A Comparative Analysis on Contingence Structured Data Methodologies

Beldar, Kavita K.; Gayakwad, Milind; Bhattacharyya, Debnath; Kim, Tai-hoon

doi:10.14257/ijseia.2016.10.5.02

Cited by 5 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy is 98.16 % for the WSN-DS dataset. [18] proposes the MQTT model based on the queuing theory, the accuracy of this model is 99.92 %. The MQTT model uses Machine Learning and other Deep Neural Network models.…”

Section: Type Style and Fontsmentioning

confidence: 99%

Intrusion Detection System using the Hybrid Model of Classification Algorithm and Rule-Based Algorithm

Kadam,

Garg,

Gayakwad

et al. 2023

IJRITCC

View full text Add to dashboard Cite

Intrusion detection system ID is necessary to secure the system from various intrusions. Analysis of the communication to categorize the data as useful or malicious data is crucial. The cyber security employed using intrusion detection systems should not also cause the extra time to perform the categorization. Nowadays machine learning techniques are used to make the identification of malicious data or an intrusion with the help of classification algorithms. The data set used for experimenting is KDD cup 99. The effect of individual classification algorithms can be improvised with the help of hybrid classification models. This model combines classification algorithms with rule-based algorithms. The blend of classification using machine and human intelligence adds an extra layer of security. An algorithm is validated using precision, recall, F-Measure, and Mean age Precision. The accuracy of the algorithm is 92.35 percent. The accuracy of the model is satisfactory even after the results are acquired by combining our rules inwritten by humans with conventional machine learning classification algorithms. Still, there is scope for improving and accurately classifying the attack precisely.

show abstract

Section: Type Style and Fontsmentioning

confidence: 99%

Intrusion Detection System using the Hybrid Model of Classification Algorithm and Rule-Based Algorithm

Kadam,

Garg,

Gayakwad

et al. 2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…prediction accuracy and performance [23]. The shortcomings of this method are that it doesn't consider the impact of the data on stock prices [24] and their closing prices do not take into account psychological considerations [25][26] [48] like news and national policies and forecasting.…”

Section: Related Workmentioning

confidence: 99%

A Parameter Based Comparative Study of Deep Learning Algorithms for Stock Price Prediction

Paygude,

Singh,

Tripathi

et al. 2023

IJRITCC

View full text Add to dashboard Cite

Stock exchanges are places where buyers and sellers meet to trade shares in public companies. Stock exchanges encourage investment. Companies can grow, expand, and generate jobs in the economy by raising cash. These investments play a crucial role in promoting trade, economic expansion, and prosperity. We compare the three well-known deep learning algorithms, LSTM, GRU, and CNN, in this work. Our goal is to provide a thorough study of each algorithm and identify the best strategy when taking into account elements like accuracy, memory utilization, interpretability, and more. To do this, we recommend the usage of hybrid models, which combine the advantages of the various methods while also evaluating the performance of each approach separately. Aim of research is to investigate model with the highest accuracy and the best outcomes with respect to stock price prediction.

show abstract