Mohd. Junedul Haque

Mohd. Junedul Haque

Auto-generated profile, based on publicly available information

Mohd. Junedul Haque

Sandip University

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 June 2017 in International Journal of Computer Applications
Verified
Journal Article
Closed access
MJMohd Junedul
Mohd Junedul
MMMohd Muntjir
Mohd Muntjir

1 August 2024 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
PUPonnuswamy Udayakumar
Ponnuswamy Udayakumar
SYSrilatha Yalamati
Srilatha Yalamati
LMLavadiya Mohan
Lavadiya Mohan
MHMohd Junedul Haque
Mohd Junedul Haque
GNGaurav Narkhede
Gaurav Narkhede
KBKrishnamohan Bhashyam
Krishnamohan Bhashyam
In today’s digital world, Android phones play a vital part in a variety of facets of both professionals and individuals’ personal and professional lives. Android phones are great for getting things done faster and more organized. The proportionate increase in the number of malicious applications has also been seen to be expanding. Since the play store offers millions of apps, detection of malware apps is challenging task. In this paper, a methodology is introduced for detecting malware in Android applications through the utilization of global image shape transform (GIST) features extracted from grayscale images of the applications. The dataset comprises samples of both malware and benign apps collected from the virus share website. After converting the apps into grayscale images, GIST features are extracted to capture their global spatial layout. Various machine learning (ML) algorithms, such as logistic regression (LR), k-nearest neighbour (KNN), AdaBoost, decision tree (DT), Naïve Bayes (NB), random forest (RF), support vector machine (SVM), extra tree classifier (ETC), and gradient boosting (GB), are employed to classify the applications according to their GIST features. Furthermore, a feed forward neural network (FFNN) is utilized as a deep learning (DL) technique to further improve the accuracy of classification. The performance of each algorithm is evaluated using metrics such as accuracy, precision and recall. The results demonstrated that the FFNN achieves superior accuracy compared to traditional ML classifiers, indicating its effectiveness in detecting malware in Android apps.

1 May 2012
Verified
Conference Paper
Closed access
MHMohd. Junedul Haque
Mohd. Junedul Haque
KMKhalid.W. Magld
Khalid.W. Magld
NHNisar Hundewale
Nisar Hundewale
Intrusion Detection system is an active and driving secure technology. Intrusion detection (ID) is the process of examining the events occurring in a computer system or network. Analyzing the system or network for signs of intrusions, defined as attempts to compromise the confidentiality, integrity, availability, or to bypass the security mechanisms of a network. The focus of this paper is mainly on intrusion detection based on data mining. The main part of Intrusion Detection Systems (IDSs) is to produce huge volumes of alarms. The interesting alarms are always mixed with unwanted, non-interesting and duplicate alarms. The aim of data mining is to improve the detection rate and decrease the false alarm rate. So, here we proposed a framework which detect the intrusion and after that, it will show the improvement of k-means clustering algorithm.

6 November 2020
Verified
Conference Paper
Closed access
RARakesh Ahuja
Rakesh Ahuja
MSManish Sharma
Manish Sharma
MHMohd Junedul Haque
Mohd Junedul Haque
The paper described a new MPEG-2 compressed domain based imperceptible, blind, robust, and secure digital video watermarking method. The scheme exploited the intra coding part of MPEG compression algorithm for inserting the watermark image as copyright information. Three cryptographic keys are used to extract the watermark. This process further enhances the security of overall watermarking algorithm. Therefore, proper extraction would never possible without negotiating the unique keys. The strength of the proposed algorithm evaluated the robustness by applying wide variety of frame-based attacks to measure grading of resemblance and divergence between the extracted and original watermark respectively. The dominance of the projected technique is to obtain the admirable result for robustness and perceptibility both. The perceptibility is maintained as the scheme doesn't require to change the motion vectors resultant from DPCM process while encoding the video through MPEG-2 compression standard.

1 February 2021 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
RARakesh Ahuja
Rakesh Ahuja
SASachin Ahuja
Sachin Ahuja
Deepali GuptaDeepali Gupta
Deepali Gupta
MHMohd. Junedul Haque
Mohd. Junedul Haque
Digital video watermarking is an effective way to protect the ownership of the multimedia contents. A novel compressed domain based digital video watermarking algorithm scheme is proposed by exploiting MPEG-2 structure. Watermark bits are embedded in DC and AC coefficients both of only smooth discrete cosine transform (DCT) blocks from selected I-frames in the original digital video. The algorithms never exploited entire frames but explore only three location from the subset of DCT blocks from the subgroup of I-frames only. This process maintains the perceptibility of the watermarked video. Two parameters, normalized correlation (NC) and bit error rate (BER) are used to evaluate the degree of similarity and dissimilarity respectively to check the robustness against image processing and video specific intentional and non-intentional attacks. The security of embedded watermark is enhanced by applying three cryptographic keys. The experimental results demonstrated that the better robustness and perceptibility achieved by comparing the results with the state of art.

1 January 2012 in International Journal of Advanced Computer Science and Applications
Verified
Journal Article
Open access
PDF file
MJMohd. Junedul
Mohd. Junedul
KWKhalid. W.
Khalid. W.
The Traveling salesman problem (TSP) is to find a tour of a given number of cities (visiting each city exactly once) where the length of this tour is minimized. Testing every possibility for an N city tour would be N! Math additions. Genetic algorithms (GA) and Memetic algorithms (MA) are a relatively new optimization technique which can be applied to various problems, including those that are NPhard. The technique does not ensure an optimal solution, however it usually gives good approximations in a reasonable amount of time. They, therefore, would be good algorithms to try on the traveling salesman problem, one of the most famous NP-hard problems. In this paper I have proposed a algorithm to solve TSP using Genetic algorithms (GA) and Memetic algorithms (MA) with the crossover operator Edge Assembly Crossover (EAX) and also analyzed the result on different parameter like group size and mutation percentage and compared the result with other solutions.