ASPG Menu
search

American Scientific Publishing Group

Research Feed

Found 3841 matches for "All Articles"

Detecting Image Spam on Social Media Platforms Using Deep Learning Techniques

Image spam involves the practice of concealing text within an image.  Various machine-learning techniques are used to categories image spam, utilizing a wide range of features extracted from the images.   Convolutional neural networks (CNNs) are commonly used for image classification and feature extraction tasks because of their outstanding performance. In this study, our focus is to analyses image spam using a CNN model that incorporates deep learning techniques. This model has been meticulously fine-tuned and optimized to deliver exceptional performance in both feature extraction and classification tasks. In addition, we performed comparative evaluations of our model on different image spam datasets that were specifically created to make the classification task more challenging. The results we obtained show a significant improvement in classification accuracy compared to other methods used on the same datasets.

groups
Himani Jain mail -
Amit Dixit mail -
Aditi Sharma mail
link https://doi.org/10.54216/JCIM.150106

Volume & Issue

Vol. Volume 15 / Iss. Issue 1

Details open_in_new

Anti-Geometry and NeutroGeometry Characterization of Non-Euclidean Data

Recently, a problem is addressed while dealing with fourth dimensional or non-Euclidean data sets. These are the data sets does not follow one of the postulates established by Euclid specially the parallel postulates. In this case, the precise representation of these data sets is major issues for knowledge processing tasks. Hence, the current paper tried to introduce some non-Euclidean geometry or Anti-Geometry methods and its examples for various applications. 

groups
Prem Kumar Singh mail
link https://doi.org/10.54216/JNFS.010102

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Certain Kinds of Bipolar Interval Valued Neutrosophic Graphs

Neutrosophic theory has several application in the field of graph theory. In this paper we initiated Certain Kinds of Bipolar interval valued nentrosphic graphs. Such as, sub divsicon BIVNG, Total BIVNG, BIVNLG and also investigate the isomorphism, Coweak isomorphism of BIVNG with properties .

groups
L. Jagadeeswari mail -
V.J. Sudhakar mail -
V.Navaneethakumar mail -
Said Broumi mail
link https://doi.org/10.54216/IJNS.160105

Volume & Issue

Vol. Volume 16 / Iss. Issue 1

Details open_in_new

Continuity and Compactness on Neutrosophic Soft Bitopological Spaces

In this manuscript, continuity, compactness and  concepts in neutrosophic soft bitopological space have been defined using star bineutrosophic soft open notion. Theorems and properties concerning to these two notions have been investigated here.

groups
Ahmed B. AL-Nafee mail -
Jamal K. Obeed mail -
Huda E. Khalid mail
link https://doi.org/10.54216/IJNS.160201

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

A Novel Approach to Necessary and Sufficient Conditions for the Diagonalization of Refined Neutrosophic Matrices

This work is dedicated to study the conditions of diagonalization in the case of refined neutrosophic matrices, where it presents the necessary and sufficient conditions for the diagonalization of these matrices by finding a relationship with classical diagonalization of matrices. Also, it describes an algorithm to obtain all eigen values and eigen vectors of refined neutrosophic matrices from the classical ones.  

groups
Necati Olgun mail -
Ahmed Hatip mail -
Mikail Bal mail -
Mohammad Abobala mail
link https://doi.org/10.54216/IJNS.160202

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

A Contribution To Kothe's Conjecture In Refined Neutrosophic Rings

The objective of this paper is to answer an open question asked in [42], about the equivalence between Kothe's conjecture in a ring R and its corresponding refined neutrosophic ring . Where it proves that Kothe's conjecture is true in R if and only if it is true in .

groups
Arwa A. Hajjari mail -
Rozina Ali mail
link https://doi.org/10.54216/IJNS.160203

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

Dark data analysis using Intuitionistic Plithogenic graphs

The precise analysis of uncertainty in given data sets and its mathematical representation is considered as one of the major issues at current time. The problem become more complex when the data sets contains several mutliattributes and its non-opposite sides. One of the suitable examples is cricket or sports data sets which create conflict among the experts in case of multi-decision process. The problem arises when the expert want to chategorize the performance of players based on its acceptation and rejection regions considering the contradiction. To deal with these types of data which contains human intuition in true and false regions intuitionistic Plithogenic set and its graphical visualization is introduced in this paper with an illustrative examples. 

groups
Prem Kumar Singh mail
link https://doi.org/10.54216/IJNS.160204

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

Bipolar neutrosophic soft generalized pre-continuous mappings

In this study, new classes of continuous mappings in bipolar neutrosophic soft topological space, namely bipolar neutrosophic soft continuous mappings and bipolar neutrosophic soft generalized pre-continuous mappings has been introduced. Continuity mappings preserves topological structures such as closeness, openness, compactness and so on. Here, we have proposed and investigated various continuous mappings based on bipolar neutrosophic soft sets. Further, we investigated some of their properties and relations with other mappings with examples.

groups
Arulpandy P mail -
Trinita Pricilla M mail
link https://doi.org/10.54216/IJNS.160205

Volume & Issue

Vol. Volume 16 / Iss. Issue 2

Details open_in_new

A Review of the Common DDoS Attack: Types and Protection Approaches Based on Artificial Intelligence

Recently, technology become an important part of our life, and it is employed to work together with Medicine, Space Science, Agriculture, industry, and more else. Stored the information in the servers and cloud become required. It is a global force that has transformed people's lives with the availability of various web applications that serve billions of websites every day. However, there are many types of attacks that could be targeting the internet, and there is a need to recognize, classify and protect thesis types of attack.  Due to its important global role, it has become important to ensure that web applications are secure, accurate, and of high quality. One of the basic problems found on the Web is DDoS attacks. In this work, the review classifies and delineates attack types, test characteristics, evaluation techniques; evaluation methods, and test data sets used in the proposed Strategic Strategy methodology. Finally, this work affords guidance and possible targets in the fight against creating better events to overcome the most dangerous Cyber-attack types which are DDoS attacks.

groups
N. A. Majeed alhammadi mail -
K. Hameed Zaboon mail -
A. Abdulhadi Abdullah mail
link https://doi.org/10.54216/FPA.070101

Volume & Issue

Vol. Volume 7 / Iss. Issue 1

Details open_in_new

Indian Premier League Using Different Aspects of Machine Learning Algorithms

The purpose of the present article is to highlight the outcomes of Indian premier league cricket match utilizing a managed taking in come nearer from a team-based point of view. The methodology consists of prescriptive and descriptive models. Descriptive model focuses mainly on two aspects they are, it describes data and statistics of the previous information. i.e., batting, balling or allrounder and It predicts past matches of IPL. Predictive model predicts ranking and winning percentage of the team. The two models show the measurements of winning level of the group Winner that the user has selected. This paper predicts the result through which technique match has highest result. The dataset consists of two groups that is the toss outcome, venue date, which tells about of the counterpart for all matches. Since the nature impact can't be expected in the game, 109 matches which were either finished by downpour or draw/tie, have been taken out from the dataset.  The dataset is partitioned into two sections to be specific the test information and the train information.The readiness dataset contains the 70% of the information from our dataset and the test dataset contains 30% of the information from our dataset. There were all out of 3500 coordinates in getting ready dataset and 1500 matches. This paper has been researched earlier by different scholars like Pathak and Wadwa, Munir etl ,and many other scholars. This viewpoint discusses the application of INDIAN PREMIER LEAGUE Matches held in different states. Gives the score of batsman and bowler with the help of machine learning techniques. Focuses on predicted analysis which is predicted by applying with various AI strategies to the real outcome actual result and gives the percentage of predicted result.

groups
Gande Akhila mail -
Hemachandran K. mail -
Juan R. Jaramillo mail
link https://doi.org/10.54216/JCHCI.010101

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new