Transactions on Machine Learning and Artificial Intelligence <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> Services for Science and Education, United Kingdom en-US Transactions on Machine Learning and Artificial Intelligence 2054-7390 Document Image Forgery Detection Using RGB Color Channel <p> </p> <p class="SSEAbstract"><strong><span lang="EN-US">Using advanced digital technologies and photo editing software, document images, such as typed and handwritten documents, can be manipulated in a variety of ways. The most common method of document forgery is adding or removing information. As a result of the changes made to document images, there is misinformation and misbelief in document images. Forgery detection with multiple forgery operations is challenging issue. As a result, special consideration is given in this work to the ten-class problem, in which a text can be altered using multiple forgery types. The characteristics are computed using RGB color components and GLCM texture descriptors. The method is effective for distinguishing between genuine and forged document images. A classification rate of 95.8% for forged handwritten documents and 93.11% for forged printed document images are obtained respectively. The obtained results are promising and competitive with state-of- art techniques reported in the literature.</span></strong></p> Shivanand S. Gornale Gayatri Patil Rajkumar Benne Copyright (c) 2022 Shivanand S. Gornale, Gayatri Patil, Rajkumar Benne 2022-09-24 2022-09-24 10 5 1 14 10.14738/tmlai.105.13126 Catchment Area Multi-Streamflow Multiple Hours Ahead Forecast Based on Deep Learning <p><strong>Modeling of rainfall-runoff is very critical for flood prediction studies in decision making for disaster management. Deep learning methods have proven to be very useful in hydrological prediction. To increase their acceptance in the hydrological community, they must be physic-informed and show some interpretability. They are several ways this can be achieved e.g. by learning from a fully-trained hydrological model which assumes the availability of the hydrological model or to use physic-informed data. In this work we developed a Graph Attention Network (GAT) with learnable Adjacency Matrix coupled with a Bi-directional Gated Temporal Convolutional Neural Network (2DGAT-BiLSTM). Physic-informed data with spatial information from Digital Elevation Model and geographical data is used to train it. Besides, precipitation, evapotranspiration and discharge, the model utilizes the catchment area characteristic information, such as instantaneous slope, soil type, drainage area etc. The method is compared to two different current developments in deep learning structures for streamflow prediction, which also utilize all the spatial and temporal information in an integrated way. One, namely Graph Neural Rainfall-Runoff Models (GNRRM) uses timeseries prediction on each node and a Graph Neural Network (GNN) to route the information to the target node and another one called STA-LSTM is based on Spatial and temporal Attention Mechanism and Long Short Term Memory (LSTM) for prediction. The different methods were compared in their performance in predicting the flow at several points of a pilot catchment area. With an average prediction NSE and KGE of 0.995 and 0.981, respectively for 2DGAT-BiLSTM, it could be shown that graph attention mechanism and learning the adjacency matrix for spatial information can boost the model performance and robustness, and bring interpretability and with the inclusion of domain knowledge the acceptance of the models.</strong></p> Divas Karimanzira Linda Ritzau Katharina Emde Copyright (c) 2022 Divas Karimanzira, Linda Ritzau, Katharina Emde 2022-09-29 2022-09-29 10 5 15 29 10.14738/tmlai.105.13049 Consumer Trust in B2C Ecommerce Strategy for Contemporary Business Transaction is Paramount for Sustaining the Emerging Commerce Market. Indicate the Similarities and Differences Between Traditional and Ecommerce Markets and Provide the Conduct of Consumer Trust Across Cultures, Globally <p><strong>E-Commerce has been going on since introduced the idea in 1995 when www was invented. Businesses / consumers that have been immersed in e-commerce transaction have reaped the benefits associated with such technological break-through, as consumers sit at comfort of their homes to transact business. However, the impediment that has hindered other businesses / consumers to transform to this technological business approach has been the trust associated with carrying out business; consumer trust across global cultures has been contentious. Authors, including Hofstede, Gefen et al. and Greenberg et al. have done research on culture differences across the globe and how these differences could affect behaviours towards accepting e-commerce for transacting business. There is therefore, the need for a global digital guideline / policy to protect all consumers and businesses that trade on the internet. Such a policy would hopefully allay the fears amongst nations’ cultures having difficulty in imbibing this wholesome technological advancement for enhanced business transaction. Conducting business transaction through brick-and-mortar approach is archaic and cumbersome and should be faded out completely.&nbsp; &nbsp;</strong></p> Francis Kwadade-Cudjoe Copyright (c) 2022 Francis Kwadade-Cudjoe 2022-09-29 2022-09-29 10 5 30 42 10.14738/tmlai.105.13170