Article
Automation & Control Systems
Zakariya Yahya Algamal, Maimoonah Khalid Qasim, Muhammad Hisyam Lee, Haithem Taha Mohammad Ali
Summary: In this paper, an improved grasshopper optimization algorithm (GOA) is proposed to optimize the hyperparameters of support vector regression (SVR) and simultaneously embed feature selection. Experimental results show that the proposed algorithm outperforms crossvalidation method in prediction accuracy, number of selected features, and running time. The efficiency of the proposed algorithm in improving prediction performance and computational time compared to other nature-inspired algorithms demonstrates the ability of GOA in searching for the best hyperparameters values and selecting the most informative features for prediction tasks.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Alok Kumar Shukla
Summary: The study developed a new intrusion detection system by combining the opposition self-adaptive grasshopper optimization algorithm with reinforcement learning in support vector machine, which can efficiently detect and classify modern cyberattacks with high accuracy, outperforming other techniques.
NEURAL COMPUTING & APPLICATIONS
(2021)
Review
Computer Science, Information Systems
Salam Fraihat, Sharif Makhadmeh, Mohammed Awad, Mohammed Azmi Al-Betar, Anessa Al-Redhaei
Summary: With the rapid expansion of IoT networks, the need for robust security measures has become urgent. This paper proposes a Network Intrusion Detection System (NIDS) using machine learning and a modified algorithm optimization algorithm for large-scale IoT NetFlow-based networks. The NIDS achieved accurate and robust detection with a reduced number of features.
INTERNET OF THINGS
(2023)
Article
Computer Science, Information Systems
Hui Xu, Yanping Lu, Qingqing Guo
Summary: This paper proposes an improved Butterfly Optimization Algorithm combined with BlackWidow Optimization (BWO-BOA) for feature selection in network intrusion detection, aiming to enhance the performance of the feature selection model and reduce feature dimensions significantly.
Article
Chemistry, Multidisciplinary
Manal Abdullah Alohali, Muna Elsadig, Fahd N. N. Al-Wesabi, Mesfer Al Duhayyim, Anwer Mustafa Hilal, Abdelwahed Motwakel
Summary: Cloud computing is an Internet-based technology that provides shared resources to users on demand. The paper proposes an intrusion detection system based on fuzzy logic to enhance cloud security. The system utilizes individualized IDS for each client, selects optimal features using an optimization algorithm, and achieves accurate intrusion detection.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Malik Braik
Summary: Feature Selection (FS) aims to improve the classification rate of dataset models by selecting a small set of appropriate features. Traditional methods often fail to reduce the high dimensionality of complex datasets, leading to weak classification models. Meta-heuristics, such as the human-based binary algorithm AFT, can provide a favorable classification rate for high-dimensional datasets. This study proposes enhanced versions of AFT, including BMAFT, BEAFT, and BSAFT, which substantially improve the performance of BAFT in terms of convergence speed and solution accuracy. The results demonstrate that BMAFT is the most competitive algorithm, outperforming other competing algorithms.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sanaa A. A. Ghaleb, Mumtazimah Mohamad, Waheed Ali H. M. Ghanem, Abdullah B. Nasser, Mohamed Ghetas, Akibu Mahmoud Abdullahi, Sami Abdulla Mohsen Saleh, Humaira Arshad, Abiodun Esther Omolara, Oludare Isaac Abiodun
Summary: Networks are often burdened by spam, which can hinder email servers and clog mailboxes. Spam detection systems help track spammers and filter unwanted emails by identifying patterns in email communications, improving the accuracy of spam detection. This study proposes a novel approach that utilizes a grasshopper optimization algorithm for feature extraction and a multilayer perceptron training algorithm for enhancing the performance of the spam detection system.
Article
Computer Science, Information Systems
K. G. Maheswari, C. Siva, G. Nalinipriya
Summary: In recent years, information technology organizations have faced challenges in scalability, mobility, and flexibility due to rapid growth. Cloud computing has become popular as a solution to address security and privacy concerns. However, the characteristics of the cloud make confidential data vulnerable to attacks. To enhance overall security, intrusion detection systems (IDS) specifically designed for cloud environments have been developed. Our proposed hybrid IDS scheme using deep recurrent neural networks and feature optimization aims to overcome limitations and known attacks in web and cloud environments.
COMPUTER COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Xiangyu Liu, Yanhui Du
Summary: With the widespread use of the Internet of Things, security issues have become increasingly prominent. The accurate detection of network attacks in the IoT environment with limited resources is a critical problem that needs to be urgently solved. This work proposes a feature selection method based on a genetic algorithm to address the problem of a large number of traffic features in the intrusion detection system. Experimental results show that this method achieves high detection accuracy and improves training time compared to other methods.
Article
Computer Science, Information Systems
Yu Zhou, Wenjun Zha, Junhao Kang, Xiao Zhang, Xu Wang
Summary: This paper proposes a problem-specific non-dominated sorting genetic algorithm (PS-NSGA) that can minimize three objectives of feature selection. By applying an accuracy-preferred domination operator and a quick bit mutation, the algorithm converges faster and better, achieving competitive classification accuracy in experiments.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Mahdieh Sabahno, Fatemeh Safara
Summary: One of the major challenges in cyber space and IoT environments is the presence of fake or phishing websites that steal users' information, highlighting the importance of effectively identifying and preventing phishing attacks.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Ahmed A. Ewees, Marwa A. Gaheen, Zaher Mundher Yaseen, Rania M. Ghoniem
Summary: Feature selection is an important phase in data mining, which improves the efficiency of learning models. Comprehensive and greedy algorithms are not suitable for handling a large number of features, and swarm intelligence algorithms are becoming more popular. This paper proposes a new method, called crossover-salp swarm with grasshopper optimization algorithm (cSG), which integrates different algorithms to enhance its performance and flexibility.
Article
Computer Science, Information Systems
Danijela Protic, Miomir Stankovic, Radomir Prodanovic, Ivan Vulic, Goran M. Stojanovic, Mitar Simic, Gordana Ostojic, Stevan Stankovski
Summary: Anomaly-based intrusion detection systems classify computer network behavior by identifying deviations from the statistical model of typical behavior. Feature selection and feature scaling are commonly used techniques to improve classifier performance.
Article
Biology
Jianfu Xia, Zhifei Wang, Daqing Yang, Rizeng Li, Guoxi Liang, Huiling Chen, Ali Asghar Heidari, Hamza Turabieh, Majdi Mafarja, Zhifang Pan
Summary: This research aimed to construct a new intelligent diagnostic method that is accurate, fast, noninvasive, and cost-effective in distinguishing between complicated and uncomplicated appendicitis. The study analyzed the data of 298 patients with acute appendicitis and identified the most significant variables, then built a diagnostic model using an improved grasshopper optimization algorithm-based support vector machine.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Haouassi Hichem, Merah Elkamel, Mehdaoui Rafik, Maarouk Toufik Mesaaoud, Chouhal Ouahiba
Summary: The grasshopper optimization algorithm, an efficient optimization technique inspired by nature, has been adapted into a binary variant to address feature selection problems and has shown superior performance in experiments compared to other swarm-based algorithms.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Nikita Singh, Tarun Kumar, Manu Vardhan
Summary: The paper proposes a framework for automating cheque settlement process based on blockchain technology, allowing for cheque generation, processing, and settlement through both online and physical modes. The framework introduces a novel trust-based consensus mechanism for block mining, reducing consensus time by 25%. It can partially transform the current banking system, but also discusses potential security threats and vulnerabilities.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Hardware & Architecture
Shubhra Dwivedi, Manu Vardhan, Sarsij Tripathi
Review
Computer Science, Information Systems
Vikas Sihag, Manu Vardhan, Pradeep Singh
Summary: With the increasing quantity and complexity of malware, Android users are facing severe security threats. Malware authors employ various techniques to evade detection, making it more challenging to detect. Strengthening security mechanisms has become increasingly important in application development.
COMPUTER SCIENCE REVIEW
(2021)
Article
Telecommunications
Shubhra Dwivedi, Manu Vardhan, Sarsij Tripathi
Summary: The study introduces a multi-parallel adaptive evolutionary technique and incorporates simulated annealing to enhance the performance of network intrusion detection systems, showing better results compared to traditional techniques in terms of threat detection efficiency.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Vikas Sihag, Gaurav Choudhary, Manu Vardhan, Pradeep Singh, Jung Taek Seo
Summary: The post-COVID world has seen an increased reliance on online businesses for daily transactions, especially through smartphones. This has resulted in new attack surfaces that need to be evaluated by security researchers. The large market share of Android has attracted malware authors to launch more sophisticated malware, making the need for detection critical.
SECURITY AND COMMUNICATION NETWORKS
(2021)
Article
Chemistry, Multidisciplinary
Ankit Agrawal, Sarsij Tripathi, Manu Vardhan, Vikas Sihag, Gaurav Choudhary, Nicola Dragoni
Summary: This research proposed a transfer-learning approach to solve nested named-entity recognition, achieving better performance using fine-tuned BERT-based models compared to other models, without requiring external resources or feature extraction.
APPLIED SCIENCES-BASEL
(2022)
Article
Geosciences, Multidisciplinary
Dharmaveer Singh, Manu Vardhan, Rakesh Sahu, Debrupa Chatterjee, Pankaj Chauhan, Shiyin Liu
Summary: The alteration in river flow patterns, particularly those that originate in the Himalaya, has been caused by climate change. It is more essential than ever to predict changes in streamflow due to the impending intensification of extreme climate events. However, very few studies have been undertaken for a mountainous catchment, especially in the western Himalaya.
HYDROLOGY AND EARTH SYSTEM SCIENCES
(2023)
Proceedings Paper
Computer Science, Information Systems
Rahul Sinha, Vikas Sihag, Gaurav Choudhary, Manu Vardhan, Pradeep Singh
Summary: People today are increasingly digitized, with smartphones and smartwatches becoming more popular. Mobile phones and wearable devices are being used in various ways, from tracking location and making payments to monitoring health. The information stored in these applications can be crucial for forensic investigations.
MOBILE INTERNET SECURITY, MOBISEC 2021
(2022)
Article
Computer Science, Information Systems
Vikas Sihag, Manu Vardhan, Pradeep Singh
Summary: The BLADE system is a novel obfuscation-resilient system based on Opcode Segments, which uses innovative methods for feature characterization and simplification of dalvik opcodes to enhance resilience. It has been found effective, accurate, and resilient against various obfuscation techniques.
FORENSIC SCIENCE INTERNATIONAL-DIGITAL INVESTIGATION
(2021)
Article
Computer Science, Artificial Intelligence
Ankit Agrawal, Sarsij Tripathi, Manu Vardhan
Summary: The study proposes a new active learning algorithm based on a hybrid query sampling strategy, which considers both sentence similarity and model probability value, showing superior performance in biomedical and Spanish language tasks compared to traditional active learning strategies, while requiring less annotated data to achieve the performance of supervised learning methods.
INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS
(2021)
Article
Computer Science, Software Engineering
Riju Bhattacharya, Naresh Kumar Nagwani, Sarsij Tripathi
Summary: Graph kernels have evolved as a promising and popular method for graph clustering over the last decade. This study compared five standard graph kernel techniques for graph clustering, considering different clustering methods. Results show that k-step random walk and shortest path kernel performed best among all graph clustering approaches.
INTERNATIONAL JOURNAL OF MULTIMEDIA DATA ENGINEERING & MANAGEMENT
(2021)
Article
Computer Science, Artificial Intelligence
Ankit Agrawal, Sarsij Tripathi, Manu Vardhan
Summary: Named entity recognition (NER) is an important subtask of information extraction that aims to identify and classify named entities in textual data. Various supervised and deep learning models are developed for this task. Active learning is an iterative method that minimizes labeling cost without affecting performance. Proposed active learning approach for NER shows minimal requirement of labeled data for training compared to other approaches.
PROGRESS IN ARTIFICIAL INTELLIGENCE
(2021)
Proceedings Paper
Computer Science, Information Systems
Anurag Shukla, Sarsij Tripathi
ADVANCES IN VLSI, COMMUNICATION, AND SIGNAL PROCESSING
(2020)