Novel Architecture For EEG Emotion Classification Using Neurofuzzy Spike Net

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

Published: Jan. 7, 2025

Emotion recognition from Electroencephalogram (EEG) signals is one of the fastest-growing and challenging fields, with a huge prospect for future application in mental health monitoring, human-computer interaction, personalized learning environments. Conventional Neural Networks (CNN) traditional signal processing techniques have usually been performed EEG emotion classification, which face difficulty capturing complicated temporal dynamics inherent uncertainty signals. The proposed work overcomes challenges using new architecture merging Spiking (SNN) Fuzzy Hierarchical Attention Membership (FHAM), NeuroFuzzy SpikeNet (NFS-Net). NFS-Net takes advantage SNNs' event-driven nature signals, are treated independently as asynchronous, spike-based events like biological neurons. It allows patterns data high precision, rather important correct recognition. local spiking feature SNNs encourages sparse coding, making whole system computational power energy highly effective it very suitable wearable devices real-time applications.

Language: Английский

---

Enhancing Secure Image Transmission Through Advanced Encryption Techniques

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

Published: Jan. 9, 2025

Secure image transmission over the Internet has become a critical issue as digital media increasingly vulnerable and multimedia technologies progress rapidly. The use of traditional encryption methods to protect content is often not sufficient, so more sophisticated strategies are required. As part this paper, an autoencoder-based chaotic logistic map combined with convolutional neural networks (CNNs) encrypt images. result optimizing CNN feature extraction, maps ensure strong while maintaining picture quality reducing computational costs. In addition Mean Squared Errors (MSE), entropy, correlation coefficients, Peak Signal-to-Noise Ratios (PSNRs), method shows higher performance. providing increased security, adaptability, effectiveness, results prove resilient many types attacks. study, CNNs systems improve data communication, transmission.

Language: Английский

---

A Deep auto encoder based Framework for efficient weather forecasting

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

Published: Feb. 19, 2025

Weather forecasting has plethora of benefits in different domains. Traditional weather approaches applied science and technology towards predicting conditions given place time. With the emergence Artificial Intelligence (AI) there are increased possibilities area research. Instead ground level observations, AI learn from historical data also current atmosphere to come up with predictions. We suggested a framework for autonomous based on deep learning. Our is variant Convolutional Neural Network (CNN) model which exploits encoder decoder parameterizations forecast weather. The proposed capable interpreting spatial information associated geopotential field automatically infers knowhow higher accuracy levels. A variable selection process incorporated determine height that impact conditions. an algorithm known as Deep Forecasting (DWF) realize framework. empirical study revealed used evaluate learning models comparing their performance. outperformed many existing regression models. U-Net showed highest performance least MAE 0.2268 when compared all other

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

---

GreenGuard CNN-Enhanced Paddy Leaf Detection for Crop Health Monitoring

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

Published: Feb. 10, 2025

The GreenGuard: CNN-Enhanced Paddy Leaf Detection for Crop Health Monitoring initiative will create multiple future-oriented results. processing of agricultural imagery becomes revolutionized through the combination median filtering and Exponential Tsallis entropy Gaussian Mixture model (ExTS-GMM) advanced techniques initially. essential preprocessing operation delivers better quality data to Convolutional Neural Network (CNN) classifier which results in optimal performance outcomes. simple integration CNN classifiers launch an innovative age that more accurate efficient paddy leaf detection images. Deep learning features a enable it uncover complex structural details found both normal sick specimens. classifier's aptitude creates pathway execute precise assessment group into appropriate categories while extended database information rapidly. Effective implementation "GreenGuard" reshape conventional field crop health monitoring systems modern standards. Modern stakeholders can make choices about pest management along with disease control irrigation schedules because timely assessments from implemented system. new capabilities generated this empowerment system major yield growth enhance food safety protocols as well promote sustainable farming throughout farms globally.

Language: Английский

---

Renyi Entropy Predictive Data Mining And Weighted Xavier Deep Neural Classifier For Heart Disease Prediction

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

Published: Feb. 16, 2025

During the past few years, Frequent Pattern Mining (FPM) has received interest of several researchers that necessitate extracting items from transactions, and sequences datasets, clarifying heart disease diagnosis materializes commonly, recognizing specific arrangements. In this era with healthcare involving significant evolutions, unforeseeable movement enormous amount data concerning classification lead way to new issues in FPM, such as space time complexity. However, most research work concentrates on identifying patterns relating transpires frequently, where within every transaction were known a priori. To address present scenario, selecting predominant or frequent is essential using relevant FPM models. The primary objective enhance mining results reduce misclassification rate Cardiovascular Disease (CVD) dataset samples. This proposes novel method called Renyi Entropy Homogenized Weighted Xavier-based Deep Neural Classifier (REHWX-DNC) for prediction. tackle first challenge, Entropy-based (RE-FPM) algorithm proposed, which filters low-quality features function. handle second issue, HWX-DNC model designed assist minimizing by employing Swish activation A CVD synthesis can be analyzed obtain accuracy study, REGEX-DNC improved compared state-of-the-art methods. Some indicators, including prediction accuracy, time, level, F1-total, are considered calculate predictor, checking REHWX-DNC proposed efficient trustworthy predicting disease.

Language: Английский

---

GAN and ResNet Fusion A Novel Approach to Ophthalmic Image Analysis for Glaucoma

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

Published: Jan. 11, 2025

Glaucoma is a major cause of blindness, often undetected in early stages due to lack symptoms. Addressing this, research study developed deep learning framework integrating Generative Adversarial Networks (GANs) with Residual Neural (ResNet) enhance glaucoma detection from fundus images. Utilizing GANs for data augmentation, we enriched the training set synthetic images that improve feature recognition, while ResNet, fine-tuned on this data, performed high-precision classification. The GAN's discriminator, trained using binary cross-entropy loss, concentrating extract key indicators these images, its performance assessed by accuracy distinguishing real GAN-ResNet channel exploited discriminator's extraction coupled ResNet's capabilities classify refined accuracy. proposed model final layer classification between glaucomatous and healthy loss function modified medical dataset imbalances. Through wide testing, proven remarkable 98% analysing glaucoma, showing high predictive results. This validates helpful detecting early. It highlights how well-advanced neural networks work

Language: Английский

---

Effectiveness of Feature Extraction Techniques for Facial Identification

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

Published: Jan. 10, 2025

Criminal activities and crime tenancy are increasing in the society when technology population increases. The process of identifying determine criminals avoiding them from involving criminal tedious task for police as well public. Therefore, tracking system is also needed to strengthen. Apart traditional system, now a days government implementing based identification. An efficient facial feature extraction algorithm face identification this system. In research, performance principal component analysis local binary pattern algorithms analysed with support convolutional neural network.

Language: Английский

---

Application of Convolutional Neural Networks and Rolling Guidance Filter in Image Fusion for Detecting Brain Tumors

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

Published: Feb. 4, 2025

Medical image fusion is the technique of integrating images from several medical imaging modalities without causing any distortion or information loss. By preserving every feature in fused image, it increases value for diagnosis and treatment conditions. A novel mechanism multimodal data sets proposed this paper. Each source smoothened using cross guided filter initial step. Guided output further to remove fine structures rolling guidance filter. Then details (high frequency) each are extracted by subtracting corresponding image. These fed convolutional neural networks obtain decision maps. Finally based on map maximum rule combination. We assessed performance our suggested methodology pairs datasets that accessible general public. According quantitative evaluation, recommended strategy improves average IE 12.4%, MI 41.8%, SF 21.4%, SD 22.81%, MSSIM 31.1%, 39% when compared existing methods, which makes appropriate use field accurate diagnosis.

Language: Английский

---