Knowledge Resource Center for Ecological Environment in Arid Area
| DOI | 10.1016/j.procs.2020.01.049 |
| Effective Diagnosis of Alzheimer's Disease using Modified Decision Tree Classifier | |
| Naganandhini, S.; Shanmugavadivu, P. | |
| 通讯作者 | Naganandhini, S (corresponding author), Gandhigram Rural Inst Deemed Univ, Gandhigram 624302, Tamil Nadu, India. |
| 会议名称 | 2nd International Conference on Recent Trends in Advanced Computing, Disruptive Innovation (ICRTAC-DTI) |
| 会议日期 | NOV 11-12, 2019 |
| 会议地点 | Vellore Inst Technol, Chennai Campus, Chennai, INDIA |
| 英文摘要 | Alzheimer's disease (AD) is described as a severe form of the neural disorder that collectively degenerate the essential cognitive activities of a human being (thinking, memory retention, etc.,) in particular among the elderly individuals and eventually results in death. In addition to the adverse ill-health effects on the patients, AD imposes paramount responsibility and burden on the caretakers too. Several genetic and pathological traits and non-invasive diagnostic strategies are being vigorously investigated and explored to discover the early onset of this debilitating disease. The prognosis of AD assumes importance,as the deterioration of health due to its progression may be either contained or controlled. Moreover, early and accurate detection of AD helps medical practitioners to prescribe case-specific medical treatment procedure. Among the popular machine learning algorithms, decision tree technique is widely used for classification/prediction, due to its accuracy and speed. This research article presents a novel decision tree-based classification technique, with optimum hyper parametertuning, that is ideally suitable for AD diagnosis, even at the early stages of development. The performance of this newly proposed Decision Tree Classifier with Hyper Parameters Tuning (DTC-HPT) is validated on the Open Access Imaging Studies Series (OASIS) dataset that contains patients' data on the different stages of AD. The DTC-HPT is designed with the primary objective to classify the nature of brain abnormality using the most relevantand potentially significant data attributes/parameters. The efficiency of DTC-HPT on AD classification is measured as Accuracy, Precision, Recall, and Fl-Score. The correctness of AD classification by DTC-HPT with an average accuracy of 99.10% endorse that this classification technique can be used for AD detection on the AD clinical datasets. |
| 英文关键词 | Alzheimer's Disease Feature Selection Classification Decision Tree Early Detection Hyper Parameter Tuning |
| 来源出版物 | 2ND INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ADVANCED COMPUTING ICRTAC -DISRUP - TIV INNOVATION , 2019 |
| ISSN | 1877-0509 |
| 出版年 | 2019 |
| 卷号 | 165 |
| 页码 | 548-555 |
| 出版者 | ELSEVIER SCIENCE BV |
| 类型 | Proceedings Paper |
| 语种 | 英语 |
| 开放获取类型 | gold |
| 收录类别 | CPCI-S |
| WOS记录号 | WOS:000582556800073 |
| WOS关键词 | PATTERNS |
| WOS类目 | Computer Science, Theory & Methods |
| WOS研究方向 | Computer Science |
| 资源类型 | 会议论文 |
| 条目标识符 | http://119.78.100.177/qdio/handle/2XILL650/369978 |
| 作者单位 | [Naganandhini, S.; Shanmugavadivu, P.] Gandhigram Rural Inst Deemed Univ, Gandhigram 624302, Tamil Nadu, India |
| 推荐引用方式 GB/T 7714 | Naganandhini, S.,Shanmugavadivu, P.. Effective Diagnosis of Alzheimer's Disease using Modified Decision Tree Classifier[C]:ELSEVIER SCIENCE BV,2019:548-555. |
| 条目包含的文件 | 条目无相关文件。 | |||||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
