Automatic Transformation Research Articles

Neural Transformation from Retinotopic to Background-Centric Coordinates in the Macaque Precuneus.

Visual information is initially represented in retinotopic coordinates and later in craniotopic coordinates. Psychophysical evidence suggests that visual information is further represented in more general coordinates related to the external world; however, the neural basis of non-egocentric coordinates remains elusive. This study investigates the automatic transformation from egocentric to non-egocentric coordinates in the macaque precuneus (two males, one female), identified by a functional imaging study as a key area for non-egocentric representation. We found that 6.2% of neurons in the precuneus have receptive fields anchored to the background rather than to the retina or the head, while 16% had traditional retinotopic receptive fields. Notably, these two types were not exclusive: many background-centric neurons initially encode a stimulus's position in retinotopic coordinates (up to ∼90 ms from stimulus onset) but later shift to background coordinates, peaking at ∼150 ms. Regarding retinotopic information, the stimulus dominated the initial period, whereas the background dominated the later period. In the absence of a background, there is a dramatic surge in retinotopic information about the stimulus during the later phase, clearly delineating two distinct periods of retinotopic encoding: one focusing on the figure to be attended and another on the background. These findings suggest that the initial retinotopic information of the stimulus is combined with the background retinotopic information in a subsequent stage, yielding a more stable representation of the stimulus relative to the background through time-division multiplexing.Significance Statement According to psychological literature, the location of visual stimuli is automatically positioned against the background of a scene. This representation relative to the background, not being influenced by eye movements, should be important for stabilizing the visual world. A human functional imaging study suggested that the precuneus in the medial cerebral cortex is a strong candidate. This study recorded neural activity from the precuneus of monkeys and demonstrated the existence of background-centered cells with receptive fields fixed relative to the background.

Exposure to angiotensin-converting enzyme inhibitors that cross the blood-brain barrier and the risk of dementia among People Living with HIV.

The decreased mortality of people living with HIV (PLWH) has revealed non-HIV-associated comorbidities such as neurocognitive disorders (e.g., dementia). There is an urgency to discover therapeutics to prevent or delay neurocognitive decline among PLWH. The artificial intelligence platform Automatic Graph-mining And Transformer based Hypothesis Generation Approach (AGATHA) was utilized to seek potential drugs to be repurposed for the management of non-HIV-associated dementia. AGATHA revealed angiotensin-converting enzyme inhibitors that cross the blood-brain barrier (BBB ACEi) as a target for decreasing dementia. Subsequently, we conducted a retrospective study evaluating incident dementia using the VA Informatics and Computing Infrastructure (VINCI) evaluating ACE inhibitors. Cox proportional hazards models were fit and hazard ratios (HR) with corresponding 95% confidence intervals (CIs) are presented. A total 9,419 PLWH exposed to an BBB ACE inhibitor (ACEi) and 8,831 PLWH unexposed demonstrated that PLWH exposed to BBB ACEi had a 21.4% (univariate) and 15.2% (multivariate) lower hazard of dementia. The propensity score matched analysis demonstrated a 14.3% lower hazard of incident dementia compared to BBB ACEi unexposed (HR 0.857, 95% CI 0.747-0.984). An artificial intelligence-based literature mining system (AGATHA) was utilized to uncover a medication with potential to be repurposed. AGATHA demonstrated that BBB ACEi as a target for decreasing dementia among PLWH. Additionally, we conducted a retrospective study demonstrating a decrease in incident dementia among PLWH exposed to BBB ACEi. Future research is needed to explore further and understand the relationship of dementia among PLWH exposed to ACEi.

Temporally Coherent Video Cartoonization for Animation Scenery Generation

The automatic transformation of short background videos from real scenarios into other forms with a visually pleasing style, like those used in cartoons, holds application in various domains. These include animated films, video games, advertisements, and many other areas that involve visual content creation. A method or tool that can perform this task would inspire, facilitate, and streamline the work of artists and people who produce this type of content. This work proposes a method that integrates multiple components to translate short background videos into other forms that contain a particular style. We apply a fine-tuned latent diffusion model with an image-to-image setting, conditioned with the image edges (computed with holistically nested edge detection) and CLIP-generated prompts to translate the keyframes from a source video, ensuring content preservation. To maintain temporal coherence, the keyframes are translated into grids and the style is interpolated with an example-based style propagation algorithm. We quantitatively assess the content preservation and temporal coherence using CLIP-based metrics over a new dataset of 20 videos translated into three distinct styles.

Automatic Audio and Image Caption Generation with Deep Learning

A novel approach to image caption generation tailored specifically for visually impaired individuals. The proposed system employs advanced computer vision algorithms to analyze images and generate descriptive textual captions. Furthermore, it integrates seamless text-to-speech conversion functionality, allowing for the automatic transformation of these captions into spoken audio, thereby enabling access to visual content for individuals with visual impairments. The goal of this project is to generate descriptive captions for a given photograph or image. We achieve this by employing Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models, both of which are advanced deep learning techniques. Using computer vision, the system identifies the content of the image and generates a relevant caption. This caption is then converted into audio using Natural Language Processing (NLP).

ARLP: Automatic multi-agent transformer reinforcement learning pruner for one-shot neural network pruning

Overparameterized Neural Networks demonstrate state-of-the-art performance; however, the escalating demand for more compact and energy-efficient neural networks has arisen to facilitate the deployment of machine learning applications on devices with limited computational resources. A prevalent approach employs various pruning techniques. However, hyperparameters, such as the pruning ratio for each layer in pruning techniques, are typically set by human experts and often lack optimization. In this paper, we therefore propose a novel method named “Automatic Multi-Agent Transformer Reinforcement Learning Pruner” (ARLP). ARLP leverages a transformer-based multi-agent reinforcement learning controller to autonomously prune networks at initialization by extracting network meta-features. This autonomous process eliminates the need for human intervention in determining the optimal pruning ratio for each layer. The meta-features are derived from various zero-cost pruning-at-initialization proxies to perform One-shot Pruning. Extensive experimental results demonstrate that ARLP outperforms other state-of-the-art methods, establishing its efficacy in achieving superior performance.

Modeling and Verification of Natural Language Requirements based on States and Modes

The relationship between states (status of a system) and modes (capabilities of a system) used to describe system requirements is often poorly defined. The unclear relationship could make systems of interest out of control because of the out of boundaries of the systems caused by the newly added modes. Formally modeling and verifying requirements can clarify the relationship, making the system safer. To this end, an innovative approach to analyzing requirements is proposed. The MoSt language (a Domain Specific Language implemented on the Xtext framework) is firstly designed for requirements modeling and a model validator is realized to check requirements statically. A code generator is then provided to realize the automatic model transformation from the MoSt model to a NuSMV model, laying the foundation for the dynamic checks of requirements through symbolic model checking. Next, a NuSMV runner is designed to connect the NuSMV with the validator to automate the whole dynamic checks. The grammar, the model validator, the code generator, and the NuSMV runner are finally integrated into a publicly available Eclipse-based tool. Two case studies have been employed to illustrate the feasibility of our approach. For each case study, we injected 14 errors. The results show that the static and dynamic checks can successfully detect all the errors.

Neural Machine Translation for Low-Resource Languages from a Chinese-centric Perspective: A Survey

Machine translation—the automatic transformation of one natural language (source language) into another (target language) through computational means—occupies a central role in computational linguistics and stands as a cornerstone of research within the field of Natural Language Processing (NLP). In recent years, the prominence of Neural Machine Translation (NMT) has grown exponentially, offering an advanced framework for machine translation research. It is noted for its superior translation performance, especially when tackling the challenges posed by low-resource language pairs that suffer from a limited corpus of data resources. This article offers an exhaustive exploration of the historical trajectory and advancements in NMT, accompanied by an analysis of the underlying foundational concepts. It subsequently provides a concise demarcation of the unique characteristics associated with low-resource languages and presents a succinct review of pertinent translation models and their applications, specifically within the context of languages with low-resources. Moreover, this article delves deeply into machine translation techniques, highlighting approaches tailored for Chinese-centric low-resource languages. Ultimately, it anticipates upcoming research directions in the realm of low-resource language translation.

An algebraic approach to simulation and verification for cyber-physical systems with shared-variable concurrency

Cyber-Physical systems (CPS), containing discrete behaviors of the cyber and continuous behaviors of the physical, have gained wide applications in many fields. Since CPS subsume the intersection of cyber systems and physical processes, the traditional modeling languages which merely include discrete variables are no longer applicable to CPS. Accordingly, a shared variable language called CPSLsc was proposed to specify CPS. In this paper, we elaborate the algebraic semantics for this language, so that every program of CPSLsc can be converted into a unified form called guarded choice form and the sequentialization of parallel programs is achieved. Additionally, we formalize the algebraic semantics in the rewriting engine Real-Time Maude. With the algebraic laws constructed, for every program specified with CPSLsc, we can simulate its execution step by step. Furthermore, automatic transformation and execution are attained. As a consequence, if the program and its initial data state are provided, the corresponding trace of data states during execution can be generated. In the light of the generated trace, automatic verification can be carried out as well.

Transformer Fault Condition Prognosis Using Vibration Signals Over Cloud Environment

he Automatic Area Transformer Fault Message Indicator is an innovative system designed to detect and report faults in transformers. It utilizes potential and current transformers, precision rectifiers, and sensors to monitor high/low voltage, current, frequency, and transformer temperature. The data is processed by a microcontroller, displayed on an LCD, and transmitted to the electric utility station via GSM, enabling timely identification and communication of transformer issues for efficient maintenance and grid reliability. This system offers several key benefits. First, its use of advanced sensors and precision rectifiers ensures accurate measurement of critical parameters, allowing for early detection of potential faults. Keywords—GSM, Step down transformer, potential and current transformer, Temperature sensor.

Correction to: Performance analysis of smart grid distribution system using global EV charging station as smart load based on automatic variac transformer

Correction to: Performance analysis of smart grid distribution system using global EV charging station as smart load based on automatic variac transformer

Hypertuned temporal fusion transformer for multi-horizon time series forecasting of dam level in hydroelectric power plants

This paper addresses the challenge of predicting dam level rise in hydroelectric power plants during floods and proposes a solution using an automatic hyperparameters tuning temporal fusion transformer (AutoTFT) model. Hydroelectric power plants play a critical role in long-term energy planning, and accurate prediction of dam level rise is crucial for maintaining operational safety and optimizing energy generation. The AutoTFT model is applied to analyze time series data representing the water storage capacity of a hydroelectric power plant, providing valuable insights for decision-making in emergency situations. The results demonstrate that the AutoTFT model surpasses other deep learning approaches, achieving high accuracy in predicting dam level rise across different prediction horizons. Having a root mean square error (RMSE) of 2.78×10−3 for short-term forecasting and 1.72 considering median-term forecasting, the AutoTFT shows to be promising for time series prediction presented in this paper. The AutoTFT had lower RMSE than the adaptive neuro-fuzzy inference system, long short-term memory, bootstrap aggregation (bagged), sequential learning (boosted), and stacked generalization ensemble learning approaches. The findings underscore the potential of the AutoTFT model for improving operational efficiency, ensuring safety, and optimizing energy generation in hydroelectric power plants during flood events.

Optimal voltage set-point of automatic tap changer transformers and generators and reactive power compensation to increase power system predictability

In recent years, renewable energy sources (RESs) such as wind turbines (WTs) have received much attention in both the operating and planning of power systems. These sources have caused many uncertainties in the operation of power systems due to their unpredictable nature. Mentioned uncertainties besides load demands uncertainty, and possible failures in power system components, make the system state unpredictable. The operational decisions are completely challenging in these situations. Any efforts to increase the network operator awareness from the system state will be completely valuable for making accurate decisions.This paper tries to increase the predictability of the power system state through optimal regulating of the voltage setpoint of automatic tap changer transformers and generators besides the reactive power of shunt capacitors. However, conventional objectives such as decreasing losses are considered, simultaneously. This paper uses the K-medoids data clustering method to evaluate the effect of uncertainties. Also, the correlation between input uncertain variables is considered and handled by the Cholesky decomposition technique combined with the Nataf transformation technique. The multi-objective optimization problem is tackled using an improved version of the non-dominated sorting genetic algorithm (NSGA-II). To ensure for validity of the results, studies are repeated using the multi-objective particle swarm optimization (MOPSO) algorithm as another evolutionary-based method.The proposed approach is applied to the IEEE 14 and 30 bus standard system. The results showed that the predictability of the power system can be considerably increased while keeping the losses approximately at its minimum amount.

Automatic transformation of polarization state of light in void medium

Abstract Customized polarization state of light plays a pivotal role in numerous scientific domains. Under normal circumstances, light always maintains its polarization state during transmission in void medium or the free space. However, in this work, we have observed that the polarization state of a light beam can be automatically transformed during the propagation without involving a waveplate or scattering of air. The beam changes polarization states at different distances in the free space propagation. Moreover, while polarization states can be preset at different distances, the intensity and phase of the light beam can also be independently designed. The mechanism behind this phenomenon is due to the superposition and diffraction of the controlled light beams. The phenomenon paves the way for applications of constructing key devices, e.g. optical isolator, and offers a broader range of possibilities for applications such as tunable structured devices, optical diodes, and so on.

Unsupervised motion artifact correction of turbo spin-echo MRI using deep image prior.

In MRI, motion artifacts can significantly degrade image quality. Motion artifact correction methods using deep neural networks usually required extensive training on large datasets, making them time-consuming and resource-intensive. In this paper, an unsupervised deep learning-based motion artifact correction method for turbo-spin echo MRI is proposed using the deep image prior framework. The proposed approach takes advantage of the high impedance to motion artifacts offered by the neural network parameterization to remove motion artifacts in MR images. The framework consists of parameterization of MR image, automatic spatial transformation, and motion simulation model. The proposed method synthesizes motion-corrupted images from the motion-corrected images generated by the convolutional neural network, where an optimization process minimizes the objective function between the synthesized images and the acquired images. In the simulation study of 280 slices from 14 subjects, the proposed method showed a significant increase in the averaged structural similarity index measure by 0.2737 in individual coil images and by 0.4550 in the root-sum-of-square images. In addition, the ablation study demonstrated the effectiveness of each proposed component in correcting motion artifacts compared to the corrected images produced by the baseline method. The experiments on real motion dataset has shown its clinical potential. The proposed method exhibited significant quantitative and qualitative improvements in correcting rigid and in-plane motion artifacts in MR images acquired using turbo spin-echo sequence.

Towards Automatic Transformations of Coq Proof Scripts

Towards Automatic Transformations of Coq Proof Scripts

Towards the Automatic Transformation of the SIMULINK Model into an FPGA-in-Loop System and its Real-Time Simulation

Towards the Automatic Transformation of the SIMULINK Model into an FPGA-in-Loop System and its Real-Time Simulation

Big data-based digital management system for the whole process of financial reporting in SMEs

Abstract Based on big data technology, this paper designs a digital management system for the whole process of financial reimbursement and gives the automatic transformation process of digitalization of financial reimbursement claims and accounting documents. In the K-Means algorithm, the AHC algorithm idea is introduced to construct the DH-K-Means clustering algorithm, which in turn enables the financial reimbursement behavioral portrait of enterprise employees to be constructed. To confirm the effectiveness of the system application in this paper, performance testing and portrait analysis were carried out. The results show that the maximum memory utilization of the database server is 50.42% when the number of concurrent users is 100, and the average response time of the system reaches a maximum of 825.63ms when the number of concurrent users is 200. Based on big data, the whole process of financial reporting digital management system has good stability, which can make enterprises more aware of their financial situation and then develop appropriate financial reimbursement strategies.

DBSCAN-based line density clustering algorithm for CAD architectural drawings

In the traditional architecture industry, architects often need to convert CAD drawings into BIM in order to express the final effect of the building more concretely and to understand whether the design of each profession is reasonable after the drawings are completed. The whole modeling process is boring and tedious, and due to human fatigue, the final result is prone to problems, which eventually leads to failure to meet expectations. In order to free architects from the tedious task of model transformation, companies have designed software for automatic model transformation using computers. The core of the software design is related to computational geometry. Line segment clustering is one of the elements of computational geometry and a frequent problem in programming. Appropriate clustering of line segments can often bring convenience to the problem. This paper combines the basic idea of the DBSCAN algorithm, improves the shortcomings of DBSCAN algorithm in dealing with line segment clustering, and proposes a density-based line clustering algorithm with shapely library as a tool. The algorithm is highly interpretable, and the method performs well and efficiently in the test of actual drawings, whether to group the line segments or to find the target line segments that meet the conditions, which provides convenience for the subsequent calculation.

Transpiler-Based Architecture Design Model for Back-End Layers in Software Development

The utilization of software architectures and designs is widespread in software development, offering conceptual frameworks to address recurring challenges. A transpiler is a tool that automatically converts source code from one high-level programming language to another, ensuring algorithmic equivalence. This study introduces an innovative software architecture design model that integrates transpilers into the back-end layer, enabling the automatic transformation of business logic and back-end components from a single source code (the coding artifact) into diverse equivalent versions using distinct programming languages (the automatically produced code). This work encompasses both abstract and detailed design aspects, covering the proposal, automated processes, layered design, development environment, nest implementations, and cross-cutting components. In addition, it defines the main target audiences, discusses pros and cons, examines their relationships with prevalent design paradigms, addresses considerations about compatibility and debugging, and emphasizes the pivotal role of the transpiler. An empirical experiment involving the practical application of this model was conducted by implementing a collaborative to-do list application. This paper comprehensively outlines the relevant methodological approach, strategic planning, precise execution, observed outcomes, and insightful reflections while underscoring the the model’s pragmatic viability and highlighting its relevance across various software development contexts. Our contribution aims to enrich the field of software architecture design by introducing a new way of designing multi-programming-language software.

A color image decomposition model for image enhancement

The primary goal of image decomposition is to decompose an observed image into several independent components, which can be further manipulated to carry out more complex tasks effectively. Existing image decomposition methods apply a decomposition model either to each of the three channels separately in RGB color space, or to the intensity channel only in other color spaces, which leads to color error or unintuitive display. To address these issues, this paper proposes a color image decomposition model that acts directly on color images and yields visually piecewise smoothing base information, low/high contrast detail information, and rich color information. Specifically, the color information with characteristics of spherical geometry is separated by a spatial transformation at first. Then, the separation of base and detail information from a given image is achieved by combining low-rank approximation and the relative total variation with no artifacts. After yielding the three components via our decomposition model, we exploit the automatic arc tangent transformation and the visual saliency principle to implement two applications, contrast enhancement and infrared image fusion, respectively. We demonstrate the remarkable performance of our method through a reasonable qualitative and quantitative analysis of the experimental results.