Throughout history, music has consistently remained a widely enjoyed source of entertainment, and technology has swiftly acknowledged its popularity. The emergence of numerous music streaming platforms has provided us...
Throughout history, music has consistently remained a widely enjoyed source of entertainment, and technology has swiftly acknowledged its popularity. The emergence of numerous music streaming platforms has provided users with a plethora of choices, emphasizing the need for a system that simplifies the organization and search management of music. A project utilizing human-computer interaction (HCI) techniques to suggest songs by analyzing the user’s emotions extracted from speech input can significantly enhance the application’s personalization. This approach aims to create a more tailored and emotionally resonant experience for the user, establishing a deeper connection between the music recommendations and the user’s emotional state. However, relying solely on emotions from speech may not be very effective as it is subject to variations across people of different genders, race and culture. Speech emotion recognition may also be ineffective for the speech-impaired people. Hence, the objective of this project is to build a music recommendation system capable of discerning emotions from both body gestures and speech, enabling more comprehensive and nuanced song recommendations. In order to make effective recommendations using minimal amount of samples, meta learning models are used in both gesture and speech emotion recognition. This data is in turn used by the recommendation module. We have used the GEMEP Audio-Video dataset for emotion recognition using speech and body gestures. These identified emotions are then correlated with suitable song moods, forming the basis for the generated recommendations. The Emotion module of the model obtained an accuracy of 78.63% for multi-modal emotion recognition. The recommendation module obtained an accuracy of 98.02%.
The rapid growth of Smart Home applications has broadened the scope for a wide range of security concerns. Blockchain technology, specifically Hyperledger Fabric, offers a promising solution. The proposed model explor...
详细信息
ISBN:
(数字)9798350370249
ISBN:
(纸本)9798350370270
The rapid growth of Smart Home applications has broadened the scope for a wide range of security concerns. Blockchain technology, specifically Hyperledger Fabric, offers a promising solution. The proposed model explores its application, leveraging the Fablo toolkit to enhance the security of Smart Home IoT devices. The decentralized nature of Hyperledger Fabric, with features such as its consensus mechanism and chaincode, helps mitigate common security issues like unauthorized access and device tampering. The resultant tamperproof network, coupled with favorable metrics like latency and transaction throughput, underscores the robustness of the proposed model. Our model promises low latency and high transaction throughput. The metrics assist the model in securely and efficiently handling a large number of transactions without compromising on speed and security.
The software development process indeed comes up with compiler related bugs, it is critical to identify and fix them correctly to improve software quality. Compiler bugs are very critical to the correctness of softwar...
详细信息
ISBN:
(数字)9798350376685
ISBN:
(纸本)9798350376692
The software development process indeed comes up with compiler related bugs, it is critical to identify and fix them correctly to improve software quality. Compiler bugs are very critical to the correctness of software applications; thus, their detection and fixes are important. This paper proposes a new method that uses ensemble learning and explainable AI to improve the identification of compiler bugs. This paper focuses on the ensemble of four classifiers: Random Forest, Support Vector Machine, Neural Network, and Gradient Boosting. Incorporating these models should enhance the predictive accuracy and generalization ability since the individual classifiers have their drawbacks. In order to make the model more interpretable, we use SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to explain which features affect bug detection decisions. The results reveal the superior performance of the proposed ensemble model which yields better results than each of the individual classifiers in terms of precision, recall, F1-score, and ROC-AUC. In addition to enhancing the bug detection rate with the help of state-of-the-art machine learning and explainable AI, the method even enhances the understanding of compiler log analysis and significantly contributes to the field of software quality assurance.
Cognitive disorders among adolescents pose significant challenges to their overall well-being and prospects. Timely detection and intervention are crucial to mitigating the potential long-term impacts of these disorde...
详细信息
ISBN:
(数字)9798350354461
ISBN:
(纸本)9798350354522
Cognitive disorders among adolescents pose significant challenges to their overall well-being and prospects. Timely detection and intervention are crucial to mitigating the potential long-term impacts of these disorders. This research aims to develop a framework that can detect multiple cognitive disorders in adolescents by first collecting subjects’ responses to various survey questions, which are derived from standard questionnaires used to assess the brain’s functioning, then utilizing the Conditional Tabular Generative Adversarial Network (CTGAN) for treating the imbalance in the dataset, and finally using the TabNet deep neural network for classifying disorders. The proposed framework outperforms traditional machine learning (ML) models and is a promising tool for the online detection of cognitive disorders in adolescents.
Speech enhancement system focuses on improving people’s communication with speech impairments by converting unclear speech into a clear and intelligible output using a Rasp- berry Pi with a microphone. The speech is ...
详细信息
ISBN:
(数字)9798350350067
ISBN:
(纸本)9798350350074
Speech enhancement system focuses on improving people’s communication with speech impairments by converting unclear speech into a clear and intelligible output using a Rasp- berry Pi with a microphone. The speech is recorded using the microphone, processed for Mel-Frequency Cepstral Coefficient extraction and logistic regression reconstruction of classified speech features. The system works in real time and gives output through a speaker. Initializations had been done, including noise reduction and feature extraction for quality inputs to the logistic regression, which is modelled for indomitable setup through grid search with cross-validation. Testing was carried out in relation to effectiveness, which the system profiles through different metrics, especially accuracy, precision, recall, and F1-score. The results obtained are, in fact, that the model would be of help in increasing the clarity of the speech and hence providing quality in enhancing communication to real-time interactors with a speech defect. The system has the potential of impacting enhancing the quality of life for the user through enhanced communication.
Medication non-adherence is a significant problem in healthcare, leading to the gradual worsening of patient health, increased hospitalizations, and higher costs. Current patient-driven solutions rely heavily on the r...
详细信息
ISBN:
(数字)9798350379945
ISBN:
(纸本)9798350379952
Medication non-adherence is a significant problem in healthcare, leading to the gradual worsening of patient health, increased hospitalizations, and higher costs. Current patient-driven solutions rely heavily on the reliability of patient compliance and self-reporting, which are often inaccurate, leaving real-time monitoring and intervention gaps. The proposed system of a smart pill box, integrated with a Raspberry Pi 4, weight sensors, and a camera, addresses these weaknesses. The weight sensors will detect medication intake and verify dosages by sensing changes in weight, while the camera will capture images of the pills. Using a self-made dataset with over 400 images of each of 10 different tablets, the system will employ deep learning to identify the pills and verify dosages, alerting patients and caregivers to anomalies such as skipped doses. This automated adherence monitoring system reduces reliance on self-reporting and increases tracking accuracy. The expected outcomes of this research include improved medication adherence, reduced medication errors, and enhanced monitoring mechanisms, ultimately leading to better healthcare provision and outcomes for patients. Innovating health technology in this manner promises significant improvements in patient care.
Plant disease detection is a crucial step in improving the quantity and quality of farm products since many plant diseases that arise in rice crops reduce the production of agriculture and cause financial loss. The ma...
详细信息
ISBN:
(数字)9798350370249
ISBN:
(纸本)9798350370270
Plant disease detection is a crucial step in improving the quantity and quality of farm products since many plant diseases that arise in rice crops reduce the production of agriculture and cause financial loss. The manual evaluation of plant health is tiring and time consuming. Combining optimization algorithms with deep learning architectures can lead to more effective and efficient plant disease detection, with improved accuracy and generalization capabilities. This paper presents a comparison study on hyperparameter tuning of deep learning architectures for early detection of rice plant diseases. The hyperparameter tuning was performed by incorporating Bayesian Optimization algorithm on CNN, ResNet, MobileNet, InceptionNet and RegNet. The experimental study is conducted on dataset containing 1007 images of rice seed crop that contains 501 images of healthy samples and 506 unhealthy samples. Performance evaluation metrics such as accuracy, precision and inference time are employed to compare models. Additionally, a comparative analysis using explainable Artificial Intelligence (XAI) is conducted to visualize the interpretability of hyperparameter combinations and their impact on disease detection.
With rising industrialization, India confronts increasing difficulties in maintaining air quality regulations. This research proposes a comprehensive analysis and prediction framework based on machine learning approac...
详细信息
ISBN:
(数字)9798350349900
ISBN:
(纸本)9798350349917
With rising industrialization, India confronts increasing difficulties in maintaining air quality regulations. This research proposes a comprehensive analysis and prediction framework based on machine learning approaches for assessing and forecasting the Air Quality Index (AQI) in different place of India. This model takes into account a wide variety of pollutant concentrations that are monitored at regular intervals. This approach, which uses historical data from numerous Indian cities, employs a variety of machine learning methods, including k-Neighbour regression, decision tree regressor, linear regression, and random forest regressor, in addition to support vector regressor. Every model had performed well but the Decision Tree Regression and Random forest has performed best achieving RMSE value as 0.0016 and 0.00095 respectivelly whereas R-Squared value as 0.99 for both the model, indicating strong performance and a substantial progress in air quality prediction. The environmental health risks associated with air pollution have been mitigated by the addition of important knowledge.
The potential applications of multimodal physiological signals in healthcare,pain monitoring,and clinical decision support systems have garnered significant attention in biomedical *** self-reporting is the foundation...
详细信息
The potential applications of multimodal physiological signals in healthcare,pain monitoring,and clinical decision support systems have garnered significant attention in biomedical *** self-reporting is the foundation of conventional pain assessment methods,which may be *** learning is a promising alternative to resolve this limitation through automated pain *** paper proposes an ensemble deep-learning framework for pain *** framework makes use of features collected from electromyography(EMG),skin conductance level(SCL),and electrocardiography(ECG)*** integrate Convolutional Neural Networks(CNN),Long Short-Term Memory Networks(LSTM),Bidirectional Gated Recurrent Units(BiGRU),and Deep Neural Networks(DNN)*** then aggregate their predictions using a weighted averaging ensemble technique to increase the classification’s *** improve computing efficiency and remove redundant features,we use Particle Swarm Optimization(PSO)for feature *** enables us to reduce the features’dimensionality without sacrificing the classification’s *** improved accuracy,precision,recall,and F1-score across all pain levels,the experimental results show that the suggested ensemble model performs better than individual deep learning *** our experiments,the suggested model achieved over 98%accuracy,suggesting promising automated pain assessment ***,due to differences in validation protocols,comparisons with previous studies are still *** deep learning and feature selection techniques significantly improves model generalization,reducing overfitting and enhancing classification *** evaluation was conducted using the BioVid Heat Pain Dataset,confirming the model’s effectiveness in distinguishing between different pain intensity levels.
The race to develop the next generation of wireless networks,known as Sixth Generation(6G)wireless,which will be operational in 2030,has already *** realize its full potential over the next decade,6G will undoubtedly ...
详细信息
The race to develop the next generation of wireless networks,known as Sixth Generation(6G)wireless,which will be operational in 2030,has already *** realize its full potential over the next decade,6G will undoubtedly necessitate additional improvements that integrate existing solutions with cutting-edge ***,the studies about 6G are mainly limited and scattered,whereas no bibliometric study covers the 6G ***,this study aims to review,examine,and summarize existing studies and research activities in *** study has examined the Scopus database through a bibliometric analysis of more than 1,000 papers published between 2017 and ***,we applied the bibliometric analysis methods by including(1)document type,(2)subject area,(3)author,and(4)country of *** study’s results reflect the research 6G community’s trends,highlight important research challenges,and elucidate potential directions for future research in this interesting area.
暂无评论