Early dementia detection is a crucial but challenging task in Bangladesh. Often, dementia is not recognized until it is too late to receive effective care. This results in part from a lack of knowledge about the illne...
详细信息
Early dementia detection is a crucial but challenging task in Bangladesh. Often, dementia is not recognized until it is too late to receive effective care. This results in part from a lack of knowledge about the illness and its signs and symptoms. Recent improvements in machine learning algorithms, however, may change this. In a recent study, we developed a model that can identify early dementia in Bangladesh using machine learning algorithms. This research paper proposed an efficient machine learning-based approach for early detection of dementia disease A dataset of 199 people with dementia and 175 healthy controls was used to develop the model. In 96% of the cases, the algorithm correctly identified dementia. This is a significant accomplishment that could revolutionize Bangladesh's dementia detection process. For patients to get the care they require, early dementia detection is essential. This study offers a proof-of-concept for the use of machine learning in dementia early detection & The results of this study suggest that machine learning models can be used as a powerful tool for early detection of dementia.
Customer segmentation is a fundamental process to develop effective marketing strategies, personalize customer experience and boost their retention and loyalty. This problem has been widely addressed in the scientific...
详细信息
Path tracking problems are challenging with the absence of dynamic models and information about robot controllers. This paper presents a method of optimizing a motion profile constructed using a set of pre-defined mot...
Path tracking problems are challenging with the absence of dynamic models and information about robot controllers. This paper presents a method of optimizing a motion profile constructed using a set of pre-defined motion primitives and a speed command to track a spatial trajectory with high accuracy, speed, and uniform motion using industrial robots. We use a bi-level optimization approach that optimizes execution accuracy using reinforcement learning and execution speed using bi-section search. We train and evaluate the reinforcement learning policy in simulation for an ABB robot. Experiment results demonstrate that the learned policy reduces the optimization cost to achieve the desired specifications. Additionally, the trained policy can generalize to trajectories not included in the training set.
Bladder cancer is a complex disease and one of the most lethal types of cancer. Recently, some malignancies, including bladder carcinomas, have shown better results with immunotherapy using immune checkpoint inhibitor...
Bladder cancer is a complex disease and one of the most lethal types of cancer. Recently, some malignancies, including bladder carcinomas, have shown better results with immunotherapy using immune checkpoint inhibitors. Tumor mutational burden (TMB) is a potential biomarker for predicting tumor behavior and immunotherapy response as an outcome. Publicly available clinical data from the bladder cancer of TCGA project is used to analyze correlations of clinical variables with an increased tumor mutation burden (TMB) number compared with those with a lower number of mutations. The threshold for the high mutation burden in the analysis was set at 10 mutations (Mut) per Megabase (Mb). The Chi-Square test (χ 2 ) was used to compare categorical data. The Chi-Square "Best first" method was used to find a correlation between clinical variables and TMB, then compared with the p-value of significance (p<0.05). A significant correlation was found between TMB and Race, Neoplasm Histologic Grade, and gender when applying the Best First/Chi-Square method to clinical variables and level of TMB. This enables further investigation and application of the prediction models of the level of TMB, responsiveness to immunotherapy, and prognosis based on the clinical features of the patients.
Global warming has increased large-scale natural disasters at an alarmingly greater frequency. These natural disasters affect humans and the ecosystems that all species rely upon for food and shelter. A significant by...
Global warming has increased large-scale natural disasters at an alarmingly greater frequency. These natural disasters affect humans and the ecosystems that all species rely upon for food and shelter. A significant byproduct of global warming is the emergence of mega-fires, which are wildfires that burn more than 100,000 acres. Mega fires have exhibited the capacity to destroy entire ecosystems and urban areas. Researchers forecast a significant increase in wildfires during the next decade. This is a fundamentally growing problem that mandates modern solutions. Currently, simulation models are employed to predict wildfire propagation and aid firefighters in suppressing them. However, these methods are computationally expensive and often inaccurate. A recent advance in this area is the usage of neural networks (NN), which are systematically more accurate and computationally efficient. This paper focuses on predicting wildfire spread using NN with an attention mechanism to improve spatial recognition and overall performance in neural networks for wildfire spread prediction. We train different models on 12 distinct observational variables derived from the Google Earth Engine catalog. Evaluation is conducted with accuracy, Dice coefficient score, ROC-AUC, and F1-score. Results show that when augmenting segmentation models with attention mechanisms, the attention component improves feature suppression and recognition, improving overall performance. Furthermore, we use ensemble modeling to reduce bias and variation, leading to more consistent and accurate predictions. The architecture presented in this research achieved a ROC-AUC score of 86.2% and an accuracy of 82.1% when inferencing on wildfire propagation at 30-minute intervals.
Demand response (DR) programs can benefit electricity consumers, distribution network service providers (DNSPs), system operators and the energy market. However, the complexity and characteristics associated with load...
Demand response (DR) programs can benefit electricity consumers, distribution network service providers (DNSPs), system operators and the energy market. However, the complexity and characteristics associated with loads connected to customer premises, utilisation of backup generators for DR and the baseline calculation process still require considerable research to optimise and further unlock the capabilities of DR programs. This paper analyses the barriers to using backup generators in medium voltage (MV) networks in DR programs. Two representative Australian MV networks (e.g., Urban-NSW1 network, Urban-VIC network) are analysed in DIgSILENT PowerFactory under different scenarios, such as variation in locations, power export limits, and dynamic export limits of backup generators. The study has found that a backup generator located at the end of the network can achieve better performance in supporting the network voltage. Moreover, the voltage limit and thermal limit of the power network mainly constrain the export limits of backup generators. Furthermore, a backup generator with a dynamic export limit can export 1 to 5 times more energy than the static export limit.
The effects of Alzheimer's disease (AD) are devastating, both personally and within the patient's family, as the disease progresses slowly over many years. It could significantly affect illness consequences an...
详细信息
This paper aims to examine the applicability of machine learning models for aiding in the diagnosis and management of arboviral illnesses, especially Dengue. The study focuses on three key objectives: Diagnosis of Den...
详细信息
ISBN:
(数字)9798331511425
ISBN:
(纸本)9798331511432
This paper aims to examine the applicability of machine learning models for aiding in the diagnosis and management of arboviral illnesses, especially Dengue. The study focuses on three key objectives: Diagnosis of Dengue, prediction of prognosis of severe disease, and the identification of the post dengue effects. Multiple strategies were used to address these challenges. They are feature engineering based multiclass classification of arboviral diseases, enhancement of standard conventional machine learning algorithms for binary classification of severe Dengue and finally MLSOL enhancing ensemble model for drawing future effects of Dengue infections. The comparison of traditional models included both Random Forest, XGBoost, and also ensemble method while applying the feature selection methods of SFA and RFE. This study presents the comparison of traditional individual models and optimal ensemble method for the multiclass classification in arboviral diseases. In the case of binomial classification, the best accuracy level was 0.93 achieved by the Random Forest with RFE feature selection compared to Logistic Regression as well as the Gradient Boosting. Furthermore, the study proposed an MLSOL augmented ensemble approach to handle label imbalance problem in the dataset which in turn substantially enhanced the prediction accuracy. This approach decreased Hamming Loss to 0. 12 and increased the F-measure to 0.82, this has the capability of handling the imbalanced dataset and improving the predictive accuracy and performance. This machine learning framework offers great potential for clinical use in such aspects as early intervention and in effects following Dengue fever. It is meant to help healthcare practitioners and policy makers on how to better prevent and combat Dengue in Sri Lanka.
We propose an alternative way to determine GaAs carrier lifetime using pump-probe measurement based on fibre optics and integrated waveguides. We find that our GaAs samples have the lifetime ranging from 30-80 ps, sup...
详细信息
Crowdsourcing plays a critical role in modern information gathering and task execution, yet it faces challenges regarding the task selection and equitable monetary incentives distribution. In this paper, we introduce ...
详细信息
ISBN:
(数字)9798350351255
ISBN:
(纸本)9798350351262
Crowdsourcing plays a critical role in modern information gathering and task execution, yet it faces challenges regarding the task selection and equitable monetary incentives distribution. In this paper, we introduce the TOPMG framework, which addresses these challenges by enabling the workers to select tasks based on their historically experienced monetary incentives and the platforms’ trustworthiness. Specifically, the TOPMG framework utilizes a reinforcement learning approach based on the principles of Optimistic Q-learning with Upper Confidence Bound (OQ-UCB) algorithm, guiding the platform selection process by considering the workers’ monetary incentives, profit, and the platforms’ trustworthiness. Also, the proposed framework introduces a multilateral bargaining game to allocate the platforms’ monetary incentives to the workers by prioritizing their information contribution, fairness, and the platforms’ reputation. Simulation results demonstrate TOPMG’s operational dynamics, scalability, and efficacy, as well as its superiority over existing methodologies.
暂无评论