A Smart Irrigation System Using the IoT and Advanced Machine Learning Model

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Nov. 26, 2024

The rapid advancement of IoT (Internet Things) technologies and sophisticated machine learning models is driving innovation in irrigation systems, laying the foundation for more effective eco-friendly smart agricultural procedures. This systematic literature review strives to uncover advancements challenges implementation IoT-based systems integrated with advanced techniques. By analyzing 43 relevant studies published between 2017 2024, research focuses on ability these have evolved meet modern agriculture system. Predictive analytics, anomaly detection, adaptive control—that enhance precision decision-making processes. Employing PRISMA methodology, this uncovers strengths limitations current highlighting significant achievements real-time data utilization system responsiveness. However, it also brings attention unresolved issues, including complexities integration, network reliability, scalability frameworks. Additionally, study identifies crucial gaps standardization need flexible solutions that can adapt diverse environmental conditions. offering a comprehensive analysis, provides key insights advancing technologies, emphasizing importance continued overcoming existing barriers wider adoption effectiveness various settings.

Language: Английский

---

CoralMatrix: A Scalable and Robust Secure Framework for Enhancing IoT Cybersecurity

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 7, 2025

In the current age of digital transformation, Internet Things (IoT) has revolutionized everyday objects, and IoT gateways play a critical role in managing data flow within these networks. However, dynamic extensive nature networks presents significant cybersecurity challenges that necessitate development adaptive security systems to protect against evolving threats. This paper proposes CoralMatrix Security framework, novel approach employs advanced machine learning algorithms. framework incorporates AdaptiNet Intelligence Model, which integrates deep reinforcement for effective real-time threat detection response. To comprehensively evaluate performance this study utilized N-BaIoT dataset, facilitating quantitative analysis provided valuable insights into model's capabilities. The results demonstrate robustness across various dimensions cybersecurity. Notably, achieved high accuracy rate approximately 83.33%, highlighting its effectiveness identifying responding threats real-time. Additionally, research examined framework's scalability, adaptability, resource efficiency, diverse cyber-attack types, all were quantitatively assessed provide comprehensive understanding suggests future work optimize larger adapt continuously emerging threats, aiming expand application scenarios. With proposed algorithms, emerged as promising, efficient, effective, scalable solution Cyber Security.

Language: Английский

---

Adaptive Computational Intelligence Algorithms for Efficient Resource Management in Smart Systems

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 9, 2025

The rapid evolution of smart systems, including Internet Things (IoT) devices, grids, and autonomous vehicles, has led to the need for efficient resource management optimize performance, reduce energy consumption, enhance system reliability. This paper presents adaptive computational intelligence (CI) algorithms as an effective solution addressing dynamic challenges in systems. Specifically, we explore application techniques such fuzzy logic, genetic algorithms, particle swarm optimization, neural networks adaptively manage resources like energy, bandwidth, processing power, storage real-time. These CI offer robust decision-making capabilities, enabling systems efficiently allocate based on environmental changes, demands, user preferences. discusses integration these with real-time data acquisition providing a framework scalable management. Additionally, evaluate performance various environments, highlighting their ability efficiency, operational costs, improve overall experience. proposed approach demonstrates significant improvements over traditional techniques, making it promising next-generation

Language: Английский

---

AI-Driven Cybersecurity: Enhancing Threat Detection and Mitigation with Deep Learning

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: March 23, 2025

AI-driven cybersecurity has emerged as a transformative solution for combating increasingly sophisticated cyber threats. This research proposes an advanced deep learning-based framework aimed at enhancing threat detection and mitigation performance. Leveraging Convolutional Neural Networks (CNNs) Long Short-Term Memory (LSTM) architectures, the proposed model effectively identifies anomalies classifies potential threats with high accuracy minimal false positives. The was rigorously evaluated using real-time network traffic datasets, demonstrating notable increase in by 18.5%, achieving of 97.4%, compared to traditional machine learning methods (78.6%). Additionally, response time significantly reduced 25%, while computational overhead decreased 30%, overall system responsiveness. Experimental results further show 40% reduction downtime incidents due faster identification proactive approach thus provides substantial improvements security performance metrics, underscoring its robust dynamic landscapes

Language: Английский

---

Innovative Computational Intelligence Frameworks for Complex Problem Solving and Optimization

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 9, 2025

The rapid advancement of computational intelligence (CI) techniques has enabled the development highly efficient frameworks for solving complex optimization problems across various domains, including engineering, healthcare, and industrial systems. This paper presents innovative that integrate advanced algorithms such as Quantum-Inspired Evolutionary Algorithms (QIEA), Hybrid Metaheuristics, Deep Learning-based models. These aim to address challenges by improving convergence rates, solution accuracy, efficiency. In context a framework was successfully used predict optimal treatment plans cancer patients, achieving 92% accuracy rate in classification tasks. proposed demonstrate potential addressing broad spectrum problems, from resource allocation smart grids dynamic scheduling manufacturing integration cutting-edge CI methods offers promising future optimizing performance real-world wide range industries.

Language: Английский

---

Metaheuristic-Driven Optimization for Efficient Resource Allocation in Cloud Environments

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 7, 2025

Intrusion Detection Systems (IDS) play a pivotal role in safeguarding networks against evolving cyber threats. This research focuses on enhancing the performance of IDS using deep learning models, specifically XAI, LSTM, CNN, and GRU, evaluated NSL-KDD dataset. The dataset addresses limitations earlier benchmarks by eliminating redundancies balancing classes. A robust preprocessing pipeline, including normalization, one-hot encoding, feature selection, was employed to optimize model inputs. Performance metrics such as Precision, Recall, F1-Score, Accuracy were used evaluate models across five attack categories: DoS, Probe, R2L, U2R, Normal. Results indicate that XAI consistently outperformed other achieving highest accuracy (91.2%) Precision (91.5%) post-BAT optimization. Comparative analyses confusion matrices protocol distributions revealed dominance DoS attacks highlighted specific challenges with R2L U2R study demonstrates effectiveness optimized detecting complex attacks, paving way for adaptive solutions.

Language: Английский

---

A novel optimized deep learning based intrusion detection framework for an IoT networks

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Nov. 26, 2024

The burgeoning importance of Internet Things (IoT) and its diverse applications have sparked significant interest in study circles. inherent diversity within IoT networks renders them suitable for a myriad real-time applications, firmly embedding into the fabric daily life. While devices streamline various activities, their susceptibility to security threats is glaring concern. Current inadequacies measures render vulnerable, presenting an enticing target attackers. This suggests novel dealing address this challenge through execution Intrusion Detection Systems (IDS) leveraging superior deep learning models. Inspired by benefits Long Short Term Memory (LSTM), we introduce Genetic Bee LSTM(GBLSTM) development intelligent IDS capable detecting wide range cyber-attacks targeting area. methodology comprises four key execution: (i) collection unit profiling normal device behavior, (ii) Identification malicious during attack, (iii) Prediction attack types implemented network. Intensive experimentations suggested are conducted using validation methods prominent metrics across different threat scenarios. Moreover, comprehensive experiments evaluate models alongside existing results demonstrate that GBLSTM-models outperform other intellectual terms accuracy, precision, recall, underscoring efficacy securing networks.

Language: Английский

---

Remote Monitoring and Early Detection of Labor Progress Using IoT-Enabled Smart Health Systems for Rural Healthcare Accessibility

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Nov. 25, 2024

Delayed detection of labor pain in pregnant women, especially during their first delivery, often leads to delays reaching healthcare facilities, potentially resulting complications. This research proposes an innovative IoT-enabled system for remote monitoring progress and fetal health, designed specifically address the needs women areas within a 100 km radius facilities. The includes wearable device integrated with sensors detect onset continuously monitor heartbeat. Upon detecting pain, automatically sends alert medical team, allowing timely intervention. Experimental results demonstrate system's efficacy 99.2% accuracy 98.5% reliability heartbeat monitoring. latency transmission was measured at average 3.2 seconds, ensuring prompt notification providers. proposed solution enhances accessibility maternal care, reduces complications due delayed hospital admission, provides continuous monitoring, even resource-constrained environments. innovation bridges gap delivery underserved regions, offering practical, cost-effective, scalable solution. .

Language: Английский

---

Deep Learning Algorithm Design for Discovery and Dysfunction of Landmines

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Dec. 21, 2024

Deep Learning is a cutting-edge technology which has noteworthy impact in the real-world applications. The multi-layer neural nets involved blueprint of deep learning enables it to deliver comprehensive decision-making system with quality “think alike human cerebrum”. assumes an essential part various fields like horticulture, medication, substantial business and so forth. can be well prompted remote sensing applications especially perilous military location land mines detected using algorithm design technique aided distinctive machine tools techniques. intelligent designed by process involves massive dataset including assorted features landmines size, sort, dampness, ground profundity on. Incorporation Geographical Information System give prevalent statistical analysis varied landmines. multiple layers present schema may increase feature extraction knowledge representation through complexities landmines’ input sets. likelihood brokenness increased utilization prediction model enormously helps survival militaries, creating social effect.

Language: Английский

---

The Impact of Clinical Parameters on LSTM-based Blood Glucose Estimate in Type 1 Diabetes

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Dec. 3, 2024

Accurate forecasting of blood sugar levels is essential for managing diabetes, especially Type-1 reducing incidences, and diminishing care, costs in patients. In this study, a Long Short-Term Memory Recurrent Neural Network (LSTM) model has been employed to predict glucose using clinical data. The research focuses on identifying analyzing several key parameters that play significant role determining future levels, ensuring robust reliable prediction framework. We have considered patient-specific features: Insulin-Sensitivity-Factor (ISF), total daily dose (TDD) insulin, HbA1C height weight patient, age gender while the performance Blood Glucose. thought training LSTM models large dataset studying most important predictors with their predictive power would be beneficial. results indicate including these improves accuracy provides valuable information individuals control diabetes. This analysis highlights efficiency networks making use patient data improve models, eventually aiding more effective individualized treatment strategies Type 1 diabetic patients (T1D). work also examines extent which each parameter influences providing deeper insights into relative impact significance model.

Language: Английский

---