A Fuzzy Expert System for The Drowsiness Detection from Blink Characteristics

Jothsna, V; Patel, Ibrahim; Raghu, K.; P, Jahnavi; Reddy, K. Nagi; Saikumar, K.

doi:10.1109/icaccs51430.2021.9441830

Cited by 16 publications

(10 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To counter this assault, each node should restrict the number of jobs it accepts and carefully pick the tasks it accepts. As a starting point, here is a conceivable strategy [7]. The node recognises "similar" tasks that could reveal the same personal information about it among the tasks for which it is qualified to provide a report this guarantees that the amount of work it accepts does not expand the amount of task groups that have received similar tasks in the same way.…”

Section: Methodsmentioning

confidence: 99%

“…An integrated phones system that tracks physically, social, and psychological state, such as sleeping, physical exercise, and interpersonal relationships and gives smart information to promote positive health is the goal of this effort. BeWell [7], an automatic Android mobile application for detecting number of co well-being, has been designed, implemented, and evaluated in this paper. BeWell has had the ability to enable consumers to increase overall entire well-being and recognise any early signs and symptoms of decline by presenting an even more comprehensive focus on health.…”

Section: Well-being Tracking Modelling and Promotion Are All Possible...mentioning

confidence: 99%

See 1 more Smart Citation

Incentives for privacy-concerned mobile sensing systems

Boppana

Maaz

Khan

et al. 2022

ijhs

View full text Add to dashboard Cite

To gather meaningful data about individuals and other environments, wireless sensor focuses on inputs posted by customers via their Smartphone (e.g., smart phone). Consumers, on the other hand, might well be hesitant to participate leading to a shortage of incentive as well as concern about probable privacy breaches. Both motivation and security challenges must be resolved in order to successfully stimulate public participation. [2] Although motivations as well as security have already been tackled independently in sensing system, addressing both concurrently remains an outstanding challenge. We introduce two resource private information additional incentives in mobile wearable sensors throughout this research, with the concentrate on data protection rather than incentives mechanism design [12]. Our methods allow Smartphone members to earn rewards by providing information without revealing what data they've supplied, and they prevent bad users from abusing the system to gain a limitless number of credits. The first approach takes into account instances in which an internet intermediary (TTP) is provided and depends just on TTP to preserve consumer privacy and avoid abusive threats [5]. The second strategy examines cases in which there is no online TTP.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Well-being Tracking Modelling and Promotion Are All Possible...mentioning

confidence: 99%

Incentives for privacy-concerned mobile sensing systems

Boppana

Maaz

Khan

et al. 2022

ijhs

View full text Add to dashboard Cite

show abstract

“…A general machine learning-based malware analysis technique that could be implemented in real time has a number of limitations. More crucially, [15] examined in depth the compelling controversies affecting the application of data science approaches. A new type of neural networks known as deep learning, and that is an upgraded version of MLAs, has recently surpassed conventional MLAs on many tasks in NLP, machine vision, voice recognition as well as many other areas [14].…”

Section: Need For the Studymentioning

confidence: 99%

intelligent robust malware detection by implementing deep learning

Reddy

Hasan

Abdullah

et al. 2022

ijhs

Self Cite

View full text Add to dashboard Cite

Malicious software (ransom ware) cyber attacks in frequency and severity, posing an increasingly serious threat to computer systems everywhere. Malware detection is a hot study area as several multiple computers, organisations, and governments have been affected by an exponential rise in malware attacks. Dynamic and static assessment of malicious characteristics and behaviour patterns is time expensive and useless in real-time malware detection, according to current technologies. It is becoming increasingly common for malicious apps to use polymorphic and adaptive techniques to rapidly modify their behaviour and develop a number of new malicious apps. In order to undertake an effective malware analysis, machine learning techniques (MLAs) are increasingly being used to create new malware varieties. This approach is time-consuming since it requires considerable feature engineering, learning and representation of features. Moreover the feature extraction process could be effectively eliminated by using advanced MLAs like deep learning. These methods have been shown to perform better with a biased training dataset, which restricts their practical application in real-time scenarios. A new improved approach for successful zero-day malware detection must be developed in order to eliminate biases and analyze these approaches autonomously.

show abstract

“…The problem was that so many of the channels weren't registered with IANA systems and weren't eligible for dynamic ports, therefore it eventually failed. [4] also provides a brief overview of Internet traffic classification.…”

Section: Introductionmentioning

confidence: 99%

Utilizing machine learning techniques to classify network traffic

Butool

Yazdani

Ahmedulla

et al. 2022

ijhs

View full text Add to dashboard Cite

With in community of internet, it may be essential to recognize whatever programs are flowing via the networks in order to execute particular activities. Network traffic categorization is primarily used by Internet service providers (ISPs) to determine the qualities needed to construct a connection, which in turn influences the cable network current effectiveness. Stream, bandwidth, and machine-learning methods were all used to categorise internet protocol, and each has its own benefits and drawbacks. Because of its widespread use across disciplines as well as the increasing awareness between many investigators of its [5] methodology when especially in comparison to everyone else, the Machine Learning method is popular these times. Nave Bayes as well as K-nearest algorithm results are then compared in this research whenever applied to a networking given dataset taken through live stream feeds using Ethernet program. Python's sklearn module and the pandas and numpy arrays modules are utilised as assist modules to create a machine learning algorithm. Our findings show that K closest approach is more efficient than Nave Bayes, Decision Tree, and Support Vector Machine algorithms.

show abstract

A Fuzzy Expert System for The Drowsiness Detection from Blink Characteristics

Cited by 16 publications

References 5 publications

Incentives for privacy-concerned mobile sensing systems

Incentives for privacy-concerned mobile sensing systems

intelligent robust malware detection by implementing deep learning

Utilizing machine learning techniques to classify network traffic

Contact Info

Product

Resources

About