A Probability-Based Routing Algorithm for Improved Message Transmission in Vehicular Social Networks Hemlata Katre, Amit Saxena 2nd IEEE International Conference on Innovations in High Speed Communication and Signal Processing Ihcsp 2024, 2024 In Vehicular Social Networks (VSN), the high speed of vehicles and the unpredictability of their directions lead to constantly changing network topologies and frequent interruptions in communication links. As a result, there are high rates of message loss and transmission delays during message transmission. To address these issues, a probability-based routing algorithm (ProSim) for VSN is proposed, which utilizes opportunistic encounters between nodes for message transmission. The VSN routing algorithm is designed based on the social relationships between vehicles to mitigate the high loss rates and delays caused by communication link interruptions. It involves selecting the encounter probability and social similarity of vehicle nodes as social relationships, quantifying them, and calculating the transmission probability. Simulations using real road data show that ProSim, compared with three classic routing algorithms: Direct Delivery (DD), Epidemic, and PRoPHET, can effectively improve the message transmission rate while controlling transmission overhead and delay. Keywords: Vehicular Social Network; Opportunistic Communication; Social Relationships; Transmission Probability; Routing Algorithm.
Statistical Features based Content Based Image Retrieval Using Machine Learning Classifiers Akshay Anand, Amit Saxena, Kaptan Singh 2024 IEEE 3rd World Conference on Applied Intelligence and Computing Aic 2024, 2024 The retrieval of images has become an essential task over the last two decades. Content-based image retrieval (CBIR) is an open field of research, driven by the abundance of data available on the internet and the increasing demand for effective image retrieval techniques. Various feature-based approaches, including global and local methods, have been established in the past; however, many of them were either overly complicated or limited to specific use cases. This paper proposes an extended statistical feature set-based CBIR method employing a support vector machine (SVM) for simple image retrieval. The article explores four different machine learning classifiers: binary tree, SVM, Gaussian SVM, and kernel-based classifiers. Images are converted to 2D grayscale for feature calculation, making the technique color-independent. The performance of the suggested method is tested and assessed using a standard dataset of versatile color images. The method aims to classify the dataset based on statistical parameters such as absolute mean, maximum, entropy, deviation, and 2D correlation of query images. Initially, the algorithm calculates the features of 500 photos divided into five types. Then, test and training data are gathered. The ultimate goal of the paper is to assess the accuracy of production for different kernel classifiers.
Polynomial Partitioning Based Reversible Data Hiding Scheme over Cloud Ashish Dubey, Amit Saxena, Kaptan Singh 2024 Opju International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4 0 Otcon 2024, 2024 Reversible data hiding in homomorphic encryption research has increased due to cloud computing and the necessity to protect personal data. Because they rely on picture pixel correlation and redundancy, most reversible data hiding encryption schemes rarely work. We offer a polynomial partitioning-based reversible data hiding technique for the NTRU encryption system to improve embedding capacity and data hiding techniques. Digital material can be encrypted using the NTRU encryption system because its polynomial space is partitioned into plaintext segments that show the original carrier and data hiding segments that hide data. Users can recover the plaintext by bypassing encryption and reading the ciphertext directly. The experiment proves the approach works with text and grayscale images. NTRU encryption may hide up to $\mathrm{N}^{*} 8$ bits of data with a plaintext value of 8 bits, where N is a parameter, according to the testing. To restore plaintext with $\mathrm{N}=503$, ciphertext can hide 495 bits. In embedding capacity and applicability, the NTRU domain reversible data concealing technique beats prior comparable systems.
Modified Parametric Optimization Color Image Security Algorithm Using Latin Square Encryption Approach Mahak Saxena, Kaptan Singh, Amit Saxena 2024 IEEE International Students Conference on Electrical Electronics and Computer Science Sceecs 2024, 2024 Ensuring the security of digital images is a challenging task that requires the preservation of image properties. Image Encryption Standards (IES) are commonly employed to achieve this objective. Latin square-based encryption is particularly advantageous in the presence of significant nuisance disturbances. Typically, image encryption algorithms are constrained by key size. Therefore, the primary goal of this paper is to develop an effective Latin Square (LS)-based image encryption algorithm. We apply an updated parameter-based Latin Square encryption to the Luminance component in the LAB color space, along with the experimentally best parameter selection. The use of the LAB color space is capable of representing color information better than the RGB space, offering greater entropy and brightness. The encryption performance is assessed through parametric evaluation. The performance of the modified encryption algorithm is tested on unique color image data. The parametric evaluation is based on the Normalized Cross-Correlation Peak Ratio (NCPR), Unified Average Changing Intensity (UACI) count, and the Peak Signal-to-Noise Ratio (PSNR) calculated over the recovered images. The efficiency of the proposed method is demonstrated through parametric evaluation, which shows an improvement over the standard method.
A Cascaded Dynamic Attention-Based Deep Learning Model Segments Brain Tumors Kartik Choudhary, Kaptan Singh, Amit Saxena Proceedings 2024 International Conference on Current Trends in Advanced Computing Icctac 2024, 2024 Brain tumor diagnosis and treatment need segmentation, Precision automated segmentation of brain tumors is difficult due to their size, shape, unexpected placements, and fuzzy boundaries. U-Net is a popular medical picture segmentation model due to its simple architecture and high performance. Underutilized contextual information, limited local receptive fields, and lost spatial information are issues. For brain tumor segmentation, CDAU-Net, a novel model with Dynamic Convolution and Non-Local Attention Mechanism, addresses these issues. Two-stage cascaded three-dimensional U-Nets rebuild brain tumor spatial information at better resolution. The cascaded network's lateral connections receive maximal attention, improving its ability to collect long-distance interconnections and use tumor context information. Finally, dynamic convolutions with local adaptive capabilities replace normal convolutions in the cascaded network to increase local features capture. Extensive experiments were conducted on publicly available BraTS 2019 and 2020 datasets, comparing the proposed method with other representative approaches. Proposed method segments brain tumors. Brain tumor segmentation dice values of 0.897/0.903 for whole tumor, 0.826/0.828 for tumor core, and 0.781/0.786 for enhanced tumor segmentation worked in the BraTS 2019/2020 validation set.
An Approach to Prevent Neighborhood Attack over Social Media Pushpendra Lodhi, Arun Pratap Singh, Amit Saxena 2nd IEEE International Conference on Innovations in High Speed Communication and Signal Processing Ihcsp 2024, 2024 Social media sites contain the personal information of the users, which entice the attackers The attacker uses several types of attacks on the social networking site in order to obtain sensitive information from the users. To protect users from active and passive social media attacks, the network operator releases anonymized data. Various third-party consumers receive data collected from social media users from operators of these platforms. The whole graph is made available in anonymized and sanitised forms by the network operator because the acquired data often contains sensitive information. But it isn't a foolproof method of keeping users' information private. In order to make social network graphs anonymous, this study developed a method based on neighbourhood adjacency matrices. One potential defence against the neighbourhood assault on social network graphs is this anonymization process. The proposed anonymization method raises the quantity of isomorphic neighbourhood networks by introducing fictitious edges into the social network graph. This means that a social network graph cannot re-identify a person based on their distinct local area network.
Stock Market Closing Cost Prediction using Neural Network via Moving Average Features Rupesh Kumar, Amit Saxena, Kaptan Singh Proceedings 2nd International Conference on Advancement in Computation and Computer Technologies Incacct 2024, 2024 In recent times, huge random variations have been observed in stock prices on a daily basis. This makes it difficult for investors to predict investment options, rendering stock market prediction an open field of ongoing research. This paper aims to predict stock market closing prices using a neural network (NN)based approach. The proposed methodology first validates the basic NN-based stock market prediction (SMP) approach. Then, the range of moving average features is varied to evaluate prediction performance. Mean Absolute Error (MAE) and error histograms are used as performance metrics. The proposed method demonstrates the capability to achieve an accuracy of $\mathbf{9 9 . 9 8 7 \%}$ for Microsoft data, and for the FB database, it achieves $\mathbf{9 9 . 6 3 \%}$. A regression model is employed to evaluate prediction performance.
Based Energy Efficient Extended Stable Election L Kurmi, K Singh, A Saxena, SK Sharma Proceedings of International Conference on Intelligent Vision and Computing … , 2024 2024
An Iterative Block Image Compressive Sensing Method for Hybrid TV Image De-Noising APSK Sharma, K Singh, A Saxena Proceedings of International Conference on Intelligent Vision and Computing … , 2024 2024
Classification of Arrhythmia Data an QRS Peak Detection For Feature Extraction Using SVM Classifiers T Goswami, A Saxena International Conference on Computational Intelligence, 173-187 , 2024 2024
A Probability-Based Routing Algorithm for Improved Message Transmission in Vehicular Social Networks H Katre, A Saxena 2024 IEEE 2nd International Conference on Innovations in High Speed … , 2024 2024 Citations: 1
An Approach to Prevent Neighborhood Attack over Social Media P Lodhi, AP Singh, A Saxena 2024 IEEE 2nd International Conference on Innovations in High Speed … , 2024 2024
A Comprehensive Review on Object Removal from Images using Deep Learning AP Singh, A Saxena International Journal 4 (4), 01-06 , 2024 2024
Handwritten Text Recognition using Deep Learning Algorithms AP Singh, A Saxena International Journal 4 (4), 19-23 , 2024 2024
Statistical Features based Content Based Image Retrieval Using Machine Learning Classifiers A Anand, A Saxena, K Singh 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC … , 2024 2024 Citations: 1
Polynomial Partitioning Based Reversible Data Hiding Scheme Over Cloud A Dubey, A Saxena, K Singh 2024 OPJU International Technology Conference (OTCON) on Smart Computing for … , 2024 2024
Fast Color Image Security Standard for IoT Applications Using Gaussian A Khan, A Saxena, K Singh Communication and Intelligent Systems: Proceedings of ICCIS 2023, Volume 3 3 … , 2024 2024
A Cascaded Dynamic Attention-Based Deep Learning Model Segments Brain Tumors K Choudhary, K Singh, A Saxena 2024 International Conference on Current Trends in Advanced Computing … , 2024 2024
Stock Market Closing Cost Prediction using Neural Network via Moving Average Features R Kumar, A Saxena, K Singh 2024 2nd International Conference on Advancement in Computation & Computer … , 2024 2024 Citations: 2
Advancements In Multi-Modality Medical Image Fusion: A Comprehensive Review A Kesharwani, K Singh, A Saxena International Journal of Innovative Research in Engineering and Management … , 2024 2024 Citations: 2
Modified Parametric Optimization Color Image Security Algorithm Using Latin Square Encryption Approach M Saxena, K Singh, A Saxena 2024 IEEE International Students' Conference on Electrical, Electronics and … , 2024 2024
A detailed survey on content based image retrieval (cbir) A Anand, K Singh, A Saxena 2024 Citations: 2
Hybrid Multimodal Medical Images Fusion Combining MWGF with DC Coefficient Scaling and Pixel Level Wavelet Fusion A Kesharwani, K Singh, A Saxena 2023 International Conference on Computational Intelligence, Networks and … , 2023 2023
Fast Color Image Security Standard for IoT Applications Using Gaussian Pyramid Based on Modified AES A Khan, A Saxena, K Singh International Conference on Communication and Intelligent Systems, 317-329 , 2023 2023
Design and Evaluation of Modified Distance Based Energy Efficient Extended Stable Election Protocol: EE-ESEP L Kurmi, K Singh, A Saxena, SK Sharma International Conference on Intelligent Vision and Computing, 238-251 , 2023 2023
An Iterative Block Image Compressive Sensing Method for Hybrid TV Image De-Noising A Pawar, SK Sharma, K Singh, A Saxena International Conference on Intelligent Vision and Computing, 225-237 , 2023 2023
Retraction Notice: An Efficient Machine and Deep Learning Classfication Technique for Depression Using EEG Y Anis, K Singh, A Saxena 2023 3rd International Conference on Technological Advancements in … , 2023 2023
MOST CITED SCHOLAR PUBLICATIONS
Importance of aho-corasick string matching algorithm in real world applications S Hasib, M Motwani, A Saxena international journal of computer science and information technologies 4 (3 … , 2013 2013 Citations: 36
Application of feature extraction technique: A review MM Sahu, A Saxena, M Manoria International Journal of Computer Science and Information Technologies 4 … , 2015 2015 Citations: 20
Comparative Analysis of VM Scheduling Algorithms in Cloud Environment P Himthani, A Saxena, M Manoria International Journal of Computer Applications 120 (6), 1-6 , 2015 2015 Citations: 15
Intrusion detection system on KDDCup99 dataset: a survey S Rathore, A Saxena, M Manoria Int J Comput Sci Inf Tech 6 (4), 3345-3348 , 2015 2015 Citations: 12
Anti-Spam Methodologies: A Comparative Study S Hasib, M Motwani, A Saxena IJCSIT) International Journal of Computer Science and Information … , 2012 2012 Citations: 8
Monitoring wireless sensor network using android based smartphone application S Tembekar, A Saxena IOSR J. Comput. Eng 16, 53-57 , 2014 2014 Citations: 7
Serial and parallel bayesian spam filtering using Aho-Corasick and PFAC S Haseeb, M Motwani, A Saxena International Journal of Computer Applications 74 (17) , 2013 2013 Citations: 7
Detection and Prevention of Selfish Node in MANET using Innovative Brain Mapping Function: Theoretical Model A Gupta, A Saxena International Journal of Computer Applications 57 (12), 17-20 , 2012 2012 Citations: 7
Designing a Secure IOT data Encryption algorithm for Smart Environmental Monitoring System Z Malik, A Saxena, K Singh 2021 International Conference on Advances in Technology, Management … , 2021 2021 Citations: 6
Improved Vault based Tokenization to Boost Vault Lookup Performance A Thakur, A Saxena International Research Journal of Engineering and Technology (IRJET) 6 (10 … , 2019 2019 Citations: 6
Comparison of AOMDV Routing Protocol under IEEE802. 11 and TDMA Mac Layer Protocol AK Shrivastava, A Vidwans, A Saxena 2013 5th International Conference and Computational Intelligence and … , 2013 2013 Citations: 6
Enhanced thinning based finger print recognition P Mishra, AK Shrivastava, A Saxena International Journal of Computer Networks & Communications (IJCNC) 2 (2), 33 , 2013 2013 Citations: 6
Analysis of Selfish and Malicious Nodes on DSR Based Ocean Protocol in MANET A Saxena, JL Rana International Journal of Computing Science and Communication Technologies 3 … , 2010 2010 Citations: 6
Remaining useful life (RUL) prediction for FDIA on IoT sensor data using CNN and GRU S Singh, K Singh, A Saxena 2021 International Conference on Advances in Technology, Management … , 2021 2021 Citations: 5
A hybrid data model for prediction of disaster using data mining approaches A Singh, A Saxena International Journal of Engineering Trends and Technology (IJETT) 41 (7) , 2016 2016 Citations: 5
Detecting input validation attacks in web application S Khan, A Saxena International Journal of Computer Applications 109 (6) , 2015 2015 Citations: 5
Security Domain, Threats, Privacy issues in the Internet of Things (IoT): A Survey S Singh, K Singh, A Saxena 2020 Fourth International Conference on I-SMAC (IoT in Social, Mobile … , 2020 2020 Citations: 4
An Efficient Data Sharing in Public Cloud using two way Authentication & Encryption R Sharma, A Saxena, M Manoria International Journal of Computer Science and Information Technologies … , 2015 2015 Citations: 4
A review on energy efficient routing in wireless sensor networks R Tiwari, A Saxena Journal of engineering trends and technology 19, 29-34 , 2015 2015 Citations: 4
An improved image fusion technique based on texture feature optimization using wavelet transform and particle of swarm optimization (POS) P Malviya, A Saxena Int J Comput Appl 101 (6) , 2014 2014 Citations: 4
