Manuscripts

Recent Papers

Research Paper

Video Shot Segmentation: Hybrid Approach using YOLOv4 and Deep Sort Algorithm

A shot is a sequence frame in an edited video taken by a single camera. Shot Segmentation is the process of splitting video and finding the boundaries of video data. In this paper, we study the method in content-based video retrieval which uses object detection and tracking for video segmentation. Data collected via segmenting can be categorized in a hierarchy manner as scene layer, camera shot layer, and the frame in their accordance. The data collected is used for segmentation. YOLOv4 is used to enhance the accuracy and the process of tracking and detection much faster.

Published by: Shakthi T.

Author: Shakthi T.

Paper ID: V7I5-1381

Paper Status: published

Published: October 29, 2021

Full Details
Research Paper

Car logo detection and classification by Deep Learning base Transfer Learning

Vehicle identification systems rely on logo recognition to identify vehicles (VLRS). Convolutional Neural Networks are used to automatically learn characteristics for car logo recognition (CNNs). However, CNN struggles with rotated or noisy pictures. CNN's Random Forest classification technique is used to create an image recognition system. Random forest decision tree ensemble and train. This work's primary contribution is a multiclass logo using convolution mapping in nonlinear space and random forest ensemble learning. In the experiment, 400 pictures with 10 classes were analyzed to increase accuracy by about 20%.

Published by: Sushil Kumar, Ms. Bhuvneshwari

Author: Sushil Kumar

Paper ID: V7I5-1392

Paper Status: published

Published: October 28, 2021

Full Details
Research Paper

An overview on application areas of soft computing

We know that Soft Computing refers to the science of reasoning, thinking, and deduction that recognizes and uses the real-world phenomena of grouping, memberships, and classification of various quantities under study. As such, it is an extension of natural heuristics and capable of dealing with complex systems because it does not require strict mathematical definitions and distinctions for the system components. It differs from hard computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty, and partial truth. In effect, the role model for soft computing is the human mind. The guiding principle of soft computing is: Exploit the tolerance for imprecision, uncertainty, and partial truth to achieve tractability, robustness, and low solution cost. The applications of soft computing have proved two main advantages. First, it made solving nonlinear problems, in which mathematical models are not available, possible. Second, it introduced human knowledge such as cognition, recognition, understanding, learning, and others into the fields of computing. This resulted in the possibility of constructing intelligent systems such as autonomous self-tuning systems, and automated designed systems. This paper highlights various Application areas of soft computing.

Published by: Dr. Shailendra Kumar Srivastava

Author: Dr. Shailendra Kumar Srivastava

Paper ID: V7I5-1393

Paper Status: published

Published: October 28, 2021

Full Details
Survey Report

Use and effectiveness of online learning with animated contents amid COVID-19

COVID-19's impact may be seen across the world, and it affects all sectors equally. The education sector worldwide is also suffering, which is impeding the educational process. Total lockdown, which was imposed in 42 countries, harmed students' lives. The pause in the educational process has impacted around 1.277 billion pupils around the world. While change is unavoidable, COVID-19 has proved that growth is optional. This situation has compelled every educational institution to invest in ICT (Information and Communication Technology) to experiment with new ideas, such as animated teaching and multimedia in online classes. This article focuses on how online learning can be made effective during times of crisis by utilizing multimedia tools and animation. As a result, various online learning multimedia technologies and strategies that can assure learning continuity are emphasized.

Published by: Aravind N., Dr. S. Jenefa

Author: Aravind N.

Paper ID: V7I5-1380

Paper Status: published

Published: October 28, 2021

Full Details
Research Paper

Adsorption behavior of Cu, Co, Mn, Pb, Mg, Ca, Ba, Zn, Cd, Al, and Th metal Ions on cation exchange resign Dowex 50WX8 (NH4+ Form) From Aqueous Acetone – Ammonium Butyrate media

In the field of inorganic separation, the incentive to explore the use of non-aqueous or mixed solvent has been enhanced selectivity’s, discovered quite early in such media for Zeolites [1] and ion exchange resins [2]. The partial substitution of an aqueous solution by organic solvent produces a number of changes in an exchange system. Such as a change in the solution structure due to the interaction between water and the organic solvent, change in the hydration and salvation of the electrolyte, change in the solvent composition in the resin phase, change in the activity coefficients of the electrolyte in the solution phase as well as in the resin phase, change in the complexation of the metal ion and change in the extent of invasion by an electrolyte. All these changes are mutually dependent and affect the distribution of the metal ion. The solution composition in the resin phase often differs very much from that in the outer solution and the difference becomes greater with less polar organic solvents. Such behavior the selective swelling is mainly attributed to the hydration and salvation proportion of the functional resin group, namely the fixed ion and counterion. The difference in the composition of the resultant solution in the two phases enhances the invasion of electrolyte so that it is larger than in the pure aqueous solution. The electrolyte plays a significant role in the ion exchange equilibrium with aqueous solutions. This effect is expected to be even more important in the adsorption equilibriums of metal ions from mixed aqueous organic solvents. Adsorption equilibrium depends on the properties of the organic solvent reactions with resin and electrolytes which determine the equilibrium.

Published by: Dr. Rajan S Kamble

Author: Dr. Rajan S Kamble

Paper ID: V7I5-1375

Paper Status: published

Published: October 28, 2021

Full Details
Research Paper

Car logo detection and classification approaches: A review

Vehicle identification systems rely on logo recognition to identify vehicles (VLRS). Convolutional Neural Networks are used to automatically learn characteristics for car logo recognition (CNNs). However, CNN struggles with rotated or noisy pictures. CNN's Random Forest classification technique is used to create an image recognition system. Random forest decision tree ensemble and train. AI has overcome object recognition problems. Convolutional Neural Networks (CNNs) is a popular type utilized to address object recognition issues due to their complicated structure and hidden layers. Logo recognition is often solved using CNN-derived techniques. The creators of used pre-trained CNNs to recognize logos. These technologies are also computationally expensive. This limits the use of computationally expensive alternatives. A logo's recognition accuracy with little computing burden remains a mystery.

Published by: Sushil Kumar, Ms. Bhuvneshwari

Author: Sushil Kumar

Paper ID: V7I5-1391

Paper Status: published

Published: October 28, 2021

Full Details