF, 1D-CNN-VAF, MI-CNN-TFT and TFFN-VAF) in the raw noise-free addition scenario. Moreover, the average testing accuracy of the proposed method can still reach 97 % above in the noisy scenarios with Gaussian white noises, which shows its competitive superiority and strong robustness against noises in machinery fault diagnosis. According to the five ensemble macro-average performance evaluation metrics (i.e., accuracy, precision, sensitivity, specificity and F1-score) and the receiver operator characteristic (ROC) analysis, our findings also emphasize the superiority of applying our method for machinery fault diagnosis under the colored noises compared with other fusion technologies (i.e., 2MNet, MFF-GBFD, MSCNN-BiLSTM, MFAN-VAF, 1D-CNN-VAF, MI-CNN-TFT and TFFN-VAF) reported in this paper.

An Agile Approach for Adopting Sustainable Energy Solutions with Advanced Computational Techniques

In the face of the burgeoning electricity demands and the imperative for sustainable development amidst rapid industrialization, this study introduces a dynamic and adaptable framework suitable for policymakers and renewable energy experts working on integrating and optimizing renewable energy solutions. While using a case study representative model for Sub-Saharan Africa (SSA) to demonstrate the challenges and opportunities present in introducing optimization methods to bridge power supply deficits and the scalability of the model to other regions, this study presents an agile multi-criteria decision tool that pivots on four key development phases, advancing established methodologies and pioneering refined computational techniques, to select optimal configurations from a set of Policy Decision-Making Metrics (PDM-DPS). Central to this investigation lies a rigorous comparative analysis of variants of three advanced algorithmic approaches: Swarm-Based Multi-objective Particle Swarm Optimization (MOPSO), Decomposition-Based Multi-objective Evolutionary Algorithm (MOEA/D), and Evolutionary-Based Strength Pareto Evolutionary Algorithm (SPEA2). These are applied to a grid-connected hybrid system, evaluated through a comprehensive 8760-hour simulation over a 20-year planning horizon. The evaluation is further enhanced by a set of refined Algorithm Performance Evaluation Metrics (AL-PEM) tailored to the specific constraints. The findings not only underscore the robustness and consistency of the SPEA2 variant over 15 runs of 200 generations each, which ranks first on the AL-PEM scale, but the findings also validate the strategic merit of combining multiple technologies and empowering policymakers with a versatile toolkit for informed decision-making.

Exploring the effects of faults on the performance of a biological wastewater treatment process

ABSTRACT To prioritise which faults should be detected in a biological wastewater treatment process, and with what level of urgency, it is necessary to understand the effect that they have on the process. Using the Benchmark Simulation Model No. 1 and 2. (BSM1 and BSM2), several process and sensor faults were considered and their impacts on various cost, quality, and controller performance evaluation metrics analysed. Both the cost of treating the wastewater and the quality of the effluent were impacted in varying degrees of severity by the faults tested. The most influential faults in both models were decreases to autotrophic and heterotrophic growth rates, decreases to the heterotrophic death rate, and the inhabitation fault. It was shown that only larger fault sizes were significant, and the required speed of detection is dependent on the fault profile. Prioritising detection of the most influential faults was shown to have significant effects on monitoring requirements for fault detection and the subsequent complexity required of a fault detection system. A valuable takeaway was the similarity of results from BSM1 and BSM2; the consistency of the influential process faults suggests that systems that can be described by these models are likely affected by the same faults.

Prediction of Human Physiological States by Using an Enhanced Recursive Feature Elimination Method

Human Action Recognition (HAR) is a vital part of the healthcare sector. Medical practitioners are experiencing difficulty in recognizing human physiological conditions due to the enormous quantity of sensory stimulation. Machine learning techniques help to predict human physiological conditions, providing medical practitioners to work more efficiently. Feature selection is an essential part of discovering new knowledge in the majority of real-world problems when there are a lot of features. Feature selection is extremely useful because it speeds up decisions and enhances classification performance. The importance of feature selection in machine learning is dimension reduction in a massive multivariate data collection. This paper presents an effective feature selection method known as the Enhanced Recursive Feature Elimination (EFRE) for selecting key features from the data set for HAR prediction. The experimental results reveal that the ERFE technique selects the most suitable features for HAR prediction. The performance of the proposed ERFE approach is tested using different performance evaluation metrics. The performance analysis shows that the ERFE method outperforms existing feature selection methods with 88% accuracy.

Radiomics as a measure superior to common similarity metrics for tumor segmentation performance evaluation.

To propose radiomics features as a superior measure for evaluating the segmentation ability of physicians and auto-segmentation tools and to compare its performance with the most commonly used metrics: Dice similarity coefficient (DSC), surface Dice similarity coefficient (sDSC), and Hausdorff distance (HD). The data of 10 lung cancer patients' CT images with nine tumor segmentations per tumor were downloaded from the RIDER (Reference Database to Evaluate Response) database. Radiomics features of 90 segmented tumors were extracted using the PyRadiomics program. The intraclass correlation coefficient (ICC) of radiomics features were used to evaluate the segmentation similarity and compare their performance with DSC, sDSC, and HD. We calculated one ICC per radiomics feature and per tumor for nine segmentations and 36 ICCs per radiomics feature for 36 pairs of nine segmentations. Meanwhile, there were 360 DSC, sDSC, and HD values calculated for 36 pairs for 10 tumors. The ICC of radiomics features exhibited greater sensitivity to segmentation changes than DSC and sDSC. The ICCs of the wavelet-LLL first order Maximum, wavelet-LLL glcm MCC, wavelet-LLL glcm Cluster Shade features ranged from 0.130 to 0.997, 0.033 to 0.978, and 0.160 to 0.998, respectively. On the other hand, all DSC and sDSC were larger than 0.778 and 0.700, respectively, while HD varied from 0 to 1.9mm. The results indicated that the radiomics features could capture subtle variations in tumor segmentation characteristics, which could not be easily detected by DSC and sDSC. This study demonstrates the superiority of radiomics features with ICC as a measure for evaluating a physician's tumor segmentation ability and the performance of auto-segmentation tools. Radiomics features offer a more sensitive and comprehensive evaluation, providing valuable insights into tumor characteristics. Therefore, the new metrics can be used to evaluate new auto-segmentation methods and enhance trainees' segmentation skills in medical training and education.

MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction.

Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.

Artificial intelligence can be used in the identification and classification of shoulder osteoarthritis and avascular necrosis on plain radiographs: a training study of 7,139 radiograph sets.

Knowledge concerning the use AI models for the classification of glenohumeral osteoarthritis (GHOA) and avascular necrosis (AVN) of the humeral head is lacking. We aimed to analyze how a deep learning (DL) model trained to identify and grade GHOA on plain radiographs performs. Our secondary aim was to train a DL model to identify and grade AVN on plain radiographs. A modified ResNet-type network was trained on a dataset of radiographic shoulder examinations from a large tertiary hospital. A total of 7,139 radiographs were included. The dataset included various projections of the shoulder, and the network was trained using stochastic gradient descent. Performance evaluation metrics, area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to assess the network's performance for each outcome. The network demonstrated AUC values ranging from 0.73 to 0.93 for GHOA classification and > 0.90 for all AVN classification classes. The network exhibited lower AUC for mild cases compared with definitive cases of GHOA. When none and mild grades were combined, the AUC increased, suggesting difficulties in distinguishing between these 2 grades. We found that a DL model can be trained to identify and grade GHOA on plain radiographs. Furthermore, we show that a DL model can identify and grade AVN on plain radiographs. The network performed well, particularly for definitive cases of GHOA and any level of AVN. However, challenges remain in distinguishing between none and mild GHOA grades.

Utilizing a CNN-RNN machine learning approach for forecasting time-series outlet fluid temperature monitoring by long-term operation of BHEs system

The Borehole Heat Exchanger (BHE) plays a pivotal role in enhancing heat exchange efficiency within Ground Source Heat Pump (GSHP) systems. The accurate prediction of the BHE's outlet fluid temperature is crucial for optimizing GSHP performance, energy storage, and resource conservation. However, conventional machine learning methods encounter challenges in manual feature extraction, learning complex nonlinear relationships, and adapting to real-world scenarios. To address these limitations, this research proposes a crossbreed model integrating Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) architectures to forecast long-term outlet fluid temperature in BHE systems. The model framework encompasses data preprocessing, utilizing refined data in the CNN module for temporal feature extraction, subsequently passed to the RNN module to capture sequential and temporal patterns from each dataset. Specifically, the advanced CNN-RNN architecture is designed to establish a comprehensive input-output mapping, leveraging essential input features such as inlet fluid, ambient air, and subsurface temperatures at varying depths (0, 10, and 20 m). Performance evaluation metrics, including R2, RMSE, MAE, and AARE, are employed to compare and assess prediction accuracy across various models, including LSTM, CNN, and SimpleRNN. The obtained results demonstrate the superior performance of the proposed model, achieving an RSME of 0.818, MAE of 0.642, AARE of 0.0305, and an R2 value of 98.75 %. This surpasses the performance of traditional prediction models (LSTM, CNN, and SimpleRNN) by 3.01 %, 5.80 %, and 19.52 %, respectively. Notably, the remarkably low MAE of 0.642 exhibited by a CNN-RNN model underscores its capability to outperform traditional approaches, especially when handling large datasets. These findings emphasize the significance of the developed model in facilitating efficient operation, positioning it as a valuable tool for advancing the long-term sustainability of BHE systems.