-22b9b34417bc6092a74-7582 20210917082729295 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Recent Technology and Engineering (IJRTE) IJRTE 22773878 10.35940/ijrte.2277-3878 https://www.ijrte.org/ 09 30 2021 10 3 10.35940/ijrte.10.3 https://www.ijrte.org/download/volume-10-issue-3/ Gauhati University Institute of Science and Technology, Gauhati University, Guwahati, (Assam), India. Dr. Hirakjyoti Sarma Dimpal Huzuri Department of Information Technology, Gauhati University, Guwahati, (Assam), India. Dr. Manoj Kumar Deka Department of Computer Science and Technology, Bodoland University, Kokrajhar, (Assam), India. This paper approaches an IoT based vehicle health monitoring system that is embedded for detecting the condition of a vehicle by monitoring the internal parameters such as heating rate, engine oil level and status of the CO of the vehicle. It is a real time vehicle health monitoring system is designed and developed to detect and identify the actuator and sensor faults created by automatically or manually by the user of the vehicle. Actually, Vehicles need repair after a certain interval of time and if are not repaired at fixed intervals, it can lead to loss of life of the persons travelling on it and there are many key issues which can affect the vehicle. So, the primary objective of this system is developing an IoT based embedded system that can detect the internal condition of a vehicle by evaluating the various parameters that are used to examine in the vehicle’s current health condition. In fact, this is a real time evaluation system that can be used for rapid condition screening. As a result, it provides all reliable information about the vehicle conditions. This IoT based system claims that it can detect and identify actuator and sensor faults with almost minimal detection latency even after lots of disturbances and uncertainties. 09 30 2021 140 143 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6338.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C63380910321.pdf Department of Computer Science, Vellore Institute of Technology, Vellore, Tamil Nadu, India. Kota Akshith Reddy Satish C J Department of Computer Science, Anna University, Tamil Nadu, India. Jahnavi Polsani Department of Computer Science, Vellore Institute of Technology, Vellore, Tamil Nadu, India. Teja Naveen Chintapalli Department of Computer Science, Vellore Institute of Technology, Vellore, Tamil Nadu, India. Gangapatnam Sai Ananya Department of Computer Science, Narayana Engineering College, Tamil Nadu, India. Automatic Image Caption Generation is one of the core problems in the field of Deep Learning. Data Augmentation is a technique which helps in increasing the amount of data at hand and this is done by augmenting the training data using various techniques like flipping, rotating, Zooming, Brightening, etc. In this work, we create an Image Captioning model and check its robustness on all the major types of Image Augmentation techniques. The results show the fuzziness of the model while working with the same image but a different augmentation technique and because of this, a different caption is produced every time a different data augmentation technique is employed. We also show the change in the performance of the model after applying these augmentation techniques. Flickr8k dataset is used for this study along with BLEU score as the evaluation metric for the image captioning model. 09 30 2021 131 139 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6439.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64390910321.pdf Department of Electrical and Electronics Engineering, Joseph Sarwuan Tarka University, Makurdi, Nigeria. J.M. Mom S.S. Tyokighir Department of Electrical and Electronics Engineering, Joseph Sarwuan Tarka University, Makurdi, Nigeria. G.A. Igwue Department of Electrical and Electronics Engineering, Joseph Sarwuan Tarka University, Makurdi, Nigeria. Performance evaluation of the ITU-R. P.530-17, Ghiani and Budalal model are considered for this work. It is found that the predicted values from the ITU-R and Ghiani distance factor models are seen to gradually decrease with an increase in path length for distances below 1km. Results further suggest that for a link length of 300 m, the Ghiani model predicts a 0.2499 dB (1.059 w) to 0.3273 dB (1.078 w) precipitation loss across all four (4) stations. For the ITU-R. P.530-17 model, a 3.4741 dB (2.225 w) to 5.329 dB (3.411 w) precipitation loss is estimated across all stations while the Budalal model estimated a 2.8608 dB (1.932 w) to 4.6250 dB (2.901 w) precipitation loss across all stations. The ITU-R. P.530-17, Ghiani and Budalal model further suggest a precipitation loss in the Received Signal Strength (RSS) of a typical 5G base station operating in the four (4) stations considered to be at least -9.4733 dBm, -8.8601 dBm, and -6.2489 dBm respectively. Generally, all models are found to predict rain attenuation and distance factor values with disparities especially for link lengths above 300 m. Further research is recommended on the models for accurate prediction and improve agreement with measured values. 09 30 2021 111 116 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6441.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64410910321.pdf Member of Training Staff, Higher Institute of Energy PAAET, Kuwait. Muhammad R A A Jamal Khaled S Al Rasheed Senior Specialized Engineer, Department of Electrical and Electronics Engineering, Public Authority for Applied Education and Training-Higher Institute of Energy, Kuwait. Measuring Vibration parameter for rotating machinery is essential for monitoring and diagnosis system in industrial plants. This paper demonstrates another approach to vibration measurement for rotating machine using electrostatic sensor and signal processing techniques. A single electrostatic sensor is used to detect charges surrounding the moving shaft of the machine. The signal from the electrostatic sensor is processed in MATLAB using Autocorrelation, Fast-Fourier, and Root Mean Square. The implementation of this technical approach was conducted on a modified test rig using three different shafts. The three shafts represent three different vibration modes: normal, abnormal, and severe. Each shaft was experimented under low and high rotation speed to observe amplitude and frequency level. Although the results of the tests did not show a direct measure of vibration displacement, due to the complex nature of the induced charges by the surface pattern. However, the results showed an indicative level of vibration at different amplitudes for the three shafts. 09 30 2021 97 105 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6442.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64420910321.pdf Faculty of Engineering, Miyazaki University, Miyazaki, Japan. Kodai Miyamoto Taketo Kamasaka Faculty of Engineering, Miyazaki University, Miyazaki, Japan. Makoto Sakamoto Faculty of Engineering, Miyazaki University, Miyazaki, Japan. As a result of conducting a questionnaire about science classes to high school students in 2016, the percentage of high school students who answered "I like science" and "Science is important" is lower than other subjects. However, more than 80% of elementary and junior high school students said they like experiments and observations. In addition, the 2019 smartphone penetration rate survey found that it is popular among about 90% of students. In addition, VR technology has recently made remarkable progress. From the above, I researched the idea that creating a simulation application using VR technology using smartphones would change the way high school students think about science classes. In this paper, we have developed a simulation application for science experiments. Subjects were asked to experience the newly created app and complete a questionnaire. As a result, the average score is 4 out of 5 and it is not bad. But at the same time, a problem was found. The problem was that this app was a simulation app, so there wasn't much user operability, so I wanted a little more operability. I want to make apps in other fields while improving the problem. 09 30 2021 107 110 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6443.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64430910321.pdf Ph.D Degree Student at College of Mechanical and Vehicle Engineering, Hunan University, China. Temesgen Abera Takiso Birtukan Tekle Manbecho worked at Infrastructure of the Municipality of Gimbichu city, Ethiopia. PV solar energy is the upcoming king of the energy source in the world, which is the fastest growing, most available, sustainable, clean, and environmentally friendly renewable energy. The essential characteristic of PV solar energy is generating the maximum power at mid-day. At the same time, the energy demand is high during the daytime. Due to this, PV solar energy replaces the conventional energy demand at peak periods. The sun is the source of PV solar energy, and it changed into electricity directly by using solar cells, which are made from semiconductor materials called silicon. Therefore, PV solar energy plays a crucial role in providing usable energy, and as well as reducing carbon dioxide emissions. However, the solar energy generation systems not achieved the desired efficiency yet, because of many unsolved problems like weather conditions, losses, materials made by and so on. The aims of this paper is to review the current literature on the improvement of the PV solar energy generation system's overall performance. First, to figure out the existing challenges, like environmental factors and natural phenomena that affect the PV solar modules efficiency. Then it presents the techniques that are used to enhance the PV solar modules overall performance. Finally, to propose the best ways and techniques to improve the PV modules efficiency and suggest to further studies. 09 30 2021 117 129 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6448.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64480910321.pdf Department of Computing Sciences and Engineering, Vellore Institute of Technology, Bhopal (M.P), India. Devesh Banwani Yatin Kalra Department of Computing Sciences and Engineering, Vellore Institute of Technology, Bhopal (M.P), India. The Chain of Custody is an intrinsic part of any inspection. Maintaining and evaluating the integrity of evidence procured from a crime scene is an important part that needs to be done properly by following a certain set of protocols to make the evidence admissible in the court. Keeping track of the evidence right from the moment it was collected from the crime scene till the time it reaches court is also a major task. It is important for the investigator to know how, where and who handles the evidence during analysis at each phase in order to safeguard the integrity of the evidence. Over a period of time, various tools and technologies have been created to handle evidence. Researchers from across the globe have presented various techniques on how evidence should be handled. Many researchers have even incorporated blockchain technology with the chain of custody or life cycle of evidence to make the process stronger. The growth in this domain has been at a rapid pace. This paper presents a method on “Maintaining and Evaluating the Integrity of a Digital Evidence in Chain of Custody” using a global positioning system. The methodology focuses on the use of global positioning system tags or chips which when embedded with the collected evidence enables an investigator to track the evidence throughout its life cycle. The proposed methodology aims to help the investigators to keep track of the evidence throughout its life cycle using very basic tools like FTK Imager and technology like a global positioning system. 09 30 2021 90 96 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6449.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64490910321.pdf Department of Computer Science and Engineering, UVCE, Bangalore University, Bengaluru, India. Rinu R Manjula S H Department of Computer Science and Engineering, UVCE, Bangalore University, Bengaluru, India. Agriculture is one field which has a high impact on life and economic status of human beings. Improper management leads to loss in agricultural products. Diseases are detrimental to the plant’s health which in turn affects its growth. To ensure minimal loss to the cultivated crop, it is crucial to supervise its growth. Convolutional Neural Network is a class of Deep learning used majorly for image classification, other mainstream tasks such as image segmentation and signal processing. The main aim of the proposed work is to find a solution to the problem of 38 different classes of plant diseases detection using the simplest approach while making use of minimal computing resources to achieve better results compared to the traditional models. VGG16 training model is deployed for detection and classification of plant diseases. Neural network models employ automatic feature extraction to aid in the classification of the input image into respective disease classes. This proposed system has achieved an average accuracy of 94.8% indicating the feasibility of the neural network approach even under unfavorable conditions. 09 30 2021 152 156 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6458.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64580910321.pdf School of Computing Sciences and Engineering, Vellore Institute of Technology, Bhopal, (M.P.) India. Varun Chopra In the embryonic stage, the usage of vehicle tracking systems were primarily restricted to getting the geographical location of the vehicular units. This scenario, however, was not perennial and with the escalation from a rudimentary stage to a highly complex archi- tecture for vehicular administration that we witness today, the standards for the vehicles security have also become monumental. With the development of V2X communications, the gamut of facilities provided by smart vehicle services has expanded prodigiously. These technological advancements, however have come at a cost. The gargantuan transition that has taken place over the recent years exacts a lot of security and safety mechanisms to be implemented, adjunct to the products and services it comes equipped with. In this paper, after a comprehensive study in the domain, we imply a security system model comprising of a Microcontroller Unit (MCU), as a part of the Vehicle Tracing Mechanism (VTM), well connected with a Management Hub. The communications be- tween the Vehicular Unit(s), Management Hub and the system Vehicle Tracing Mecha- nism (VTM) are made viable via V2X communications with conducive aid from technolo- gies like Global Positioning System, Radio Frequency Identifications and GPRS network. The paper aims to ameliorate the extant security protocols and improve the security and safety standards of smart vehicles by broaching cyber intelligence in smart vehicles. 09 30 2021 144 151 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.C6464.0910321 https://www.ijrte.org/wp-content/uploads/papers/v10i3/C64640910321.pdf