Fraud detection holds significant importance in e-commerce transactions as it serves unauthorized activities like identity theft, account takeovers, and fraudulent transactions. Recently, machine learning algorithms have gained widespread adoption for fraud detection in e-commerce transactions. These algorithms function by discerning patterns within the data indicative of fraudulent behavior. Pattern detection entails identifying discriminative features in the data, such as irregular transaction amounts, locations, or behaviors deviating from a user's norm, by inputting into the machine learning model. In this research, four fundamental machine learning algorithms (decision tree, random forest, voting classifier) are employed for fraud detection in e-commerce transactions, utilizing a freshly curated dataset containing diverse features related to online shopping activities on Boyner Group's e-commerce platform and mobile app. This study contributes to the existing literature by experimenting with various machine learning classifiers and incorporating distinct features, diverging from prevailing methodologies in the field.

Keywords : Fraud Detection , e-Commerce, ML, AI, Feature Engineering.

Author : K Lakshmaiah , S Mohan Krishna , P DharmaTeja , N Charan Kumar , S Ganesh Kumar

Title : Fraud Detection on e-Commerce using Machine Learning Techniques

Volume/Issue : 2024;1(2 (April - June))

Page No : 01 - 05

Satellite imagery plays a vital role in various fields, including agriculture, urban planning, disaster management, and environmental monitoring. Efficient and accurate classification of satellite images is essential for extracting valuable information and making informed decisions. In this study, we propose the use of artificial intelligence techniques for satellite image classification. A comprehensive dataset of labelled satellite images is collected, representing different land cover types or objects of interest. The dataset is pre-processed to enhance the image quality, remove noise, and normalize the data. Data augmentation techniques such as rotation, scaling, and flipping are applied to increase the dataset size and improve the model's generalization ability. Future research directions may include exploring advanced deep learning architectures, such as attention mechanisms or graph neural networks, to further improve the classification performance. Additionally, the integration of multi-sensor satellite data and temporal analysis can enhance the capabilities of the classification models for dynamic monitoring and change detection applications.

Keywords : Satellite Imagery, AI, Image Classification, CNN, DL, Transfer Learning, Data Augmentation.

Author : K Lakshmaiah , V Umera Sulthana , N. Sujitha , S Ramya Sree , K Sravani

Title : Satellite Image Classification by using Artificial Intelligence

Volume/Issue : 2024;1(2 (April - June))

Page No : 06 - 13

To avoid fraudulent post for job in the internet, it is a one of the machine learning technique based on classification techniques is proposed in the project. Different classifiers are used for checking fraudulent post in the web and the results of those classifiers are compared for identifying the best employment scam detection model. It helps in detecting fake job posts from an enormous number of posts. The major classifier, such as ensemble classifiers are considered for fraudulent job posts detection. However, experimental results indicate that ensemble classifiers are the best classification to detect scams over the other classifiers.

Keywords : ML, Ensemble Classifier, Fake Job Post Detection , Random Forest.

Author : R Md Shafi , Reddem Janardhan Reddy , Kathi Harsha Vardhan , P Azharuddin , M Manohar

Title : Design and Implementation of Fake Job Post Detection using Machine Learning Techniques

Volume/Issue : 2024;1(2 (April - June))

Page No : 14 - 16

Preventing the spread of tuberculosis (TB) and enhancing patient outcomes are largely dependent on early detection. This presents a new method for detecting tuberculosis by utilizing convolutional neural networks to examine X-ray pictures of the chest. To extract and learn hierarchical information from x-ray images- a critical component for effective predictions the CNN’s architecture has been meticulously built. By examining the interpretability of the CNN model, the study sheds light on the characteristics and patterns that the network considers important when forming predictions. For medical professionals to trust the model and use it as a useful diagnostic tool, this feature is essential. Firstly, it outlines the limitations of conventional TB diagnostic methods, emphasizing the need for more accurate, efficient, and accessible solutions.

Keywords : Tuberculosis Detection, Chest X-Rays, Convolutional Neural Networks, Medical Imaging, Deep Learning.

Author : D N Keerthana , D Jayasree , V Jyothirmayee , C Jyoshna Reddy , S Ankitha

Title : Diagnosis of Tuberculosis using Deep Learning

Volume/Issue : 2024;1(2 (April - June))

Page No : 17 - 21

Breast cancer screening is a critical area of medical diagnostics, where the accuracy and performance of radiologists play a pivotal role in early detection and diagnosis. In this Project, we present a novel approach aimed at enhancing radiologists performance in breast cancer screening through the optimization of parameters for a Multi-Class Support Vector Machine (MSVM). We compare the results of our proposed method against an existing approach based on Deep Neural Networks (DNN) in terms of accuracy, specificity, and the types of cancer detected, including both benign and malignant cases. The existing method employs DNN as the primary algorithm, achieving an accuracy rate of 92.8%. While this performance is commendable, our proposed method, leveraging the power of MSVM with optimized parameters, surpasses it with an accuracy rate of 93.5%. The proposed DCNN architecture is designed to automatically learn discriminative features from mammography images. The model consists of multiple convolutional layers followed by pooling layers to extract hierarchical features. Additionally, batch normalization and dropout layers are incorporated to improve the generalization and robustness of the model.

Keywords : MSVM(Multi-Class Support Vector Machine),DNN, DCNN(Deep Convolution Neural Networks)

Author : D N Keerthana , Nandini Kakarakayala , Susmitha Kondapalli , Vydehi Chamiraju , Sahithya Kunchepu

Title : Breast Cancer Detection using DCNN and MSVM

Volume/Issue : 2024;1(2 (April - June))

Page No : 22 - 27