Writer Identification Based on Hand Writing using Artificial Neural Network

Humans are social beings who depend on social interaction. Social interaction that is often used is communication. Communication is one of the bridges to connect social relations between humans. Communication can be delivered in two ways, namely verbal or nonverbal. Handwriting is an example of nonverbal communication using paper and writing utensils. Each individual's writing has its own uniqueness so that handwriting often becomes the character or characteristic of the author. The handwriting pattern usually becomes a character for the writer so that people who recognize the writing will easily guess the ownership of the related handwriting. However, handwriting is often used by irresponsible people in the form of handwriting falsification. The acts of writing falcification often occur in the workplace or even in the field of education. This is one of the driving factors for creating a reliable system in tracking someone's handwriting based on their ownership. In this study, we will discuss the identification of a person's handwriting based on their ownership. The output of this research is in the form of ID from the author and accuracy in the form of percentage of system reliability in identifying. The results of this study are expected to have a good impact on all parties, in order to minimize plagiarism. Identification of handwriting to be built consists of two main processes, namely the training phase and the testing phase. At the training stage, the handwritten image is subjected to several processes, namely threshold, wavelet conversion, and then will be trained using the Backpropagation Artificial Neural Network. In the testing phase, the process is the same as in the training phase, but at the end of the process, a comparison will be made between the image data that has been stored during training with a comparison image. Backpropagation ANN can work optimally if it is trained using input data that has determined the size, learning rate, parameters, and the number of nodes on the network. It is expected that the offered method can work optimally so that it produces an accurate percentage in order to minimize handwriting falcification.

Body text

Body text: Typography and the corporeality of literature In one of his fragments, Georg Christoph Lichtenberg explains that German books printed with roman type, instead of the then default gothic type, always give him a feeling that he needs to translate them – evidence, he says, of “the degree to which our concepts are dependent on these signs”. The article elaborates on this thought. It explores the relation between literature, text (abstract and material), and typography, and argues – by means of bibliographical theory, Goethe’s mother, Jean-Luc Nancy, Roman Ingarden, and a diagnostic comparison between hand writing and digital fonts – that the longstanding, idealistic view, within literary criticism and history, of texts’ ‘content’ as independent of books’ and texts’ materiality and form, obstructs scholars’ striving for understand-ing. Text is not only representation; it is also presentation. Text has form, and the form produces meaning.

Textile-Based Humidity-Driven Wearable Electroluminescent for Visual Sensing

Miniaturization and integration have become a trend of modern wearable intelligent electronics. But how to visualize sensing information in a single-level device remains a challenge. Here, we present a humidity-driven textile-based electroluminescent (EL) interactive display that allows for both sensing and visualization of humidity changes. Based on an interdigitated EL structure, a transparent humidity sensor layer with high humidity sensitivity was creatively introduced on the top-emitting layer as a bridging electrode. The visualization and sensing of humidity can be attributed to the electrical conductivity difference of the sensor layer, thus leading to the varied lighting emitting of EL devices on the application of given electric fields. Benefiting from the highly sensitive sensor layer and well-designed device structure, a variety of humidity-based behavior can be read immediately, including hand-writing and finger approach. Furthermore, our devices fabricated from textiles have great flexibility, breathability, and skin affinity, which is very suitable for human wearing. More importantly, this humidity-driven textile-based EL interactive display shows great application potential in breathing monitoring and health assessment.

An adiabatic method to train binarized artificial neural networks

An artificial neural network consists of neurons and synapses. Neuron gives output based on its input according to non-linear activation functions such as the Sigmoid, Hyperbolic Tangent (Tanh), or Rectified Linear Unit (ReLU) functions, etc.. Synapses connect the neuron outputs to their inputs with tunable real-valued weights. The most resource-demanding operations in realizing such neural networks are the multiplication and accumulate (MAC) operations that compute the dot product between real-valued outputs from neurons and the synapses weights. The efficiency of neural networks can be drastically enhanced if the neuron outputs and/or the weights can be trained to take binary values $$\pm 1$$ ± 1 only, for which the MAC can be replaced by the simple XNOR operations. In this paper, we demonstrate an adiabatic training method that can binarize the fully-connected neural networks and the convolutional neural networks without modifying the network structure and size. This adiabatic training method only requires very minimal changes in training algorithms, and is tested in the following four tasks: the recognition of hand-writing numbers using a usual fully-connected network, the cat-dog recognition and the audio recognition using convolutional neural networks, the image recognition with 10 classes (CIFAR-10) using ResNet-20 and VGG-Small networks. In all tasks, the performance of the binary neural networks trained by the adiabatic method are almost identical to the networks trained using the conventional ReLU or Sigmoid activations with real-valued activations and weights. This adiabatic method can be easily applied to binarize different types of networks, and will increase the computational efficiency considerably and greatly simplify the deployment of neural networks.

A Treatment-Response Comparison Study of Resting-State Functional Magnetic Resonance Imaging Between Standard Treatment of SSRI and Standard Treatment of SSRI Plus Non-dominant Hand-Writing Task in Patients With Major Depressive Disorder

Background: Researches have recently shifted from functional/structural imaging studies to functional connectivity (FC) studies in major depressive disorder (MDD). We aimed to compare treatment response of two treatment groups before and after treatment, in terms of both with psychiatric evaluation scales and resting-state functional connectivity (RSFC) changes in order to objectively demonstrate the possible contribution of the non-dominant hand-writing exercise (NHE) effect on depression treatment.Methods: A total of 26 patients who were right-handed women with similar sociodemographic characteristics were enrolled. Their pre-treatment resting-state functional magnetic resonance imaging (rs-fMRI) and neuropsychiatric tests were recorded, and then, patients were divided into two groups randomly. A standard treatment (ST) (fix sertraline 50 mg/day) was given to both groups. One randomly selected group was given the NHE in addition to the ST. After 8 weeks of treatment, all patients were reevaluated with rs-fMRI and neuropsychiatric tests. Pre- and post-treatment FC changes within the groups and post-treatment connectivity changes between groups were evaluated.Results: Post-treatment neuropsychiatric tests were significantly different in both groups. Post-treatment, two brain regions' connectivity changed in the ST group, whereas 10 brain regions' connectivity changed significantly in the ST + NHE group. When treatment groups were compared with each other after the treatment, the FC of 13 regions changed in the ST + NHE group compared to the ST group (p-unc/p-PFD <0.05). The density of connectivity changes in the frontal and limbic regions, especially connectivities shown to change in depression treatment, in the ST + NHE group indicates a positive contribution to depression treatment, which is also supported by neuropsychiatric scale changes.Conclusion: NHE, which we developed with inspiration from the Eye Movement Desensitization and Reprocessing (EMDR) method, showed significantly more connecitivity changes related with MDD treatment. Beyond offering a new additional treatment method, our study will also contribute to the current literature with our efforts to evaluate all brain regions and networks that may be related to MDD and its treatment together, without being limited to a few regions.Trial Registration: The rs-fMRI and treatment registers were recorded in the BizMed system, which is the patient registration system of Bezmialem Vakif University Medicine Faculty, under the BAP support project approval code and the registration number 3.2018/8.

Developing a Learning Module About Integers for 7th Grade Students through Writing-to-Learn

Previous research shows that seventh-grade students lack a sense of flexibility about numbers, lack comprehension of the effect of the operation on numbers, and lack estimation skills. On the other hand, writing to learn is one of the learning activities where the students actively write to express themselves in learning specific material/topic. This project aims to develop a learning module for students about the integers by utilizing the basic number sense framework: the six strands of number sense (Mcintosh et al., 1997) and combining it using writing to learn mathematics (Burns, 1995). The module developed using the steps proposed by Purwanto (2007) and then validated by the experts and tested to the subjects’ trial. The module was then validated by three experts who are lecturers at Sampoerna University. After validation, the module was then tested on four seventh-grade students, where the data gathered by both observation and group interview. As a result, all participants agree that the learning module is easier than what they taught at school and would recommend the module to their friends.