Parkinson's disease (PD) is a progressive neurological disorder that gradually worsens over time, making early diagnosis difficult. Traditionally, diagnosis relies on a neurologist's detailed assessment of the...
详细信息
Parkinson's disease (PD) is a progressive neurological disorder that gradually worsens over time, making early diagnosis difficult. Traditionally, diagnosis relies on a neurologist's detailed assessment of the patient's medical history and multiple scans. Recently, artificial intelligence (AI)-based computer-aided diagnosis (CAD) systems have demonstrated superior performance by capturing complex, nonlinear patterns in clinical data. However, the opaque nature of many AI models, often referred to as "black box" systems, has raised concerns about their transparency, resulting in hesitation among clinicians to trust their outputs. To address this challenge, we propose an explainable ensemble machine learning framework, XEMLPD, designed to provide both global and local interpretability in PD diagnosis while maintaining high predictive accuracy. Our study utilized two clinical datasets, carefully curated and optimized through a two-step data preprocessing technique that handled outliers and ensured data balance, thereby reducing bias. Several ensemble machine learning (EML) models—boosting, bagging, stacking, and voting—were evaluated, with optimized features selected using techniques such as SelectedKBest, mRMR, PCA, and LDA. Among these, the stacking model combined with LDA feature optimization consistently delivered the highest accuracy. To ensure transparency, we integrated explainable AI methods—SHapley Adaptive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME)—into the stacking model. These methods were applied post-evaluation, ensuring that each prediction is accompanied by a detailed explanation. By offering both global and local interpretability, the XEMLPD framework provides clear insights into the decision-making process of the model. This transparency aids clinicians in developing better treatment strategies and enhances the overall prognosis for PD patients. Additionally, our framework serves as a valuable tool for clinical data
This research paper presents the results of two studies investigating human mobility patterns in the 15 largest Metropolitan Statistical Areas (MSAs) in the United States. It studied 14 daily mobility parameters aggre...
详细信息
This research paper presents the results of two studies investigating human mobility patterns in the 15 largest Metropolitan Statistical Areas (MSAs) in the United States. It studied 14 daily mobility parameters aggregated at the MSA level, derived from four primary mobility parameters: Number of Visited Locations (N_LOC), Number of Unique Visited Locations (N_ULOC), Radius of Gyration (R_GYR), and Distance Traveled (D_TRAV) over a 30-day period. The first study was conducted on data from two large MSAs, one coastal and one inland (Boston and Atlanta, respectively). The aim was to examine associations between daily values of mobility parameters aggregated at the MSA level and identify those carrying similar or identical information. Results of factor analysis showed that these could be adequately described by two independent factors, pointing to one or two of the mobility parameters as sufficient to represent the whole set in analyses based on associations. These could either be D_TRAV, as it had high loadings on both factors, or N_LOC and R_GYR due to their high loadings on the two extracted factors. The second study was conducted on daily mobility datasets from the 15 MSAs. The aim was to compare daily mobility patterns of these MSAs and group them based on their mobility pattern similarities. Factor analysis of the aggregated mean daily distances (D_TRAV) across different MSAs over the studied period classified them into two distinct groups: one predominantly composed of inland MSAs and the other primarily of coastal MSAs. Strong weekly cycle trends emerged in these groups. Specifically, individuals from the inland MSA group tended to travel the furthest on Fridays and the least on Sundays, whereas those from the coastal MSA group traveled the most on Saturdays and the least on Mondays. This weekly pattern was robust, with 7-day lag autocorrelations of mean daily parameter values ranging between 0.81 to 0.99, excluding the mean daily N_LOC. These findings offer a
Detection of forest fire should be quick and accurate as forests are the important sources to lead a vital life on earth. Detection of fire can be extremely difficult using existing methods of smoke sensors installed ...
详细信息
Federated Learning is a distributed machine learning technique that enables on-device training without exchanging the sensitive data over the centralized server. In this paper, Federated Learning is used to train fina...
详细信息
Natural fibers such as bamboo, kenaf, flax, ramie and hemp were chemically treated to improve their adherence with hydrophobic matrices. One common chemical process for altering the surface of these natural fibers is ...
详细信息
Background: Currently, Artificial Intelligence (AI) and the Internet of Things (IoT) have transformed the field of agriculture with the innovative idea of automation and intelligence. The agriculture field completely ...
详细信息
Blockchain technology represents a modern supply chain management revolution which fixes operational challenges while providing enhanced transparency at reduced costs. The research develops HB-SCOF (Hybrid Blockchain-...
详细信息
Cryptographic hash functions are fundamental to secure digital interactions. This paper surveys one-way hashing, covering theoretical foundations, historical developments, cryptanalytic challenges, and widely trusted ...
详细信息
Healthcare Blockchains grant access to a modern technique to accumulate healthcare information, achieve healthcare, and make a belief for medical records distribution and records combination in a decentralized unlock ...
详细信息
This research explores the application of deep learning techniques for soil analysis in precision agriculture, focusing on the classification of soil types using convolutional neural networks (CNNs). The study address...
详细信息
暂无评论