Transactions on Machine Learning and Artificial Intelligence https://journals.scholarpublishing.org/index.php/TMLAI <p>Transactions on Machine Learning and Artificial Intelligence is peer-reviewed open access online journal that provides a medium of the rapid publication of original research papers, review articles, book reviews and short communications covering all areas of machine learning and artificial Intelligence. The journal publishes state-of-the-art research reports and critical evaluations of applications, techniques and algorithms in machine learning, artificial intelligence, cognitive science, software engineering, database systems, soft computing, optimization and modelling and related application areas.</p> en-US tmlai@scholarpublishing.org (Thomas Harvey) tmlai@scholarpublishing.org (Olivia Adam) Wed, 01 May 2019 00:00:00 +0000 OJS 3.1.1.4 http://blogs.law.harvard.edu/tech/rss 60 Population-Based Algorithms Applied to Brain-Computer Interfaces upon Steady-State Visual Evoked Potentials https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6215 <p class="AbsKeyBibli">The development of brain-computer interfaces based upon steady-state visual evoked potentials (SSVEP) requires the processing of electroencephalogram signals to detect brain activity triggered on the occipital region of the scalp caused by visual stimuli. Different algorithms based on stochastic and analytical processes have been proposed. However, most of them involve complex transformations and are highly susceptible to local errors. The present work presents algorithms based upon population to optimize the dimensionality of the characteristics of electroencephalogram signals focusing on SSVEP. Population-based algorithms are substantiated on the collective behavior of individuals observed in nature, such as flocks of birds, fish populations and some microorganisms, in order to find optimal solutions. This work shows the algorithms of optimization of particle swarm optimization, ant colony optimization, genetic algorithm and differential evolution algorithms in order to generate an optimum subset of features that improves the identification of features of electroencephalogram signals. Spectral Density of Power, Spectral Coherence methods and the computational cost between these algorithms are presented as measure of comparison.</p> Marco Antonio Aceves-Fernandez, Santiago M. Fernandez-Fraga, José Emilio Vargas Soto, Juan Manuel Ramos Arreguín ##submission.copyrightStatement## https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6215 Wed, 01 May 2019 00:06:08 +0000 Collaborative Integration of Bioinformatics Knowledge Management System and Mobile Wireless Devices https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6203 <p>Knowledge Management System (KMS) currently becomes a common medium to distribute knowledge by using the Information Technology (IT) as enabler tools for everyone to reach, share with among the members, and used it from any workplace in the world at any time. In the context of bioinformatics community of practice (CoP) is also has opportunities to leverage and share their knowledge with collaborative technology to create, gather, access, organize, distribute and disseminate the knowledge among them for various purposes such as learning process, research and development (R&amp;D) and others. This paper describes on the theoretical concepts and approach of integrating mobile wireless devices into Bioinformatics KMS that could be implemented in institution by demonstrating on how the framework of KMS model that is developed using relevance software. The achievement of conducting mobile wireless devices into Bioinformatics KMS framework is an added value for the CoP in the institution that needs to implement the Bioinformatics KMS, which can help them to achieve their aims and mission statements. The emphasis also will be given to the activities for each stage in the KM life cycle including the critical success factor (CSF) in order to make sure that Bioinformatics KMS initiatives will deliver competitive advantage to the CoP in the institutions.</p> Fahad Omar Alomary ##submission.copyrightStatement## https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6203 Wed, 01 May 2019 00:06:08 +0000 A New Indexing Method for Uncertain Databases https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6234 <p><span style="font-family: Calibri; font-size: medium;">This paper presents an indexing method called the uncertain data index (UD-index) for uncertain databases. The design objectives of the UD-index are improving the range query performance of the multidimensional indexing methods and providing a compromise between optimal index node clustering. Although more than ten years of database research has resulted in a great variety of multidimensional indexing methods, most efforts have focused on the data-level clustering and there has been no attempt to cluster index nodes themselves in dynamic environments. As a result, most related index nodes are widely scattered on the disk due to dynamic page allocation, and it requires many random disk accesses during the range search. The UD-index avoids that by storing the related nodes contiguously in a segment that contains a sequence of contiguous disk pages. The UD-index improves the range query performance by offering high-performance sequential disk access within a segment. A new cost model is introduced to estimate the range query performance. It takes into consideration the physical adjacency of pages read as well as the number of pages accessed. The analytic performance analysis indicates that the UD-index shows better performance than the traditional indexing methods in most cases. </span></p> Guang-Ho Cha ##submission.copyrightStatement## https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6234 Wed, 01 May 2019 00:06:09 +0000 Analysis on Reported Cases of HIV at Ekiti State University Teaching Hospital, Ado-Ekiti, South-Western Nigeria https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6333 <p>The nation Nigeria has been ranked the second among the nations of world with largest population of people with HIV. This information does not mean that every region and state in the country is not safe. Ekiti, a state in the south western part of the country has the lowest rate, which this study aims at establishing scientifically. Considering certain risk factors, such as age, gender and the local government area of the individuals tested, it is found out that none of the factors is significantly contributing to having or not having HIV in the state at 5% of significance. The parameter estimates obtained using the binary logistic regression are very low, the lack of fit test and the model test show that the factors are not good for modelling HIV cases in Ekiti state, thereby corroborating the fact that the state has lowest rate in Nigeria.</p> Isaac O. Ajao, Kayode S. O. Ibikunle ##submission.copyrightStatement## https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6333 Wed, 01 May 2019 00:06:09 +0000 Demonstration of Machine Learning Capabilities on Internet of Things Devices https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6447 <p>Since the problem definition mentioned in the title of this paper is very broad it was narrowed down to temperature sensing using the IoT device and demonstrating the machine learning capabilities using the TensorFlow with the Python libraries. The data was started collecting starting 1:45 PM and collected till 6:00 PM. As the temperature in India starts cooling down from 2:00 till the evening, we should be getting down-ward slope i.e temperature starts tapering down. It is clearly linear regression problem where the slope is down-ward as we proceed further in time line. If we start collecting the data in the morning and collect till after-noon we should again get the linear regression model however this time the temperature increases as we proceed in the time line till 2:00 PM.</p> Abhinandan H. Patil ##submission.copyrightStatement## https://journals.scholarpublishing.org/index.php/TMLAI/article/view/6447 Wed, 01 May 2019 00:06:09 +0000