Journal of Advanced Trends in Medical Research · مجلد 2 (3) · 523-528
Background: Diabetic neuropathy is a common and disabling complication of type 2 diabetes (T2D), often linked to Vitamin B12 deficiency. Despite observed B12 malabsorption in T2D patients, the role of gut microbiota in this process is poorly understood. Methods: We established a novel fecal microbiota transplantation (FMT) model using samples from T2D patients stratified by B12 status and neuropathy severity, transplanted into germ-free mice. We assessed ileal expression of B12 transporters, serum B12 levels and cobalamin-related metabolites. Neuropathy progression was evaluated through nerve conduction studies and histopathological analysis. Microbial composition was analysed through 16S rRNA sequencing, and metabolomic data were obtained using ion mobility-enhanced liquid chromatography-mass spectrometry. Machine learning algorithms integrated microbial and host data to identify predictive patterns and therapeutic targets. Results: FMT from T2D donors with B12 deficiency led to decreased expression of B12 absorption markers and reduced serum B12 levels in recipient mice. These mice showed early signs of neuropathy, confirmed by slowed nerve conduction and structural nerve damage. Specific microbial taxa were significantly associated with altered B12 metabolism and indicators of neuropathy. Multiomics and machine learning analyses revealed key microbial signatures and metabolic pathways involved in B12 dysregulation. Conclusion: Gut microbiota plays a mechanistic role in Vitamin B12 malabsorption and the progression of diabetic neuropathy. This model provides a platform for microbiota-informed diagnostics and targeted interventions in T2D complications.
Human Activity Recognition (HAR) has applications in diverse fields, including sports management and behavior classification. Existing HAR methods can be categorized into three main approaches: camera-based, wearable sensor-based, and Wi-Fi sensing-based. Camera-based methods suffer from privacy concerns, while wearable sensor-based methods face limitations in battery longevity and continuous monitoring. Wi-Fi sensing methods mitigate privacy and battery issues but rely on costly Intel 5300 network cards or software-defined radio (SDR) platforms, limiting scalability. This paper presents a cost-effective IoT-based human activity recognition system using ESP32, leveraging its Wi-Fi sensing capabilities. The proposed system follows a structured workflow: (i) channel state information (CSI) is extracted from ESP32 modules, (ii) data preprocessing is performed using Hampel and Gaussian filters for noise and outlier removal, (iii) dimensionality reduction is achieved through Principal Component Analysis (PCA) and Discrete Wavelet Transform (DWT), and (iv) activity classification is conducted using Dynamic Time Warping (DTW) and the K-Nearest Neighbors (KNN) algorithm. Experimental evaluations demonstrate that the proposed system achieves an average recognition accuracy of 98.6 % across six human activities, comparable to high-end Intel 5300-based HAR systems, while significantly reducing hardware costs and improving ease of deployment.
human activity recognitionwearable sensorsInternet of ThingsESP32 microcontroller
KSII Transactions on Internet and Information Systems · مجلد 19 (10)
Human-Computer Interaction for autonomous communication systems is traditionally developed through the stages of the usability engineering paradigm.However, a major challenge within this paradigm is synchronizing evolving user needs with the dynamic interaction environment.To address this gap, this article proposes the Relativity Turner Training Algorithm (RTTA).The algorithm estimates the relativity measure between the user's interaction context and the actual requirements, allowing the system to adapt more effectively over time.Unlike rule-based techniques, the RTTA leverages machine learning to identify contextual adjustment trends and optimize requirement matching, drawing on past interaction data.The relativity factor is derived from users' previous interaction responses.When relativity is low, the algorithm anticipates potential context changes.The "Turner" component then evaluates whether these changes can yield higher relativity-that is, a closer alignment between the new context and the user's requirements.If such alignment is achieved, interaction quality improves, and the need for further adjustments decreases.In this way, the algorithm dynamically balances relativity (measuring context-requirement alignment) and Asma Aledrees et al.: Enhancing Human-Computer Interaction Context Awareness through the Relativity Turner Training Algorithm Turner (guiding beneficial context shifts) across both short-and long-term interaction intervals.To advance research in adaptive HCI systems, the proposed RTTA framework provides a robust foundation by enabling the seamless integration of advanced machine learning techniques with multimodal interaction methods.
Background and Objectives Hand and wrist fractures are among the most frequently encountered injuries in emergency departments and are often misdiagnosed, particularly when interpreted by non-specialist clinicians. These diagnostic errors can lead to treatment delays and long-term complications. Artificial intelligence (AI), particularly deep learning algorithms, is emerging as a promising adjunct to improve diagnostic accuracy in radiographic fracture detection. This study aims to evaluate the effectiveness of Artificial Intelligence (AI) in detecting hand and wrist fractures compared to manual radiographic interpretation by clinicians. Materials and Methods A systematic review and meta-analysis were conducted to assess the diagnostic performance of AI models in detecting hand and wrist fractures compared to conventional radiographic interpretation by clinicians. A comprehensive search of PubMed, Google Scholar, Science Direct, and Wiley Online Library was performed. Eligible studies included those utilizing AI for fracture detection with sensitivity and specificity data. Pooled estimates were calculated using fixed- and random-effects models. Heterogeneity was assessed via I 2 statistics, and publication bias was examined using funnel plots and Egger’s test. Results Eighteen studies met inclusion criteria. The pooled sensitivity and specificity under the random-effects model were 0.910 and 0.912, respectively, indicating high diagnostic accuracy of AI models. However, substantial heterogeneity (I 2 = 99.09% for sensitivity; 96.43% for specificity) and publication bias were observed, likely due to variations in AI algorithms, sample sizes, and study designs. Conclusions Most AI models demonstrated good diagnostic accuracy, with high sensitivity and specificity scores (≥90%). However, some models fell short in sensitivity and specificity (≤90%), indicating performance variations across different AI models or algorithms. From a clinical perspective, AI models with lower sensitivity scores may fail to detect hand and wrist fractures, potentially delaying treatment, while those with lower specificity scores could lead to unnecessary interventions—treating hands and wrists that are not fractured.
hand fractureswrist fracturesartificial intelligencedeep learning
Human Behavior and Emerging Technologies · مجلد 2025 (1)
ASD (autism spectrum disorder) is a neurodevelopmental disorder affecting people’s social interaction, learning, and communication skills worldwide. It is a behaviorally distinct syndrome that is combined with several unknown and known disorders. The symptoms include sleep disorders, seizures, gastrointestinal tract symptoms, anxiety, wandering, hyperactivity/attention‐deficit disorder, and obesity. Hence, early detection of ASD is significant. However, clinically standardized screening tests are considered a prolonged diagnostic time, which is prone to errors and also leads to a rise in medical costs. Therefore, to decrease the time required for diagnosis and improve the precision of the model, AI (artificial intelligence) (machine learning (ML)) techniques are used to complement other traditional methods. Hence, this study has proposed a modified deep dynamic Levenberg–Marquardt (DDLM) optimized approach, which enhances the accuracy and classifier’s precision for implementing binary classification of children with ASD and children without ASD and tackles the issues in early detection. The process starts by preprocessing the data using label encoding and feature scaling techniques for eradicating irrelevant and noisy data, and then classification proceeds by utilizing the modified DDLM model. The dataset used in the proposed model is an amalgamation of datasets, which are ASD meta‐abundance and GSE113690_Autism_16S_rRNA. Additionally, a comparison of classifiers with three ML‐based algorithms, namely, MLP (multilayer perceptron), NB (naïve Bayes), and XGBoost (extreme gradient boost), is performed to analyze the effectiveness of the proposed system in the binary classification of ASD. The efficacy of the proposed system is evaluated using performance factors such as specificity, precision, F 1‐score, accuracy, and recall.
Abstract Land use and land cover (LULC) analysis is crucial for understanding societal development and assessing changes during the Anthropocene era. Conventional LULC mapping faces challenges in capturing changes under cloud cover and limited ground truth data. To enhance the accuracy and comprehensiveness of the descriptions of LULC changes, this investigation employed a combination of advanced techniques. Specifically, multitemporal 30 m resolution Landsat-8 satellite imagery was utilized, in addition to the cloud computing capabilities of the Google Earth Engine (GEE) platform. Additionally, the study incorporated the random forest (RF) algorithm. This study aimed to generate continuous LULC maps for 2014 and 2020 for the Shrirampur area of Maharashtra, India. A novel multiple composite RF approach based on LULC classification was utilized to generate the final LULC classification maps utilizing the RF-50 and RF-100 tree models. Both RF models utilized seven input bands (B1 to B7) as the dataset for LULC classification. By incorporating these bands, the models were able to influence the spectral information captured by each band to classify the LULC categories accurately. The inclusion of multiple bands enhanced the discrimination capabilities of the classifiers, increasing the comprehensiveness of the assessment of the LULC classes. The analysis indicated that RF-100 exhibited higher training and validation/testing accuracy for 2014 and 2020 (0.99 and 0.79/0.80, respectively). The study further revealed that agricultural land, built-up land, and water bodies have changed adequately and have undergone substantial variation among the LULC classes in the study area. Overall, this research provides novel insights into the application of machine learning (ML) models for LULC mapping and emphasizes the importance of selecting the optimal tree combination for enhancing the accuracy and reliability of LULC maps based on the GEE and different RF tree models. The present investigation further enabled the interpretation of pixel-level LULC interactions while improving image classification accuracy and suggested the best models for the classification of LULC maps through the identification of changes in LULC classes.
land use and land cover changerandom forestLandsat 8Google Earth Engine
Smart grid represents an advanced and interconnected system that incorporates modern technologies to enhance efficiency, reliability and sustainability. In comparison to the conventional grid, the smart grid (SG) uses many cutting-edge technologies. This research introduces a fog computing encryption-based model for privacy preservation in the smart grid model. By using different advanced technologies, our model addresses the balance between privacy, security, effectiveness and functionality. The model facilitates efficient communication and function inquiry while mitigating challenges posed by massive Internet of Things (IoT) systems in the smart grid environment. Specifically, it tackles the secure data consolidation challenge by employing encryption-based techniques for transmitting private data from smart meters to fog devices. These devices consolidate the data before updating to cloud. Conventional data consolidation approaches for SGs have high computation and communication costs and suffer from high storage requirement. The proposed model resolves these issues; algorithms for data consolidation and extraction of data at fog device and cloud respectively to obtain the secure communication has also been included. The performance of the developed mechanism has been computed against existing data consolidation mechanisms GCEDA (Grouping of Clusters for Efficient Data Aggregation), SPPDA (Secure Privacy-Preserving Data Aggregation) and LPDA (Lightweight Privacy-preserving Data Aggregation) for numerous performance parameters. And the results proves that the performance of developed mechanism with respect to bytes of storage, communication cost and ratio of transmission is better than the existing ones.
smart gridInternet of Thingsfog computingdata encryption
This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R2 = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.
The Internet of Things (IoT) is an emerging technology that allow smart devices to communicate through various heterogeneous channels (wired or wireless). However, for conventional networks, it has become a challenging task to efficiently control and manage the data flows of a huge number of devices. Software-defined networking (SDN) is a new way of thinking about networking. Because it is programmable, flexible, agile, and gives you a big picture of the network, it has tried to solve some IoT problems, like scalability, heterogeneity, and complexity. In large-scale SDN-IoT networks, there is a requirement for routing protocols that are both efficient and secure in order to ensure a superior level of quality of service (QoS) and quality of experience (QoE). To address the above stated challenges, a novel deep reinforcement learning (DRL) known as DQQS model is proposed. The aim is to achieve QoS and QoE while also ensuring the security of the SDN-IoT network. The proposed DQQS model dynamically extracts patterns from the past network history by interacting with the underlying network and generating optimized routing policies. This article employs three network metrics—throughput, latency, and the probability of avoiding malicious nodes—to measure the performance of DQQS. Simulations reveal that the proposed framework outperforms four state-of-the-art routing algorithms: OSPF, L-L Routing, Sailfish Routing, and RL-Routing in terms of both throughput and latency. For instance, in an attacked environment, the proposed DQQS model achieved the highest throughput value of 14.5 Mbps, surpassing OSPF at 8 Mbps, L-L at 8.2 Mbps, Sailfish at 9 Mbps, and RL at 9.5 Mbps. Similarly, this model exhibited superior performance in latency, recording the lowest latency value of 52 ms, compared to OSPF 88 ms, L-L 85 ms, Sailfish 72 ms, and RL 75 ms routing algorithms. The experimental results demonstrate that this new DQQS model is a pioneering deep reinforcement learning-based technique that optimally addresses secure routing in the SDN-IoT environment, ensuring enhanced quality of service and experience, and outperforming state-of-the art DL methodologies in both security and network performance metrics.
software-defined networkingInternet of Thingssecure routingdeep reinforcement learning
Fraudulent activities especially in auto insurance and credit card transactions impose significant financial losses on businesses and individuals. To overcome this issue, we propose a novel approach for fraud detection, combining convolutional neural networks (CNNs) with support vector machine (SVM), k nearest neighbor (KNN), naive Bayes (NB), and decision tree (DT) algorithms. The core of this methodology lies in utilizing the deep features extracted from the CNNs as inputs to various machine learning models, thus significantly contributing to the enhancement of fraud detection accuracy and efficiency. Our results demonstrate superior performance compared to previous studies, highlighting our model's potential for widespread adoption in combating fraudulent activities.
Background: Differentiated thyroid cancer (DTC) is the most prevalent endocrine malignancy with a recurrence rate of about 20%, necessitating better predictive methods for patient management. This study aims to create a relational classification model to predict DTC recurrence by integrating clinical, pathological, and follow-up data. Methods: The balanced dataset comprises 550 DTC samples collected over 15 years, featuring 13 clinicopathological variables. To address the class imbalance in recurrence status, the Synthetic Minority Over-sampling Technique for Nominal and Continuous (SMOTE-NC) was utilized. A hybrid model combining classification algorithms with association rule mining was developed. Two relational classification approaches, regularized class association rules (RCAR) and classification based on association rules (CBAR), were implemented. Binomial logistic regression analyzed independent predictors of recurrence. Model performance was assessed through accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. Results: The RCAR model demonstrated superior performance over the CBAR model, achieving accuracy, sensitivity, and F1 score of 96.7%, 93.1%, and 96.7%, respectively. Association rules highlighted that papillary pathology with an incomplete response strongly predicted recurrence. The combination of incomplete response and lymphadenopathy was also a significant predictor. Conversely, the absence of adenopathy and complete response to treatment were linked to freedom from recurrence. Incomplete structural response was identified as a critical predictor of recurrence risk, even with other low-recurrence conditions. Conclusion: This study introduces a robust and interpretable predictive model that enhances personalized medicine in thyroid cancer care. The model effectively identifies high-risk individuals, allowing for tailored follow-up strategies that could improve patient outcomes and optimize resource allocation in DTC management.
The Levenberg–Marquardt (LM) backpropagation optimization algorithm, an artificial neural network algorithm, is used in this study to perform integrated numerical computing to evaluate the electromagnetohydrodynamic bioconvection flow of micropolar nanofluid with thermal radiation and stratification. The model is then reduced to a collection of boundary value problems, which are solved with the help of a numerical technique and the proposed scheme, i.e., the LM algorithm, which is an iterative approach to determine the minimum of a nonlinear function defined as the sum of squares. As a blend of the steepest descent and the Gauss–Newton method, it has become a typical approach for nonlinear least-squares problems. Furthermore, the stability and consistency of the algorithm are ensured. For validation purposes, the results are also compared with those of previous research and the MATLAB bvp4c solver. Neural networking is also utilized for velocity, temperature, and concentration profile mapping from input to output. These findings demonstrate the accuracy of forecasts and optimizations produced by artificial neural networks. The performance of the bvp4c solver, which is used to reduce the mean square error, is used to generalize a dataset. The artificial neural network-based LM backpropagation optimization algorithm operates using data based on the ratio of testing (13%), validation (17%), and training (70%). This stochastic computing work presents an activation log-sigmoid function based LM backpropagation optimization algorithm, in which tens of neurons and hidden and output layers are used for solving the learning language model. The overlapping of the results and the small computed absolute errors, which range from 10−3 to 10−10 and from 106 to 108 for each model class, indicate the accuracy of the artificial neural network-based LM backpropagation optimization algorithm. Furthermore, each model case’s regression performance is evaluated as if it were an ideal model. In addition, function fitness and histogram are used to validate the dependability of the algorithm. Numerical approaches and artificial neural networks are an excellent combination for fluid dynamics, and this could lead to new advancements in many domains. The findings of this research could contribute to the optimization of fluid systems, resulting in increased efficiency and production across various technical domains.
Monoamine oxidases (MAOs), specifically MAO-A and MAO-B, play important roles in the breakdown of monoamine neurotransmitters. Therefore, MAO inhibitors are crucial for treating various neurodegenerative disorders, including Parkinson's disease (PD), Alzheimer's disease (AD), and amyotrophic lateral sclerosis (ALS). In this study, we developed a novel cheminformatics pipeline by generating three diverse molecular feature-based machine learning-assisted quantitative structural activity relationship (ML-QSAR) models concerning MAO-B inhibition. PubChem fingerprints, substructure fingerprints, and one-dimensional (1D) and two-dimensional (2D) molecular descriptors were implemented to unravel the structural insights responsible for decoding the origin of MAO-B inhibition in 249 non-reductant molecules. Based on a random forest ML algorithm, the final PubChem fingerprint, substructure fingerprint, and 1D and 2D molecular descriptor prediction models demonstrated significant robustness, with correlation coefficients of 0.9863, 0.9796, and 0.9852, respectively. The significant features of each predictive model responsible for MAO-B inhibition were extracted using a comprehensive variance importance plot (VIP) and correlation matrix analysis. The final predictive models were further developed as a web application, MAO-B-pred ( https://mao-b-pred.streamlit.app/ ), to allow users to predict the bioactivity of molecules against MAO-B. Molecular docking and dynamics studies were conducted to gain insight into the atomic-level molecular interactions between the ligand-receptor complexes. These findings were compared with the structural features obtained from the ML-QSAR models, which supported the mechanistic understanding of the binding phenomena. The presented models have the potential to serve as tools for identifying crucial molecular characteristics for the rational design of MAO-B target inhibitors, which may be used to develop effective drugs for neurodegenerative disorders.
monoamine oxidase B inhibitorsMAO-B inhibitionPubChem fingerprintsmolecular descriptors
Phishing, an Internet fraud where individuals are deceived into revealing critical personal and account information, poses a significant risk to both consumers and web-based institutions. Data indicates a persistent rise in phishing attacks. Moreover, these fraudulent schemes are progressively becoming more intricate, thereby rendering them more challenging to identify. Hence, it is imperative to utilize sophisticated algorithms to address this issue. Machine learning is a highly effective approach for identifying and uncovering these harmful behaviors. Machine learning (ML) approaches can identify common characteristics in most phishing assaults. In this paper, we propose an ensemble approach and compare it with six machine learning techniques to determine the type of website and whether it is normal or not based on two phishing datasets. After that, we used the normalization technique on the dataset to transform the range of all the features into the same range. The findings of this paper for all algorithms are as follows in the first dataset based on accuracy, precision, recall, and F1-score, respectively: Decision Tree (DT) (0.964, 0.961, 0.976, 0.968), Random Forest (RF) (0.970, 0.964, 0.984, 0.974), Gradient Boosting (GB) (0.960, 0.959, 0.971, 0.965), XGBoost (XGB) (0.973, 0.976, 0.976, 0.976), AdaBoost (0.934, 0.934, 0.950, 0.942), Multi Layer Perceptron (MLP) (0.970, 0.971, 0.976, 0.974) and Voting (0.978, 0.975, 0.987, 0.981). So, the Voting classifier gave the best results. While in the second dataset, all the algorithms gave the same results in four evaluation metrics, which indicates that each of them can effectively accomplish the prediction process. Also, this approach outperformed the previous work in detecting phishing websites with high accuracy, a lower false negative rate, a shorter prediction time, and a lower false positive rate.
Frontiers in Computational Neuroscience · مجلد 18 · 1391025-1391025
According to experts in neurology, brain tumours pose a serious risk to human health. The clinical identification and treatment of brain tumours rely heavily on accurate segmentation. The varied sizes, forms, and locations of brain tumours make accurate automated segmentation a formidable obstacle in the field of neuroscience. U-Net, with its computational intelligence and concise design, has lately been the go-to model for fixing medical picture segmentation issues. Problems with restricted local receptive fields, lost spatial information, and inadequate contextual information are still plaguing artificial intelligence. A convolutional neural network (CNN) and a Mel-spectrogram are the basis of this cough recognition technique. First, we combine the voice in a variety of intricate settings and improve the audio data. After that, we preprocess the data to make sure its length is consistent and create a Mel-spectrogram out of it. A novel model for brain tumor segmentation (BTS), Intelligence Cascade U-Net (ICU-Net), is proposed to address these issues. It is built on dynamic convolution and uses a non-local attention mechanism. In order to reconstruct more detailed spatial information on brain tumours, the principal design is a two-stage cascade of 3DU-Net. The paper's objective is to identify the best learnable parameters that will maximize the likelihood of the data. After the network's ability to gather long-distance dependencies for AI, Expectation-Maximization is applied to the cascade network's lateral connections, enabling it to leverage contextual data more effectively. Lastly, to enhance the network's ability to capture local characteristics, dynamic convolutions with local adaptive capabilities are used in place of the cascade network's standard convolutions. We compared our results to those of other typical methods and ran extensive testing utilising the publicly available BraTS 2019/2020 datasets. The suggested method performs well on tasks involving BTS, according to the experimental data. The Dice scores for tumor core (TC), complete tumor, and enhanced tumor segmentation BraTS 2019/2020 validation sets are 0.897/0.903, 0.826/0.828, and 0.781/0.786, respectively, indicating high performance in BTS.