Many machine learning algorithms have been introduced to solve different types of problems. Recently, many of these algorithms have been applied to deep architecture models and showed very... Show More

Many machine learning algorithms have been introduced to solve different types of problems. Recently, many of these algorithms have been applied to deep architecture models and showed very impressive performances. In general, deep architecture models suffer from the over-fitting problem when there is a small number of training data. In this article the attempt is made to remedy this problem in deep architecture with regularization techniques including overlap pooling and flipped image augmentation and dropout; the authors also compared a deep structure model (convolutional neural network (CNN)) with shallow structure models (support vector machine and artificial neural network with one hidden layer) on a small dataset. It was statistically confirmed that the shallow models achieved better performance than the deep model that did not use a regularization technique. Faces represent complex multidimensional meaningful visual stimuli and developing a computational model for face recognition is difficult. The authors present a hybrid neural-network solution which compares favorably with other methods.

Predicting valence and arousal values from EEG signals has been a steadfast research topic within the field of affective computing or emotional AI. Although numerous valid techniques to predict... Show More

Predicting valence and arousal values from EEG signals has been a steadfast research topic within the field of affective computing or emotional AI. Although numerous valid techniques to predict valence and arousal values from EEG signals have been established and verified, the EEG data collection process itself is relatively undocumented. This creates an artificial learning curve for new researchers seeking to incorporate EEGs within their research workflow. In this article, a study is presented that illustrates the importance of a strict EEG data collection process for EEG affective computing studies. The work was evaluated by first validating the effectiveness of a machine learning prediction model on the DREAMER dataset, then showcasing the lack of effectiveness of the same machine learning prediction model on cursorily obtained EEG data.

In many smart city projects, a common choice to capture spatial information is the inclusion of lidar data, but this decision will often invoke severe growing pains within the existing... Show More

In many smart city projects, a common choice to capture spatial information is the inclusion of lidar data, but this decision will often invoke severe growing pains within the existing infrastructure. In this article, the authors introduce a data pipeline that orchestrates Apache NiFi (NiFi), Apache MiNiFi (MiNiFi), and several other tools as an automated solution to relay and archive lidar data captured by deployed edge devices. The lidar sensors utilized within this workflow are Velodyne Ultra Puck sensors that produce 6-7 GB packet capture (PCAP) files per hour. By both compressing the file after capturing it and compressing the file in real-time; it was discovered that GZIP and XZ both saved considerable file size being from 2-5 GB, 5 minutes in transmission time, and considerable CPU time. To evaluate the capabilities of the system design, the features of this data pipeline were compared against existing third-party services, Globus and RSync.

In the countries or areas where the supply-demand ratio of blood is not maintained, the medication process is being deteriorated, and this may be as fatal as death of the patients. It is being... Show More

In the countries or areas where the supply-demand ratio of blood is not maintained, the medication process is being deteriorated, and this may be as fatal as death of the patients. It is being observed in different areas in different seasons or may be at the time of festival scarcity of blood may happen. On the other hand, if the blood donation camp is organized frequently, there may be a surplus of blood as it has expiry dates. Along with these issues, due to the transportation or mismanagement, blood units are wasted. These problems are addressed in this research work, and methodologies are proposed to determine the most suitable blood bank with respect to the blood donation camp. Further, a demand forecasting algorithm is used both for predicting the blood unit demand of every blood bank and for transferring excess blood units to the blood bank where it is needed the most, and also, for the efficient transportation of the blood units, taxicab geometry-based paths are employed.

Students' academic performance is a critical issue as it decides his/her career. It is pivotal for the educational institutes to track the performance record because it can help to enhance the... Show More

Students' academic performance is a critical issue as it decides his/her career. It is pivotal for the educational institutes to track the performance record because it can help to enhance the standard of their quality education. Thus, the role of the academic result prediction system comes into existence which uses semester grade point average (SGPA) as a metric. The proposed work aims to create a model that can forecast the SGPA of students based on certain traits. It predicts the result in the form of SGPA of computer science students considering their past academic performance, study, and personal habits during their academic semester using different machine learning models, and to compare them based on different accuracy parameters. Some models that are widely used and are found effective in this field are regression algorithms, classification algorithms, and deep learning techniques. The results conclude that deep learning techniques are the most effective in the proposed work because of their high accuracy and performance, depending upon the attributes used in the prediction.

Maintenance and complexity issues in software development continue to increase because of new requirements and software evolution, and refactoring is required to help software adapt to the changes.... Show More

Maintenance and complexity issues in software development continue to increase because of new requirements and software evolution, and refactoring is required to help software adapt to the changes. The goal of refactoring is to fix smells in the system. Fixing architectural smells requires more effort than other smells because it is tangled in multiple components in the system. Architecture smells refer to commonly used architectural decisions that negatively impact system quality. They cause high software coupling, create complications when developing new requirements, and are hard to test and reuse. This paper presented a tool to analyze the causes of architectural smells such as cyclic dependency and unstable dependency and included a priority metric that could be used to optimize the smell with the most refactoring efforts and simulate the most cost-effective refactoring path sequence for a developer to follow. Using a real case scenario, a refactoring path was evaluated with real refactoring execution, and the validity of the path was verified.