Rapid technological advancements are altering people’s communication styles. With the growth of the Internet, social networks (Twitter, Facebook, Telegram, and Instagram) have become popular forums for people to share their thoughts, psychological behavior, and emotions. Psychological analysis analyzes text and extracts facts, features, and important information from the opinions of users. Researchers working on psychological analysis rely on social networks for the detection of depression-related behavior and activity. Social networks provide innumerable data on mindsets of a person’s onset of depression, such as low sociology and activities such as undergoing medical treatment, a primary emphasis on oneself, and a high rate of activity during the day and night. In this paper, we used five machine learning classifiers—decision trees, K-nearest neighbor, support vector machines, logistic regression, and LSTM—for depression detection in tweets. The dataset is collected in two forms—balanced and imbalanced—where the oversampling of techniques is studied technically. The results show that the LSTM classification model outperforms the other baseline models in the depression detection healthcare approach for both balanced and imbalanced data.
8 February 2024 in International Journal of Machine Learning and Cybernetics
The online banking system is the new trend in the developing digital world. The transferring of a large amount of currency in a millisecond is leading to fast accessing of the banking system as it saves more time at the online payment and digital shopping. The increase in rate of use of banking credit and debit card leads to a large amount of fraud in the field of finance. Machine learning has the new discovering faces in the field of the finance. So, this research work proposed a hybrid model using the logistic regression, multilayer perceptron, and the XgBoost. The study involves both the balance and imbalance dataset to conclude the result based on the accuracy precision and recall. The results show that accuracy of the model is 100%, and precision, recall, and F1-scores are 95.63%, 99.99%, and 97.76% respectively.
It is a web and cellular-based app designed commonly for use in the meals & beverage enterprise. These apps solve the problems of labour cost in the restaurants and food court resulting in an increase in overall business. It also provides the owner to manage and make changes as per the requirements in the shop. The customer can order their food by accessing the food app through their mobile. The shopkeeper can easily complete the order in time, as there will be a regular check-in for the availability of ingredients. In this paper, we will be representing the overall description and software requirement specification of the entire system designed for use in different food courts. Our apps will provide the restaurant employees to manage their online menu and keep track of all the orders placed by their customers. The customers will be able to access the menu from anywhere so they can order their food and collect it immediately after it is ready. Inside this paper, we have depicted a general model of the framework, layouts of functional and non-functional prerequisites, and a definite portrayal of the UI. Eventually, this idea represents an account of the expansion of the device alongside predicted protection.
1 January 2020 in International Journal of e-Collaboration
Blockchain and Internet of Thing (IoT) has been widely used to impart constructive and smart healthcare services to the community. Blockchain technology has also invaded complete facet of information communications technology (ICT) and it has been growing and growing in today's fast paced world. Use of Blockchain Technology will increase the certainty and efficiency of electronic healthcare records (EHRs). The data mining approaches and machine learning algorithms assist in predicting the chronic disorders in patient thereby helping in the identification of the patient's treatment. This article provides a survey of the state of art in this domain. The key features, as well as the challenges of the various approaches, have been analyzed. A novel methodology to overcome the existing limitations has been proposed for future work and research. This proposed framework will make the data aggregations much easier to save and for decision-making. The function of alerting to caretakers and to inform hospital in critical condition will make this system new and unique.