Facial expression-based emotion detection is very attractive because of the possibilities in security systems, mental health monitoring, and human-computer interaction. Even with the progress in accuracy in real-world settings, issues such as the lack of balanced datasets and the inability to differentiate between faint or superimposed emotions continue to plague it. This study aims to bridge these constraints by developing a CNN-based model that would be able to recognize face emotions reliably and be utilized in real-time situations, such as webcam integration. The Affect Net dataset, which is a comprehensive collection of over a million facial photos labeled with the seven major emotions of anger, disgust, fear, happiness, neutrality, sadness, and surprise, was used to train the proposed model. Other pre-processing data techniques used include grayscale conversion, normalization, scaling, and data supplementation to increase the robustness of the model. Using metrics like accuracy and loss trends for evaluation, the model demonstrated efficiency stability at around the 30th training phase. When the model is compared to existing models, this proposed model can attain the competitive level of accuracy up to approximately 60%. It also has the potential to run in real applications through its webcam integration. While the model can differentiate between various clear-cut emotions, it becomes ineffective at identifying subtle emotions, which include “Fear” and “Neutral” majorly because of unbalanced data and the subtleness of these expressions.

Nowadays, we use emails almost in every field; there is not a single day, hour, or minute when emails are not used by people worldwide. Emails can be categorized into two types: ham and spam. Hams are useful emails, while spam is junk or unwanted emails. Spam emails may carry some unwanted, harmful information or viruses with them, which might harm user privacy. Spam mails are used to harm people by wasting their time and energy and stealing valuable information. Due to increasing in spam emails rapidly, spam detection and filtering are the prominent problems that need to be solved. This paper discusses various machine learning models like Naïve Bayes, Support Vector Machine, Decision Tree, Extra Decision Tree, Linear regression., and surveys about these machine learning techniques for email spam detection in terms of their accuracy and precision. In this paper, a comprehensive comparison of these techniques and stacking of different algorithms is also made based on their speed, accuracy, and precision performance.

Nowadays data analytics OLAP (online Analytical Processing) is mostly accepted domain of current researchers and the concept of data mining serves better for the same. There are so many data mining methodologies defined for data analytics. Mining Association rule is widely used in data mining methods for data categorization. Apriori Algorithm is popular method for defining n-element. Frequent item set form k number of huge transactional data set online transaction processing (OLP) using Association Mining rule (AMR). In this paper, researchers executed original Apriori on transactional data set containing 35039 number of transactions, divided into three data sets DS-1 to DS-3 with 20039, 12000, 5000 number of transactions with variable length with minimum support of 30%, 60% and 80% respectively. Researchers carried out experimental work and compared results of Apriori Algorithm with our proposed algorithm (enhanced version of Apriori algorithm) on the same perimeter and state improvement with 11%, 30% and 27% of Rate of Improvements in DS-1 to Ds-3 respectively for 30% minimum support. Our proposed algorithm is working far much better then Apriori algorithm at each parameter which was included to condude the results.

Question classification plays vital role in Question Answering (QA) systems. The task of classifying a question to appropriate class is performed to predict the question type of the natural language question. In this paper, initially we have presented a brief overview of classification approaches adapted by different question answering systems so far and then propose a two-way question classification approach for higher education domain which not only identifies focus word and question class but also reduces answer search space within corpus comprise of question-answer pair, adding to the classification accuracy. For precise semantic interpretation of domain keywords, a domain specific dictionary is constructed which primarily have four domain word type. Classified features are built upon domain attributes in the form of constraints. The experiment proved the efficiency for restricted domain, even though we used quite simplistic approach.