Indian Journal of Computer Science

Skin cancer is the most common human malignancy according to American Cancer Society. It is primarily diagnosed visually, starting with an initial clinical screening and followed potentially by dermoscopic (related to skin) analysis, a biopsy and histopathological examination. Skin cancer occurs when errors (mutations) occur in the DNA of skin cells. The mutations cause cells to grow out of control and form a mass of cancer cells. The aim of this study was to try to classify images of skin lesions with the help of Convolutional Neural Networks. Deep neural networks show humongous potential for image classification while taking into account the large variability exhibited by the environment. Here, we trained images on the basis of pixel values and classified them on the basis of disease labels. The dataset was acquired from an Open Source Kaggle Repository (Kaggle Dataset) which itself was acquired from ISIC (International Skin Imaging Collaboration) archive. The training was performed on multiple models accompanied with Transfer Learning. The highest model accuracy achieved was over 86.65%. The dataset used is publicly available to ensure credibility and reproducibility of the aforementioned result.

Kartikeya Agarwal

Tismeet Singh

Classification of Skin Cancer Images Using Convolutional Neural Networks

基于卷积神经网络的皮肤癌图像分类

One of the common types of cancer is liver cancer, early detection and diagnosis of which are critical. Discovery, decision, and aggressive therapy can prevent most cancer deaths. We use data mining approaches (Convolutional Neural Networks) to build prediction models for liver cancer with the most widely used statistical analysis methodology. Around 579 records and 10 variables were included in the data collection. The model was built, evaluated, and compared using a k-fold cross-validation process. CNN was the best accurate predictor for this domain with a test set accuracy of 100%.

Sirajali Nagalpara

Bhavesh M. Patel

A Deep Learning Strategy for Predicting Liver Cancer Using Convolutional Neural Network Algorithm

使用卷积神经网络算法预测肝癌的深度学习策略

The rise of digital technology raises the importance of data security when transmitting data across a wireless communication medium. Steganography is a method of ensuring information security on a digital media. The goal of this work is to look at information hiding techniques in images which are in the spatial domain. This paper will also distinguish between watermarking and steganography, the two most popular domains of information concealment. The paper examines the benefits and drawbacks of existing algorithms, tools, and strategies to safeguard data in the digital image steganography domain.

Juhi Singh

Mukesh Singla

An Extensive Study of Digital Image Steganography Techniques

数字图像隐写术技术的广泛研究

For numerous times, numerous people have failed due to undetected conditions. Early discovery of these conditions at the micro bracket stage can be useful for furnishing proper treatment of the cases at an early stage and could have saved a lot of lives. A lot of exploration is being done to describe these conditions at the foremost. Thus, a computer-backed or Artificial Intelligence approach for detecting conditions at the early stage is being proposed, which makes use of machine, literacy and deep literacy algorithms for detecting conditions. This system will describe all general conditions similar to different types of cancer, malaria, diabetic retinopathy, etc. AI-Doc Helper is being proposed as there's no system available that detects all these general conditions.

Ranveer Kothavale

Archana P. Ekbote

AI Doc Helper

AI 文档助手

Internet shopping has become part and parcel of our day to day lives. Coupled with COVID-19 pandemic and the necessity to keep social distancing, many people have resorted to online shopping as a way of reducing potential exposure to the deadly virus. Online vendors have tried to follow the trends and put up online shops in unprecedented numbers. These myriad of alternatives have given room to unscrupulous vendors to also sneak in their products with an intention to defraud inexperienced online buyers. This massive number of online shops makes it impractical for an average user to assess with certainty which shop is trustworthy and which one is potentially fraudulent. In this study, we carry out a research to establish the indicators of trust in an e-commerce platform from the consumer perspective. We carry out a survey, focus group discussions and in-depth interview with a community within a public university to establish the factors they consider to conclude that an e-commerce platform is trustworthy or otherwise. We the use Exploratory Factor Analysis (EFA) and Principal Component Analysis (PCA) as our data analysis procedures. For EFA, we obtain uniqueness, factor loadings, scree plot, Eigen values, parallel analysis, optimal coordinates, and acceleration factor. For PCA, we obtain PCA Importance of Components, Loadings, Scree Plot, and biplot. We also obtain a Cronbach’ alpha of 0.959 which indicates reliable data. Further research will involve creating a model from these results which can be used as a trust adjustment factor for autonomous use in artificial intelligence driven recommender system in ecommerce platforms.

Edwin Ouma Ngwawe

Elisha Odira Abade

Stephen Nganga Mburu

Predicting Trustworthiness of an E-Commerce Platform from the Consumer Perspective

从消费者角度预测电子商务平台的可信度

M.N. Mangipudi

Sabarmathi G.

Data Analysis of Loan Defaulters Prediction Model Using Machine Learning Techniques

基于机器学习技术的贷款违约者预测模型数据分析

M. Arthi

V. P. Eswaramurthy

Convolution Neural Network Based Deep Learning Approach for MRI Based Brain Tumour Image Detection

基于卷积神经网络的深度学习方法用于基于MRI的脑肿瘤图像检测

V. Karpagavalli

G. Poornima

M. Sathya

Role of AI in Educational Sector With Reference to Tirupur

AI在蒂鲁布尔教育领域的角色

Madhavi Waghmare

Kaushik Raikar

Gaurav Phatkare

Rushikesh Parab

Vikram Shitole

Enhancing Driver Safety : Real-Time Distraction and Drowsiness Detection Using Deep Learning

出版信息	出版商: Associated Management Consultants, PVT., Ltd.，出版周期: ，期刊类型: journal，开源期刊: 否
基本数据	创刊年份: ，原创研究文献占比: ，自引率:， Gold OA占比:

Indian Journal of Computer Science

期刊引文格式

有 1 位以上作者的期刊

有 2 位作者的期刊

有 3 位作者的期刊

有 5 位以上作者的期刊

书籍引用格式

学位论文引用格式

网页引用格式

专利引用格式

手工熬夜修改参考文献？研飞自动匹配期刊，一键轻松成稿，支持 Word/WPS

投稿经验分享