Journal of Advanced College of Engineering and Management

Spectral Estimation of Electroencephalogram Signal using ARMAX Model and Particle Swarm Optimization

2023-06-21T08:31:07+00:00

Electroencephalogram (EEG) signal is short-length time series data. Parametric and non-parametric methods are used to estimate the power spectral density (PSD) of the time series data. While the non-parametric approach of spectrum estimate of short-length data is unreliable, the parametric approach of spectrum estimate is widely suggested. In the presented work, a parametric autoregressive moving average with exogenous input (ARMAX) model was implemented to find the PSD of the EEG signal. The performance of the implemented ARMAX model was contrasted with other parametric methods like autoregressive AR) and autoregressive moving average (ARMA) and nonparametric methods like periodogram.

Coefficients of ARMAX and (ARMA) were estimated using the particle swarm optimization (PSO) technique based on swarm intelligence. The PSO algorithm adapted with the system identification technique and statistics yielded highly satisfactory results in finding the coefficients of the ARMAX model. All the programming and visualization were performed in a MATLAB environment.

Short Updates- Machine Learning Based News Summarizer

2023-06-21T08:40:17+00:00

Automated Text Summarization is becoming important due to the vast amount of data being generated. Manual processing of documents is tedious, mostly due to the absence of standards. Therefore, there is a need for a mechanism to reduce text size, structure it, and make it readable for users. Natural Language Processing (NLP) is critical for analyzing large amounts of unstructured, text-heavy data. This project aims to address concerns with extractive and abstractive text summarization by introducing a new neural network model that deals with repetitive and incoherent phrases in longer documents. The model incorporates a novel Seq2Seq architecture that enhances the standard attentional model with an intra-attention mechanism. Additionally, a new training method that combines supervised word prediction and reinforcement learning is employed. The model utilizes a hybrid pointer-generator network, which distinguishes it from the standard encoder-decoder model. This approach produces higher quality summaries than existing models.

Computational Analysis of Bifurcation of Raghuganga Hydropower Project

2023-06-21T09:12:54+00:00

Computational analysis is the modern design optimization tool used widely for determining the effect of different loading parameters where operating conditions and geometry are complex for manual solutions to execute. This study has great significance in the design and optimization of penstock branches as the ancient technology used for the design has least chance of having minimum head loss and good structural strength at the same time. Bifurcation of Raghuganga Hydropower Project of 40 MW installed capacity is chosen for this study in which, head loss, velocity and pressure distribution and stress distribution around the branching regions have been observed by varying the angle of cone of bifurcation. Upon varying the cone angles gradually starting from 3 degrees up to 15 degrees, the values of head loss have been reduced from 0.972 m to 0.086 m till 13-degree angle of cone and upon further increasing the angle to 15 degrees, the head loss increased sharply to 2.201 m. Also, for the structural analysis on the optimized cone angle profile, pipe thickness was varied from 25 mm till the values of stress was in the acceptable range. Upon simulations, it was found that optimum pipe thickness is 40 mm and sickle reinforcement of 75 mm with the value of maximum stress (Von-Mises) at the branching to be 167 MPa and minimum factor of safety of 1.49 for the material chosen i.e. E 250 corresponding to I S 2062.

Electrical Energy Auditing And Enhanchment of Power System at Basbari Water Treatment Plant, Kathmandu

2023-06-21T09:18:00+00:00

The water treatment plant (WTP) employs a variety of electrical machines and utilities, making it an intensive energy consumption plant. In this study, an energy audit was conducted on the Basbari WTP in Kathmandu, Nepal to identify the hotspots that consume most of the energy in the plant and recommend solutions for energy-efficient operation. A power quality analyzer was used to analyze the energy consumption patterns of electrical parameters and data from the electricity authority. The study found that transmission pumps and backwash/makeup pumps consume 77% and 6% of the energy, respectively. Efficient utilization of pump motors could result in an annual cost savings of NRS 160,954.81 from transmission pumps, backwash pumps, and make pumps. The payback period for light replacement and installation of a capacitor bank is 2.16 years and 1.95 years, respectively.

Computational Study on Structural and Thermal Behavior of Aircraft Disk Brake Rotor for Different Materials

2023-06-21T09:23:15+00:00

Brakes are one of the most significant safety systems in an aircraft. The rotor will be exposed to large stresses which result in surface cracking, overheating of brake fluid, seals and other components during the braking process. Thus, one of the main tasks for the design of braking system is to reduce the stress, deformation and surface temperature of the brake rotor. This can be achieved by choosing the right material which will undergo the least thermal stresses. In this research a detailed study of structural and thermal analysis is carried out for disc brake rotor of DHC-6 Twin Otter with different materials. The objective of this research is to provide an efficient material for disc brake rotor which can dissipate heat generated during braking at faster rate and also being structurally safe. The materials chosen for the study are Mild Steel, Grey cast iron, Stainless steel, Cabon-carbon composite and Aluminum silicon carbide MMC. From the structural and thermal analysis it was found that the aluminum silicon carbide MMC disc brake rotor exhibits the superior performance against other materials with a mass of 2.37 Kg, deformation of 0.043617 mm, maximum stress of 167.91 MPa, maximum temperature of 250.85 ^oC and heat flux of 5.2043 W/mm2. The mass, stress, deformation and temperature developed in the aluminum silicon carbide MMC rotor is less than the original stainless steel rotor by 61.3%, 3.66%, 6.9% and 35.6% respectively. Similarly, the aluminum silicon carbide MMC rotor provides better heat dissipation as compared to original rotor due to an increment in heat flux by 15.26%.

Grid Impact Study of Micro-Grid with an Improved Transient Response using PV Panel in MATLAB-SIMULINK

2023-06-21T09:28:50+00:00

The paper present a system that convert a power generated from a renewable resources to a source having same voltage and frequency with respect to traditional power plant. As the conventional fossil fuel resources such as Coal, Diesel, Gas etc is limited in quantity which will run out very soon. Hence all the researchers throughout the world are looking for alternative form of energy[1]. As a consequence the penetration of WIND & PV – generated electrical energy into the grid system is increasing exponentially worldwide [2]. The paper consist of PV array, boost converter, 3phase VSC Inverter, synchronous generator and utility grid. PV system has low conversion efficiency, so to improve conversion efficiency it is important for PV system to work always at its maximum power point. Maximum Power Point Tracker (MPPT) control technique is used to get maximum power as possible [3]. The voltage source inverter interface with grid and transfer an energy drawn from PV array to the grid by keeping the common voltage & frequency constant. The simulation results such as voltage, current, output power for each various combination have been recorded. The simulation has been accomplished in a Software of MATLAB Math Works.

Computational and Experimental Analysis of Conical Draft Tube's Effect on Conical Basin of Gravitational Water Vortex Turbine

2023-06-21T09:31:47+00:00

This paper presents an insight into the performance of the Gravitational Water Vortex Turbine (GWVT), a type of Ultra-Low Head (ULH) turbine, with and without the implementation of draft tube. Till date, no attention has been given on the effect of draft tube on GWVT. A model of GWVT along with a conical basin is developed on CATIA v5, and then subjected to a series of computational studies on ANSYS 2020R2. A similar setup is constructed in which a straight divergent draft tube is installed at the exit of the conical basin. The numerical approach suggested that maximum efficiency of the setup in the former case was 72.0% at 53 RPM whereas the efficiency in the latter case was 79.0% at 65 RPM. The increase in the efficiency was calculated to be 9.72%. This conclusion was validated through experimental verification conducted at Himalaya College of Engineering, Chyasal on a pre-fabricated test-rig of capacity 480 L, where the maximum efficiency of 69.4% and 64.5% were obtained with and without the installation of the draft tube respectively. Consequently, an increase of 7.59% in the efficiency of GWVT as an effect of draft tube was observed experimentally. It can be concluded that draft tube plays a vital role in the efficiency of the Gravitational Water Vortex Turbine.

Roles of Existing Policies on The Conservation and Management of Cultural Heritage in Kathmandu Valley, Nepal

2023-06-21T09:35:48+00:00

In 1956, the Ancient Monuments Preservation Act (AMPA) was first introduced, ushering in a more contemporary approach to cultural preservation in Nepal. The focus of this legislation is primarily on the material (physical) aspects of cultural heritage. The Guthi Corporation, formed by the Government of Nepal under the Guthi Corporation statute of 1976, focuses on the intangible legacy of the Kathmandu valley in a manner similar to that described above. The Department of Archaeology (DOA), a federal government body backed by the AMPA and in charge of safeguarding the country's cultural heritage. International organizations like the United Nations Educational, Scientific and Cultural Organization (UNESCO) criticized the difficulties in managing the Kathmandu valley's world heritage sites, which led to their inclusion on the endangered list in 2003, which has since been removed. The purpose of this research paper is to examine the effects that different government organizations' (stakeholders') policies have throughout time on the management and preservation of the cultural heritage of the Kathmandu valley. In order to maintain cultural assets using historical as well as case study methodologies, the research of this article recommends a review of current policies on dispersed policies and organizational responsibilities. Study reveals that now the time to development of unified policies and organisation to minimise the overlapping roles for good management and conservation in the Kathmandu valley, which will primarily be based on local cultural context as well as UNESCO criteria.

Algorithms Comparison in Drowsiness Detection

2023-06-21T09:39:05+00:00

Drowsy driving is a recognized leading cause of road accidents, resulting in a considerable number of fatalities and injuries. This paper presents a proposed system that leverages machine learning algorithms, specifically Convolutional Neural Network (CNN) and Support Vector Machine (SVM), to accurately detect the drowsy state of drivers by analyzing the diameter of their eyes and comparing the level of dilation or constriction. Drowsy driving poses a significant problem on roadways, as indicated by the National Highway Traffic Safety Administration's data, which reports approximately 100,000 police-reported collisions each year involving drowsy driving, leading to over 1,550 fatalities and 71,000 injuries. The proposed system demonstrates the potential to reduce accidents associated with drowsy driving. We conducted an evaluation and comparison of the effectiveness of CNN and SVM algorithms with the objective of identifying the optimal algorithm for drowsiness detection. Our algorithms were trained on a comprehensive dataset comprising images of drowsy and alert drivers, enabling real-time and accurate identification of the driver's state. Employing advanced image processing techniques, the proposed system analyzes changes in eye diameter associated with drowsiness. Its purpose is to promptly alert drivers, thus mitigating accidents caused by drowsy driving. We anticipate that this system will provide a reliable and cost-effective solution to the problem of drowsy driving, with potential benefits for both drivers and passengers. Further research and development efforts could facilitate its widespread adoption in the automotive industry. This paper underscores the significance of addressing drowsy driving and introduces a promising solution through the application of machine learning algorithms.

Career Guidance System Using Machine Learning

2023-06-21T09:45:45+00:00

Career Guidance System is important for students going through academic and pursuing courses to access their capabilities and identify their interests. This paper mainly concentrates on career guidance through personality prediction. It helps them decide which job role suits the best based on their performance and other evaluations. The system will predict the Big Five personality, and VAK learning type of the users through data collected from web-based questionnaires. The system recommends different career choices based on their answers. Machine learning algorithms will be used to check the performance of the system and validate the result.

Flood Propogation

2023-06-21T09:50:30+00:00

The catastrophic failure of the dam creates to a rapid changes of flow depth which causes a devastating damage in the cultivated land in the downstream of the dam. The precise calculation to its attenuation of the wave height is critical to the design of the protection work for the cultivated land of the downstream communities. Therefore, this topic is aimed to present an illustration the estimation of the open channel surges in the downstream river reaches.

Water Hammer

2023-06-21T09:52:42+00:00

Dynamic Pressure rise or fall in all kinds of pipelines due to the operation of the valve which are transmitting fluids are very much essential part to consider in the design of pipeline. This paper presents how to calculate these dynamic pressure waves while designing pipelines.

Students Cognitive Development in Basic Level Schools in Nepal: Provisions and Practices

2023-06-21T09:55:05+00:00

This study explores the current status of basic-level students’ cognitive learning and examines how school education provisions are functioning to facilitate perceptive education. The study was conducted by adopting a mixed-method research design, including a quantitative survey and a qualitative case study for data generation from six schools in four districts across the country. With a small research grant support from UNESCO Nepal, this research was conducted under the Centre for Educational Research, Innovation and Development (CERID) to provide a new and innovative concept to learning from different aspects ranging from knowing to creating. Students’ achievement at six levels of cognitive development was evaluated based on a questionnaire containing items from the revised Bloom's taxonomy of educational objectives. Classroom practices were systematically observed, and the main events and activities were recorded. The study revealed that the students performed better in remembering and showed lower performance at creating level. Classroom pedagogies were found dominantly lecture-based and concentrated around the acquisition of knowledge from the textbook. Besides, teachers were found not preparing the lesson plan, nor were they taking classes in a planned way. There was no plan, program, or practice regarding cognitive teaching-learning for addressing the specific potentials, weaknesses, and aptitudes of students at the basic level of education in Nepal.

Drishya: Object Detection And MonocuLar Depth Estimation Using Deep Learning

2023-06-21T09:58:44+00:00

This project focuses on object detection and depth estimation using computer vision. The aim of this project is to develop an accurate and reliable system for detecting objects and estimating their distances from a camera. The system uses deep learning-based algorithms to detect objects and estimate their distances. The results of the project show that the system can accurately detect objects and estimate their distances in some scenarios. This project presents an Android app for real-time object detection and depth estimation using computer vision with YOLOv5 and U-Net architecture.