Robiul Islam

The aim of this work is to find a good mathematical model for the classification of brain states during visual perception with a focus on the interpretability of the results. To achieve it, we use the deep learning models with different activation functions and optimization methods for their comparison and find the best model for the considered dataset of 31 EEG channels trials. To estimate the influence of different features on the classification process and make the method more interpretable, we use the SHAP library technique. We find that the best optimization method is Adagrad and the worst one is FTRL. In addition, we find that only Adagrad works well for both linear and tangent models. The results could be useful for EEG-based brain–computer interfaces (BCIs) in part for choosing the appropriate machine learning methods and features for the correct training of the BCI intelligent system.

The graph coloring problem (GCP) is one of the most studied NP-HARD problems in computer science. Given a graph , the task is to assign a color to all vertices such that no vertices sharing an edge receive the same color and that the number of used colors, is minimal. Different heuristic, meta-heuristic, machine learning and hybrid solution methods have been applied to obtain the solution. To solve this problem we use mutation of evolutionary algorithm. For this purpose we introduce binary encoding for Graph Coloring Problem. This binary encoding help us for mutation, evaluate, immune system and merge color easily and also reduce coloring dynamically. In the traditional evolutionary algorithm (EA) for graph coloring, k-coloring approach is used and the EA is run repeatedly until the lowest possible is reached. In our paper, we start with the theoretical upper bound of chromatic number, that is, maximum out-degree + 1 and in the process of evolution some of the colors are made unused to dynamically reduce the number of color in every generation. We test few standard DIMACS benchmark and compare resent paper. Maximum results are same as expected chromatic color and few data sets are larger than expected chromatic number

In this paper, we are using EEG data to establish a relationship between channel and frequency band in terms of visual activity through the human brain. The idea behind this method is that we are using SHAP as a tool to know how those different components are connected. We find accuracy in between 87–98% for each user for three different observations: (i) All channel, (ii) left channel, (iii) Right channel; and for that basic relationship is established.

Nowadays there is a large amount of demographic data which should be analyzed and interpreted. From accumulated demographic data, more useful information can be extracted by applying modern methods of data mining. Two kinds of experiments are considered in this work: 1) generation of additional secondary features from events and evaluation of its influence on accuracy; 2) exploration of features influence on classification result using SHAP (SHapley Additive exPlanations). An algorithm for creating secondary features is proposed and applied to the dataset. The classifications were made by two methods, SVM and neural networks, and the results were evaluated. The impact of events and features on the classification results was evaluated using SHAP; it was demonstrated how to tune model for improving accuracy based on the obtained values. Applying convolutional neural network for sequences of events allowed improve classification accuracy and surpass the previous best result on the studied demographic dataset.

Social networks have developed as a promising point for everybody to communicate with their interested friend and share their opinions, photos, and videos. Also, it has been an upcoming research field and has picked an established position globally. In this paper, we considered depression problems among various Facebook users. Already, a number of researchers have studied and applied many techniques to detect depression, but still need to detect accurately from social network data. So, we investigate the possibility to utilize Facebook data and apply KNN (k-nearest neighbors) classification technique for detecting depressive emotions. We do believe that our investigation and approach might be helpful to raise consciousness in online social network users.