Capacitive touch sensors capture the two-dimensional spatial profile (referred to as a touch heatmap) of a finger's contact with a mobile touchscreen. However, the research and design of touchscreen mobile keyboards -- one of the most speed and accuracy demanding touch interfaces -- has focused on the location of the touch centroid derived from the touch image heatmap as the input, discarding the rest of the raw spatial signals. In this paper, we investigate whether touch heatmaps can be leveraged to further improve the tap decoding accuracy for mobile touchscreen keyboards. Specifically, we developed and evaluated machine-learning models that interpret user taps by using the centroids and/or the heatmaps as their input and studied the contribution of the heatmaps to model performance. The results show that adding the heatmap into the input feature set led to 21.4% relative reduction of character error rates on average, compared to using the centroid alone. Furthermore, we conducted a live user study with the centroid-based and heatmap-based decoders built into Pixel 6 Pro devices and observed lower error rate, faster typing speed, and higher self-reported satisfaction score based on the heatmap-based decoder than the centroid-based decoder. These findings underline the promise of utilizing touch heatmaps for improving typing experience in mobile keyboards.

The whole idea of QWERTY is about spreading the most often used characters over the keyboard space in order to avoid malfunctions. This means this layout is not optimized in terms of typing time and yet it is still widely used nowadays by convention. However, the issues it addressed back then are no longer and the non-optimality of this layout is an issue for digital devices. For example, writing on a phone with one finger is harder than it should be with QWERTY. In this regard, here we propose novel keyboard layouts that address this particular issue of reducing the writing time.

Anna Maria Feit (feit@cs.uni-saarland.de) is a professor at Saarland University, Germany. This work was done while a researcher at Aalto University and ETH Zurich, Switzerland. Mathieu Nancel is a research scientist in the Loki research group at Inria Lille–Nord Europe; Lille, France. Maximilian John is a researcher at Max Planck Institute for Informatics, Saarbrücken, Germany. Andreas Karrenbauer is a senior researcher at Max Planck Institute for Informatics.

My son has grown up using a MacBook Air for Minecraft. He swears by the keyboard layout, and having witnessed the blazing speed with which he does things in the game, I understand his reluctance to use his Alienware laptop. Both machines are almost six years old and due a refresh, so I'm looking for a Windows laptop that is powerful enough to run games like Civilization 6 (with mods) but with a keyboard layout that is sufficiently similar to a MacBook that he can continue to use the muscle memory he has built up over the years. Does such a beast exist? One alternative is to buy a MacBook Pro and use it to run Windows (either Bootcamp or Parallels), but the Windows performance strikes me as a compromise (for more money).

Tunde Adegbola, born 1 August 1955, also known as T. A. or Uncle T, is a scientist, musician, engineer, linguist and culture activist. He is best known for his work in setting up most of the pioneering private Television and Radio stations in Nigeria. He is the founder of TIWA systems, and the Executive Director of Alt-i (African Languages Technology Initiative). Tunde completed a bachelor's degree in Electrical Engineering at the University of Lagos, and later specialized in broadcast technology. He subsequently obtained a master's degree in Computer Science from the University of Wales (Swansea).

In this paper we present an optimal Bangla Keyboard Layout, which distributes the load equally on both hands so that maximizing the ease and minimizing the effort. Bangla alphabet has a large number of letters, for this it is difficult to type faster using Bangla keyboard. Our proposed keyboard will maximize the speed of operator as they can type with both hands parallel. Here we use the association rule of data mining to distribute the Bangla characters in the keyboard. First, we analyze the frequencies of data consisting of monograph, digraph and trigraph, which are derived from data wire-house, and then used association rule of data mining to distribute the Bangla characters in the layout. Finally, we propose a Bangla Keyboard Layout. Experimental results on several keyboard layout shows the effectiveness of the proposed approach with better performance.