Browsing by Author "Sharma, Bidyut"

Now showing 1 - 3 of 3

Depression Detection in Social Media Comments Data Using Machine Learning Algorithms
(Institute of Electrical and Electronics Engineers Inc., 2023-04-15) Vasha, Zannatun Nayem; Sharma, Bidyut; Esha, Israt Jahan; Nahian, Jabir Al; Polin, ohora Akter
Depression is the next level of negative emotions. When a person is in a sad mood or going through a difficult situation and it is not leaving him and giving him pain continuously and he is unable to bear it anymore, that situation is called depression. The last stage of depression occurs in suicide. According to the World Health Organization (WHO), Currently, 4.4% of people in the world are currently suffering from depression. In 2021, fourteen thousand people committed suicide all over the world and the rating of suicide is increasing day by day. So, our study is to find depressed people by their comments, posts, or texts on social media. We collected almost 10,000 data from Facebook posts, comments, and YouTube comments. Data mining and machine learning (ML) algorithms make our work easier and play a big role in easily detecting a person’s emotions. We applied six classifiers to predict depression & non-depression and found the best accuracy on a support vector machine (SVM).
Depression Detection in Social Media Comments Data Using Machine Learning Algorithms
(Daffodil International University, 23-02-18) Vasha, Zannatun Nayem; Sharma, Bidyut; Esha, Mst. Israt Jahan
Nowadays, depression is a common and dangerous mental problem for our society, the country even the whole world. When a person is in a heartbreaking mood or going through an exquisite condition and it is not leaving him, trying to live alone, and giving him pain continuously is called depression. The last stage of depression is killing himself. According to WHO, currently,4.4 of people worldwide suffer from depression. Many depressed people die almost every day. So, we will generate a model to find out who is suffering from depression and who is not. And finding depression is quite easy through our model. We collected huge data from Facebook, YouTube, and social media for the buildup models and learn to model and machine. Here we applied six classifiers to detect depression such as SVM, DT, LR, KNN etc. And when we are searching for which classifier gives the best accuracy then we see that the Support Vector Machine gives the best accuracy and which is 75%.
Tomato Pest Recognition Using Convolutional Neural Network in Bangladesh
(Institute of Electrical and Electronics Engineers Inc., 2024-02-01) Polin, Johora Akter; Hasan, Nahid; Habib, Md. Tarek; Rahman, Atiqur; Vasha, Zannatun Nayem; Sharma, Bidyut
The tomato is one of the most popular and well-liked veggies among Asians. It is interesting to note that in Bangladesh, it is the second most significant vegetable consumed. Moreover, tomato is served not only as a vegetable, but it is also served as sauce, jam, etc., and used in making different types of cuisines. But the fact is due to the pests, thousands of tons of tomatoes are harmed every year in Bangladesh. The production of tomatoes in Bangladesh is harmed by a number of dangerous pests. We develop a solution to recognize pests at an early stage. Five different pest types, including aphids, red spider mites, whiteflies, looper caterpillars, and thrips, have been studied in this research. To identify tomato pests, we curated image datasets from online and offline repositories and processed them using a convolutional neural network (CNN) model. We used features from CNN layers for three machine learning algorithms: Random Forest (RF), support vector machine (SVM), and K-Nearest Neighbors (K-NN). This comprehensive approach allowed a thorough comparison of these algorithms in tomato pest recognition. For recognizing tomato pests, our methods generate excellent results. The accuracy of our experiment is 95.49% which indicates the successful completion of the experiment.