The global real estate market is a significant asset class, which was valued at over $6.27 billion dollars in 2020. It is anticipated to grow at a compound annual growth rate (CAGR) of 6.4% between 2021 and 2028. Due ...
详细信息
Worldwide, oral cancer is one of the most common cancers. Even with easy access to the oral cavity and significant improvements in treatment, oral cancer death rates remain high, primarily due to late-stage diagnoses ...
详细信息
Diabetes is a chronic condition affecting blood sugar regulation and impacts a significant portion of the global population. Early detection is crucial, as it can help reduce complications and improve health outcomes....
详细信息
ISBN:
(数字)9798350357509
ISBN:
(纸本)9798350357516
Diabetes is a chronic condition affecting blood sugar regulation and impacts a significant portion of the global population. Early detection is crucial, as it can help reduce complications and improve health outcomes. Many cybercrime attacks are directed toward the healthcare sector, underscoring the importance of secure data handling. In this study, we use a dataset to predict diabetes risk, employing Machine Learning (ML) which offers a powerful means for accurate prediction by leveraging complex patterns in health data, yet privacy concerns around sensitive medical information remain a significant challenge. This study addresses this concern by incorporating Differential Privacy (DP), specifically utilizing the Laplacian Mechanism (LM), to protect patient data. We employ a range of ML algorithms, including Extreme Gradient Boosting (XGB), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Bootstrap Aggregating (Bagging), and Stacked Generalization (Stacking), to ensure robust model performance. Using the Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) for statistical analysis, our results reveal that even under DP constraints, the XGB model achieves an impressive accuracy of 89.43% while providing superior privacy protections. In contrast, without DP constraints, the RF model reaches a higher accuracy of 98.27%. To enhance interpretability, we integrate Explainable Artificial Intelligence (XAI) techniques such as Shapley Additive explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), allowing us to understand the influence of individual features on the model's predictions. Our study also employs 10-fold cross-validation to confirm the model’s stability and reliability. This approach not only supports accurate and private diabetes prediction but also paves the way for the application of DP in broader healthcare ML applications, balancing data privacy with predictive utility.
Wearable Augmented Reality integrated with predictive analytics is revolutionizing the healthcare monitoring system innovative and individualized. This paper outlines a new paradigm integrating AR devices for capturin...
详细信息
In this study, we use various RNN architectures namely, RNN, Bi-LSTM, and GRU — alongside BERT to analyze sentiment across university departments. Our aim is a comparative analysis of these models in sentiment classi...
详细信息
ISBN:
(数字)9798350355468
ISBN:
(纸本)9798350355475
In this study, we use various RNN architectures namely, RNN, Bi-LSTM, and GRU — alongside BERT to analyze sentiment across university departments. Our aim is a comparative analysis of these models in sentiment classification within education. We collected and pre-processed textual data from multiple departments for balanced training and validation. Results showed that traditional RNNs achieved 90% accuracy, Bi-LSTM 93%, and GRU 89%. BERT, leveraging its Transformer architecture, outperformed with 94% accuracy. These findings highlight the superiority of BERT in capturing complex language patterns for sentiment analysis. This study underscores the potential of advanced neural network architectures to gain insights into departmental sentiments, informing policy decisions and educational strategies. Aligning with sustainable development goals in education, we aim to use AI models to develop effective, inclusive, and responsive educational strategies, enhancing quality and accessibility.
Microplastic pollution threatens aquatic ecosystems and public health, requiring innovative detection solutions. This paper presents an IoT-based system combining a microscopic camera with a YOLOv8 model for real-time...
详细信息
ISBN:
(数字)9798331521691
ISBN:
(纸本)9798331521707
Microplastic pollution threatens aquatic ecosystems and public health, requiring innovative detection solutions. This paper presents an IoT-based system combining a microscopic camera with a YOLOv8 model for real-time detection and classification of microplastics, including types like LDPE, PE, PHA, and PS. The system achieves high accuracy, robustness in diverse environmental conditions, and real-time data visualization through a cloud-based dashboard. Challenges like class imbalance and IoT hardware constraints were mitigated using model optimization and advanced preprocessing. This scalable solution offers a practical tool for monitoring microplastic pollution, with future potential for marine vessel integration and enhanced detection using advanced imaging and deep learning methods.
Selfish federated learning model trainers may launch data poisoning attacks by introducing specific factors into the data or tampering the sample data, either to obtain a model suitable for themselves or to make the m...
详细信息
Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effec...
详细信息
Accurate prediction of CO 2 emissions is significant in the development of appropriate strategies to mitigate climate change. This study applies machine learning methodologies for the forecast of CO 2 emissions using ...
详细信息
ISBN:
(数字)9798331515683
ISBN:
(纸本)9798331515690
Accurate prediction of CO 2 emissions is significant in the development of appropriate strategies to mitigate climate change. This study applies machine learning methodologies for the forecast of CO 2 emissions using a global dataset from I960 to 2022. The dataset used from Kaggle comprises all the relevant features: power output from fossil fuels, nuclear, and renewables, in addition to GDP and land area. Three machine learning models were constructed and evaluated for their effectiveness in prediction: Random Forest, Gradient Boosting, and Linear Regression. The Random Forest model had the highest accuracy, as demonstrated by its R 2 score of 0.995, which showcases its strength in handling intricate, nonlinear interactions and identifying key variables, such as dependence on fossil fuels. The R 2 score for Gradient Boosting was 0.987, which shows that this model is similarly good at identifying complex relationships between features. Conversely, Linear Regression underperformed despite its processing efficiency due to its constraints with nonlinear data. This study highlights the efficacy of ensemble models in predicting CO 2 emissions. It offers practical recommendations for policymakers to formulate strategies to decrease fossil fuel use and promote renewable energy utilization. Future endeavors will include real-time data and investigate hybrid models to enhance temporal forecasting and practical application.
Smart Classrooms (SCR) are reshaping the learning experience with their interactive technology and personalized knowledge, leading to improved student engagement by seamlessly integrating digital gadgets. In this rapi...
详细信息
暂无评论