International Journal of Engineering and Management Research

Enhancing Spammer Fake Profile Detection on Social Media Platforms using Artificial Neural Networks

Farheen Siddiqui — 2023-08-02

The proliferation of social media platforms has led to an increase in spammer fake profiles, posing significant security, privacy, and trustworthiness concerns. Traditional manual monitoring and content filtering techniques are insufficient to combat this growing issue, necessitating the development of more efficient and accurate detection methods. Machine learning techniques have been increasingly employed for this purpose, demonstrating promising results in identifying spammers and fake profiles. This paper presents a novel approach for spammer fake profile detection using Artificial Neural Networks (ANNs) to enhance the accuracy of the detection process. Our proposed ANN-based method addresses the challenges associated with spammer fake profile detection, such as the dynamic nature of spammers, data heterogeneity, scalability, and imbalanced datasets. We evaluate the performance of our method on real-world datasets and compare it with existing machine learning techniques, demonstrating its effectiveness and superiority in detecting spammers and fake profiles with higher accuracy. This research contributes to ongoing efforts to secure social media platforms, ensuring the trustworthiness of online content and providing a safer user experience.

Prediction of Loan Approval in Banks using Machine Learning Approach

Viswanatha V — 2023-08-02

Due to significant technology advancements, people's needs have expanded. As a result, there have been more requests for loan approval in the banking sector. A few qualities, taken for consideration, when choosing a candidate for loan approval in order to, determine loan's status. Banks face a major challenge; when it, comes to assessing loan applications and lowering the risks associated with potential borrower defaults. Since they must thoroughly evaluate each borrower's eligibility for a loan, banks find this process to be particularly challenging. This research proposes combining machine learning (ML) models and ensemble learning approaches to find the probability of accepting individual loan requests. This tactic can increase the accuracy with which qualified candidates are selected from a pool of applicants. As a result, this method can be used to address the problems with loan approval processes outlined above. Both the loan applicants and the bank employees profit from the strategy's dramatic reduction in sanctioning time. Because of the banking industry's expansion, more people were applying to loans at banks. In order to predict the accuracy of loan approval status for applied person, we used four different algorithms namely Random Forest, Naive Bayes, Decision Tree, and KNN. By using these, we obtained better accuracy of 83.73% with Naïve Bayes algorithm as best one.

Implementation of Decision Tree Algorithm for Prediction of Rheumatoid Arthritis Disease

Viswanatha V — 2023-08-04

A very challenging and difficult part of finding a cure for Rheumatoid Arthritis ( RA) disease is the same as finding a cure for an autoimmune disease. In the case of autoimmune diseases, it is very difficult to find the cause. RA is also one of the autoimmune diseases that causes inflammation in joints. It does not only limit to joints but also can spread or occur in various parts of the body like skin, lungs, and many others. Many features like age, sex, and previous history of certain diseases affect the occurrence of RA. The proposed ML model uses a decision tree algorithm to analyze a comprehensive set of clinical and laboratory variables collected from RA patients. These variables include age, ID, time, treatment, gender, and other baseline features. The ML model employs feature selection techniques to identify the most relevant predictors that contribute to disease progression. By training the decision tree algorithm on a large dataset of RA patients, the model generates an accurate predictive model for assessing disease severity and progression. The model is able to detect RA disease with almost 80% accuracy with the given training dataset. RA can have many other symptoms and characteristics. This data was trained on a basic dataset available from the Kaggle website. The dataset is in CSV format and has 6 features. The model was trained using a decision tree algorithm, which categorizes the data into different categories and then checks for specific data when needed in Jupyter Notebook. The study explored detecting basic symptoms and characteristics of RA disease. The Decision tree model has given accuracy of 86.5% and 74.4% on training and testing respectively. So Accuracy of the model is pretty good for the dataset used.

IoT based Plant Growth and Health Monitoring System for Mushrooms

Punsala S.M.P. — 2023-08-05

This research paper proposes the development of an IoT-based monitoring system using a robot camera for mushroom cultivation in Sri Lanka. The system aims to address several sub-objectives, including harvest time prediction, disease detection, quality assurance, and environmental monitoring. The research utilizes image processing and machine learning techniques to capture mushroom images, analyze their size, shape, morphology, and color, and predict the optimal harvest time. It also focuses on identifying common diseases, researching their early symptoms, and recommending appropriate treatment options. The system incorporates user-friendly mobile interfaces for farmers to provide input on mushroom quality and receive alerts. Moreover, it establishes quality standards, defines criteria and thresholds, and uses machine learning algorithms to train a model for quality assessment. The research introduces an IoT device that integrates environmental sensors to optimize crop growth by analyzing real-time sensor data and recommending corrective actions. The novelties include the use of robotic camera and machine learning for feature detection, personalized disease recommendations based on individual mushroom conditions, promotion of sustainable farming practices, ui-based quality assurance score, and prioritization of corrective actions based on severity and impact. The proposed system aims to improve accuracy, increase product value, enhance profitability, and promote environmentally friendly agriculture.

Sentiment Analysis using Opinion Mining on Customer Review

Prachiti Akre — 2023-08-05

Opinion mining is the process of discovering user opinions about a subject, a product, or an issue. Sentiment analysis is the process of separating opinions' feelings from those opinions. This work presents a comprehensive review of techniques in sentiment analysis using opinion mining. We start by discussing the basic concepts of opinion mining and then delve into various techniques and approaches used for sentiment analysis. This work focuses on analyzing the user reviews on products from e-commerce websites such as amazon.com and compares products of similar specifications based on the polarity of user reviews for the products calculated using nlp and naive bayes classification.

Online Fraud Detection Using Machine Learning Approach

Viswanatha V — 2023-08-07

Online extortion discovery has ended up a tremendous issue in today’s advanced age and poses a danger to individuals, businesses, and budgetary teachers all over the world. The increment in extortion illustrates the requirement for compelling extortion discovery, especially within the setting of anti-money laundering (AML) endeavors. This extent is planned to create a machine learning-based arrangement utilizing Python to distinguish and avoid online extortion in genuine time.

The proposed framework employment chronicled exchange information, combining different components such as client behavior, exchanges, and budgetary information. First, the information control preparation is utilized to clean the information and change over it organized reasonably for the preparing show. At that point, different machine learning calculations such as calculated relapse, choice trees, irregular timberlands, or angle boosting are used to build predictive algorithms that can spot fraud. The extended concludes with the usage of the created show in a genuine world online exchange environment, permitting genuine time extortion location and avoidance. The system’s adequacy is persistently checked and assessed, and essential overhauls and advancements are made to adjust to advancing extortion designs and procedures. By and large, this extends points to supply a strong and proficient arrangement utilizing Python and machine learning strategies to combat online extortion. By precisely recognizing false exchanges in genuine time, this framework can altogether contribute to fortifying AML endeavors and ensuring people and organizations from money-related misfortunes and reputational harm related to online extortion.

Tuberculosis Prediction using KNN Algorithm

Viswanatha V — 2023-08-07

In this paper, a machine learning model is used to develop a model that is used for tuberculosis prediction. Tuberculosis is known to be one of the top reasons for death from an infectious agent that affects the lungs and continues to threaten the human population on a wider basis. According to WHO, tuberculosis is a serious threat to the human population after HIV/AIDS. It is estimated by the World Health Organization (WHO) that 1/3^rd of the global population is infected with TB and that seven to eight million new cases of TB occur each year across the globe Because the disease is difficult to differentiate between the common cold, it takes a long time to decide the patient is affected by the disease. So we use the detection of tuberculosis by utilizing the K-NN algorithm method for classification and HOG as feature extraction. K-NN abbreviated as K-Nearest Neighbour is one of the simplest Machine Learning algorithms based on the Supervised Learning technique.

The data provided K-NN model should be labeled one. Then these datasets are given to a training model where the training process of the model is being undergone. Once the training is completed, the next step is to predict the output. For this process, we have to provide new data that may or may not belong to the dataset, so that the model can predict the output of it. If the prediction is wrong, again the training is done until we get the actual output matching with the desired output given by the designer for verification purposes. This is the basic working process under the K-NN algorithm. The data that is used for this separation is a Tuberculosis dataset that contains various information about the different symptoms that are helpful in detecting tuberculosis effectively. Here it is used in the early detection of tuberculosis which helps save millions of people which might otherwise lead to death because of lack of detection. ML model helps to improve the efficiency in detecting by considering various symptoms. ML models are more accurate at differentiating even the slightest difference that deviates from the data that was used to train the model. Unlike the manpower we fail to detect the slightest as we notice the symptoms only after they become more severe. The accuracy of this model was found to be 98%. The following model uses a dataset consisting of data that contrasts between males and females and the various symptoms are shown in them. It also contrasts the severity of these two.

Casing While Drilling - Revolutionizing Drilling Operations for Enhanced Efficiency and Safety

Mohit Kumar — 2023-08-09

Efficiency and safety are at the core of any field operations in the Oil and Gas industry. During drilling a well, the biggest risk is a stuck pipe incident owing to the wellbore issues. If these issues are not treated timely, they can have devastating effects on the whole drilling operations. Also, running drilling and casing in and out of the borehole poses a huge operational risk on the drilling crew. It is the objective of any well design to minimize safety risks. This paper discusses about a new drilling technology commonly known as Casing While Drilling (CwD) along with factors to design the CwD operations to achieve the desired success.

Robage BOT

Sushant Pawar — 2023-08-16

One of the biggest issues facing the entire globe today is waste management. Rapid population growth is a result of fast industrialisation, which also causes problems with waste management. It has been observed that there is a considerable likelihood that dumping light weight solid waste items may pollute public areas where the public congregates momentarily. There is no ideal method for keeping an eye on and maintaining these locations. It is possible to create a self-controlled robot application to solve these issues. Here machine can identify garbage and separate it into several categories, such as metallic and non-metallic waste.Implemented system uses IR sensors to detect garbage, metal proximity sensors to distinguish between metallic and non-metallic junk, and moisture sensors to further divide garbage into wet and dry waste. Here robot is controlled by an ESP32 microcontroller.

Volatility Response to “Black Swan Event” of Covid-19 in Asian Stock Market: An Empirical study Using EGARCH Model

Dr. Neeru Gupta — 2023-08-16

By detailing the volatility response to shocks in several Asian nations, a dimension that has not been examined in the existing literature, our study contributes to the body of literature. The empirical data from the study indicate that volatility displayed asymmetric behavior in a few select Asian stock markets over the study period. In relation to this study, we saw that the volatility reaction followed a consistent pattern in the Asian region. For all but a few select markets, shocks are homogeneous in size and sign. Additionally, there is evidence that volatility responses are persistent across all Asian stock markets, which suggests that the impact of volatility will gradually diminish. This study offers helpful information to the investor community to help them make informed decisions about their investments.

Analysing Competencies of Health Care Workers of Private Multispecialty Hospital toward Responsibility of Job the Training Need Analysis Approach

Dr. Gajanan Jagadish Salunkhe — 2023-08-16

The healthcare and hospital industry in India has grown rapidly. People are conscious about their health and well-being. Multi-specialty and super-specialty hospitals have been established in many urban and semi-urban areas of our country. Several and super hospitals offer quality medical and technological services. There is no doubt that these hospitals have highly qualified doctors, but the support staff has been neglected. Nursing plays a key role in this hospital industry. The need for training, which is the skills of the employee and the required training skills, has never been evaluated for nursing staff. A Training Needs Analysis (TNA) is a job needs analysis that aims to identify which training needs are truly a priority. Roles and responsibilities must be considered when assessing these training needs. Communicating these needs helps the organization use resources effectively and efficiently. It also helps to avoid unnecessary exercise. Analysis of training needs can also mean a systematic and comprehensive study of various problems to accurately identify the dimensions of any organizational problem. Therefore, the organization will determine whether the problem will be solved through a training program or in some other way. Organizational problems refer to a lack of skills or knowledge when normal results cannot be achieved; the above explanation explains the difference between real and situational performance.

Design and Simulation of Switched Capacitor Based Multilevel Inverter with Reduced Components

Rohith G B — 2023-08-17

Function of inverter is to convert DC signal to AC signal. Boost voltage and to improve the power quality and capacity with sinusoidal type waveform is obtained by use of multi-level inverter. The Multilevel inverter increases number of devices and other components, switched-capacitor (SC) units have ability to boost the input voltage considerably switched capacitor-based inverter with reduced switch is proposed in this paper without inductor and transformer operation with voltage boosting feature and inherent capacitor self-voltage balancing performing with no interference. The structure proposed in this paper is capable of producing 17 level output waveform with double voltage gain using a dual voltage source with reduced switches and other equipment’s. The inverter switching pulse is modulated using PD-PWM technique, which enables a high quality output waveform.

Hygiene Practices and Community Well-being in a Rural Setting: The Case of Mhawlewadi Village

Dr. Umesh Gadekar — 2023-06-18

In rural areas, the relationship between hygiene practices and community well-being holds paramount importance due to limited access to resources and healthcare facilities. This study investigates the intricate interplay between hygiene practices and the overall well-being of a rural community. Focused on the unique context of a rural setting, this research aims to comprehensively analyze hygiene behaviors, infrastructure, and awareness, thereby uncovering insights into their impact on community health. Utilizing a mixed-methods approach, both qualitative and quantitative data were collected from the residents of Mhawlewadi Village, representing the rural setting under study. Qualitative interviews and surveys were conducted to understand the prevailing hygiene practices, knowledge, attitudes, and challenges faced by the community members. The results of this study reveal a complex relationship between hygiene practices and community well-being. While certain aspects of hygiene practices were found to be deeply ingrained within the community's traditions and lifestyle, other areas displayed room for improvement. Limited access to clean water, proper sanitation facilities, and health education emerged as significant challenges affecting hygiene practices and subsequently, community health. The implications of this study underscore the need for targeted interventions that address the unique challenges faced by rural communities. Health education campaigns, infrastructure development, and collaborative efforts among stakeholders can contribute to enhancing hygiene practices and, consequently, the well-being of the community. This research contributes to the growing body of knowledge concerning hygiene practices in rural areas, offering insights that can inform policies, programs, and initiatives aimed at fostering holistic community health.

In conclusion, this study illuminates the intricate dynamics between hygiene practices and community well-being in a rural setting. By unveiling the challenges and opportunities within this context, it provides a foundation for evidence-based strategies that empower rural communities to improve their hygiene practices and enhance overall well-being.

Extended Collaborative Filtering Recommendation System with Adaptive KNN and SVD

Sagedur Rahman — 2023-08-21

In recent years, recommendation systems have gained significant importance due to the vast amount of digital content available on various online platforms. Collaborative filtering is a widely adopted approach in recommendation systems, leveraging user-item interactions to make personalized predictions. However, traditional collaborative filtering methods face challenges such as the cold-start problem and data sparsity. To address these issues, researchers have proposed advanced techniques, including Adaptive KNN-Based and SVD-Based Extended Collaborative Filtering. This paper provides a comprehensive review of these two recommendation systems, discussing their underlying principles, advantages, and limitations. Furthermore, we explore recent research advancements and real-world applications, providing insights into the potential future developments in this field.

A Study on Essence of Employee Engagement: An Organisational Perspective

Dr. Rajesh Kumar Pandey — 2023-08-25

Engagements in any form have been the crux of the cultural balance. The Organisations to a large extent aim to achieve this balance and engage the Employees in order to achieve Organisational goals. Employee engagement in an organization is massively related to the ability of an organization to manage its employees and generate high-performance levels. The key ingredients of an engaged employee seem to be a display of emotional involvement in what the employee does, and pride in the work place. Employee Engagement is seen as a powerful source of competitive advantage for companies in turbulent times. A deserving & good employee engagement is only going to happen if employees feel positive and strong about their relationship with their Superiors and the Organisation at large.

The Researchers have adopted Exploratory & Descriptive Research design. The Research is conducted with the help of both Primary and Secondary data. The primary data is in the form of Interviews with Five Companies. The HR Heads were approached for the Interview. This Paper attempts to discuss on the Employee Engagement domain of Organisations. The Researchers aim to understand the essence & significance of Employee Engagement. The study further aims to study the factors influencing Employee Engagement at Organisations. The Researchers have gathered the Organisational perspective towards Employee Engagement and identified the relative challenges. The study encompasses the learning on Employee Engagement and understanding its essence. The Researchers have taken Employee Engagement aspect for Organisations at large rather any specific sector or region or set of Employee like Gender based etc., hence the inferences gathered are indicative in nature rather exhaustive. Employee Engagement is an essential virtue for Organisations and the same gets reflected through the Employee satisfaction, organizational success, and financial performance etc.

Finite Element Analysis of Material Handling System Components

Aarbaz Mutwalli — 2023-08-26

In any industry, a transport system is always required. Lifting and moving heavy goods over great distances has traditionally been done by workers. This may be economically beneficial to the employer but certainly is counter-productive in a way, considering the time required for the displacement as well as the health risks associated due to prolonged work. This work focuses on the design and analysis of an overhead Monorail system. The design analysis of overhead monorail crane with a single beam has been proposed. In this paper the design analysis of hoist track, support column and hook has been done and study of results of finite element analysis of crane components with 1 ton capacity and 27 m span length has been conducted. The optimum design was selected using various materials handling system method and further tested for its structural performance using finite element analysis. The 3D model prepared and finite element analysis was also used to confirm the structural integrity of the new concept design.

Feasibility of Water Hyacinth Ash as an Accelerator in Cement Slurry Formulation

Neminebor Gift Pepe — 2023-08-26

Cement is primarily used in drilling operations to protect the casing against the corrosive tendency of formation fluid and to support the casing with the external load on and around it. Cement slurry is formed by mixing water with Portland cement or with cement containing various essential additives as the case may be and pumping it down through to critical points in the annulus around the casing using various techniques. Class G cement is widely used in cementing jobs because it allows the use of accelerators and retarders for wide range of well depths and temperatures. Due to wait-on-cement time before commencement of drilling of the next section of the well, it is necessary to reduce the waiting time and it ripple effects on cost of drilling by introducing accelerator to the cement slurry. The chlorides of calcium, potassium and sodium are the commonly used accelerators. Water hyacinth ash have been known to contain high percentage of calcium, potassium and chlorine, these elements readily combine with water to form potassium chloride and calcium chloride of which both are used as accelerator additives in cement slurry formulation. The utilization of these compounds in water hyacinth ash as accelerator additives would be a major breakthrough in cementing jobs especially in shallow section of the wells. Locally sourced water hyacinth plants were dried and combusted in air, the ash was then activated with water and filtered. The filtrate was used to determine the thickening time of class G cement slurry and the results obtained was compared with that of inorganic calcium chloride. The thickening times at the various set temperatures for this experiment were close to the inorganic calcium chloride used. Though, the thickening time of cement slurry is dependent on temperature, the concentration of the accelerator in the slurry also affect it.. It was found out that water hyacinth ash reduces the thickening time of class G cement slurry comparatively and therefore, should be considered as accelerator additive in the formulation of oil well cement slurry for accelerating the cement setting time.

Online Candidate Selection System for Elections

Meregngnage H.E. — 2023-08-29

This research proposes an innovative online platform for political parties in Sri Lanka to enhance the candidate selection process. The platform incorporates features such as sentiment analysis, background checks, aptitude tests, ranking system, and analysis of candidates' promises and activities. Developed using advanced technologies, it aims to ensure transparency, efficiency, and accessibility for all eligible candidates, ultimately contributing to a more democratic election.

Bird Flu Tracking System using Naive Bayes Classifier

Kedar Sawant — 2023-08-31

Complexity in the food-related Supply chains also introduces economic ineﬃciency at every point of transaction, be it a poultry farmer or a distributor. Therefore, a system is required that tracks every point of Poultry transaction with an intuitive rather than minimal technology medium that can trace bird disease and maximize eﬃciency in operations at every level, from Poultry farm to Chicken Butcher/seller. A solution for farm-to-butcher/seller chicken tracker that rapidly traces bird ﬂu while also providing a platform to maximize operational eﬃciency. To make the chain eﬀective the proposed system needs enrolment at every level (Farmers, Distributors, Sellers) where poultry transactions can be recorded, and hence, our solution maximizes platform enrolment by cutting down the distributors’ labor costs by providing access to accounting and management tools and providing a one-stop marketplace to both distributors and farmers. With the ease of use of the RFID tagged system for distributors and sellers to tap and add batches to their inventory for easy supply chain management. The same data will also help in ﬂu detection.

Design and Development of Experimental Test Rig for Fault Diagnosis of Ball Bearing Using Fuzzy Logic Concept

Rutuja Mane — 2023-08-31

Rolling element bearings are frequently employed in industry. Many machine-related issues are linked to bearing failures. To minimize downtime and preserve product quality in a highly automated production, an online detection system is required. Condition-based monitoring for deep groove ball bearings is becoming more common. All rotating machinery uses these bearings extensively to accommodate both static and dynamic loads. Techniques for condition-based monitoring can be utilized to diagnose bearing defects to prevent this failure. So, it is important to study these faults present in the machines. The techniques for fault detection will be described in this paper. We are discussing Fast Fourier Transform (FFT) technique. In FFT, we obtain frequency-relationship graphs, and based on peak frequencies, we predict faults. A detailed analysis using the FFT Methodology is done to find out the possible faults, and finally validate with MATLAB software. For the aim of bearing diagnostics, the system performs vibration analysis. More advanced diagnostic systems use fuzzy logic and classification methods to identify the state of the machinery. These techniques enable the creation of more automatic and trustworthy diagnostic systems.

Optimize Banana Production through Innovative Growing System

T.P.Wijewardena — 2023-08-31

Optimizing banana production through innovative systems is essential for sustainable cultivation. This research primarily focuses on banana variety identification using images and Convolutional Neural Networks (CNNs), detection of leaf diseases in banana trees through a machine learning approach, analysis and recommendation of optimal cultivation practices derived from interactions with farmers and external supervisors, and the generation of unique product ideas using differentiation strategies based on market research, consumer preferences, and insights from industry experts. Collectively, this study aims to revolutionize banana cultivation and marketing by amalgamating traditional farming insights with modern technological tools.

Cloud Computing Accounting Information System Design of Business Entity Village Owned (BUMDESA)

Anak Agung Gde Satia Utama — 2023-08-31

This study aims to design an accounting information system for business entities—Village-owned (BUMDesa) Ketapang Banyuwangi with cloud computing. BUMDesa Ketapang has experienced good development in the last five years but has not been matched by an effective accounting system. The research methodology used is qualitative exploratory research with PIECES analysis. The results of this study refer to the cash receipt cycle, cash disbursement, and reporting cycle starting from recording transactions from the business unit and reporting to the treasurer then recorded in a journal, posted to a ledger, and producing financial reports in the form of a Financial Position Report, Profit Loss Report, and cash flow statements. The processes shown are data flow diagrams (DFD), flow charts, entity-relationship diagrams (ERD).

Intelligent Assistance for Smart Shopping

Shraddha Gosavi — 2023-08-31

Over the past few years there has been vast development in Android Application technology. This development made people's lifestyle much easier and interesting through various innovations by finding solutions to day-to-day problems. Even though many things became easier, still shopping is tough. For customers finding the required product in the supermarket is the most challenging task and moreover it is exhausting to stand in long queues at the billing counters. Shopping is a day-to-day activity. Many people visit supermarket for shopping on regular basis and during weekends, holidays and festive season supermarkets witness huge crowds. The development of online shopping websites has attracted people to purchase products online without visiting any supermarket. Mostly all the products are available on websites like Amazon, Flipkart, etc. But people cannot verify the quality of the product physically and can only verify after the product’s delivery. If the product is not up to the customer’s expectations, then it becomes a hefty task of returning and reordering the product.