Adaptive Learning Mechanism Research Articles

Establishing effective learning bridge cross multi-scale feature maps for object detection and semantic segmentation

ABSTRACT In the field of image object detection and semantic segmentation, improving the accuracy of object identification and segmentation is a primary goal. To achieve this, leveraging the potential of multi-scale information through feature map refinement and fusion has been widely recognized. However, existing feature fusion methods either design more complex feature pyramid networks, replace existing detectors, or incrementally introduce feature fusion modules, overlooking the effective approach of enhancing spatial information in deep feature maps. We propose a novel pluggable feature fusion paradigm termed ‘Effective Learning Bridge’. Our research introduces an efficient and adaptive learning mechanism that builds learning bridges between feature maps at different scales within the feature pyramid, thereby enhancing the spatial information of objects in deep feature maps. This mechanism is specifically designed for multi-scale feature maps and can be seamlessly integrated into any network incorporating feature maps. By altering the model’s backpropagation path, we successfully improve learning efficiency, which in turn enhances the accuracy of object detection and segmentation. Our proposed paradigm and method were extensively evaluated through experiments on SIMD, HRSID, and WHDLD datasets and benchmark models. The results unequivocally demonstrate the effectiveness of our approach in significantly improving the accuracy of object detection and semantic segmentation, as well as the overall learning efficiency of the model.

Advancements in smart agriculture through innovative weed management using wavelet-based convolution neural network

Smart agriculture has shifted the paradigm by integrating advanced technologies, particularly weed management. This paper introduces an innovative approach to weed control by applying a Wavelet-based Convolution Neural Network (WCNN). In the era of precision agriculture, our study explores the integration of WCNN into real-world scenarios, emphasizing its adaptability to diverse environmental conditions. Utilizing the spatial-frequency analysis features of wavelets and convolutional neural networks, the WCNN model is the most effective at finding weeds, classifying them, and managing them specifically in agricultural fields in real-time. This research contributes to the scientific discourse on smart agriculture and addresses the challenges of invasive weeds, presenting a sustainable solution for optimizing resource utilization. Our investigation includes a detailed exploration of WCNN’s adaptive learning mechanisms and dynamic adjustment to changing agricultural landscapes. The model seamlessly integrates with existing smart farming infrastructure, showcasing a substantial reduction in manual intervention and a simultaneous increase in agricultural productivity. We incorporate fog computing and resource optimization into our framework, enhancing the efficiency of onboard data processing. To evaluate the real-world efficacy of WCNN, we conducted comprehensive experiments in texture classification and image labelling using two distinct datasets: the plant seedling and soybean weed datasets. Results demonstrate the superior performance of WCNN, achieving higher accuracy in training and test scenarios with significantly fewer parameters than traditional CNNs. For the soybean weed dataset, WCNN achieved remarkable accuracy in the training (0.9970) and testing (0.9987) phases, with correspondingly low losses of 0.0109 and 0.0048. The WCNN model demonstrated high accuracy during training (0.9739) and testing (0.9902), with minimal losses of 0.0898 and 0.0239 in the plant seedling dataset.

Improved identification of network anomalies through optimal CURE clustering

Abstract In this paper, we propose an advanced network anomaly behavior identification framework to overcome the constraints inherent in conventional rule- or signature-based approaches, which often struggle with emerging and previously unknown threats. Central to our framework is an Enhanced CURE (Cluster Updating and REfining) clustering algorithm, meticulously tailored and refined to incorporate a density-based methodology. This enhancement enables the algorithm to discern subtle shifts in network anomaly patterns with heightened precision. The implementation workflow commences with the application of the optimized CURE algorithm to analyze network data, followed by the deployment of a sophisticated anomaly degree ranking mechanism. This mechanism, through meticulous calculation of individual data points' anomaly degrees and subsequent ranking, effectively isolates those deviating significantly from standard behavioral norms, incorporating a strategic threshold to filter out false positives. To validate our methodology's efficacy and its superiority over existing techniques, experiments were conducted utilizing a substantial real-world network dataset. These tests affirm not only a marked increase in the accuracy of abnormal behavior recognition and a reduction in computational intricacy but also demonstrate the adaptability across diverse network ecosystems. Our approach has proven successful in pinpointing a wide array of network anomalies, encompassing malicious cyberattacks, fraudulent activities, unauthorized intrusions, and breaches of security protocols, thereby highlighting its comprehensive capability in bolstering network defense strategies. Despite the notable advancements and successful identification of various network anomalies, our framework currently lacks integration with real-time learning capabilities, limiting its immediate responsiveness to rapidly evolving attack patterns and necessitating ongoing research for dynamic updates and adaptive learning mechanisms.

Temporal dynamics of uncertainty and prediction error in musical improvisation across different periods

Human improvisational acts contain an innate individuality, derived from one’s experiences based on epochal and cultural backgrounds. Musical improvisation, much like spontaneous speech, reveals intricate facets of the improviser’s state of mind and emotional character. However, the specific musical components that reveal such individuality remain largely unexplored. Within the framework of human statistical learning and predictive processing, this study examined the temporal dynamics of uncertainty and surprise (prediction error) in a piece of musical improvisation. This cognitive process reconciles the raw auditory cues, such as melody and rhythm, with the musical predictive models shaped by its prior experiences. This study employed the Hierarchical Bayesian Statistical Learning (HBSL) model to analyze a corpus of 456 Jazz improvisations, spanning 1905 to 2009, from 78 distinct Jazz musicians. The results indicated distinctive temporal patterns of surprise and uncertainty, especially in pitch and pitch-rhythm sequences, revealing era-specific features from the early 20th to the 21st centuries. Conversely, rhythm sequences exhibited a consistent degree of uncertainty across eras. Further, the acoustic properties remain unchanged across different periods. These findings highlight the importance of how temporal dynamics of surprise and uncertainty in improvisational music change over periods, profoundly influencing the distinctive methodologies artists adopt for improvisation in each era. Further, it is suggested that the development of improvisational music can be attributed to the adaptive statistical learning mechanisms. This study explores the period-specific characteristics in the temporal dynamics of improvisational music, emphasizing how artists adapt their methods to resonate with the cultural and emotional contexts of their times. Such shifts in improvisational ways offer a window into understanding how artists intuitively respond and adapt their craft to resonate with the cultural zeitgeist and the emotional landscapes of their respective times.

Reservoir Operation based Machine Learning Models: Comprehensive Review for Limitations, Research Gap, and Possible Future Research Direction

The operation of dams and reservoirs is critical for water resource management, including flood control, irrigation, hydropower generation, and environmental conservation. Traditional optimization techniques like Dynamic Programming (DP), Linear Programming (LP), and Nonlinear Programming (NLP) have been foundational in managing these operations. However, they often fall short in addressing the complexities of modern water management challenges posed by climate variability and increasing water demands. Machine learning (ML) techniques have emerged as powerful tools to enhance the efficiency and accuracy of dam and reservoir operations. This paper provides a comprehensive review of various ML models, including Neural Networks, Genetic Algorithms, Decision Trees, and Ensemble Methods, highlighting their applications in predicting reservoir inflows, optimizing water release schedules, and improving flood risk management. Notably, ML models like Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs) have shown significant improvements in forecasting accuracy and operational decision-making. Despite these advancements, several limitations and research gaps persist, including the need for real-time data integration, adaptive learning mechanisms, and models that consider socio-economic and climatic factors. This review underscores the importance of addressing these gaps to develop more robust and generalizable ML models. Future research directions are suggested to focus on hybrid models combining ML with traditional optimization techniques, comprehensive validation across diverse conditions, and the integration of ecological and economic considerations. By systematically identifying and addressing these limitations, this research aims to pave the way for more effective and sustainable dam and reservoir management practices. Leading towards suggesting that enhancing real-time data integration and developing adaptive learning mechanisms are in order to improve model responsiveness.

Multi-order graph clustering with adaptive node-level weight learning

Current graph clustering methods emphasize individual node and edge connections, while ignoring higher-order organization at the level of motif. Recently, higher-order graph clustering approaches have been designed by motif-based hypergraphs. However, these approaches often suffer from hypergraph fragmentation issue seriously, which degrades the clustering performance greatly. Moreover, real-world graphs usually contain diverse motifs, with nodes participating in multiple motifs. A key challenge is how to achieve precise clustering results by integrating information from multiple motifs at the node level. In this paper, we propose a multi-order graph clustering model (MOGC) to integrate multiple higher-order structures and edge connections at node level. MOGC employs an adaptive weight learning mechanism to automatically adjust the contributions of different motifs for each node. This not only tackles hypergraph fragmentation issue but enhances clustering accuracy. MOGC is efficiently solved by an alternating minimization algorithm. Experiments on seven real-world datasets illustrate the effectiveness of MOGC.

Challenges of Using Synthetic Data Generation Methods for Tabular Microdata

The generation of synthetic data holds significant promise for augmenting limited datasets while avoiding privacy issues, facilitating research, and enhancing machine learning models’ robustness. Generative Adversarial Networks (GANs) stand out as promising tools, employing two neural networks—generator and discriminator—to produce synthetic data that mirrors real data distributions. This study evaluates GAN variants (CTGAN, CopulaGAN), a variational autoencoder, and copulas on diverse real datasets of different complexity encompassing numerical and categorical attributes. The results highlight CTGAN’s sensitivity to training parameters and TVAE’s robustness across datasets. Scalability challenges persist, with GANs demanding substantial computational resources. TVAE stands out for its high utility across all datasets, even for high-dimensional data, though it incurs higher privacy risks, which is indicative of the curse of dimensionality. While no single model universally excels, understanding the trade-offs and leveraging model strengths can significantly enhance synthetic data generation (SDG). Future research should focus on adaptive learning mechanisms, scalability enhancements, and standardized evaluation metrics to advance SDG methods effectively. Addressing these challenges will foster broader adoption and application of synthetic data.

State-of-the-art review on the use of AI-enhanced computational mechanics in geotechnical engineering

Significant uncertainties can be found in the modelling of geotechnical materials. This can be attributed to the complex behaviour of soils and rocks amidst construction processes. Over the past decades, the field has increasingly embraced the application of artificial intelligence methodologies, thus recognising their suitability in forecasting non-linear relationships intrinsic to materials. This review offers a critical evaluation AI methodologies incorporated in computational mechanics for geotechnical engineering. The analysis categorises four pivotal areas: physical properties, mechanical properties, constitutive models, and other characteristics relevant to geotechnical materials. Among the various methodologies analysed, ANNs stand out as the most commonly used strategy, while other methods such as SVMs, LSTMs, and CNNs also see a significant level of application. The most widely used AI algorithms are Artificial Neural Networks (ANN), Random Forest (RF), and Support Vector Machines (SVM), representing 35%, 19%, and 17% respectively. The most extensive AI application is in the domain of mechanical properties, accounting for 59%, followed by other applications at 16%. The efficacy of AI applications is intrinsically linked to the type of datasets employed, the selected model input. This study also outlines future research directions emphasising the need to integrate physically guided and adaptive learning mechanisms to enhance the reliability and adaptability in addressing multi-scale and multi-physics coupled mechanics problems in geotechnics.

Artificial Intelligence (AI) Towards Students’ Academic Performance

The study examines the impact of artificial intelligence (AI) on students’ academic performance, focusing on factors such as improved student performance, attitudes toward learning, motivation for study habits, and learning mechanisms. Further, it aims to evaluate and analyze how AI enhances student academic outcomes. A mixed-methods approach, incorporating focus group discussions (FGD), was used to gather quantitative and qualitative data. Random sampling was employed to select a sample size of 100 respondents based on predefined criteria. The results indicate that AI effectively targets the specific learning needs of students, facilitating comprehensive and improved learning experiences. It identifies struggling learners and provides necessary interventions and support to enhance their academic performance. Additionally, AI accurately measures and enhances students’ attitudes toward learning, offering deeper insights into the learning process. It also boosts students’ motivation toward study habits and learning behavior. Furthermore, AI’s adaptive learning mechanisms guide students’ learning processes and provide valuable feedback.

Fuzzy logic framework for financial distress prediction: Enhancing corporate decision-making under uncertainty

This research aims to develop an enhanced Fuzzy Logic Framework for Financial Distress Prediction to improve corporate decision-making under uncertainty. The primary objective is to address limitations in traditional fuzzy logic models, such as static rule bases and lack of adaptability to dynamic financial conditions. To achieve this, a time-dependent fuzzy logic system is proposed, incorporating real-time financial data and adaptive learning mechanisms to improve predictive accuracy over time. The research design involves creating a dynamic fuzzy rule base, assigning weights to rules based on predictive performance, and optimizing membership functions and rule weights using real-time data. The methodology applies the proposed framework to financial indicators such as liquidity, profitability, and leverage, with a numerical example demonstrating the system's effectiveness in predicting financial distress. The results show that the model can accurately predict financial distress levels, with a predicted distress value of 0.588 compared to an actual value of 0.6. The model’s ability to update rule weights and optimize predictions over time represents a significant improvement over static fuzzy logic models. This research fills a critical gap in financial distress prediction by introducing a dynamic, adaptive fuzzy logic framework that evolves with real-time data. The model offers significant implications for both academics and industry, providing a tool for more accurate risk assessment in volatile financial environments. However, further research is needed to refine the model’s computational efficiency and test its long-term predictive capabilities across different industries

A learning numerical spiking neural P system for classification problems

In recent years, classification problems have been widely studied as one of the critical research directions in artificial intelligence. Efficiently simulating the human brain’s ability to solve deterministic classification problems has become a prominent research branch in the field of classification problems. Numerical spiking neural P systems (NSN P systems) with the characteristics of the highly flexible spiking neural P (SNP)systems architecture and addressing numerical variants have special advantages for solving classification problems in the real world. This paper proposes, a novel NSN P system, namely, a learning numerical spiking neural P system (LNSN P system), is proposed to solve classification problems. In LNSN P systems, each neuron contains not only discrete spikes and rules that must be described by regular expressions but also numerical variables and production functions that can be in any form, overcoming the discontinuity of traditional SN P systems. In addition, an ascending structure without an outer encoder has been designed in this study to encode information from low-dimensional indivisible space to high-dimensional divisible space. At the same time, an adaptive learning mechanism has been introduced to improve algorithm convergence and precision. Finally, the experimental results obtained using eight benchmark datasets from the machine learning repository demonstrate the feasibility and effectiveness of the proposed LNSN P system. Moreover, the proposed LNSN P system exhibits lower space complexity and better generalisation ability than the existing SN P systems with the learning ability to solve different classification problems.

Exploring the impact of AI-driven solutions on cybersecurity adoption in small and medium enterprises

This study delves into the intricate dynamics of cybersecurity adoption within small and medium enterprises (SMEs), with a specific focus on the transformative potential of AI-driven solutions from a machine learning perspective. Leveraging a rich and diverse dataset of real-world cybersecurity incidents tailored to the SME context, the research meticulously investigates the efficacy of three prominent machine learning models: logistic regression, random forest, and gradient boost classifiers. Through a comprehensive evaluation using a suite of performance metrics, including accuracy, precision, recall, and F1 scores, the study scrutinizes the predictive capabilities of these models in forecasting and categorizing cyber threats encountered by SMEs. The findings unveil nuanced insights into the multifaceted challenges and opportunities inherent in the cybersecurity landscape of SMEs, shedding light on the complex interplay between AI-driven solutions and evolving cyber threats. While the analysis reveals commendable performance across the models, it also uncovers inherent limitations in accurately discerning and categorizing specific types of attacks. These findings underscore the critical need for ongoing refinement and optimization of AI-driven cybersecurity solutions, necessitating a continuous, iterative process informed by real-world data and adaptive learning mechanisms. By harnessing the strengths of machine learning and embracing a proactive stance towards cybersecurity, SMEs can fortify their defense mechanisms and safeguard their digital assets in the increasingly volatile and interconnected digital ecosystem.

Construction of Algorithms for English Learners to Read Foreign Literature Based on Machine Translation Technology

The construction of algorithms for English learners to read foreign literature based on machine translation technology involves several key steps. Initially, the algorithm utilizes machine translation to convert the foreign text into English, ensuring accessibility for learners. Next, it employs natural language processing (NLP) techniques to enhance the readability and comprehension of the translated text, such as simplifying complex sentences, clarifying ambiguous phrases, and providing annotations or explanations for cultural or linguistic nuances. Additionally, the algorithm may incorporate adaptive learning mechanisms to personalize the reading experience, adjusting the difficulty level and content based on the learner's proficiency and preferences. This paper explores the development and implementation of algorithms designed to facilitate English learners' comprehension of foreign literature using machine translation technology. Leveraging Probability Path analysis and classification techniques, investigate the effectiveness of various algorithms in improving translation accuracy, fluency, and comprehension for English learners. Through the Probability Path analysis, we delve into the complexities of language structures, translation probabilities, learner interaction, and linguistic adaptation, illuminating the intricate dynamics of machine translation in the context of language learning. Additionally, classification results provide insights into the performance of different algorithms in translating diverse literary genres, showcasing their potential to support English learners in comprehending foreign texts. The findings reveal translation accuracies ranging from 87.8% to 92.0%, with corresponding fluency scores ranging from 4.0 to 4.6. Additionally, algorithms result in comprehension improvements of 23% to 30% for English learners.

Statistical pathways to low-carbon cities: Analyzing renewable integration, energy-efficient design, and job creation

To address the existing gap in understanding the intricate dynamics of resource management in Cloud Fog Computing (CFC)-driven Smart Grids (SG), this study introduces an innovative adaptive framework integrating Genetic Optimization Algorithm (GOA) and Cuckoo Search Optimization Algorithm (CSOA), aiming to optimize response times and enhance overall efficiency. In the domain of contemporary energy grids, the implementation of intelligent grids (IG) has ushered in a new era of dependable, streamlined, eco-friendly, and economically viable electric services. These grids constitute a fundamental facet of present-day energy resources. Moreover, the advent of cloud and mist computing (CMC) provides on-demand access to computational resources. Overcoming associated challenges, CMC not only delivers advantages like cost-effectiveness, energy conservation, scalability, flexibility, and adaptability but also presents an innovative model for resource management in IG. This study introduces a CMC-driven strategy for managing resources in IG by digitally replicating key grid components. The proposed framework aims to furnish diverse computational services for resource management within IG through a hierarchical arrangement of CMCs. Additionally, this investigation scrutinizes and simulates two optimization approaches: the cuckoo search and grasshopper optimization algorithms. These algorithms operate on an adaptive machine learning mechanism designed to balance the load, and the study meticulously compares their efficacy. These algorithms operate on an adaptive machine learning mechanism designed to balance the load, and the study meticulously compares their efficacy in the context of Renewable Integration, Energy-Efficient Design, and Job Creation.

An Adaptive Temporal Convolutional Network Autoencoder for Malicious Data Detection in Mobile Crowd Sensing.

Mobile crowdsensing (MCS) systems rely on the collective contribution of sensor data from numerous mobile devices carried by participants. However, the open and participatory nature of MCS renders these systems vulnerable to adversarial attacks or data poisoning attempts where threat actors can inject malicious data into the system. There is a need for a detection system that mitigates malicious sensor data to maintain the integrity and reliability of the collected information. This paper addresses this issue by proposing an adaptive and robust model for detecting malicious data in MCS scenarios involving sensor data from mobile devices. The proposed model incorporates an adaptive learning mechanism that enables the TCN-based model to continually evolve and adapt to new patterns, enhancing its capability to detect novel malicious data as threats evolve. We also present a comprehensive evaluation of the proposed model's performance using the SherLock datasets, demonstrating its effectiveness in accurately detecting malicious sensor data and mitigating potential threats to the integrity of MCS systems. Comparative analysis with existing models highlights the performance of the proposed TCN-based model in terms of detection accuracy, with an accuracy score of 98%. Through these contributions, the paper aims to advance the state of the art in ensuring the trustworthiness and security of MCS systems, paving the way for the development of more reliable and robust crowdsensing applications.

Dense Multi-Scale Graph Convolutional Network for Knee Joint Cartilage Segmentation.

In this paper, we propose a dense multi-scale adaptive graph convolutional network (DMA-GCN) method for automatic segmentation of the knee joint cartilage from MR images. Under the multi-atlas setting, the suggested approach exhibits several novelties, as described in the following. First, our models integrate both local-level and global-level learning simultaneously. The local learning task aggregates spatial contextual information from aligned spatial neighborhoods of nodes, at multiple scales, while global learning explores pairwise affinities between nodes, located globally at different positions in the image. We propose two different structures of building models, whereby the local and global convolutional units are combined by following an alternating or a sequential manner. Secondly, based on the previous models, we develop the DMA-GCN network, by utilizing a densely connected architecture with residual skip connections. This is a deeper GCN structure, expanded over different block layers, thus being capable of providing more expressive node feature representations. Third, all units pertaining to the overall network are equipped with their individual adaptive graph learning mechanism, which allows the graph structures to be automatically learned during training. The proposed cartilage segmentation method is evaluated on the entire publicly available Osteoarthritis Initiative (OAI) cohort. To this end, we have devised a thorough experimental setup, with the goal of investigating the effect of several factors of our approach on the classification rates. Furthermore, we present exhaustive comparative results, considering traditional existing methods, six deep learning segmentation methods, and seven graph-based convolution methods, including the currently most representative models from this field. The obtained results demonstrate that the DMA-GCN outperforms all competing methods across all evaluation measures, providing DSC=95.71% and DSC=94.02% for the segmentation of femoral and tibial cartilage, respectively.

Domain Adaptation for Sensor-Based Human Activity Recognition with a Graph Convolutional Network

Sensor-based human activity recognition (HAR) plays a fundamental role in various mobile application scenarios, but the model performance of HAR heavily relies on the richness of the dataset and the completeness of data annotation. To address the shortage of comprehensive activity types in collected datasets, we adopt the domain adaptation technique with a graph neural network-based approach by incorporating an adaptive learning mechanism to enhance the action recognition model’s generalization ability, especially when faced with limited sample sizes. To evaluate the effectiveness of our proposed approach, we conducted experiments using three well-known datasets: MHealth, PAMAP2, and TNDA. The experimental results demonstrate the efficacy of our approach in sensor-based HAR tasks, achieving impressive average accuracies of 98.88%, 98.58%, and 97.78% based on the respective datasets. Furthermore, we conducted transfer learning experiments to address the domain adaptation problem. These experiments revealed that our proposed model exhibits exceptional transferability and distinguishing ability, even in scenarios with limited available samples. Thus, our approach offers a practical and viable solution for sensor-based HAR tasks.

SFS-AGGL: Semi-Supervised Feature Selection Integrating Adaptive Graph with Global and Local Information

As the feature dimension of data continues to expand, the task of selecting an optimal subset of features from a pool of limited labeled data and extensive unlabeled data becomes more and more challenging. In recent years, some semi-supervised feature selection methods (SSFS) have been proposed to select a subset of features, but they still have some drawbacks limiting their performance, for e.g., many SSFS methods underutilize the structural distribution information available within labeled and unlabeled data. To address this issue, we proposed a semi-supervised feature selection method based on an adaptive graph with global and local constraints (SFS-AGGL) in this paper. Specifically, we first designed an adaptive graph learning mechanism that can consider both the global and local information of samples to effectively learn and retain the geometric structural information of the original dataset. Secondly, we constructed a label propagation technique integrated with the adaptive graph learning in SFS-AGGL to fully utilize the structural distribution information of both labeled and unlabeled data. The proposed SFS-AGGL method is validated through classification and clustering tasks across various datasets. The experimental results demonstrate its superiority over existing benchmark methods, particularly in terms of clustering performance.

A Review of AIoT-based Human Activity Recognition: From Application to Technique.

This scoping review paper redefines the Artificial Intelligence-based Internet of Things (AIoT) driven Human Activity Recognition (HAR) field by systematically extrapolating from various application domains to deduce potential techniques and algorithms. We distill a general model with adaptive learning and optimization mechanisms by conducting a detailed analysis of human activity types and utilizing contact or non-contact devices. It presents various system integration mathematical paradigms driven by multimodal data fusion, covering predictions of complex behaviors and redefining valuable methods, devices, and systems for HAR. Additionally, this paper establishes benchmarks for behavior recognition across different application requirements, from simple localized actions to group activities. It summarizes open research directions, including data diversity and volume, computational limitations, interoperability, real-time recognition, data security, and privacy concerns. Finally, we aim to serve as a comprehensive and foundational resource for researchers delving into the complex and burgeoning realm of AIoT-enhanced HAR, providing insights and guidance for future innovations and developments.

Multi-Level Fusion for Enhanced Host-based Malware Detection in ICT-Enabled Smart Cities

In smart cities, the widespread adoption of Information and Communication Technologies (ICTs) presents both opportunities and challenges for security. While ICTs enable increased productivity, data sharing, and improved citizen services, they also create new vulnerabilities for malicious actors to exploit. This necessitates robust host-based security solutions to protect critical infrastructure and data. This paper proposes a novel multi-level fusion approach for enhanced host-based malware detection in ICT-enabled smart cities. By leveraging diverse data sources and employing advanced fusion techniques, our approach achieves significant improvements in malware detection accuracy, network evaluation, and security analysis compared to existing methods. Specifically, our proposed approach demonstrates a 72.1% malware detection rate across various attack scenarios, 69.7% accuracy in host network evaluation, 82.8% reduction in security analysis error, 75.4% accuracy in network probability detection, and an overall accuracy of 67.2%. These results showcase the potential of multi-level fusion for strengthening host-based security in smart cities. This approach offers several advantages over traditional host-based security solutions. Firstly, it provides more comprehensive threat detection by utilizing multiple data sources. Secondly, it reduces the burden on IT administrators by automating security analysis and decision-making. Finally, it enables continuous improvement through adaptive learning and feedback mechanisms. Overall, our multi-level fusion approach represents a promising advancement in host-based security for ICT-enabled smart cities. It offers significant improvements in accuracy and efficiency, paving the way for a more secure and resilient urban environment.