Turkish Journal of Computer and Mathematics Education (TURCOMAT)
Not a member yet
9094 research outputs found
Sort by
Deep CNN Model for Condition Monitoring of Road Traffic: An Application Of Computer Vision
No full textThe traffic surveillance system accumulates an enormous amount of data regarding road traffic each second. Monitoring these data with the human eye is a tedious process and it also requires manpower for monitoring. Deep learning Convolutional Neural Network (DLCNN) can be utilized for traffic monitoring and control. The traffic surveillance data are preprocessed to construct the training dataset. The Traffic net is constructed by transferring the network to traffic applications and retraining it with a self-established data set. This Traffic-net can be used for regional detection in large scale applications. Further, it can be implemented across-the-board. Further, DLCNN is used for prediction of traffic status i.e., dense traffic, low traffic, accident, and fire occurred from test sample. Finally, the simulations revealed that the proposed DLCNN resulted in superior performance as compared to existing model
DETECTION OF CRIME SCENE OBJECTS FOR EVIDENCE ANALYSIS USING DEEP LEARNING TECHNIQUES
No full textResearch on the detection of objects at crime scenes has flourished in the last two decades. Researchers have been concentrating on colour pictures, where lighting is a crucial component, since this is one of the most pressing issues in computer vision, with applications spanning surveillance, security, medicine, and more. However, nighttime monitoring is crucial since most security problems cannot be seen by the naked eye. That\u27s why it\u27s crucial to record a dark scene and identify the things at a crime scene. Even when its dark out, infrared cameras are indispensable. Both military and civilian sectors will benefit from the use of such methods for nighttime navigation. On the other hand, IR photographs have issues with poor resolution, lighting effects, and other similar issues. Surveillance cameras with infrared (IR) imaging capabilities have been the focus of much study and development in recent years. This research work has attempted to offer a good model for object recognition by using IR images obtained from crime scenes using Deep Learning. The model is tested in many scenarios including a central processing unit (CPU), Google COLAB, and graphics processing unit (GPU), and its performance is also tabulated
Design and Simulation of variable gain amplifier using cadence Tool
No full textThe radio frequency (RF) amplifiers are widely used in a variety of communication systems. However, the conventional analog RF resulted in reduced volage gain, magnitude, and phase responses. So, this work provides an overview of a research paper focused on the design and analysis of a single-stage variable gain amplifier (SSVGA) utilizing cascaded linear transconductance amplifier (Gm cell) and linear transimpedance amplifier (TIA) blocks with feedback via shunt resistors. The SSVGA architecture aims to maintain constant bandwidth while offering controllable voltage gain, making it versatile for applications with varying input signal strengths. The first stage of the SSVGA is realized as a current mode TIA, converting the input voltage signal to an output current efficiently. The second stage features a Gm cell with source degeneration, enhancing bias current efficiency and transconductance at the supply voltage. The proposed SSVGA design offers flexibility and adaptability, making it suitable for diverse communication systems and signal processing applications. The incorporation of feedback control ensures consistent performance across different voltage gain settings, resulting in a robust and efficient solution for varying signal strengths
MACHINE LEARNING MODEL TO DETECT PNEUMONIA USING CHEST X-RAY
No full textPneumonia, a respiratory infection caused by the inflammation of air sacs due to viruses and bacteria, affects approximately 7% of the global population annually, with 4 million patients facing fatal risks. Early diagnosis is crucial, and typical symptoms include chest pain, shortness of breath, and cough. However, diagnosing pneumonia in children is challenging due to the low sensitivity of tests and weak clinical findings. Chest X-rays have become an important diagnostic tool, but the conventional approach involving manual examination by radiologists is time-consuming, subjective, and can vary in accuracy. To address this, the proposed model leverages machine learning (ML), specifically designed for image analysis, to automatically learn and extract relevant features from chest X-ray images. The dataset consists of annotated chest X-rays collected from diverse patient populations, including both pneumonia-positive and pneumonia-negative cases. This model holds significant implications for the medical field and patient care, as it can rapidly analyze large volumes of chest X-ray images and accurately detect pneumonia patterns with a high level of precision. This will enable healthcare professionals to prioritize urgent cases, expedite diagnosis, and promptly initiate appropriate treatments, leading to improved patient outcomes, reduced hospital stays, and optimized resource allocation within healthcare facilities
THE PRIMAL FEAR: THE LANGUAGE OF THE FUTURE IN THE HUNGER GAMES
No full textThe Hunger Games series was banned to begin with before even it became a cult classic because of its anti-family concerns, the rebellion and the attitude of challenging the governmental authority. The system of futuristic governance is a warning to the readers, especially the teens of tomorrow as to how their lives would be in future if they continue to remain complacent about the ways of the authorities who rule them over. There is crime, retribution and rebellion each of which has its causes, consequences and repercussions. The paper aims to look at the struggle for food which Katniss and Dale confront to take care of their families written in the language of the future. The words which the author has coined for the future and the shades of meaning that they give are also highlighted
AI-Powered HRM and Finance Information Systems for Workforce Optimization and Employee Engagement
No full textThis comprehensive analysis examines the implementation and impact of AI-powered Human Resource Management (HRM) and Finance Information Systems in government organizations, focusing on workforce optimization and employee engagement. The study, drawing from extensive research across multiple public sector entities, reveals that organizations implementing these systems achieve significant improvements in operational efficiency, with processing times reduced by 47.2% and budgetary allocation accuracy increased by 31.4%. Through analysis of implementation data from 156 federal agencies, the research demonstrates how AI-driven solutions address key challenges in regulatory compliance, budget constraints, and operational transparency. The investigation encompasses four core functional areas: intelligent recruitment, workforce planning, employee experience enhancement, and financial management integration, supported by machine learning algorithms and cloud infrastructure. The results show significant progress in every area, including a noteworthy 56.8% decrease in hiring bias, a 41.3% increase in staff retention, and an 82.6% accuracy rate in document classification
DYNAMIC GENERATIVE RESIDUAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR ELECTRICITY THEFT DETECTION
No full textIllegal electricity users pose a significant threat to the economic and security aspects of the power system by illicitly accessing or manipulating electrical resources. With the widespread adoption of Advanced Metering Infrastructure (AMI), researchers have turned to leveraging smart meter data for electricity theft detection. However, existing models rely on methods that model a single electricity load curve and cannot capture the temporal dependencies, periodicity, and underlying features between electricity consumption cycles. This study introduces a novel electricity theft detection method based on dynamic residual graph networks. Innovatively, it proposes a dynamic topological graph construction technique that allows for the real-time updating of adjacency matrices during the training process, thereby effectively capturing the complex relationships in electricity usage patterns. Utilizing the MixHop graph convolutional network, it delves into the temporal sequence dependencies, periodicity, and hidden characteristics within user electricity consumption data. Additionally, to address the issue of model instability caused by scarce theft data, we employ the SMOTE (Synthetic Minority Over-sampling Technique) oversampling technique and enhance overall classification performance by modifying class weights in the loss function. We trained this network architecture on the real SGCC (State Grid Corporation of China) dataset, and the results demonstrate its superiority over other mainstream existing models
The RELATIONSHIP OF ATTITUDE AND PERFORMANCE IN MATHEMATICS OF THE BEED AND BSE STUDENTS
No full textThis study aimed to determine if the attitude toward mathematics of BSE and BEED students in DMMMSU NLUC is significantly correlated to their Mathematics performance. Specifically, it seeks answers to the following questions: What is the profile of the students enrolled in Mathematics along sex, CAT Result in Mathematics and IQ level. What is the attitude of students towards Mathematics? What is performance of the respondents in Mathematics? Is there a significant relationship between profile variables and attitude towards Mathematics profile variables and performance in Mathematics, attitude toward Mathematics and Mathematics performance? Which among the variables are predictors of Mathematics performance? What action plan can be proposed to enhance the level of performance and attitude of the students in Mathematics?
This study utilized the descriptive method of investigation. This is best fitted to the study because this method involves describing, recording, analyzing and interpreting conditions that exist. It also includes some forms of comparison and contrast and discovers relationship between existing non-manipulative variables. The respondents are two classes enrolled in Basic Mathematics and Contemporary Mathematics for the SY 2014-2015. Their attitude towards Mathematics were obtained using an attitude inventory, their IQ and CAT Math results were obtained from the Guidance Office and their performance were taken from their final grade in Mathematics. The attitude of students toward Mathematics and their performance in Mathematics were described, analyzed, compared, and interpreted. Mean was used to describe the attitude and performance in Mathematics. Furthermore, the relationship of the aforementioned variables will be obtained. Hence, the use of statistics of correlation under descriptive method was also used.
The following are the salient findings of this study: Majority of the Mathematics students are females with fair to good performance in the Math CAT and IQ level. The students have positive to highly positive attitude towards Mathematics. The students have very good performance in Mathematics.IQ and CAT performance are significantly correlated with Mathematics performance. CAT significantly correlates with attitude and attitude is significantly correlated with Mathematics performance.
In the light of the above-stated findings, the following conclusions are drawn: The Math classes are dominated with females who have only fairly satisfactory to satisfactory IQ levels and performance in the CAT along Mathematics. A greater majority of the students find mathematics enjoyable, interesting and fun. Most of the students have acquired the needed competencies in Mathematics. They are good in computation, comprehension and problem solving. Those who have high IQ and high CAT results perform excellently in Mathematics. The better is the attitude towards Mathematics the higher is the performance in the subject. Attitude has a positive impact of performance in Mathematics.
Based on the conclusions, the researcher offered the following recommendations: Teachers are encouraged to customize their instruction and improve the use of modernized and innovative teaching techniques and strategies to enhance performance and attitude of students toward Mathematics. The Mathematics teachers especially the Math Club Adviser should consider the implementation of the Action Plan to improve attitude and performance in Mathematics. The administrators should support the implementation of the Action Plan by providing the opportunities and logistics for its accomplishment. The Action Plan should be considered for adoption by other HEIs in La Union with the administrators and Head of Mathematics Department planning its mechanics of implementation. A research on the effectiveness of the proposed action plan when implemented be conducted as basis for revisions and improvement
SUB CLASS OF HARMONIC UNIVALENT FUNCTIONS WITH INTEGRAL OPERATOR
No full textThis paper introduced a new class of harmonic univalent function defined by an integral operator. Additionally study investigates some properties of this subclass such as essential as well as adequate coefficient bounds, extreme points, distortion bounds and hadamard product
PREDICTION OF TYPE 2 DIABETES USING LOGISTIC REGRESSION TECHNIQUES: Prediction of Type 2 Diabetes
No full textAbstract
Diabetes is recognized as a significant public health concern and a global epidemic. It is a chronic condition resulting from insufficient insulin production by the pancreas. The long-term elevated blood sugar levels associated with diabetes lead to chronic damage and impaired function in multiple tissues, such as the eyes, kidneys, heart, blood vessels, and nerves.
The objective of this study is to demonstrate the utilization of machine-learning algorithms, specifically logistic regression, in predicting an individual\u27s likelihood of having diabetes based on medical data. Furthermore, the study aims to develop a prediction model that determines whether a patient has diabetes by analyzing specific diagnostic measurements included in the dataset. Various techniques will be explored to enhance the performance and accuracy of the prediction model.
Results: The logistic regression algorithm for the dataset containing various patient data, found that the algorithm predicted whether people would be diagnosed with diabetes with an 82 percent success rate