Hybrid Model for Early Diabetes Diagnosis

Ojugo, Arnold Adimabua; Eboka, Andrew Okonji; Yoro, Rume Elizabeth; Yerokun, Mo.; Efozia, Fidelia Ngozi

doi:10.1109/mcsi.2015.35

Cited by 21 publications

(29 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While a costly model requiring costly infrastructure, it can help protect valuable data in an enterprise from security threats and prevent immense financial damage. Its only demerit is that it require large processing power and thus, cannot be adopted by a home users (Singhal and Raul, 2012;Gao et al, 2011" Ojugo et al, 2013d. Studies on mathematical epidemiology as successfully used in malware detection, is focused on analytic epidemic thresholds for varying spread models and families of graphs -seeking insight into the nature of such epidemic, its threshold and to unveil if such epidemic will continue to spread or die.…”

Section: B Rationale For Choice Of Algorithmsmentioning

confidence: 99%

Malware Propagation on Social Time Varying Networks: A Comparative Study of Machine Learning Frameworks

Ojugo

Eseoghene²,

Kekeje³

et al. 2014

IJMECS

View full text Add to dashboard Cite

Abstract-Significant research into the logarithmic analysis of complex networks yields solution to help minimize virus spread and propagation over networks. This task of virus propagation is been a recurring subject, and design of complex models will yield modeling solutions used in a number of events not limited to and include propagation, dataflow, network immunization, resource management, service distribution, adoption of viral marketing etc. Stochastic models are successfully used to predict the virus propagation processes and its effects on networks. The study employs SI-models for independent cascade and the dynamic models with Enron dataset (of e-mail addresses) and presents comparative result using varied machine models. Study samples 25,000 emails of Enron dataset with Entropy and Information Gain computed to address issues of blocking targeting and extent of virus spread on graphs. Study addressed the problem of the expected spread immunization and the expected epidemic spread minimization; but not the epidemic threshold (for space constraint).

show abstract

Section: B Rationale For Choice Of Algorithmsmentioning

confidence: 99%

Malware Propagation on Social Time Varying Networks: A Comparative Study of Machine Learning Frameworks

Ojugo

Eseoghene²,

Kekeje³

et al. 2014

IJMECS

View full text Add to dashboard Cite

show abstract

“…Diabetes mellitus (also known as the silent sugar killer) is a metabolic disorder characterized by presence of hyperglycemia from defective insulin secretion, action or both. This metabolic disease features high glucose level in a body with insufficient insulin to breakdown glucose, or in a body that is resistant to the effects of insulin [2]. To improve its early diagnosis, various studies have used data mining tools to help experts effectively classify the disorder with criteria based on glycemia thresholds associated with micro-vascular disease and especially with the retinopathy.…”

Section: A Literature Reviewmentioning

confidence: 99%

“…Individuals with diabetes are grouped into: chronic hyperglycemia (a relatively specific long-term micro-vascular disorder affecting the eyes, kidneys and nerves with increased risk for cardiovascular defect), and prediabetes (a practical, convenient term for impaired fasting glucose, impaired glucose tolerance or glycated hemoglobin of 6.0% to 6.4%). Both of these classes, places patient at a high risk of developing diabetes [1][2]12].…”

Section: A Literature Reviewmentioning

confidence: 99%

“…We extend the study [2] via frameworks modelled in [25][26][27], we use dataset as presented in table 1obtained via a survey of questionnaires, consisting of two phases: (a) demographic data, and (b) tele-medical data. A total of a hundred questionnaires were distributed to various medical (diabetic) professional across forty teaching hospitals in six ( 6) Geo-political zones in Nigeria.…”

Section: A Data Gathering / Samplingmentioning

confidence: 99%

“…The chronic hyperglycemia of diabetes is associated with long-term damage, dysfunction, and failure of different organs, especially the eyes, kidneys, nerves, heart, and blood vessels. Symptoms of marked hyperglycemia include polyuria, polydipsia, weight loss, sometimes with polyphagia, and blurred vision [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictive Intelligent Decision Support Model in Forecasting of the Diabetes Pandemic Using a Reinforcement Deep Learning Approach

Ojugo¹,

Ekurume²

2021

IJEME

View full text Add to dashboard Cite

Diabetes has since become global pandemicwhich must be diagnosed early enough if the patients are to survive a while longer. Traditional means of detection has its limitations and defects. The adoption of data mining tools and adaptation of machine intelligence is to yield an approach of predictive diagnosis that offers solution to task, which traditional means do not proffer low-cost-effective results. The significance thus, is to investigate data feats rippled with ambiguities and noise as well as simulate model tractability in order to yield a low-cost and robust solution. Thus, we explore a deep learning ensemble for detection of diabetes as a decision support. Model achieved a 95-percent accuracy, with a sensitivity of 0.98. It also agrees with other studies that age, obesity, environ-conditions and family relation to the first/second degrees are critical factors to be watched for type-I and type-II management. While, mothers with/without previous case of gestational diabetes is confirmed if there is: (a) history of babies with weight above 4.5kg at birth, (b) resistant to insulin showing polycystic ovary syndrome, and (c) have abnormal tolerance to insulin.

show abstract

Boyer Moore string-match framework for a hybrid short message service spam filtering technique

Ojugo

Oyemade

2021

IJ-AI

View full text Add to dashboard Cite

Advances in technology and the proliferation of mobile device have continued to advance the ubiquitous nature of computing alongside their many prowess and improved features it brings as a disruptive technology to aid information sharing amongst many online users. This popularity, usage and adoption ease, mobility, and portability of the mobile smartphone devices have allowed for its acceptability and popularity. Mobile smartphones continue to adopt the use of short messages services accompanied with a scenario for spamming to thrive. Spams are unsolicited message or inappropriate contents. An effective spam filter studies are limited as short-text message service (SMS) are 140bytes, 160-characters, and rippled with abbreviation and slangs that further inhibits the effective training of models. The study proposes a string match algorithm used as deep learning ensemble on a hybrid spam filtering technique to normalize noisy features, expand text and use semantic dictionaries of disambiguation to train underlying learning heuristics and effectively classify SMS into legitimate and spam classes. Study uses a profile hidden Markov network to select and train the network structure and employs the deep neural network as a classifier network structure. Model achieves an accuracy of 97% with an error rate of 1.2%.

show abstract

Hybrid Model for Early Diabetes Diagnosis

Cited by 21 publications

References 13 publications

Malware Propagation on Social Time Varying Networks: A Comparative Study of Machine Learning Frameworks

Malware Propagation on Social Time Varying Networks: A Comparative Study of Machine Learning Frameworks

Predictive Intelligent Decision Support Model in Forecasting of the Diabetes Pandemic Using a Reinforcement Deep Learning Approach

Boyer Moore string-match framework for a hybrid short message service spam filtering technique

Contact Info

Product

Resources

About