Improvement In Performance Metrics Research Articles

PID-based control strategies for enhancing stability and precision in electro-hydraulic actuation systems

Electro-hydraulic actuation systems are essential in industrial applications but often face challenges related to nonlinearity, leading to instability and reduced precision. This paper explores the application of Proportional-Integral-Derivative (PID) control strategies to enhance the stability and precision of these systems. A detailed system model is developed, and the PID controller is designed and tuned using optimization techniques. Simulation results demonstrate improvements in performance metrics, such as reduced overshoot, settling time, and steady-state error. The proposed control strategy is validated experimentally on a physical setup, confirming its effectiveness in real-world applications. The findings show that PID-based control significantly enhances both stability and precision in electro-hydraulic actuation systems, offering a practical solution for industrial control challenges.

GEEES: Inferring Cell-specific Gene-Enhancer Interactions from Multi-modal Single Cell Data.

Gene-enhancer interactions are central to transcriptional regulation. Current multi-modal single cell datasets that profile transcriptome and chromatin accessibility simultaneously in a single cell are yielding opportunities to infer gene-enhancer associations in a cell type specific manner. Computational efforts for such multi-modal single cell datasets thus far focused on methods for identification and refinement of cell types and trajectory construction. While initial attempts for inferring gene-enhancer interactions have emerged, these have not been evaluated against benchmark datasets that materialized from bulk genomic experiments. Furthermore, existing approaches are limited to inferring gene-enhancer associations at the level of grouped cells as opposed to individual cells, thereby ignoring regulatory heterogeneity among the cells. We present a new approach, GEEES for "Gene EnhancEr IntEractions from Multi-modal Single Cell Data", for inferring gene-enhancer associations at the single cell level using multi-modal single cell transcriptome and chromatin accessibility data. We evaluated GEEES alongside several multivariate regression-based alternatives we devised and state-of-the-art methods using a large number of benchmark datasets, providing a comprehensive assessment of current approaches. This analysis revealed significant discrepancies between gold-standard interactions and gene-enhancer associations derived from multi-modal single-cell data. Notably, incorporating gene-enhancer distance into the analysis markedly improved performance across all methods, positioning GEEES as a leading approach in this domain. While the overall improvement in performance metrics by GEEES is modest, it provides enhanced cell representation learning which can be leveraged for more effective downstream analysis. Furthermore, our review of existing experimentally driven benchmark datasets uncovers their limited concordance, underscoring the necessity for new high-throughput experiments to validate gene-enhancer interactions inferred from single-cell data. https://github.com/keleslab/GEEES. Supplementary data are available at Bioinformatics online.

Scalable In2S3 based optical memristor devices as artificial synapse for logic realization and neuromorphic computing

This paper presents the scalable production of indium sulfide (In2S3) based optical memristors as an artificial synapse for logic realization and neuromorphic computing applications. The optical memristor device's performance was tested using the electrical and optical stimulation (ultraviolet (UV) to near infrared (NIR)) at room temperature. The memristor has shown the improved performance metrics for optical stimulation as compared to electrical stimulation. The In2S3 based optical memristor offers a resistance switching ratio of ∼103 at room temperature. In addition, the memristor has ultra-fast program and reprogram capability (38.8/39 μs) at 880 nm. Moreover, stability/scalability of the device was tested using the cycle-to-cycle variability test at different modulated frequencies. The electrical and optical signals were used as an input for logic gate realization. The neuromorphic computing model was implemented to predict the digits and alphabets with an accuracy of 98.19 % and 99.18 % respectively. These demonstrated optical memristors can be the key technology for future memory devices that surpass the limitations of von-Neumann bottleneck.

Secure and efficient trust enabled routing in mobile ad hoc network using game theory and grey wolf optimisation techniques

AbstractMobile Ad hoc Networks (MANETs) are crucial wireless networks for military, corporate, and emergency use, yet they are vulnerable to disruptions from malicious nodes. The presence of malicious nodes can lead to message transmission and routing disorganisation, and network performance is effectively compromised. Game theory‐based fuzzy secure clustering (GTFSC) improves performance metrics in low‐scale and high‐scale networks. This protocol's novel ability to dynamically scale performance measures as nodes expand improves efficiency and adaptability. While improving performance metrics, the proposed algorithm also efficiently identifies malicious nodes and re‐routes the transmission, excluding the found malicious nodes. For any MANET system, secure and successful data transmission is paramount. The proposed protocol integrates various algorithms to fulfil its aim of customised EGT, GWO, and fuzzy clustering. Black hole attacks, grey hole attacks, Sybil attacks, and data tampering attacks are all considered to provide comprehensive attacks on MANET. Every node is assigned trust values, which get updated on data transmission. Fuzzy Clustering is employed to identify malicious nodes. Evolutionary Game Theory (EGT) optimises network organisation by designating cluster heads and clusters as nodes. Additionally, the proposed protocol leverages the Grey Wolf Optimisation Routing Algorithm (GWO), which establishes efficient routes from the source to the sink node. The analysis result shows maximum performance with a packet delivery ratio of around 98%, throughput of 90% end‐to‐end delay reduced by 15%, and energy consumption reduced by 18%, respectively, compared to an existing protocol.

Investigating the performance of a gas turbine system combined with steam methane reforming as a thermochemical recuperator in a power, cooling, freshwater, and hydrogen production multigeneration system

Depletion of fossil fuel resources at a high speed and increasing demand for energy supply for various purposes in today's life integrated with industry has led to collective contemplation for the optimal and maximum utilization of fossil fuels through the implementation of multigeneration systems. In the presented study, a multigeneration system for cooling, power, freshwater, and Hydrogen production is proposed and investigated from exergy, energy, and economic viewpoints through a specific scenario. A case study is performed, revealing that the system can deliver a net output power of 16,251.8 kW, a cooling load of 15,905.0 kW, produce freshwater at a rate of 3.891 kg/s, and generate hydrogen at 0.284 kg/h. The energy and exergy efficiencies of the system are 60.48 % and 32.55 %, respectively. An economic analysis shows a payback period of 0.474 years. A parametric evaluation is performed to perceive the system operation in various conditions. Subsequently, a multi-objective optimization using the MOPSO-LINMAP method is conducted to identify the optimal operating conditions for the system. The optimization results are compared with the case study findings, demonstrating further improvements in performance metrics. The optimized system achieves a slightly higher energy efficiency of 61.62 % and a lower payback period of 0.40 years, underscoring the benefits of the optimization process. This study highlights the potential of the proposed system to efficiently and economically meet the demands for power, hydrogen, cooling, and freshwater in various applications.

Parametric modeling and optimization of the intake port in a naturally aspirated opposed rotary piston engine across the full speed range

The opposed rotary piston (ORP) engine offers advantages such as compact size, simple structure, and high power density, making it highly promising for long-endurance unmanned aerial vehicles (UAVs). Parametric modeling of intake ports and the investigation of structural parameters on intake characteristics for ORP engines are crucial for improving the intake performance. In this paper, based on the kinematic model of the ORP engine, parametric modeling of the intake and exhaust ports are performed, a 3D numerical model is established to explore the intake characteristics at different engine speeds. The impact of intake delayed closing angle (IDCA), intake inclination angle (IIA), and dual intake ports on the intake characteristics of the ORP engine are investigated. Finally, the combustion characteristics and performance metrics of the engine using optimized intake ports are compared against the baseline intake phase. The results indicate that the CGE and pumping loss of the ORP engine initially increase and then decrease with rising engine speed. The CGE exceeds 92 % at 1000 r·min−1 and 94 % at 5000 r·min−1 when the IDCA are set at 8° and the IIA at −20°. The pumping losses at 4000 r·min−1 and 5000 r·min−1 are reduced by 33.3 % and 30.9 %, respectively, after intake port optimization. The performance metrics at 1000 r·min−1 and 2000 r·min−1 show a slight decline compared to pre-optimization due to lower turbulence kinetic energy (TKE) and intake backflow. However, at 3000–5000 r·min−1, the optimized intake port structure significantly improves performance metrics of the ORP engine.

Implementation of a performance management system for environmental sustainability in an industrial organization

Abstract The paper explores the implementation of process performance management systems in the automotive industry, specifically focusing on improving the assembly line of an organization within this sector thanks to the introduction of cobots in the line of manufacturing electronic modules used in car seat control systems. With an emphasis on environmental sustainability and circular economy (CE) concepts, the study investigates the positive effects of optimizing mechanical and electromechanical systems within the assembly line. Leveraging concepts such as KAIZEN and Gemba Kaizen, along with the guiding principles of Just-In-Time (JIT), Continuous Improvement and Automation with a Human Touch (JIDOKA), the research aims to elucidate the potential benefits of such enhancements. Key performance indicators (KPIs) including Overall Equipment Effectiveness (OEE), First Pass Yield (FPY), and scrap rates were considered. Rejects, primarily stemming from human error in part handling, emerged as the major challenge facing this assembly line. To address this issue, collaborative robots were introduced to automate part handling, replacing manual processes with precise and reliable automation. Before the implementation, the cycle time stood at 13.6 units, which was reduced to 12.5 units post-implementation, resulting in a significant increase in productivity equating to 3000 more parts produced per week. OEE increasing from 80% to 87.74%, FPY rising from 96.42% to 98.48%, and the scrap rate decreasing from 0.06% to 0.02%. By addressing inefficiencies at the assembly line level, organizations can achieve significant improvements in performance metrics while concurrently contributing to a greener and more sustainable future.

The Meta-Heuristic routing method by integrating index parameters to optimize energy consumption and real execution time using FANET

Decreasing energy consumption in Unmanned Aerial Vehicles (UAVs) while simultaneously enhancing their reliability and processing capabilities is considered a fundamental challenge. The routing mechanisms employed in Flying Ad Hoc Networks (FANETs) are more complex compared to those in Mobile Ad Hoc Networks (MANETs) and Vehicular Ad Hoc Networks (VANETs), a challenge addressed by the FMORT method. To tackle these complex routing challenges, clustering techniques that utilize hybrid Meta-heuristic algorithms can be applied. Data analysis within the FMORT framework identified factors influencing service integration, leading to a reduction in redundant request transmissions and overall redundancy in the proposed method. The identification of food sources in the hybrid Meta-heuristic algorithm of the FMORT method is achieved through the integration of the Sparrow and Dragonfly algorithms. These algorithms work simultaneously to increase energy efficiency and increase network lifetime. This strategy optimizes information exchange by selecting an intelligent threshold detector and categorizing inputs, thereby minimizing node mobility. As a result, it improves performance metrics and decreases delivery costs, energy consumption, and delays. In the proposed method, a balanced performance is achieved by comparing existing methods in terms of transmission delay, Packet Delivery Ratio( PDR), throughput, and energy consumption. Simulation results show that the FMORT approach provides effective and stable outcomes in terms of reliability, decreased delays, and improved packet delivery rates. The FMORT framework includes principles for neighbor selection, determining suitable cluster heads, and scoring based on the average Euclidean distance. Additionally, it manages topology access, ensures proper distribution, guarantees data connectivity, and accurately categorizes inputs. By optimizing the sensitivity rate, this method minimizes the average delays and meekly values input data through effective load balancing. key parameters considered for real time optimization of overall performance include the number of cluster heads during re-clustering, the ratio of request-to-acknowledgment packet transmission, node, and network lifetime, end-to-end delay, and energy consumption. Ultimately, the simulation results show that compared to the MWCRSF algorithm, the average optimization of index parameters,% 0.73 decrease in energy consumption,% 2.23 network lifetime, 1.35 re-cluster construction time and also% 0.11 re-cluster lifetime has increased.

Extracting optimal fuel cell parameters using dynamic Fick’s Law algorithm with cooperative learning strategy and k-means clustering

This article introduces an enhanced stochastic search method tailored for optimizing the parameters of fuel cells (FCs), which hold significant relevance across various applications. The nonlinear nature of FCs poses a modeling challenge, prompting the proposal of an advanced Dynamic Fick’s Law Algorithm (DFLA). This improved approach incorporates a cooperative learning strategy, leveraging K-Means clustering, to derive optimal FC parameters. DFLA introduces a dynamic swarm topology by segmenting the population into subswarms, boosting diversity, and enabling broader global exploration. Simultaneously, the cooperative learning strategy fosters information exchange among subswarms, enhancing the algorithm’s ability to explore vast solution spaces and exploit diverse subswarm-derived solutions. The evaluation of DFLA utilized real-world datasets from commercial PEMFC stacks: 250-W stack, BCS 500-W, and NedStack PS6. Performance assessment relied on the Sum Squared Error (SSE), a standard evaluation metric, with comparisons drawn against established competing methods. The results underscored DFLA’s superior efficiency, showcasing improved performance metrics and convergence behaviors compared to the tested algorithms.

ROS Gateway: Enhancing ROS Availability across Multiple Network Environments.

As the adoption of large-scale model-based AI grows, the field of robotics is undergoing significant changes. The emergence of cloud robotics, where advanced tasks are offloaded to fog or cloud servers, is gaining attention. However, the widely used Robot Operating System (ROS) does not support communication between robot software across different networks. This paper introduces ROS Gateway, a middleware designed to improve the usability and extend the communication range of ROS in multi-network environments, which is important for processing sensor data in cloud robotics. We detail its structure, protocols, and algorithms, highlighting improvements over traditional ROS configurations. The ROS Gateway efficiently handles high-volume data from advanced sensors such as depth cameras and LiDAR, ensuring reliable transmission. Based on the rosbridge protocol and implemented in Python 3, ROS Gateway is compatible with rosbridge-based tools and runs on both x86 and ARM-based Linux environments. Our experiments show that the ROS Gateway significantly improves performance metrics such as topic rate and delay compared to standard ROS setups. We also provide predictive formulas for topic receive rates to guide the design and deployment of robotic applications using ROS Gateway, supporting performance estimation and system optimization. These enhancements are essential for developing responsive and intelligent robotic systems in dynamic environments.

Efficient DC motor speed control using a novel multi-stage FOPD(1 + PI) controller optimized by the Pelican optimization algorithm.

This paper introduces a novel multi-stage FOPD(1 + PI) controller for DC motor speed control, optimized using the Pelican Optimization Algorithm (POA). Traditional PID controllers often fall short in handling the complex dynamics of DC motors, leading to suboptimal performance. Our proposed controller integrates fractional-order proportional-derivative (FOPD) and proportional-integral (PI) control actions, optimized via POA to achieve superior control performance. The effectiveness of the proposed controller is validated through rigorous simulations and experimental evaluations. Comparative analysis is conducted against conventional PID and fractional-order PID (FOPID) controllers, fine-tuned using metaheuristic algorithms such as atom search optimization (ASO), stochastic fractal search (SFS), grey wolf optimization (GWO), and sine-cosine algorithm (SCA). Quantitative results demonstrate that the FOPD(1 + PI) controller optimized by POA significantly enhances the dynamic response and stability of the DC motor. Key performance metrics show a reduction in rise time by 28%, settling time by 35%, and overshoot by 22%, while the steady-state error is minimized to 0.3%. The comparative analysis highlights the superior performance, faster response time, high accuracy, and robustness of the proposed controller in various operating conditions, consistently outperforming the PID and FOPID controllers optimized by other metaheuristic algorithms. In conclusion, the POA-optimized multi-stage FOPD(1 + PI) controller presents a significant advancement in DC motor speed control, offering a robust and efficient solution with substantial improvements in performance metrics. This innovative approach has the potential to enhance the efficiency and reliability of DC motor applications in industrial and automotive sectors.

A Robust Generalized Zero-Shot Learning Method with Attribute Prototype and Discriminative Attention Mechanism

In the field of Generalized Zero-Shot Learning (GZSL), the challenge lies in learning attribute-based information from seen classes and effectively conveying this knowledge to recognize both seen and unseen categories during the training process. This paper proposes an innovative approach to enhance the generalization ability and efficiency of GZSL models by integrating a Convolutional Block Attention Module (CBAM). The CBAM blends channel-wise and spatial-wise information to emphasize key features, thereby improving the model’s discriminative and localization capabilities. Additionally, the method employs a ResNet101 backbone for systematic image feature extraction, enhanced contrastive learning, and a similarity map generator with attribute prototypes. This comprehensive framework aims to achieve robust visual–semantic embedding for classification tasks. The proposed method demonstrates significant improvements in performance metrics in benchmark datasets, showcasing its potential in advancing GZSL applications.

Наноструктурные материалы для хранения энергии: инновации и применение

Background: As the world shifts towards renewable energy, there is a growing demand for efficient energy storage systems. Because of their unique features, nanostructured materials have emerged as key to improving the performance and efficiency of these storage systems. Objective: This research aims to assess the most recent discoveries and uses of nanostructured materials in energy storage technologies, emphasizing its disruption in the industry. Methods: A detailed assessment of recent advances was undertaken, focusing on diverse nanostructured materials utilized in batteries, supercapacitors, and other energy storage systems. Synthesis and characterization techniques for these materials and their incorporation into energy storage devices were investigated. Results: The nanostructured materials considerably increase energy density, charge/discharge speeds, and durability of energy storage devices. Graphene, carbon nanotubes, and metal-oxide nanostructures have significantly improved performance metrics across various applications. Conclusion: Nanostructured materials have to revolutionize energy storage systems. Continued research and development in this sector are critical for developing high-performance, long-term energy storage technologies capable of meeting the growing demands of contemporary technology and renewable energy systems. Further investigation into these materials' scalability and environmental effects is necessary to ensure their practicality and sustainability.

Evaluating Prediction Models with Hearing Handicap Inventory for the Elderly in Chronic Otitis Media Patients.

This retrospective, cross-sectional study aimed to assess the functional hearing capacity of individuals with Chronic Otitis Media (COM) using prediction modeling techniques and the Hearing Handicap Inventory for the Elderly (HHIE) questionnaire. This study investigated the potential of predictive models to identify hearing levels in patients with COM. We comprehensively examined 289 individuals diagnosed with COM, of whom 136 reported tinnitus and 143 did not. This study involved a detailed analysis of various patient characteristics and HHIE questionnaire results. Logistic and Random Forest models were employed and compared based on key performance metrics. The logistic model demonstrated a slightly higher accuracy (73.56%), area under the curve (AUC; 0.73), Kappa value (0.45), and F1 score (0.78) than the Random Forest model. These findings suggest the superior predictive performance of the logistic model in identifying hearing levels in patients with COM. Although the AUC for the logistic regression did not meet the benchmark, this study highlights the potential for enhanced reliability and improved performance metrics using a larger dataset. The integration of prediction modeling techniques and the HHIE questionnaire shows promise for achieving greater diagnostic accuracy and refining intervention strategies for individuals with COM.

Design and Comparison of Fractional-Order Controllers in Flotation Cell Banks and Flotation Columns Used in Copper Extraction Processes

This work explores efficiency improvements in the copper flotation stage, a complex nonlinear, multivariable process subject to numerous perturbations. The primary objective is to design a fractional-order PID (FOPID) control strategy and a fractional-order model reference adaptive control (FOMRAC) system. The parameters for these controllers are optimized using the particle swarm optimization (PSO) algorithm with an objective function tailored to the control goals. This study employs models of both a bank series of five flotation cells and a flotation column. Their performance results are compared against traditional controllers, such as an integer-order PID and MRAC. The findings reveal that fractional-order controllers offer notable advantages over their integer-order counterparts, showing improved performance metrics with minimal changes to the existing control framework. This research highlights the effectiveness of fractional control in enhancing flotation processes and introduces a novel application of fractional control techniques in this area.

Enhanced performance of Lithium–Sulfur cells via novel nano-sized iron-plated sulfur composites

Lithium–sulfur cells are promising energy-storage systems because of their high energy density and the desirable electrochemical utilization rates of cost-effective sulfur cathodes. However, the commercialization of high-performance lithium–sulfur cells, which are characterized by a high discharge capacity and cyclic stability, necessitates simultaneous optimization of both the cell-fabrication parameters and cell-performance values. Here, we introduce a novel iron-plated sulfur composite featuring nano-sized conductive iron plating applied to micro-sized insulating sulfur particles through an innovative electroless-iron plating method. The iron-plated sulfur composite facilitates the realization of a lean-electrolyte lithium–sulfur cell at a low electrolyte-to-sulfur ratio of 5 μL mg−1, enabling high-loading sulfur cathodes (sulfur loadings of 10–14 mg cm−2) to attain a reversible discharge capacity (945–1033 mAh g−1) and a cycle life of 400 cycles. These well-controlled cell-fabrication parameters, coupled with the high cell performance, result in improved performance metrics, such as high areal capacity (10–13 mAh cm−2), improved energy density (22–28 mWh cm−2), and a low electrolyte-to-capacity ratio (4.8 μL mAh−1). These advancements are attributable to the incorporation of plated nano-sized iron, which endows the cathode with rapid electron/ion transfer, robust polysulfide retention, and heightened electrocatalysis capabilities for conversion-type battery chemistry.

Research on the surface quality improvement of 3D-printed parts through laser surface treatment

This study investigates laser polishing as a post-processing technique to reduce surface roughness in ABS and Nylon parts produced via Fused Deposition Modeling (FDM). The research utilized CO2 and Nd:YAG lasers to polish these materials, achieving surface roughness reductions of 95.9 % and 96.0 % for CO2-treated ABS and Nylon samples, respectively, while Nd:YAG-treated samples exhibited reductions of 67.3 % and 68.6 %. Additionally, the study explores the impact of various laser parameters on surface quality through both single-factor and orthogonal experiments. It also introduces wet laser polishing as a novel method to mitigate color changes and enhance polishing effectiveness. This innovative approach demonstrates substantial improvements in performance metrics, underscoring its potential for industrial-scale production of plastic components and biomedical implants. The technique, in particular, shows promising applications in meeting the polishing requirements of 3D-printed parts.

Optimizing Breast Cancer Diagnosis with Machine Learning Algorithms

Breast cancer is the most common disease among women worldwide, and it continues to pose a serious threat to global health [2]. Early and accurate diagnosis is critical for effective treatment and improved patient outcomes. Traditional diagnostic methods, while effective, have limitations in consistency and speed. Medical diagnostics have undergone a revolution with the introduction of machine learning (ML), which provides tools to analyze complex data and increase diagnosis accuracy. Using the Breast Cancer Wisconsin (Diagnostic) Dataset[1], this investigation dives into the application of several machine learning (ML) algorithms to improve the effectiveness of the diagnosis of breast cancer in terms of accuracy. Logistic Regression (LR), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), Support Vector Classifier (SVC), XGBoost Classifier (XGBC), and Convolutional Neural Network (CNN) are used. Improved performance metrics were obtained across models by applying optimization approaches, particularly genetic algorithm for the selection of features, following preprocessing and initial training. RandomForestClassifier, XGBClassifier, and CNN notably showed significant enhancements in accuracy, ROC AUC score, recall, precision, and F1 score post-optimization. Ensemble methods and deep learning architectures proved effective in handling complex data and reducing overfitting, with Random Forest Classifier standing out as consistently superior. Conversely, Decision Tree Classifier and Support Vector Classifier exhibited mixed results, showcasing the importance of optimization strategies. This research shows the capability of ML in augmenting breast cancer diagnostics, advocating for further exploration of ensemble methods and advanced neural networks to refine diagnostic tools and improve patient outcomes.

Optimizing mechanical behavior in polymer bio-composites reinforced with basalt, graphene, and PP-g-MA

This paper aims to investigate the mechanical properties of bio-composites reinforced with basalt natural fibers/nanographene in polypropylene by incorporating pp-g-ma compatibilizer. The study employs the Response Surface Method with the Behnken box approach to formulate a novel mathematical model for bio-composite behavior based on the parameters of basalt fiber weight percentage, nanographene weight percentage, and PP-g-MA weight percentage. Unlike previous studies, our work uniquely integrates basalt fibers and nanographene to enhance tensile, bending, and impact strengths, achieving a composite with optimal mechanical properties. The performance of the research samples was evaluated through tensile, bending, and impact tests, with the results substantiated using Field Emission Scanning Electron Microscopy images. The failure surface in these samples revealed that the central mechanism influencing the performance of the introduced bio-composite is the failure of the fibers and their separation, accompanied by the stretching of the fibers from the base material. Subsequently, multi-objective optimization was conducted with the aim of increasing tensile strength, bending strength, and impact strength while reducing the weight of the samples. A Pareto diagram is presented based on the design goals. The outcomes indicate that the bio-composite sample values in the most suitable state for three mechanical characteristics including, tensile, impact, and bending strength are equal to 28, 90, and 49 MPa, respectively. This innovative combination and optimization significantly improve performance metrics, demonstrated through extensive testing and multi-objective optimization, which reveals the bio-composite’s superior mechanical characteristics.

Hybrid Adaptive Multiple Intelligence System (HybridAMIS) for classifying cannabis leaf diseases using deep learning ensembles

Optimizing cannabis crop yield and quality necessitates accurate, automated leaf disease classi-fication systems for timely detection and intervention. Existing automated solutions, however, are insufficiently tailored to the specific challenges of cannabis disease identification, struggling with robustness across varied environmental conditions and plant growth stages. This paper introduces a novel Hybrid Adaptive Multi-Intelligence System for Deep Learning Ensembles (HyAMIS-DLE), utilizing a comprehensive dataset reflective of the diversity in cannabis leaf diseases and their progression. Our approach combines non-population-based decision fusion in image prepro-cessing with population-based decision fusion in classification, employing multiple CNN archi-tectures. This integration facilitates a significant improvement in performance metrics: Hy-AMIS-DLE achieves an accuracy of 99.58 %, outperforming conventional models by up to 4.16 %, and exhibits superior robustness and an enhanced Area Under the Curve (AUC) score, effectively distinguishing between healthy and diseased leaves. The successful deployment of HyAMIS-DLE within our Automated Cannabis Leaf Disease Classification System (A-CLDC-S) demonstrates its practical value, contributing to increased crop yields, reduced losses, and the promotion of sus-tainable agricultural practices.