Likelihood Prediction of Diabetes at Early Stage Using Data Mining Techniques

Islam, Md. Manowarul; Ferdousi, Rahatara; Rahman, Sadikur; Bushra, Humayra Yasmin

doi:10.1007/978-981-13-8798-2_12

Cited by 159 publications

(114 citation statements)

References 3 publications

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…However, other options of similarity computation are open for exploration, which would give alternative choice for DM algorithm selection. [27] C4.5 C4.5 False-Alarm Detection [28] HMM HMM Thyroid Prediction [19] NB AdaBoost Diabetes Risk Prediction [26] RF RF Activity Detection (Walking) [15] LR RF Activity Detection (Jogging) [15] MLP MLP Activity Detection (Sitting) [15] j48 DT Activity Detection (Standing) [15] j48 DT Activity Detection (Upstairs) [15] MLP RF The proposed work has a positive implication in that it is capable of selecting appropriate DM algorithms for the data mining task, which is often facilitated by researchers or developers through numerous time-consuming procedures. These procedures in general include the study of several existing DM algorithms repeatedly to choose the best fit for a specific dataset.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Framework for Recommending Data Mining Algorithm in Dynamic IoT Environment

et al. 2020

Self Cite

View full text Add to dashboard Cite

Internet of Things (IoT) has been the driving force for many smart city applications. The huge volume of IoT data generated from these applications require efficient processing to get the insight, which poses significant difficulty. Data mining and machine learning (DM) algorithms are used to minimize such difficulty. However, it is still very challenging to select a particular DM algorithm that can process a dynamic IoT dataset based on some application-specific goals to achieve better accuracy. This paper proposes a knowledge-driven framework that considers the knowledge of datasets, available DM algorithms, and application goals to select the suitable DM algorithm for performing a target data processing task. This work considers data from cultural domain, health domain, and transportation domain in the experiment. The results show that the proposed approach dynamically selects the best-suited DM algorithms for the available datasets and target goals that exhibits satisfactory performance in obtaining accurate results compared to the existing work. The proposed approach not only provides flexibility in conducting dynamic IoT data mining tasks, but also reduces the complexity that would otherwise be necessary while adopting the traditional data mining approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In order to conduct the experiment, we considered a set of application goals, different datasets, and available DM algorithms. [26]. There are many DM algorithms as well as about 179 distinct ways for implementing supervised algorithms [8].…”

Section: A Experimental Setupmentioning

confidence: 99%

A Novel Framework for Recommending Data Mining Algorithm in Dynamic IoT Environment

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hasil percobaan menunjukkan bahwa secara keseluruhan kinerja metode ansambel adaboost lebih baik daripada bagging serta pohon keputusan J48 yang berdiri sendiri. Penelitian Islam, et al [13] mengenai prediksi kemungkinan diabetes pada tahap awal menggunakan teknik data mining. Dalam penelitian ini, kami telah menggunakan kumpulan data 520 kasus, yang dikumpulkan menggunakan kuesioner langsung dari pasien Rumah Sakit Diabetes Sylhet di Sylhet, Bangladesh.…”

Section: Tinjauan Literaturunclassified

Prediksi Kemungkinan Diabetes pada Tahap Awal Menggunakan Algoritma Klasifikasi Random Forest

Apriliah¹,

Kurniawan

Baydhowi³

et al. 2021

SISTEMASI

View full text Add to dashboard Cite

Diabetes adalah salah satu penyakit kronis yang mengancam jiwa dengan pertumbuhan tercepat yang telah mempengaruhi 422 juta orang di seluruh dunia menurut laporan Organisasi Kesehatan Dunia (WHO), pada tahun 2018. Diabetes dianggap sebagai salah satu penyakit paling mematikan dan kronis yang menyebabkan peningkatan gula darah. Banyak komplikasi terjadi jika diabetes tetap tidak diobati dan tidak teridentifikasi. Namun, peningkatan pendekatan machine learning memecahkan masalah kritis ini. Tujuan dari penelitian ini adalah merancang model yang dapat memprakirakan kemungkinan terjadinya diabetes pada pasien dengan ketelitian yang maksimal. Klasifikasi adalah teknik data mining yang menetapkan kategori pada kumpulan data untuk membantu dalam memprediksi dan analisis yang lebih akurat. Oleh karena itu tiga algoritma klasifikasi machine learning yaitu Suport Vector Machine, Naive Bayes dan Random Forest digunakan dalam percobaan ini untuk mendeteksi diabetes secara dini. Eksperimen dilakukan menggunakan dataset Diabetes Hospital in Sylhet, Bangladesh yang bersumber dari UCI repository. Performa ketiga algoritma dievaluasi pada berbagai ukuran seperti Precision, Accuracy, F-Measure, dan Recall. Akurasi diukur melalui instance yang diklasifikasikan dengan benar dan salah. Hasil yang diperoleh menunjukkan Random Forest mengungguli dengan nilai akurasi tertinggi 97,88% dibandingkan algoritma lain. Hasil ini diverifikasi menggunakan kurva Receiver Operating Characteristic (ROC) secara tepat dan sistematis.

show abstract

“…For future research directions, the researchers proposed Boruta wrapper algorithm as the feature selection technique before building the diabetes prediction model. A recent study proposed by Faniqul et al (2019) considered new factors for diabetes detection at the early stage. The dataset was collected from patients with diabetes at the Hospital of Sylhet in Bangladesh.…”

Section: Related Workmentioning

confidence: 99%

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

Al-Behadili

Ku-Mahamud

2021

Journal of Information and Communication Technology

View full text Add to dashboard Cite

Diabetes classification is one of the most crucial applications of healthcare diagnosis. Even though various studies have been conducted in this application, the classification problem remains challenging. Fuzzy logic techniques have recently obtained impressive achievements in different application domains especially medical diagnosis. Fuzzy logic technique is not able to deal with data of a large number of input variables in constructing a classification model. In this research, a fuzzy logic technique using greedy hill climbing feature selection methods was proposed for the classification of diabetes. A dataset of 520 patients from the Hospital of Sylhet in Bangladesh was used to train and evaluate the proposed classifier. Six classification criteria were considered to authenticate the results of the proposed classifier. Comparative analysis proved the effectiveness of the proposed classifier against Naive Bayes, support vector machine, K-nearest neighbour, decision tree, and multilayer perceptron neural network classifiers. Results of the proposed classifier demonstrated the potential of fuzzy logic in analyzing diabetes patterns in all classification criteria.

show abstract

Likelihood Prediction of Diabetes at Early Stage Using Data Mining Techniques

Cited by 159 publications

References 3 publications

A Novel Framework for Recommending Data Mining Algorithm in Dynamic IoT Environment

A Novel Framework for Recommending Data Mining Algorithm in Dynamic IoT Environment

Prediksi Kemungkinan Diabetes pada Tahap Awal Menggunakan Algoritma Klasifikasi Random Forest

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

Contact Info

Product

Resources

About