Fleet optimization for time and cost factors in residential building
Construction sectors are one of the widest sectors in the world. In which there is tremendous growth in terms of profit and development. it increases in terms of new inventions, new designs, new equipment, and a new concept in a wide manner. In that road transportation or road construction has a huge scope of work and chances of development of roads to connect cities and villages to each other. Basically roads of the particular area define their development of the area in terms of success, quality area of living, workplaces respectively. road construction is mainly considered as important work for connecting states, cities, and villages for transportation of goods and other things. In the construction sectors, mainly in road constructions, fleet management is one of the most important factors that define total cycle time, total cost, cost index, and total time required for completing the activity and related parameters. Fleet management can be defined by equipment assignment and optimization. Equipment assignment and optimization is the main reason many construction companies choose to implement fleet management systems in the first place. By enabling the scheduling and assignment of all types of equipment from multiple manufacturers as well as shift change management from a central office location, fleet management helps minimize unproductive machine wait time and optimize equipment usage on site.
Published by: Pravin Sable, S. M. Waysal
Author: Pravin Sable
Paper ID: V6I4-1351
Paper Status: published
Published: August 8, 2020
Software Defect Prediction by optimizing features weight with a CNN
Machine Learning approaches are helpful & have well-tried to be helpful in resolution issues & technical problems that lack data. In most cases, the package domain issues may be characterized as a method of learning that depends on the assorted circumstances and changes of the technical issue being addressed in keeping with the principles of machine learning, a prophetic model is made by exploitation machine learning approaches and classified into defective and non-defective modules. Machine learning techniques facilitate developers to retrieve helpful data when the classification of kinds of technical problems being addressed in an exceedingly specific field. This successively permits them to analyze knowledge from totally different views, which may be used because of the formation base of constructive concepts & varied techniques to handle the technical problems. Machine learning techniques are well-tried to be helpful within the detection of package bugs. during this analysis prediction by Convolution based mostly feature choice and Learning by Random forest. In the proposed approach, the accuracy and precision always improve and it also improves class wise. There is a significant enhancement in defective and non-defective class prediction as the random forest non-linearity features help to improve the selection of effective parameters by bagging approach. In the proposed approach, hybridization of three approaches such as deep learning, machine learning and sampling approach is done which significantly improve overlapping of features and imbalance of class like KC2 dataset.
Published by: Asheesh Raju, Anuj Gupta
Author: Asheesh Raju
Paper ID: V6I4-1353
Paper Status: published
Published: August 7, 2020
Voice over IP mobile telephony using Wi-Fi
Today, we are on the verge of wireless networking where everyone wants to be online without a bunch of cables. Colleges, B-Schools, corporate offices, and cafeterias provide Wi-Fi internet connectivity. The aim of this project is to make use of available resources to provide a free voice calls facility, without using a service provider. Pre-established Wireless Fidelity (i.e. Wi-Fi) service more often uses WLAN, which is offered as a voice transmission medium by Wi-Fi. Smartphones allowed by Wi-Fi can be connected to the router and can communicate with one another. This system will be the perfect alternative to the present intercom device.
Published by: Bharath M. S., Dr. Padmashree T.
Author: Bharath M. S.
Paper ID: V6I4-1335
Paper Status: published
Published: August 6, 2020
Vehicle detection based on deep learning
Vehicle detection is a challenging problem in autonomous driving systems, due to its large structural and appearance variations. In recent years convolutional neural networks (CNN) have achieved great success. Presently the state-of-art R-CNN and YOLO architectures are explored, implemented, and adopted for performance comparison on real-time data. From the experimental results, the R-CNN has faster detecting speed and accuracy in complex scenes. However, the transfer learning-based CNN model can be further analyzed and validated over other datasets and can be carried out. In comparison to the state-of-art, the proposed transfer learning approach may accurately regress the vehicle shape and classify vehicle fine-grained categories. Presently, the performances are validated over the UA-DETRAC datasets. The obtained performance strongly suggests the RCNN and has better classification accuracy. The proposed transfer learning approach can be a better alternative competing to the state-of-art approaches.
Published by: Debasmita Mishra, Rashmita Routray
Author: Debasmita Mishra
Paper ID: V6I4-1329
Paper Status: published
Published: August 6, 2020
Implementation of CAN BUs in designing of smart vehicle control system using ARM7 Microprocessor
The reliable and high speed data communication between the sensing devices and actuating devices through a controller is the real time requirement in an automobile. The higher the speed lessens response time in critical situation. The parameter such as ABS, airbags, engine temperature need on time response. Otherwise the whole system may met with severe collapse or some time may threaten life also. To make all the factor be in a system that performs better, the communication between the controller with sensing and actuating devices should be with in a frame of high speed communication. The CAN bus is highly reliable and provides high speed communication between control input and resultant output. The earlier generation of CAN is a point to point communication that was using more number of wire. As a result, wired load lags the system speed. This is a major issue when threat is so critical. To overcome all these drawbacks CAN was introduced that reduces the load on system. CAN offers higher flexibility and expandability. The integration of CAN bus with automobile industry is new perception that created a proper link in controlling devices. The factors such as headlight, engine, wiper, door lock, car speed and location tracking are analyzed and taken a valid action against them. The director of the project is Advanced RISC Machine (ARM) 7 LPC2129 microprocessor. In CAN bus the communication arisen with the help of CAN Transceiver. The CAN transceiver is responsible for the CAN communication. The MASTER and SLAVE is controlled by CAN controller. The CAN communication enhances the flexibility, performance and security of the system.
Published by: Kishora Achary, Lavanya B. L.
Author: Kishora Achary
Paper ID: V6I4-1320
Paper Status: published
Published: August 6, 2020
School van safety and surveillance system
Now a day’s school van accidents are increasing day by day. This is mainly due to the negligence of van drivers. The major causes of accidents are due to alcohol consumption by the driver, over-speed, etc. It's always a headache for the parents to think about the safer journey of their children. It would be very convenient if there is a system to decrease these types of accidents. This Project is a new idea to implement the different kinds of safety features in the vehicle. If the driver consumed alcohol then the alcohol sensor senses the consumption of alcohol and stops the ignition of the vehicle at that instant. It also sends a message to all the parents and the police station nearby with the exact location using a GPS sensor used in our project. If the speed of the vehicle crosses the specified limit system, first it gives an alarm to the driver to let him know that he is over speeding and if still, he continues, it sends alerting message to the parents and concerned authorities. In case of any accident takes place, that also will be notified to nearby police stations and parents of all the students inside the bus. This system sends the information to the parents about the arrival of the bus prior to one-stop, also parents can access the information about the current location of the bus anytime. The phenomenon of forgetting kids on the bus is one of the problems suffered by the children. This project, through the entry and exit recordings, aims to create a suitable environment by following a certain set of criteria of security and safety for school buses that will have a positive impact on the student and their family. When a complete prototype of the proposed system is implemented, the system will promise safer transportation of school children.
Published by: Abilash R., Anantha Sanker R., Kishan Kumar R.
Author: Abilash R.
Paper ID: V6I4-1311
Paper Status: published
Published: August 6, 2020
