Papers by Dr. Mukul Aggarwal
Expert System on Diagnosis of Mental Diseases
Journal of Soft Computing Exploration, Jan 27, 2023
Comparative Analysis of Deep Learning Models on Brain Tumor Segmentation Datasets: BraTS 2015-2020 Datasets
Revue d'intelligence artificielle, Dec 31, 2022
Proposed Web Application for Guidance and Support of Students: SmartLAD
International Journal of Computer and Communication Technology
SmartLAD is a Support Platform that connects students, mentors, and professionals of the field an... more SmartLAD is a Support Platform that connects students, mentors, and professionals of the field and enables them to share their knowledge and experience. We equip the students with a powerful network to rely on, skill-oriented courses that impart real-life skills, and experienced mentors to guide them. Our platform helps students to stay focused on their goals and keep on working hard to achieve their dreams. SmartLAD works as a Support Platform that helps students in their journey of being successful and excelling in their careers by providing them with skills, resources, guidance, and network. We help the students by providing them with a Network that the students can use without any charges and limits and can connect to people and share knowledge.
A Chatbot Application by using Natural Language Processing and Artificial Intelligence Markup Language
International Journal of Soft Computing and Engineering
A program which helps in making conversation with the help of textual methods is referred to as c... more A program which helps in making conversation with the help of textual methods is referred to as chatbot. Chatbot helps in responding to a message quickly and that too without human intervention. Startups are inventing thousands of chatbots in order to provide a better service and keep their customers busy by a kind and simple conversation. It also helps in providing far better services to customers and helps in buying products. It takes an input from the user in the form of keywords, and it matches those keywords in its data-set to give out the corresponding output saved in it. It gives all the possible answers related to user queries. Since, most of the times like during pandemic, we cannot go outside and cannot meet people, it is an interactive way to get to know about how world is dealing with it. Chatbots exploits AI and ML platforms. Chatbots are becoming popular day by day in this modern era, they are being used in business groups and helps in reducing costs and can help in pr...
Usability of KSOM and classical set in information retrieval
2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), 2016
The Kohonen self-organizing feature map (KSOFM) also known the Kohonen self-organizing map (KSOM)... more The Kohonen self-organizing feature map (KSOFM) also known the Kohonen self-organizing map (KSOM) under comes the artificial neural network. An important characteristic of ANN is ability to learn. Learning is a process by adjusting the weight with respect to input features so that the actual output response will matches to the desired output. The role of learning based network is that the point distributes themselves across the input space to selected or mapped group of similar input vectors, while the output nodes compete among themselves. Once network trained, the network produces a low dimensional data clustering of the input value that preserves the ordering of the actual structure. Thus nodes can be recognizing groups of similar input vectors. It generates a mapping of the input vector to the output layer, which depends on input vectors and overall result in dimensionality reduction of the input space. Follows the “winner-take-all” policy means which cluster unit weight matches...
Comparison of COSYSMO Model with Different Software Cost Estimation Techniques
2019 International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), 2019
Cost Estimation of any software is process of evaluating the estimating cost and effort which is ... more Cost Estimation of any software is process of evaluating the estimating cost and effort which is must necessary to build any software system or project for increasing the output. The basic input is the cost drivers set and the size of code and the output is the effort which is calculated in terms of Person-Months (PM’s). To estimate cost for software is the main portions of any project type and right estimation of cost for the software will help in completing project in of time and budget. Proper cost estimation of a software project is highly needed to avoid any risk failure. So, there is a strong need to calculate the project’s cost annually and compare it to the other techniques. This paper deals with the analysis and comparison of COCOMO model of Boehm’s and COSYSMO model of Valerdi’s through the help of formulae’s and an online tool present at the CSSE website. For this we have used the COCOMO dataset and it has been observed that COSYSMO model works better than the COCOMO model in every aspect.
Information Retrieval and Question Answering NLP Approach: An Artificial Intelligence Application
Natural Language Processing (NLP) is a major area of artificial intelligence research, which in i... more Natural Language Processing (NLP) is a major area of artificial intelligence research, which in its turn serves as a field of application and interaction of a number of other traditional AI areas. Until recently, the focus in AI applications in NLP was on knowledge representation, logical reasoning, and constraint satisfaction—first applied to semantics and later to the grammar. In the last decade, a dramatic shift in the NLP research has led to the prevalence of very large-scale applications of statistical methods, such as machine learning and data mining. Naturally, this also opened the way to the learning and optimization methods that constitute the core of modern AI, most notably genetic algorithms and neural networks. In this talk I will give an overview of the current trends in NLP and discuss the possible applications of traditional AI techniques and their combination in this fascinating area. Question- Answering(QA)aims at delivering concise information that contains answers...
Approach for Information Retrieval by Using Self-Organizing Map and Crisp Set
Advances in Intelligent Systems and Computing, 2017
Nowadays, mostly users want to search anything they have done by Web search. For finding the conc... more Nowadays, mostly users want to search anything they have done by Web search. For finding the concerned information with the reduced retrieval time they go through the search engine. Finding the relevant information with the help of mapped area affects the supervised and unsupervised learning method and works on the designing part of the information retrieval by using SOM and crisp set (CrispSOM), as well as reduces the retrieval time and collects the scattered information using self-organizing map and crisp set. The innovative idea of this paper is to evaluate the application of self-organizing maps (SOM) with the help of crisp value for finding the relevant information in lesser time as compared to other information retrieval system (IRS).
Sentiment Analysis and Feature Extraction Using Rule-Based Model (RBM)
International Conference on Innovative Computing and Communications, 2018
In the current era, each and every individual get benefited with available information on Interne... more In the current era, each and every individual get benefited with available information on Internet that is used in decision-making by perceiving others’ attitude, opinions, sentiments, and emotions. As we know sentiment analysis is one of the fields of natural language processing (NLP) that evaluates opinion of users and their sentiments, based on these sentiments and opinions, an individual or group can review their product and services. In this paper, we compared our rule-based model (RBM) sentiment lexicon features precision, recall, and F1 score to other known and established sentiment lexicons on Cornell movie review dataset and found the result is better and more accurate.
Squaring Back off Based Media Access Control for Vehicular Ad-hoc Networks
Advances in Intelligent Systems and Computing, 2014
Inter-vehicle communications have great potential to induce great interest in research and indust... more Inter-vehicle communications have great potential to induce great interest in research and industry. Vehicular ad hoc networks (VANETs) may significantly improve passenger safety and comfort. The deployment of VANETs is a challenging task in weakly interconnected and in highly overloaded networks both. A good back off technique can reduce a large number of collisions in the MAC layer I VANET. This will reduce the collision probability and hence increases the utilization of network resources. A uniform random distribution has been employed to choose the back off value in the Binary Exponential Back off (BEB) technique used in the IEEE 802.11 MAC protocol. This random choosing VANETs leads to unnecessary idle times and reduced throughput. This paper proposes a new back off technique called “Squaring Back off (SB)” in which the differences between the consecutive contention window sizes are reduced to a negligible value. Here, the value of the back off timer is based on the size of the contention window. The size of the contention window is varied in accordance with the result of the previous transmission. A successful transmission reduces the size of the contention window whereas a failure leads to the increase in the contention window size. Simulation results indicate that the proposed technique provides better throughputs and less idle times than the logarithmic and Fibonacci based techniques when used in a mobile ad-hoc environment. Squaring back off based media access control can prove very useful for vehicular ad-hoc networks.
BMC Medical Informatics and Decision Making
Background Magnetic resonance image (MRI) brain tumor segmentation is crucial and important in th... more Background Magnetic resonance image (MRI) brain tumor segmentation is crucial and important in the medical field, which can help in diagnosis and prognosis, overall growth predictions, Tumor density measures, and care plans needed for patients. The difficulty in segmenting brain Tumors is primarily because of the wide range of structures, shapes, frequency, position, and visual appeal of Tumors, like intensity, contrast, and visual variation. With recent advancements in Deep Neural Networks (DNN) for image classification tasks, intelligent medical image segmentation is an exciting direction for Brain Tumor research. DNN requires a lot of time & processing capabilities to train because of only some gradient diffusion difficulty and its complication. Methods To overcome the gradient issue of DNN, this research work provides an efficient method for brain Tumor segmentation based on the Improved Residual Network (ResNet). Existing ResNet can be improved by maintaining the details of all...
Journal of Soft Computing Exploration
The expert system solves problems within a specific area of the knowledge base. Prolog is a logic... more The expert system solves problems within a specific area of the knowledge base. Prolog is a logical programming language which works on its knowledge base and effectively can be used to develop an expert system. Covid 19 is a pandemic deices and an expert system can be developed to diagnose this disease with the help of its symptoms that can be used as a knowledge base in Prolog. This expert system can make a fast diagnosis process for the covid 19 which is important to prevent the spread of the virus. Here we developed an expert system using prolog for diagnosis purposes. Like humans, these systems can get better with time as they gain more experience. Expert systems combine their experiences and expertise into a knowledge base that is then used by an inference or rules engine, a set of rules that the software employs, to apply to certain scenarios. Prolog is ideal for use with intelligent systems for a few reasons. Prolog can be viewed as a straightforward theorem prover or infere...
The expert system solves problems within a specific area of the knowledge base. Prolog is a logic... more The expert system solves problems within a specific area of the knowledge base. Prolog is a logical programming language which works on its knowledge base and effectively can be used to develop an expert system. Covid 19 is a pandemic deices and an expert system can be developed to diagnose this disease with the help of its symptoms that can be used as a knowledge base in Prolog. This expert system can make a fast diagnosis process for the covid 19 which is important to prevent the spread of the virus. Here we developed an expert system using prolog for the diagnosis purpose. Similar to humans, these systems can get better with time as they gain more experience. Expert systems combine their experiences and expertise into a knowledge base that is then used by an inference or rules engine, a set of rules that the software employs, to apply to certain scenarios. Prolog is ideal for use with intelligent systems for a number of reasons. Prolog can be viewed as a straightforward theorem p...
Intelligent search agent is popularly used for searching relative information in the Internet and... more Intelligent search agent is popularly used for searching relative information in the Internet and there are a lot of tools that are used to satisfy the needs of the users. These intelligent agents are independent to each other and there is insufficient cooperation to make an efficient search of information in the distributed environment. Therefore, a typical search agent is difficult to use in the distributed environment and can contain irrelevant information for the users. In this paper, we report on our work on developing distributed collections of intelligent software agents that cooperate asynchronously to perform goal-directed information retrieval and information integration in support of performing a variety of decision making tasks.
TELKOMNIKA (Telecommunication Computing Electronics and Control)
An Aadhaar is a unique number issued to every citizen in India. Aadhar's current identity authent... more An Aadhaar is a unique number issued to every citizen in India. Aadhar's current identity authentication relies on the central identities data repository (CDIR) of the unique identification authority of India (UIDAI), which is at risk of a single-point fault attack. Perhaps worse, internal attacks can tamper with the sensitive data of authenticated devices without being detected. In this paper, the proposed system utilizes emerging technology: blockchain for solving the issue of centralized authentication. The proposed system provides a distributed, secure, and tamper-proof ledger platform for Aadhar in that Aadhar is implemented using blockchain ethereum technology. The proposed system considers the unique Aadhar identification (ID) for each citizen of India and registered it on the smart contract of ethereum so that this unique ID may be authenticated by each other in a peer-to-peer network without a central authority. For securing the data, the proposed framework uses hashing technique for significant data (i.e. firmware). Blockchain stores hashed data and instantly any change in the state of the data may be possible to detect.
Traffic Detection System is an Android application that aims at determining the behavior of traff... more Traffic Detection System is an Android application that aims at determining the behavior of traffic in a particular location. It calculates the speed of the vehicle and the level of congestion or the amount of traffic is determined on the basis of the values of sensors. If any such obstruct found, then the driver is provided an option to send messages regarding high traffic to his/her friends. After a distinct number of repeated low speed and breaks, the location of the vehicle (latitude and longitude) send to a pre-specified contact (selected in case of traffic congestion) through an SMS. This application uses the features of the Global positioning system. The Latitude, as well as the longitude of the location where traffic jams are formed, is sent to the friends of the user. The Goggle map of the location also sends to the friends. It uses the SMS Manager a functionality of Android. The friends receiving the messages will thereby avoid taking the congested route and hence the level of traffic on the congested road will decrease, and the friends will reach the destination in comparatively less time.
Inter-vehicle communications have great potential to induce great interest in research and indust... more Inter-vehicle communications have great potential to induce great interest in research and industry. Vehicular ad hoc networks (VANETs) may significantly improve passenger safety and comfort. The deployment of VANETs is a challenging task in weakly interconnected and in highly overloaded networks both. A good back off technique can reduce a large number of collisions in the MAC layer I VANET. This will reduce the collision probability and hence increases the utilization of network resources. A uniform random distribution has been employed to choose the back off value in the Binary Exponential Back off (BEB) technique used in the IEEE 802.11 MAC protocol. This random choosing VANETs leads to unnecessary idle times and reduced throughput. This paper proposes a new back off technique called ''Squaring Back off (SB)'' in which the differences between the consecutive contention window sizes are reduced to a negligible value. Here, the value of the back off timer is based on the size of the contention window. The size of the contention window is varied in accordance with the result of the previous transmission. A successful transmission reduces the size of the contention window whereas a failure leads to the increase in the contention window size. Simulation results indicate that the proposed technique provides better throughputs and less idle times than the logarithmic and Fibonacci based techniques when used in a mobile ad-hoc environment. Squaring back off based media access control can prove very useful for vehicular ad-hoc networks.
Uploads
Papers by Dr. Mukul Aggarwal