Sandip Kumar Goyal
@mmumullana.org
Professor in CSE Department
Maharishi Markandeshwar Engineering College
EDUCATION
PhD (CSE), MTech (CSE), BTech (CoE)
RESEARCH INTERESTS
Distributed Computing, Load Balancing
Scopus Publications
Scopus Publications
Anup Lal Yadav and Sandip Kumar Goyal
The Science and Information Organization
—Vehicle collisions are a significant problem worldwide, causing injuries, fatalities, and property damage. There are several reasons for the collapse of vehicles such as rash driving, over speeding, less driving skills, increasing number of vehicles, drunk and drive, etc. However, over speeding is one of the critical factors out of all the reasons for vehicle collisions. To address the critical issues, the current article proposes a Fuzzy-based algorithm to prevent and control the speed of the vehicle. The major objective of the proposed system is to control the speed of the vehicle for proactive collision avoidance. Deep learning and fuzzy system provide better integrated approach for the controlling of the speed and avoid vehicle collision. Fuzzification of the speed variable provides an advanced or viable solution for speed control. The current research used RNN and other deep learning algorithm to predict the traffic and identify the traffic frequency. The traffic frequency in a time-series frame provides the frequency of the traffic within a time frame that can be detected by using involvement of IoT.
Vatan Sehrawat and Sandip Kumar Goyal
Springer Science and Business Media LLC
Anup Lal Yadav and Sandip Kumar Goyal
IEEE
The increasing number of vehicles on the roads has resulted in a higher risk of accidents and collisions. To address this critical issue, this research proposes an intelligent system for vehicle collision avoidance using the Internet of Things (IoT). The system aims to enhance road safety by providing real-time monitoring, analysis, and proactive collision avoidance mechanisms. The system operates in three main stages: perception, decision-making, and action. In the perception stage, sensor data from vehicles and infrastructure are collected and processed to gather relevant information about the surrounding environment. This includes detecting the presence, position, and velocity of nearby vehicles, pedestrians, and obstacles. In the decision-making stage, the collected data is analyzed and evaluated using machine learning techniques. The system generates real-time predictions and risk assessments based on the analyzed data to determine potential collision scenarios and prioritize the most critical situations. This system also has an over-speed detection feature that monitors speed and notifies the driver when the car exceeds a certain speed restriction.
Mitu Sehgal and Sandip Goyal
IEEE
The Intelligent Hybrid Model for energy efficiency on Wireless Body Area Networks (WBANs) has gained substantial attention for its potential to enable remote monitoring and healthcare applications. However, energy efficiency remains a crucial challenge in the design and operation of WBANs due to the constrained resources of wearable devices and the need for continuous operation. In this research paper, we recommend an intelligent hybrid framework for energy efficiency in WBANs. The model combines the benefits of two key techniques: dynamic duty cycling and machine learning-based optimization. By intelligently adapting the duty cycle of individual sensor nodes based on their activity levels and environmental context, the proposed framework may optimize energy consumption while maintaining reliable data transmission. Additionally, machine learning algorithms are used, that can also help in the prediction of sensor node activity patterns and optimize duty cycle settings in real-time. The intelligent hybrid framework may achieve significant energy savings that extend the WBAN devices' lifetime and also enhance their reliability for critical healthcare applications. The proposed model holds the potential to revolutionize the energy efficiency paradigm in WBANs, paving the way for widespread adoption and deployment in various healthcare and remote monitoring scenarios.
Vatan, Sandip Kumar Goyal, and Avinash Sharma
Springer Nature Singapore
Akanksha Bhardwaj, Bhupesh Gupta, Sanjeev Rana, Sandip Kumar Goyal, and Rajneesh Kumar Gujral
IEEE
A Wireless Sensor Network (WSN) contains of bitsy/slashed devices. These devices are known as sensor nodes. Sensor node has storage, sensing and communicating capacity. For energy optimization of sensor network concept of Hierarchical Routing protocol was used. This approach partitioned network into fixed size clusters of sensor nodes. Every cluster consists of cluster head, which is responsible for the transmission of data towards the base station. For improving network lifespan by energy optimization of sensor nodes this research proposes a Back Propagation Sleep Awake clustering (BPSP) protocol. For comparison purpose LEACH protocol is taking into consideration and for simulation based analysis was done with NS2 Simulator. For Simulation, the performance parameters energy consumption, delay, throughput and packet delivery were taken into consideration.
Bhupesh Gupta, Sanjeev Rana, Sandip Kumar Goyal, Rajneesh Kumar Gujral, and Arwa N. Aledaily
IEEE
Wireless Sensor Network's based on Artificial Intelligence (AI) technique is an emerging field in today's environment for researchers. It gives fruitful results in various applications like weather forecasting, medical, forest fire detection etc. This paper presents detection of fire in forests at first level. For detecting probability of fire in forests previously proposed Mutual Exclusive Sleep Awake Distributed Data Aggregation (MESA2DA) protocol and fuzzy logic of Artificial Intelligence are used. Cluster head produced by MESA2DA protocol uses fuzzy logic of AI for detection of fire. Simulation results are obtained by using FIS tool of MATLAB 8.6.
Naveen Malik, Sandip Kumar Goyal, and Vinisha Malik
Springer Nature Singapore
Mitu Sehgal, Sandip Goyal, and Sunil Kumar
IEEE
Awareness of one's own health needs is a quickly spreading revolution in contemporary living. Wireless Body Area Network (WBAN), that uses smart IoT devices for device evaluation, enables affordable healthcare services. WBANs offer a wide range of applications in telemedicine, the military, sports, entertainment, and other areas that call for ongoing Quality of Service (QoS) optimization with relation to dependability, energy use, delay and ease. The communication phase of WBANs presents energy optimization problems for low-powered battery devices. The prediction models for energy consumption were properly designed in conjunction with machine learning (ML) techniques. Improvements in QoS parameters are seen in ML models, along with accuracy, resilience, and precision. Artificial Neural Networks (ANN), Support Vector Regression (SVR), Deep Neural Networks (DNN), K-nearest neighbours (KNN), among other existing ML approaches, are acknowledged as the best method for preserving energy usage and performance. The objective of this paper is to further the understanding of WBAN with ML and its practical application among readers and academics. By methodically examining the results and limitations of previous research, this review paper seeks to provide an overview of the present practical challenges associated with using machine-learning models to improve building energy efficiency.
Santosh Kumar and Sandip Kumar Goyal
IEEE
Anup Lal Yadav and Sandip Kumar Goyal
IEEE
The main causes of accidents are roads that have been broken and weathered, dangerous weather and human errors such as speed, distracted traffic and non-controlled road safety This is irritating to keep the speed balance to prevent accidents and to ensure the driver’s safety. A new approach is therefore proposed to prevent accidents and to save victims during accidents. When the distance between two vehicles is too short, sensors are used to give alarm ‘ON’ If an accident occurs, the camera is switched on automatically and takes the images at about 180%. Including location, this information is transmitted by GSM modem to the nearest police, ambulance and family stations. An Arduino, motion sensor and touch sensors as well as a relay and the GSM modem are the main elements of the project.
Santosh Kumar and Sandip Kumar Goyal
Springer Singapore
Virendra Singh Kushwah, Sandip Kumar Goyal, and Avinash Sharma
Springer Singapore
Load balancing over the cloud environment for computing is not a new problem. However, balancing the loads in proper and efficient way to maximize resource utilization is an issue or a problem. This paper focuses that how to balance the loads and use the resources in maximum utilization using CloudSim tool. The average number of cloudlets and the total cost are the key parameters those are used to interpret and analyze the certain results. While loading the balance, these parameters are distinguished cost and failing ratio of the obtained results. The results are used to take care of enhancing the proper resource utilization using ACO algorithm. An ACO is a better approach to provide the higher great ability in terms of usage of virtual machine, bandwidth, number of clouds, memory, etc. The work can be carried out by the improving designing new modified ACO and minimum execution time.
Anuj Kumar Jain, Sandip Goel, Devendra Prasad, and Avinash Sharma
Springer Singapore
Wireless sensor networks provide a wide array of applications. They have crucial application areas of intrusion detection, fire detection, or several other critical information reporting applications. In such condition, any information delayed is information of no use. Thus, real-time data delivery is essential. An optimal route for fast data delivery and fault-tolerant, error-free operations are keys to such a real-time wireless sensor networks. In this paper, we propose an optimal route selection for error localization in real-time wireless sensor network (ORSEL) scheme. It can guarantee soft reliability in real-time data delivery and provides improved miss ratio of data packets. It considers the fact that there are a number of reasons that increase the end-to-end delay in data delivery in WSN. A packet en-route can be lost due to channel contention, interference, link break, dead nodes in the path, malicious/compromised node/s in path or simply die in a queue of retransmission in a node on the route. ORSEL uses a communication link trust (CLT) value of a link between two nodes which acts as the factor of deciding the minimum end-to-end delay in delivery of packet while avoiding the interference and malfunctioning nodes in the network, if any. As the results received, it is verified that the number of packets successfully delivered to the sink has increased and the miss ratio and cumulative packets consumption have improved.
Android malware have risen exponentially over the past few years, posing several serious threats such as system damage, financial loss, and mobile botnets. Various detection techniques have been proposed in the literature for Android malware detection. Some of the techniques analyze static parameters such as permissions, or intents, whereas, others focus on dynamic parameters such as network traffic or system calls. Static techniques are relatively easier to implement, however, stealthy recent malware evade static detection by virtue of update attacks. Dynamic detection can be used to detect such stealthy malware, however, it increases the computation overhead. Hence, both kinds of techniques have their own advantages and disadvantages. In this paper, we have proposed an innovative hybrid detection model that uses both static and dynamic features for malware analysis and detection. We first rank the static and dynamic parameters according to the information gain and then apply machine learning algorithms in the testing phase. The results indicate that hybrid approach is better than both static and dynamic approaches and the proposed model achieves 98.9% detection accuracy with Decision Tree classifier
Vatan, A. Sharma and S. Goyal
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
A member of the Radio Frequency Identification Development (RFID) Association originated the idea of IoT in 1999. Currently it become more applicable to the practical universe due to the growth of mobile appliances, installed and global information, cloud computing and analysis of data. At present IoT acquired a large observation from researchers because it beseems a significant machinery which assurance smart human life by recognizing communication theory between articles, gadgets and every belonging of human beings. Presume wherever millions of objects can feel, convey and share knowledge, all inter-related through either public or private Internet Protocol networks. These inter-connected objects have constantly composed the data, evaluate and used to commence act, supplying abundance of knowledge for designing, control and judgement making. This is exactly the world of IoT (Internet of Things). IoT describes a manner that comprise things of the actual world and detectors connected to these things, attached to the internet by guided and unguided network design. The IoT detectors can employ various types of attachments such as RFID, Wireless-Fidelity, Bluetooth and ZigBee. Additionally IoT approves broad domain connectivity by adopting many automations e.g. Global System Mobile communication, General Packet Radio Services, 4G and Long Term Evolution. IoT empowered objects will share knowledge of the provision of things, the nearby atmosphere with people, operating systems and other appliances of IoT related with technology. Since the Internet of Things will produce a medium of smart city, healthcare, connected houses and architecture in extension to several significant applicabilities such as smart power, networks, conveyance, garbage control so that the universe will become smart in every aspects.
Anuj Kumar Jain, Sandip Goel, Devendra Prasad, and Avinash Sharma
American Scientific Publishers
Sensing the natural phenomenon, sensing the eventual activities, sensing the abrupt change in human developed systems has a wide number of applications. To sense, one needs the tiny sensor devices called sensor nodes. To collect the data from these devices, one has to arrange these tiny devices into a intelligently managed network, called as sensor networks. Due to mostly unattended application areas and zones, these devices are supposed to be wireless which adds one more dimension to our discussion, known as wireless sensor networks. So basically these are an intelligent arrangement of small, tiny sensing devices with wide array of attributes, namely, sensing ability, low communication range mechanism, limited power sources, small processing ability, small memory. With these limitations, even handling a small data generated/sensed in the network becomes crucial to handle. Therefore there has to be an effective data aggregation technique. The prime goal of any data aggregation algorithms is to collect/retrieve/gather the data in an efficient possible way so that the effort to communicate the data over the network can be reduced. Less work from the network means less energy dissipated, thus lifetime can be enhanced. An effective data aggregation technique reduces the latency also. Small network latency is crucial for time critical applications in real time wireless sensor networks. Ant colony based optimization provides us such a possibility to find an optimal route for efficient data aggregation with significantly reduced network latency. In our work, Ant colony based Data Aggregation in Real Time wireless sensor networks (ACDAR), Ants use their pheromones to establish a new path or follow already established path by other ants. Similarly data packets in wireless sensor networks can take advantage of freshly established paths by Route Ants. As the results received, it is verified that number of packets successfully delivered to the sink have increased and the miss ratio, cumulative packets consumption have improved, network latency has decreased.
Pooja Mangla and Sandip Kr. Goyal
American Scientific Publishers
Today one of the new and emerging technologies is Cloud Computing, which denotes to operating, organizing, and retrieving the services over the internet. It is the pre-requisite of IT services on the Internet. In this, Load balancing is the issue region of Cloud Computing, which has a noteworthy effect for characterizing the resource accessibility. In this, Meta-heuristic techniques are applied on Load Balancing in Cloud Computing and their results are shown.
Sharma Sachin, Sandip Kumar Goyal, Sharma Avinash, and Kumar Kamal
Springer Singapore
Data transformation from text files to database files, relational database management systems, and distributed database management systems in recent past has emerged a vast field of data warehouse. Currently data analytics is the most appealing field for the data scientists and challenges are very big as data volume is very huge. Not only data volume is high but the speed at which data is growing annually is exponentially. Data analytics has become a tool to grow the business by forecasting, business intelligence and decision support systems. In a simplified way, data is organized in the form of database, collective databases makes the data warehouse and the technologies like business intelligence, decision support system, and data analytics make use of data warehouse for their purpose. Big data is the enhanced form of the data warehouse which consists of the cloud storage and MapReduce-based architecture which consists of the clustering of data. This survey paper will give a high-level understanding of the existing data warehouse processing mechanisms including conventional processing and the distributed processing. Existing Extraction Transformation and Loading process will be analyzed for better understanding of the sub processes of the data warehouse building process.
Virendra Singh Kushwah, Sandip Kumar Goyal, and Avinash Sharma
Springer Singapore
This paper focuses on a study on meta-heuristic techniques for fault tolerance under cloud computing environment. Cloud computing introduces the support to increasing complex applications, the need to check and endorse handling models under blame imperatives which turns out to be more vital, meaning to guarantee applications execution. Meta-heuristics are problem-independent techniques and workload planning is known to be a NP-Complete problem, therefore meta-heuristics have been used to solve such problems. The idea behind using meta-heuristics is to increase the performance and decrease the computational time to get the job done and in our case, meta-heuristics are to be considered the robust solution of finding the right combinations of resources and tasks to minimize the computational expenses, cut costs and provide better services for users. Fault tolerance plays an important key role in ensuring high serviceability and unwavering quality in cloud. In these days, the requests for high adaptation to noncritical failure, high serviceability, and high unwavering quality are turning out to be exceptionally solid, assembling a high adaptation to internal failure, high serviceability and high dependability cloud is a basic, challenging, and urgently required task.
Naveen Malik, Vinisha Malik, and Sandip Kumar Goel
IEEE
Semantic Web based Applications have become very applauded these days due to their huge employment in social networks, e-learning, multimedia processing and health care industry besides their engagement in information retrieval. Semantic Web based Applications are accented by machine comprehensibility of the content, sharing and reuse among heterogeneous applications, modular structure of its domain vocabulary, and their availability as a service. Their welfares and vast usage implies us to assess quality with consideration to divergent aspects such as ontology and few other quality attributes. This paper ventures a rigorous verdict of the state-of-art in this direction. Quality assessment of Semantic Web based Applications has been probed with focus on the process, contributions and limitations of each work besides research gaps in the direction.