Smart Computing and Systems Engineering - 2025 (SCSE 2025)

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/30037

Browse

Now showing 1 - 20 of 32

A Deep Learning-Based Approach for Detecting Duplicate GitHub Issues in Open-Source Repositories Using LSTM
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Dharmadasa, T. K. R. S.; Rupasingha, R. A. H. M.; Kumara, B. T. G. S.
GitHub is a platform used along with the popular version control tool Git to provide hosting facilities to software repositories. Users can publish GitHub issues to notify the repository contributors about bugs, questions, and feature requests. GitHub hosts open-source repositories that are contributed by developers across the globe. The asynchronous and uncoordinated nature of these contributions in open-source repositories increases the probability of posting duplicate GitHub issues, resulting in redundant efforts. The standard mechanism introduced by GitHub to mark duplicate issues is adding a comment to that issue body mentioning the original issue. Then GitHub will add the corresponding duplicate tag and close that issue. However, due to manual labor required to find duplicates, developers are discouraged from seeking similar issues before publishing a new issue to GitHub. The study’s main objective is to address this problem and propose an automated solution using deep learning algorithms. Our research introduces a novel approach that combines feature extraction and similarity calculations to identify duplicate GitHub issues. The proposed methodology extracted over 4000 GitHub issues covering different programming languages and repositories. After pre-processing, various features were extracted using multiple feature extraction techniques, and semantic similarity metrics such as cosine similarity were utilized to create the feature vector. The feature vector was used with different algorithms like Artificial Neural Network (ANN) and Recurrent Neural Network (RNN) including deep-learning algorithms like Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). Algorithm results are compared to detect the most suitable approach for detecting duplicate GitHub issues. Based on the different evaluations, LSTM is the better approach resulting in 88% accuracy with the highest precision, recall, and f-measures while giving the lowest error rates. With this proposed methodology, duplicate GitHub issues can be easily detected, reducing the manual work.
A Hybrid Architecture with Efficient Fine Tuning for Abstractive Patent Document Summarization
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Jayatilleke, N.; Weerasinghe, R.
Automatic patent summarization approaches that help in the patent analysis and comprehension procedure are in high demand due to the colossal growth of innovations. The development of natural language processing (NLP), text mining, and deep learning has notably amplified the efficacy of text summarization models for abundant types of documents. Summarizing patent text remains a pertinent challenge due to the labyrinthine writing style of these documents, which includes technical and legal intricacies. Additionally, these patent document contents are considerably lengthier than archetypal documents, which complicates the process of extracting pertinent information for summarization. Embodying extractive and abstractive text summarization methodologies into a hybrid framework, this study proposes a system for efficiently creating abstractive summaries of patent records. The procedure involves leveraging the LexRank graph-based algorithm to retrieve the important sentences from input parent texts, then utilizing a Bidirectional Auto-Regressive Transformer (BART) model that has been fine-tuned using Low-Ranking Adaptation (LoRA) for producing text summaries. This is accompanied by methodical testing and evaluation strategies. Furthermore, the author employed certain meta-learning techniques to achieve Domain Generalization (DG) of the abstractive component across multiple patent fields.
A Systematic Literature Review of Deepfake Face Image Detection with Transfer Learning Techniques
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Wimalasena, W.; Herath, H.; Hewapathirana, I
Artificial intelligence-based fake content generation, also known as deepfake media content, is spreading rapidly with the advancement of technology. This can manipulate or completely change the real media by threatening the authenticity of the data. With the availability of major amounts of data, deepfake face image generation has become an emerging issue in today’s digitalized world. Therefore, it is crucial to understand the most effective methods to detect this deepfake face image content. This paper provides a comprehensive discussion about how transfer learning can be used in this specific area to detect deepfake face images through a systematic literature review of (49) papers using the PRISMA method. The paper addresses the gap in up-to-date detailed analysis of transfer learning methods in this area which emphasizes the effectiveness of the process of deepfake image detection by studying papers in the past decade. This paper presents a comprehensive discussion of the models that have been used in this area along with the transfer learning approaches that have been used. The key findings highlight that the most common transfer learning approach for deepfake image detection is CNN combined and the most effective model for deepfake image detection in transfer learning is fine-tuned models. This paper also highlights the challenges and possible improvements in the area of deepfake face image detection with transfer learning techniques.
A Unified Pipeline for Improving Financial Aid Eligibility Predictions in Deep Learning Models
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Kishanthan, S.; Hevapathige, A.
This paper systematically evaluates the performance of widely used deep learning architectures for financial aid prediction, identifying critical bottlenecks that hinder optimal performance. To address these limitations, we further propose a novel pipeline that enhances deep learning models by incorporating three key components: text vectorization, data equalization, and adaptive feature recalibration. This pipeline improves the models’ representational power and predictive accuracy, offering seamless integration with existing architectures. It significantly boosts performance in predicting financial aid eligibility, providing up to a 145% increase in balanced accuracy and a 45% increase in F1 score.
Accelerating Meta-Learning with the Enhanced Reptile Algorithm for Rapid Adaptation in Neural Networks
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Shree Smeka J.; SheejaKumari V.; Vijaya Raj M.; Santhosh Kumar S. P.; Angalaeswari S.
Reptile is an innovative meta-learning approach that improves the process of neural networks training across diverse tasks. Reptile differs from the preference gradient strategies. It searches for a model weight vector which can enable a model to learn a new set of tasks with a small number of weight updates. This is accomplished via a first-order optimization process which makes it less intricate than other strategies like model-agnostic meta-learning MAML. Reptile is said to sample a number of tasks and then trains the model on each of the tasks via performing a series of a few gradient steps, systematically updating the model towards the average gradient direction across all the tasks. This enables the model to generalize well with new tasks trained with few iterations, thus proving beneficial in few-shot learning. Reptile enables faster adaptation of the model by focusing on the learning of better initial parameters thereby lowering computational overhead and the training duration. The algorithm is noted for its ability not only to learn but also to adapt itself to new tasks in a short period of time, which greatly extends the scope of its application, especially in areas where data is scarce. Examples of these areas are robotics, personalized advertisements, and decision-making approaches that need to operate in real time. Reptile Algorithm builds good on gradient-based approaches and can spearhead volumetric applications of meta reasoning by being exceptionally efficient, scalable and less computationally intensive.
AI-Driven Approach for Measuring and Classifying Diabetic Retinopathy Severity
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Shaik, A.; Little Flower, K.; Veerabhadraiah, S.; Nandini, A.; Sai Kiran, C.; Yashwanth Goud, K.
Diabetic Retinopathy is one of the most common complications affecting people with diabetes and is a leading cause of blindness worldwide. Advanced technological methods through image analysis and artificial neural networks have become major assets in addressing the escalating problem of DR. This paper discusses various approaches to implementing automation in DR detection, focusing on image acquisition and preprocessing, feature extraction, and classification using AI. We review the utility of these systems in terms of cost, benefits, and performance, as well as the challenges related to data quality, model interpretability, and regulatory requirements. The study demonstrates that automation holds the key to delivering higher patient-impact opportunities in clinical applications such as screening programs and telemedicine. Finally, we discuss directions for future research and community implementation, emphasizing the importance of highly controlled, naturalistic designs and the translation of research findings into clinical practice.
AI-Driven Fault-Tolerant ETL Pipelines for Enhanced Data Integration and Quality
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Kaushalya, C.; Perera, S. K.; Thelijjagoda, S.
The reliability and fault tolerance of ETL (Extract, Transform, Load) pipelines are crucial for ensuring data integrity in corporate environments. Traditional ETL systems often rely on manual interventions to resolve data inconsistencies, leading to inefficiencies and increased operational costs. This study introduces an AI-driven framework to enhance ETL fault tolerance by automating data cleaning, standardization, and integration. Leveraging machine learning models, the framework minimizes human intervention, improves data quality, and scales across diverse data formats. Using real-world datasets, the proposed solution demonstrates its ability to enhance operational efficiency and reduce errors in corporate data pipelines. The findings highlight the framework's ability to strengthen fault tolerance, ensure data quality, and provide organizations with a competitive edge in managing complex data ecosystems.
An Integrated Deep Learning Framework for Early Detection of Vision Disorders
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Jayathilaka, S.; Balaruban, D.; Kumanayake, I.; Elladeniya, A.; Wijendra, D.; Krishara, J.; De Silva, M.
Vision impairment due to retinal diseases like Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD), Glaucoma, and Retinal Vein Occlusion (RVO) poses a significant health challenge in Sri Lanka, where these conditions are leading causes of blindness. This research presents a novel multi-disease prediction system leveraging advanced deep learning techniques for early detection of DR, AMD, Glaucoma, and RVO. The study utilized publicly available datasets, including retinal fundus images from repositories such as RFMiD, IDRiD, APTOS validated by medical professionals to ensure diagnostic reliability. These images were preprocessed and augmented to train robust convolutional neural network (CNN) models tailored to each disease. The predictive models were developed and optimized using hybrid architectures, integrating attention mechanisms and feature fusion for enhanced performance. This approach achieved high accuracies—93% for DR, 92% for AMD, 94% for Glaucoma, and 94% for RVO—demonstrating robustness and consistency across diverse retinal conditions. To validate real-world applicability, the models underwent further testing in clinical settings using a Sri Lankan dataset, reflecting local disease prevalence and imaging conditions. By combining validated public data with clinical testing, this scalable system supports ophthalmologists in early diagnosis, reducing diagnostic delays and improving patient outcomes. This work offers a reliable, innovative solution to mitigate the burden of blindness in Sri Lanka and beyond.
Bridging Linguistic Gaps: A Review of AI- Driven Speech-to-Speech Translation for Sinhala and Tamil in Sri Lanka
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Dilshani, I.; Chandrasena, M.
Sri Lanka maintains two official languages which constitute Sinhalese and Tamil making it linguistically diverse. Almost all communication requires effective dialogue between Sinhalese-speaking and Tamil-speaking communities especially when operating through real-time speech-to-speech translation. The current version of Speech-to-Speech Translation (S2S) solutions serves a useful purpose yet faces three major limitations, including internet dependence, performance difficulties in loud environments, and unnatural Text-to-Speech (TTS) outputs. The Automatic Speech Recognition (ASR) systems from CallTran along with Android-based solutions through Google APIs and PocketSphinx, struggle with flexible operations when processing different accent varieties. Furthermore, the Machine Translation (MT) system performs poorly in achieving semantic relevance due to the scarcity of parallel corpora. The combination of ASR, MT and TTS systems produces performance delays and misinterpretation issues, which interfere with real-time functionality. This review examines current models, highlights theoretical and practical gaps, and proposes directions for future research, followed by a comparison of existing approaches. The research requires attention to three essential gaps, including bilingual dataset annotation tasks alongside offline functionality and natural voice synthesis development. We propose future research directions to establish massive bilingual datasets as well as implement noise-resistant ASR models using self-supervised approaches such as Whisper and Wave-to-Vector v2 (Wav2Vec2) and the fine-tuning of multilingual MT models like Multilingual Bidirectional and Auto-Regressive Transformer (mBART) for Low Resource Sinhala-Tamil Language translation systems. Additionally, TTS models like Tacotron, FastSpeech and Coqui TTS should be optimized for prosody and intonation.
Computer Vision Technique for Quality Grading of Cardamom Spice
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Ahnaf, M. R. A.; Nizzad, A. R. M.; Mafaza, N. F.
In the agriculture industry, spices such as cardamom must be graded and their quality evaluated to maintain product standards and increase market value. Traditionally, cardamoms are graded manually, but this process is time-consuming, inconsistent, and prone to human error due to fatigue and subjectivity. This study proposes computer vision-based techniques to detect and categorize cardamom into four grades—premium, standard, substandard, and defective—based on size, shape, and texture. Researchers prepared 880 images representing these categories under uniform lighting conditions. Preprocessing techniques, including resizing, noise addition, and augmentation, were applied to enhance the dataset for robust model training. YOLOv8 was utilized for the detection and grading of cardamoms due to its capability for real-time object detection and classification. The proposed method effectively differentiated between quality grades with an accuracy of 92%, demonstrating reliability and efficiency. A user-friendly interface was developed using the Streamlit library, allowing users to upload images and obtain grading results instantly. This system offers a practical and scalable solution for improving quality control processes in the agricultural sector. Future work aims to incorporate larger datasets, texture analysis, and integration with automated machinery to further enhance its applicability in industrial settings. The proposed solution can also be generalized to other use cases in the agricultural industry.
Deep Learning based Screen Display Fault Detection System for Vehicle Infotainment Applications
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Ramesh, B.; Dheeba, J.; Raja Singh, R.
Modern vehicles are integrated with in-vehicle infotainment systems and are subject to software faults. This paper explores the application of deep learning algorithms to identify visual defects in infotainment systems and automatically document the issues. A real-time capable framework is deployed, delivering immediate feedback on detected defects. The proposed system performs thorough analysis, automatically summarizes detected defects, and generates detailed reports, significantly reducing manual documentation effort and supporting faster decision-making. The performance of the developed models is evaluated using Convolutional Neural Networks (CNN) and Artificial Neural Network (ANN) classifiers. Experimental results demonstrate the superior performance of the CNN model, achieving a training accuracy of 82.21% with an F1 score of 0.85, and a testing accuracy of 80.51% with an F1 score of 0.811. In comparison, the ANN model achieves a training accuracy of 70.18% with an F1 score of 0.7314, and a testing accuracy of 69.32% with an F1 score of 0.705.
Deepfake Detection Using a Hybrid Deep Learning Approach with Swin Transformers and ConvNeXt
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Amarasinghe, H. M. S.; Kasthuri Arachchi, S. P.
The rapid advancement of artificial intelligence has led to the proliferation of deep-fake technology, which poses significant challenges to digital security and trust. As deepfakes become increasingly sophisticated, there is an urgent need for effective detection methods that can accurately identify manipulated media across various platforms and contexts. Deepfakes are outcomes of advanced Artificial Intelligence algorithms such as Generative Adversarial Networks, and have become a danger to digital integrity, personal privacy, and public trust. With continuous advancements in the techniques for generating deepfakes, conventional methods of detection based on the artifact analysis of visuals and inconsistencies in physiological signals have started to wear out. This paper presents a hybrid deep learning model that works between Swin Transformers and ConvNeXt architectures for better detection. The proposed model achieves better detection accuracy and robustness by leveraging Swin Transformers' hierarchical feature extraction capabilities and the efficient processing strengths of ConvNeXt. Obtained results on the "Deepfake and Real Images" dataset demonstrated performance of 95.6% accuracy, 97.4% precision, 93.7% recall, and a 95.2% F1 score. The hybrid model is more effective than existing ones, demonstrating their potential for concrete application in social media platforms, news agencies, and digital forensics to help fight misinformation and preserve digital trust.
Detection of Cyberbullying to Reduce Mental Health Problems using Machine Learning Algorithms
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Perera, M. V. V.; Piyumal, K. M.
Social networks and other online platform services are where people are more likely to experience issues with cyberbullying, including kids, young and older adults who are addicted to them. Cyberbullying is an activity that takes place on digital platforms where victims are threatened or bullied individually or in groups by messages or comments online. Various cyberbullying detection techniques are continuously used on social media platforms; however, not all online platform services follow those mechanisms, which may lead to psychological problems that can cause depression and even suicide because people are unaware of taking action to prevent it. Many past cyberbullying detection studies used small datasets and omitted disclosing the total number of features used to train the model. To fill this gap, this study explores how model performance changes with the feature count and what happens when the dataset size increases. Therefore, two cyberbullying datasets with a combined total of 47,183 and 120,556 records were used, containing suspicious activities on Twitter and Facebook that most commonly belong to the cyberbullying category. To compare performance metrics of each model, three methods for feature extraction and three classifiers were used, namely Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM). The highest accuracy for the models created utilizing 47,183 data under the three feature extraction approaches was 94.43%, while the highest accuracy for the 120,556 data was 89.96%.
Enhancing network intrusion detection with stacked deep and reinforcement learning models
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Kalpani, N.; Rodrigo, N.; Seneviratne, D.; Ariyadasa, S.; Senanayake, J.
This study investigates the effectiveness of Ensemble Learning (EL) techniques by integrating reproducible Deep Learning (DL) and Reinforcement Learning (RL) models to enhance network intrusion detection. Through a systematic review of the literature, the most effective DL and RL models from 2020 to 2024 were identified based on their F1 scores and reproducibility, focusing on recent advancements in network intrusion detection. A structured normalisation and evaluation process allowed for an objective comparison of model performances. The best performing DL and RL models were subsequently integrated using a stacking ensemble technique, chosen for its ability to combine the complementary strengths of the DL and RL models. Experimental validation in a benchmark dataset confirmed the high accuracy and robust detection capabilities of the model, outperforming the individual DL and RL models to detect network intrusions in multiple classes. This research demonstrates the potential of ensemble methods for advancing Intrusion Detection Systems (IDSs), offering a scalable and effective solution for dynamic cybersecurity environments.
Enhancing Network Security using MachineLearning for Automated Anomaly-based Intrusion Detection Systems for IoT Environment
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Mahamud, N.; Uddin, M. J.; Sumaiya, U.
The rapid expansion of the Internet of Things (IoT) has revolutionized modern life, offering unparalleled automation and seamless interconnectivity between devices, often operating without user intervention. However, this convenience comes with a significant trade-off: increased susceptibility of IoT devices to cyberattacks, which can result in severe consequences if not promptly addressed. To tackle this pressing challenge, our study proposes innovative strategies powered by machine learning algorithms, achieving an exceptional 99.97% detection accuracy and a 0.0% false positive rate. Leveraging the Bot-IoT dataset for evaluation, our approach demonstrates marked improvements over existing detection methodologies. Furthermore, its adaptability to diverse IoT applications underscores its potential as a transformative advancement in IoT security.
Enhancing Sign Language Communication: Advanced Gesture Recognition Models for Indian Sign Language
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Kumar, S. G. S.; Abbass, J.
Globally, millions of individuals experience varying degrees of hearing impairment, creating an urgent demand for effective communication solutions. The limited number of proficient sign language users exacerbates this challenge. Recent advancements in machine learning provide promising avenues to address this issue. This study introduces an innovative automated system that translates one of the most popular sign languages, namely, Indian Sign Language (ISL), into English text using a webcam. Our comprehensive dataset includes ~1M images across 36 categories, covering digits (0-9) and alphabet letters (A-Z). The dataset features diverse gestures captured from various angles and performed by 6 individuals with different characteristics followed by data augmentation. We evaluated the effectiveness of 5 models, 3 standard and 2 customized respectively: (1) MobileNetV2, a pre-trained convolutional neural network (CNN) optimized for mobile applications, (2) VGG16, a well-established pre-trained deep learning model, (3) the standard CNN, (4) a custom-designed CNN tailored for ISL recognition, trained on 32x32 images for 20 epochs, and (5) Customized MobileNetV2 for ISL recognition retrained on 128x128 images for 20 epochs. Both customized models achieved an F1-Score of 94 whilst standard ones achieved an F1-Score of no more than 85. The comprehensive comparison underscores the enhanced accuracy and efficiency of our custom models, establishing them as a significant advancement in sign language recognition.
Federated SCFGWO for Secure and High-Accuracy Brain Tumor Detection Across Multi-Center MRI
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Alphonsa, J.; Kumari, V. S.
Privacy preservation and security concerns in medical imaging have led to the implementation of federated learning (FL) as an alternative to centralized machine learning approaches. This study introduces a novel Sine and Cosine Fitness Grey Wolf Optimization (SCFGWO) algorithm integrated into an FL framework to enhance the accuracy and efficiency of brain tumor detection across multi-center MRI datasets. SCFGWO addresses traditional Grey Wolf Optimization (GWO) limitations, such as early convergence and local optima, by incorporating adaptive sine–cosine strategies for improved global exploration and local exploitation. Compared to existing methods, the proposed SCFGWO-based framework achieves superior accuracy (97.2%), Dice Similarity Coefficient (0.94), and Intersection over Union (0.90) while maintaining computational efficiency (0.015s per slice). Innovative privacy-preserving methods, including differential privacy and homomorphic encryption, ensure data security across the dataset. These contributions establish SCFGWO as a robust optimization tool for federated learning applications in medical imaging, offering improved performance and enhanced data security.
FITSTYLE: An Application Revolutionizing Online Shopping by Enhancing the Virtual Try-On Experience
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Divyanjalee, G.; Ilmini, K.; Uwanthika, I.
In the last decade, the fashion industry has been significantly influenced by the rise of e-commerce and mobile commerce. As online consumers, we often face the challenge of selecting the right clothing size without the ability to physically try on garments, leading to frustration, uncertainty, and high return rates. These issues negatively impact customer satisfaction and online sales productivity, highlighting the need for advanced virtual shopping solutions. To address this problem, FITSTYLE proposes a sophisticated virtual try-on tool based on Generative Adversarial Networks (GANs) to simulate how clothes fit a consumer’s body. The FITSTYLE system tackles challenges in online clothing shopping by utilizing advanced technologies such as ResNet101 for image preprocessing, OpenPose for pose estimation, image segmentation to isolate users from backgrounds, and garment deformation algorithms for accurate fitting. Designed for ease of use and realistic visualization, it enhances customer satisfaction and reduces return rates. The research employed a mixed quantitative and qualitative methodology, collecting data from online shoppers to understand user needs and preferences. Based on these insights, the system was implemented using the most suitable technologies, with initial results showing improved customer decision-making and engagement. The system enhances satisfaction, reduces return rates, and boosts productivity in online sales, while also paving the way for future advancements in virtual try-on technologies and the broader fashion e-commerce landscape.
Gait pattern analysis for a weight carrying hexapod ant robot using reinforcement learning
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Karunarathna, J. A. T. D. B.; Mohamed Saki, W.; Kanesalingam, S.; Prasanga, D. K.; Weerasinghe, W. A. B. G. H. B. P.; Abeykoon, A. M. H. S.; Ruwanthika, R. M. M.
Robot hexapods are coming into focus in robotics fields due to their stable base and versatility in handling different terrains. The current study aims at identifying gait patterns to enhance efficiency and stability under dynamic payload conditions. It investigated six payload conditions: no payload, central payload, and four asymmetric payloads, which were front-left and back-left and front-right and back-right. To enable the dynamic modification of gait patterns, Proximal Policy Optimization (PPO), which is a type of reinforcement learning, was used in order to foster efficient and stable forward propulsion. To train and simulate a robot, Brax, an open-source physics simulation environment, was used under different payload conditions. It was shown that gait adaptation to loading distribution is achievable, while bilateral loading causes energy expenditures to grow. The research on hexapod movement is useful in the advancement of the field of bio-inspired robotics; it provides ideas for increasing hexapod mobility with unequal weight loadings and also helps to further extend hexapod robots’ usability.
Hybrid CNN-LSTM Framework for Robust Speech Emotion Recognition
(Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Shaik, A.; Reddy, G. P.; Vidya, R.; Varsha, J.; Jayasree, G.; Sriveni, L.
A key component of emotional computing is voice Emotion Recognition (SER), which is concerned with recognizing and categorizing human emotions from voice data. Human communication is heavily influenced by emotions, and giving machines the ability to recognize these emotional states improves their capacity for intelligent and sympathetic interaction. A reliable SER system that accurately classifies emotions using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model is presented in this research. The suggested approach integrates sophisticated feature extraction methods that efficiently capture both temporal and spatial emotional patterns in speech, including Mel-Frequency Cepstral Coefficients (MFCC), pitch, and chroma data. Metrics including accuracy, precision, recall, and F1-score were used to assess the system on two common datasets, RAVDESS and EMO-DB. The trial findings show that the hybrid CNN-LSTM model outperformed traditional machine learning approaches, with an overall accuracy of 89.4%. The system also demonstrated resistance to external noise and emotional overlap, making it appropriate for real-world applications.