Volume-12 Issue-3, September 2023 – International Journal of Recent Technology and Engineering (IJRTE)

C78600912323

IJRTE Journal — Sat, 30 Sep 2023 11:35:59 +0000

AI Curriculum Design for Korea K-12 AI Education Through Analyzing AI Education Curriculum
Dong Hwa Kim
Dong Hwa Kim, DSTSC (Daeduck S&T Social Cooperation, S. Korea.

Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: This paper deals with the curriculum design of Korean K-12 AI education. AI is the core technology of the 4th wave, and its impact is broad and strong. Therefore, every country has a robust nurturing system for AI talent. However, there are few materials available about curriculum design and operational experience documentation because AI has been an area of interest since 2016, and its educational applications are relatively new. In Korea, a program for teacher manpower education was initiated in 2020. Therefore, there is a lack of manpower with experience in designing and operating the K-12 AI curriculum. The AI curriculum is a core parameter for AI manpower. Therefore, AI-advanced countries are attempting to develop AI education methods. This paper analyses the K-12 AI curricula of advanced countries and then designs and suggests Korea’s K-12 AI curriculum.

Keywords: Computer Education, AI, AI Curriculum, K-12, AI Education.
Scope of the Article: AI

Download PDF

The post C78600912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78970912323

IJRTE Journal — Fri, 29 Sep 2023 07:34:02 +0000

Assessing Transfer Learning Models for Medical Image Classification: A Comparative Study on Alzheimer’s MRI, Chest CT-Scan, and Chest X-ray Images
Ryan Marcus Jeremy M. Lupague¹, Romie C. Mabborang², Alvin G. Bansil³, Melinda M. Lupague⁴
¹Ryan Marcus Jeremy M. Lupague, Department of Mathematics, Pamantasan ng Lungsod ng Maynila (University of the City of Manila), Manila, Philippines.

²Romie C. Mabborang, Department of Mathematics, Pamantasan ng Lungsod ngMaynila (University of the City ofManila),Manila, Philippines.

³Prof. Alvin G. Bansil, Department of Mathematics, Pamantasan ng Lungsod ngMaynila (University of the City ofManila),Manila, Philippines.

⁴Melinda M. Lupague, Department of Mathematics, Pamantasan ng Lungsodng Maynila (University of the City of Manila),Manila, Philippines.

Abstract: Deep learning has revolutionized the field of neural network models, offering limitless applications in various domains. This study focuses on Transfer Learning (TL), a technique leveraging pre-trained deep learning models trained on large datasets for image classification tasks. Specifically, this research explores the effectiveness of various transfer learning models in three medical image datasets: Alzheimer’s MRI images, Chest CT-Scan images, and Chest X-ray images. The main objective of this study is to assess and compare the performance of various TL models, including MobileNetV2, ResNet50, Xception, and InceptionV3, on the three medical image datasets. Additionally, a customised Convolutional Neural Network (CNN) model is developed to compare its performance with that of the pre-trained TL models. Each model was trained and evaluated on the three medical image datasets. The performance of the TL models was compared in terms of accuracy and training time. The results of this study revealed that ResNet50 consistently outperforms other TL models, demonstrating accurate predictions at the expense of longer training times. MobileNetV2 and InceptionV3 exhibit the fastest training times across all datasets, but they demonstrate poorer performance in specific datasets. The developed CNN model performs poorly in terms of accuracy and tends to overfit, indicating that creating a CNN model for medical image classification is not feasible in this study. The findings of this study offer valuable insights into the performance of TL models in medical image datasets. Researchers can utilize this information to make informed decisions when selecting TL models for medical imaging applications. Understanding the strengths and weaknesses of different TL models enhances the potential for accurate and efficient medical image classification. The insights gained from this study contribute to researchers’ understanding of selecting transfer learning models for medical imaging. aging applications, aiding in the advancement of medical image analysis and diagnosis.

Keywords: Convolutional Neural Networks, Deep Learning, Medical Image Classification, Transfer Learning Models, ResNet50.
Scope of the Article: Deep Learning

Download PDF

The post C78970912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C79030912323

IJRTE Journal — Fri, 29 Sep 2023 07:27:42 +0000

Thermodynamic Study of Properties in Certain Binary Liquid Mixtures Containing Anisole with 2-Butoxyethanol at Different Temperatures (303.15K to 318.15K)
P. Mahesh¹, M. Bonju Babu², K. Poornima³, K. Samatha⁴
¹Mahesh. P, Department of Physics, Andhra University, Visakhapatnam (A.P), India.

²Dr. M. Bonju Babu, Department of Humanities and Basic Sciences, Wellfare Engineering College, Pinagadi, Visakhapatnam (A.P), India.

³K. Poornima, Department of Humanities and Basic Sciences, Wellfare Engineering College, Pinagadi, Visakhapatnam (A.P), India.

⁴K. Samatha, Department of Physics, Andhra University, Visakhapatnam (A.P), India.

Abstract: Comprehensive experimental investigations were carried out on density (ρ), viscosity (η), and ultrasonic velocity (u) for binary mixtures comprising Anisole and 2-Butoxyethanol within the temperature range of 303.15K to 318.15K, covering the complete range of mole fractions. These parameters were measured at intervals of 5K. Derived excess parameters, including acoustic impedance (ZE), intermolecular free length (LE f), molar volume (VEm), excess ultrasonic velocity (uE), and excess viscosity (ηE), were calculated to probe the molecular interactions present in the mixture. These excess parameters were correlated with temperature and mole fraction, revealing the complexity and nature of intermolecular interactions. Notably, the Arrhenius, Bingham, Eyring, Grunberg, Kurata, Nissan, and Tamura models were employed to validate the acquired empirical data theoretically. This study aims to offer invaluable insights into the thermodynamics and molecular dynamics that govern these binary liquid mixtures.

Keywords: Viscosity, Density, Ultrasonic Velocity, Excess Parameters, Molecular Interaction
Scope of the Article: Thermal Engineering

Download PDF

The post C79030912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78690912323

IJRTE Journal — Fri, 29 Sep 2023 07:19:06 +0000

Drilling Casing Design using Drilling Software at Well “Well X-01” Field “S”
KRT. Nur Suhascaryo¹, Sulistyorini Widi Hastuti², Eko Suyanto³
¹Dr. KRT. Nur Suhascaryo, Faculty of Mineral Technology, UPN “Veteran” Yogyakarta, Yogyakarta, Indonesia.

²Sulistyorini Widi Hastuti, Faculty of Mineral Technology, UPN “Veteran” Yogyakarta, Yogyakarta, Indonesia.

³Eko Suyanto, Drilling & Well Intervention, PT. Pertamina Hulu Rokan Zone 4, Prabumulih, Indonesia.

Abstract: Well “X-01” is a slant (J-Type) directional well and will be subjected to appropriate and technically qualified drilling casing planning to prevent problems such as burst, collapse, and tension that can cause increased internal and external pressure loads experienced by the casing. The methodology used in this research is a combination of document study and quantitative analysis in casing planning, utilising Drilling Software to account for the loading acting on the casing, which includes burst, collapse, tension, biaxial, and triaxial loads. Casing design planning for Well “X-01” is carried out by analysing the casing setting depth based on PPFG data, considering kick tolerance. Then, casing planning is carried out using Drilling Software. The results of drilling casing planning in Well “X-01” Field “S” using Drilling Software, five design routes were obtained, that is conductor casing using X-52 casing; 157.5 ppf, surface casing using K-55 casing; 94 ppf, intermediate casing using K-55 casing; 54.5 ppf, kick tolerance 32.55 bbls, production casing using K-55 casing; 40 ppf, kick tolerance 42.1 bbls, and production liner using K-55 casing; 23 ppf, kick tolerance 69.08 bbls. The safety factor of each route met API standards for the durability of the selected casing. In well “X”, casing planning can serve as a reference point in the casing design process stage, as optimal and safe results are achieved.

Keywords: Total Loss, Kick, Drilling Software
Scope of the Article: Automated Software Design and Synthesis

Download PDF

The post C78690912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78760912323

IJRTE Journal — Fri, 29 Sep 2023 07:13:23 +0000

Machine Learning Algorithms Based Non Alcoholic Fatty Liver Disease Prediction
Bindu Bhargavi Munukuntla¹, Mrutyunjaya S Yalawar²
¹Bindu Bhargavi Munukuntla, Department of Computer Science and Engineering, CMR Engineering College, Hyderabad (Telangana), India.

²Mrutyunjaya S. Yalawar, Assistant Professor, Department of Computer Science and Engineering, CMR Engineering College, Hyderabad (Telangana), India.

Abstract: Predicting early-stage liver diseases is an essential health-related research area, as it can facilitate the early detection of diseases and prompt effective remedies. The liver diseases are classified into different types, such as liver cancer, liver tumour, fatty liver, hepatitis, cirrhosis, etc. Non-Alcoholic Fatty Liver Disease is a kind of chronic disease for which rigorous prediction is quite tricky at early stages. The prediction of fatty liver disease plays a significant role in both treating the disease and preventing its associated health consequences. This paper presents Machine Learning Algorithms based Non Alcoholic Fatty Liver Disease (NAFLD) prediction. The primary objective of this project is to identify potential factors contributing to NAFLD using Machine Learning algorithms, including the Decision Tree (DT) classifier, Support Vector Machine (SVM) classifier, Random Forest (RF) classifier, and Logistic Regression (LR). Accuracy is a parameter used for evaluating performance analysis. The findings of this paper demonstrate that the random forest model accurately predicts the presence of non-alcoholic fatty liver disease in patients.

Keywords: Liver Disease, Classification, Machine Learning, NAFLD, Electronic Health Records.
Scope of the Article: Classification

Download PDF

The post C78760912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

A75770512123

IJRTE Journal — Fri, 29 Sep 2023 07:05:17 +0000

Efficient Descriptor of Histogram of Ridges Orientation Delineate for Fingernail
Abdullah Alzahrani

Abdullah Alzahrani, School of Electrical and Electronic Engineering, Taif University, Al Hawiyah, Taif 26571, KSA.

Abstract: Orientation, ridges, and edges are prominent features of fingernail structure. This paper proposes a local descriptor based on ridge orientation, called Histogram of Ridges Orientation Delineate (HROD), based on Edge Histogram Descriptor (EHDD). As humans perceive images by looking at edge features, Finger HROD utilizes this sensitivity. Before performing feature extraction, the HROD algorithm conducts a range of preprocessing steps, including resizing, filtering, enhancing, and segmenting images. After this, the ridges orientation delineate maps are obtained by selecting an orientation with the maximum edge magnitude for each pixel based on predefined orientations. This study utilised five oriented edge maps to generate and detect the maximum edge orientations of each block: vertically, horizontally, diagonally at 45°, diagonally at 135°, and isotropically (non-orientation-specific). The results of experiments conducted on fingernail images demonstrate that the performance of HROD is similar to that of advanced orientation-based methods such as the Gabor filter, histogram of oriented gradients, and local directional code. Additionally, the HROD algorithm being suggested offers the benefits of minimal feature complexity and quick execution, making it ideal for a real-time system designed to recognize fingernail orientations.

Keywords: Edge Histogram Descriptor (EHD), Histogram of Ridges Orientation Delineate (HROD), Edge Orientation; Bit-Point (BP); Vertical Edge Orientation; horizontal Edge Orientation; Diagonal Edge; Non-Edge Orientation (Isotropic).
Scope of the Article: Internet of Things (IoT) & IoE & Edge Computing

Download PDF

The post A75770512123 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78650912323

IJRTE Journal — Fri, 29 Sep 2023 06:58:29 +0000

FPGA Based Efficient OFDM Based Design and Implementation for Data and Image Transmission for Healthcare
Vasanth Kumar T. R
Vasanth Kumar T R, Department of Electrical Communication Engineering, AMD, Bangalore (Karnataka) India.

Abstract: Enormous growth in the telecommunication industry demands high-speed data transmission with better quality of service (QOS). Telecommunication networks offer services with speeds ranging from 1 Mbps to several megabits per second (Mbps). However, most existing techniques aim to ensure very high-speed data for multimedia communication. Multimedia data may have suitable applications in a healthcare system. The OFDM modulation technique promises to provide multimedia services at a relatively high speed using a spectrum more efficiently compared to traditional schemes like TDMA and FDMA. The orthogonality of carriers eliminates interference among closely packed carriers, offering a comparatively efficient bandwidth. The OFDM design requires selecting proper parameters. An essential feature of OFDM is that multipaths are effectively eliminated by choosing higher cyclic prefix values, which yields significant results but causes more energy loss. This paper presents an efficient design for an OFDM transceiver using an FPGA. The design is modelled and simulated using MATLAB Simulink. Finally, the design is coded using Verilog RTL and simulated in ModelSim. Synthesis and implementation are performed using the Xilinx EDA tool. The image type of data is taken for transmission in the proposed OFDM transceiver system. The received image type data achieves a PSNR value of 29.920, and the binary input data achieves a 36.06% improvement in power utilisation and less area overhead. The paper also demonstrates improvements in area and power compared to existing authors.

Keywords: FPGA, High Speed, OFDM, Power Optimization, Healthcare.
Scope of the Article: Healthcare Informatics

Download PDF

The post C78650912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78610912323

IJRTE Journal — Fri, 29 Sep 2023 06:53:46 +0000

Zigbee based Wireless Sensor Network for Smart Energy Meter
Pratham Sharma

Pratham Sharma, Department of Electronics Engineering Aligarh Muslim University, Aligarh (U.P) India.

Abstract: Wireless sensor networks are expanding across a wide range of application scenarios. The most widely used transmitter is “ZigBee,” which is used in wireless sensor networks. Based on the IEEE standard known as IEEE 802.15.4, ZigBee is an enabling low-cost technology that offers minimal energy consumption and a low data rate. It is used for remote control, medical aid, home automation, industry control, and other wireless sensor applications, in addition to wireless sensor networks and personal area network applications. This paper aims to develop a wireless sensor network and a protocol for innovative energy meter applications. Our proposed system comprises a digital energy meter, a ZigBee coordinator, and a management application. A terminal alert and a cover alarm can be automatically sent to the management software by the wireless meter reading system once it has read the unit. Mistakes from Errors in leakage metering reading to manual meter reading can be avoided. This proposed system will improve efficiency by reducing labour intensity, thereby liberating labour and resources. The system setup can accommodate a large number of energy meters with sufficient hop network depth to automatically detect new energy meters. The technology can be widely used in wireless monitoring and control applications due to its low cost, low power consumption, extended battery life, and mesh networking’s ability to provide high reliability over a broader range. To connect a variety of low-power devices wirelessly, ZigBee will satisfy the rising demand. For the future generation of industrial technologies, ZigBee will be deployed.

Keywords: Wireless Sensor Network, ZigBee
Scope of the Article: Wireless Sensor Network

Download PDF

The post C78610912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78670912323

IJRTE Journal — Fri, 29 Sep 2023 06:48:33 +0000

Calibration Considering the Direction of Rotation for Contact Type Three-Dimensional Position-Measuring Instruments
Hirofumi Maeda
Hirofumi Maeda, Department of Information Science and Technology, National Institute of Technology (KOSEN), Yuge College, Ehime Prefecture, Japan.

Abstract: In Japan, the aging of sewage facilities due to longterm use has become a significant social issue. As a result, there has been a growing interest in portable and easy-to-operate standalone pipe inspection robots in recent years. However, the pipes being inspected not only have level differences due to joint connections but also pose a high risk of toppling over due to deterioration, collapses, and sludge caused by external disturbances. Many standalone robots address this issue by adjusting the tire shape and axle placement to suppress tipping. However, this method is intended for suppression, rather than complete prevention. Therefore, we are exploring a software-based approach to prevent tipping by controlling robot movement and aiming to achieve advanced self-position estimation. We are currently verifying this self-position estimation. However, due to the curved nature of the pipes, it is difficult to accurately measure the robot’s position and orientation using conventional measurement instruments. Thus, we have developed a specialised three-dimensional position measurement instrument for use with pipe inspection robots. Furthermore, although we performed calibration in the translational direction of the instrument, improvements in accuracy were observed in the translational direction; however, accuracy in the rotational direction deteriorated. In this paper, we propose a method to simultaneously calibrate the translational and rotational accuracy of the instrument to address this issue. We discuss the mechanism model, calibration parameters, elimination of redundant parameters by introducing redundancy, and parameter estimation using the Newton method. Additionally, through comparative validation utilising the instrument, we confirm that the position accuracy after calibration is within the range of approximately ±1.0 mm, and the orientation accuracy is within the range of roughly ±0.3 degrees. This demonstrates the effectiveness of the proposed method.

Keywords: Measuring Instrument, Calibration, Contact Type, Exploration Robot, Water Pipe
Scope of the Article: Robotics

Download PDF

The post C78670912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

C78620912323

IJRTE Journal — Fri, 29 Sep 2023 06:43:03 +0000

An Optimized and Privacy-Preserving System Architecture for Effective Voice Authentication over Wireless Network
Aniruddha Deka¹, Debashis Dev Misra²
¹Dr. Aniruddha Deka, Associate Professor, Department of Computer Science and Engineering, Assam Down Town University, Guwahati (Assam), India.

²Dr. Debashis Dev Misra, Associate Professor, Department of Computer Science and Engineering, Assam Down Town University, Guwahati (Assam), India.

Manuscript received on 13 July 2023 | Revised Manuscript received on 18 July 2023 | Manuscript Accepted on 15 September 2023 | Manuscript published on 30 September 2023 | PP: 1-9 | Volume-12 Issue-3, September 2023 | Retrieval Number: 100.1/ijrte.C78620912323 | DOI: 10.35940/ijrte.C7862.0912323

Abstract: The speaker authentication systems assist in determining the identity of a speaker in audio through distinctive voice characteristics. Accurate speaker authentication over wireless networks is becoming more challenging due to phishing attacks on the network. Multiple types of speech authentication models have been constructed for use in various applications where voice authentication is a primary focus for user identity verification. However, existing voice authentication models have some limitations related to accuracy and phishing attacks in real-time over wireless networks. In research, an optimised and privacypreserving system architecture for effective speaker authentication over a wireless network has been proposed to accurately identify the speaker’s voice in real-time and prevent phishing attacks over the network with greater accuracy. The proposed system achieved excellent performance metrics, with measured accuracy, precision, and recall, as well as an F1 score of 98.91%, 96.43%, 95.37%, and 97.99%, respectively. The measured training losses at epochs 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100 were 2.4, 2.1, 1.8, 1.5, 1.2, 0.9, 0.6, 0.3, 0.3, 0.3, and 0.2, respectively. Additionally, the measured testing losses for epochs 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100 were 2.2, 2.0, 1.5, 1.4, 1.1, 0.8, 0.8, 0.7, 0.4, 0.1, and 0.1, respectively. Voice authentication over wireless networks is a significant concern due to various phishing attacks and inaccuracies in voice identification. Therefore, this requires huge attention for further research in this field to develop less computationally complex speech authentication systems

Keywords: CNN, LSTM, Speaker Authentication, Privacy-Preserving, Phishing Assaults, Wireless Network.
Scope of the Article: Network Protocols & Wireless Networks

Download PDF

The post C78620912323 appeared first on International Journal of Recent Technology and Engineering (IJRTE).