Krishna Kumar
Research Subjects
Krishna Kumar has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hardwari Lal Mandoria
G. B. Pant University of Agriculture and Technology
3 shared publications - Prashant Ranjan
Department of Electronics and Communication Engineering, University of Engineering and Management, Jaipur, India
3 shared publications Ram Shringar Rao
3 shared publications- Pankaj Sharma
Institute of Cardiovascular Research, Royal Holloway University of London (ICR2UL), London TW20 0EX, UK; Department of Neurology, Imperial College Healthcare NHS Trust, UK
2 shared publications - Chetan Singh Negi
College of Technology G. B. Pant University of Agriculture Technology,Department of Information Technology,Pantnagar,Uttarakhand,India
1 shared publication - Pankaj Sharma
Symbiosis Centre for Management and Human Resource Development, Symbiosis International (Deemed University)
1 shared publication
Latest Publications
- 1 October 2025
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 72 (1) , 232-245
Performance Analysis of Visualization-Based Malware Classification Using CNN
- 1 October 2025
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 72 (1) , 232-245
Performance Analysis of Visualization-Based Malware Classification Using CNN
- 17 October 2024
- Published by Springer Nature
- p. 281-295
Cybersecurity Threats, Forensics, and Challenges
- 17 October 2024
- Published by Springer Nature
- p. 281-295
Cybersecurity Threats, Forensics, and Challenges
- 19 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Efficient Malware Classification Using 1D-CNN and Stacked Ensemble Techniques
Malware detection and classification systems are essential components of cybersecurity. The identification and categorization of various unknown and variant malware strains present an ongoing challenge. Current literature indicates that visualization-based malware detection and classification models leveraging deep learning demand substantial datasets, high computational resources, significant storage space, and extensive training times. There is a pressing need to reduce these computational costs, storage requirements, and training durations while enhancing model performance to achieve greater efficiency. This paper contributes by proposing an improved malware classification model that employs 1D-CNN and stacked ensemble techniques. In our experiments, we utilized two sets of custom and classical 1D-CNN models as weak learners. The top-performing weak learners were selected to create two ensemble models. Among these, the best-performing ensemble model achieved a classification accuracy of 98.01% with minimal computational resources, significantly improving efficiency.
- 19 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Efficient Malware Classification Using 1D-CNN and Stacked Ensemble Techniques
Malware detection and classification systems are essential components of cybersecurity. The identification and categorization of various unknown and variant malware strains present an ongoing challenge. Current literature indicates that visualization-based malware detection and classification models leveraging deep learning demand substantial datasets, high computational resources, significant storage space, and extensive training times. There is a pressing need to reduce these computational costs, storage requirements, and training durations while enhancing model performance to achieve greater efficiency. This paper contributes by proposing an improved malware classification model that employs 1D-CNN and stacked ensemble techniques. In our experiments, we utilized two sets of custom and classical 1D-CNN models as weak learners. The top-performing weak learners were selected to create two ensemble models. Among these, the best-performing ensemble model achieved a classification accuracy of 98.01% with minimal computational resources, significantly improving efficiency.
- 20 June 2022
- Published by Taylor & Francis
- p. 1-41
Internet of Things (IoT)
The Internet of Things (IoT) defines the network of physical objects, referred to as ‘things,’ which are integrated with a different type of sensors, devices, software, applications, and other technologies to connect and exchange data with other devices and systems through the internet [1]. These things are digital and mechanical devices, machines, objects, animals, or individuals with uniqueness and transmitting capabilities over a network without contact between human and human or computer [2]. The concept of IoT has grown due to the integration of numerous innovations, such as real-time processing, data analytics, deep learning, various sensors, embedded systems, and firmware engineering. The IoT embraces typically integrated systems of wireless networks with sensors, automation, control systems, etc. IoT for consumer consists of connectivity of the smart devices in the home that involves sensors and equipment (such as thermostats, lighting fixtures, home security systems, cameras, and some other home appliances) they can be managed by smartphones and apps [1].
- 20 June 2022
- Published by Taylor & Francis
- p. 1-41
Internet of Things (IoT)
The Internet of Things (IoT) defines the network of physical objects, referred to as ‘things,’ which are integrated with a different type of sensors, devices, software, applications, and other technologies to connect and exchange data with other devices and systems through the internet [1]. These things are digital and mechanical devices, machines, objects, animals, or individuals with uniqueness and transmitting capabilities over a network without contact between human and human or computer [2]. The concept of IoT has grown due to the integration of numerous innovations, such as real-time processing, data analytics, deep learning, various sensors, embedded systems, and firmware engineering. The IoT embraces typically integrated systems of wireless networks with sensors, automation, control systems, etc. IoT for consumer consists of connectivity of the smart devices in the home that involves sensors and equipment (such as thermostats, lighting fixtures, home security systems, cameras, and some other home appliances) they can be managed by smartphones and apps [1].
- 20 June 2022
- Published by Taylor & Francis
- p. 151-162
UAV
Unmanned aerial vehicles (UAVs), also known as drones, have become one of the fastest-growing fields, with several applications in various fields. The chapter aims to provide insights into the key application scenarios along with the challenges. More recently, researchers have become more interested in the use of multiple UAVs for object detection. Furthermore, real-time object detection is essential for many applications of UAVs, such as traffic monitoring, search-and-rescue, and infrastructure inspection. Many of these applications necessitate computer vision algorithms, particularly object detection using data acquired by an onboard camera. Neural Networks (CNNs), Machine Learning (ML), and IoTs have played an essential role in object detection in the last few years. However, it is still challenging due to several factors such as appearance deviation, background confusion, and severe occlusion. Therefore, the author gives the basic idea of an object detection system with its limitations.
- 20 June 2022
- Published by Taylor & Francis
- p. 151-162
UAV
Unmanned aerial vehicles (UAVs), also known as drones, have become one of the fastest-growing fields, with several applications in various fields. The chapter aims to provide insights into the key application scenarios along with the challenges. More recently, researchers have become more interested in the use of multiple UAVs for object detection. Furthermore, real-time object detection is essential for many applications of UAVs, such as traffic monitoring, search-and-rescue, and infrastructure inspection. Many of these applications necessitate computer vision algorithms, particularly object detection using data acquired by an onboard camera. Neural Networks (CNNs), Machine Learning (ML), and IoTs have played an essential role in object detection in the last few years. However, it is still challenging due to several factors such as appearance deviation, background confusion, and severe occlusion. Therefore, the author gives the basic idea of an object detection system with its limitations.
- 20 June 2022
- Published by Taylor & Francis
- p. 163-175
Smart Pole System
The control and maintenance of a conventional street lighting system still remains old fashioned in this period of revolutionary technological advancement. Powered streetlights consumed a large amount of energy, everyday, which can be utilized in a better way for other essential purposes. This chapter aims to report this issue by means of a Smart Pole System. In addition to the auto turn off and on and auto-dimming feature of the streetlights, several other segments like 5G, LoRaWAN, smart monitor to display, awareness of air pollutants, telecom tower, traffic management, temperature and humidity measurement, surveillance camera and many more have also been integrated on smart street lighting systems to make a “Smart Pole System”. Essential criteria for making a smart city are to make the city advanced and clean with use of minimum equipment. Smart cities should have good traffic systems, a top security system and good IT infrastructure also. For these purposes huge numbers of poles are installed in normal cities, which is much disorganized w.r.t not only congestion wise but also pricewise. Highly advanced smart poles are well equipped with technology, which replaces the conventional poles.
- 20 June 2022
- Published by Taylor & Francis
- p. 163-175
Smart Pole System
The control and maintenance of a conventional street lighting system still remains old fashioned in this period of revolutionary technological advancement. Powered streetlights consumed a large amount of energy, everyday, which can be utilized in a better way for other essential purposes. This chapter aims to report this issue by means of a Smart Pole System. In addition to the auto turn off and on and auto-dimming feature of the streetlights, several other segments like 5G, LoRaWAN, smart monitor to display, awareness of air pollutants, telecom tower, traffic management, temperature and humidity measurement, surveillance camera and many more have also been integrated on smart street lighting systems to make a “Smart Pole System”. Essential criteria for making a smart city are to make the city advanced and clean with use of minimum equipment. Smart cities should have good traffic systems, a top security system and good IT infrastructure also. For these purposes huge numbers of poles are installed in normal cities, which is much disorganized w.r.t not only congestion wise but also pricewise. Highly advanced smart poles are well equipped with technology, which replaces the conventional poles.