Computer Machine Research Articles

Recent Advances on Carbon-Based Metal-Free Electrocatalysts for Energy and Chemical Conversions.

Over the last decade, carbon-based metal-free electrocatalysts (C-MFECs) have become important in electrocatalysis. This field is started thanks to the initial discovery that nitrogen atom doped carbon can function as a metal-free electrode in alkaline fuel cells. A wide variety of metal-free carbon nanomaterials, including 0D carbon dots, 1D carbon nanotubes, 2D graphene, and 3D porous carbons, has demonstrated high electrocatalytic performance across a variety of applications. These include clean energy generation and storage, green chemistry, and environmental remediation. The wide applicability of C-MFECs is facilitated by effective synthetic approaches, e.g., heteroatom doping, and physical/chemical modification. These methods enable the creation of catalysts with electrocatalytic properties useful for sustainable energy transformation and storage (e.g., fuel cells, Zn-air batteries, Li-O2 batteries, dye-sensitized solar cells), green chemical production (e.g., H2O2, NH3, and urea), and environmental remediation (e.g., wastewater treatment, and CO2 conversion). Furthermore, significant advances in the theoretical study of C-MFECs via advanced computational modeling and machine learning techniques have been achieved, revealing the charge transfer mechanism for rational design and development of highly efficient catalysts. This review offers a timely overview of recent progress in the development of C-MFECs, addressing material syntheses, theoretical advances, potential applications, challenges and future directions.

Advanced Techniques for Real-time Facial Expression Recognition Using Deep Learning

Abstract—Developing systems that can automatically recognize and interpret human emotions from facial expressions is the aim of the quickly expanding field of facial emotion identification and detection research. This technology finds applications in a wide range of areas, including as healthcare, marketing, security, and human-computer interface. Using computer vision and machine learning algorithms, facial emotion recognition systems analyze a face’s features and classify it into numerous emotional categories, including joyful, sorrowful, angry, fearful, and surprised.The three steps in the multi-step process that goes into identifying facial emotions are face detection, facial feature extraction, and emotion categorization. Thanks to recent advances in deep learn- ing, facial emotion detection systems can now identify emotions with high resilience and precision. Further, the development of real-time face expression recognition systems has opened up new avenues for applications such as sentiment analysis, emotional intelligence, and affective computing. This technology could fundamentally alter human-machine interactions and open the way to more compassionate and personalized relationships.A multitude of applications, including virtual assistants, mental health aids, and human-centered technology, will be greatly impacted by the development of systems for identifying and de- tecting facial expressions. Artificial intelligence (AI) technologies that recognize emotions allow people to interact with the digital world in more intelligent and flexible ways. But the complexity of emotion identification lies in the fact that it requires context and geometric elements in addition to facial expressions.

Generating Descriptive Text From Images - Image Caption Generator

In the modern era, image captioning has become one of the most widely required tools. Moreover, there are inbuilt applications that generate and provide a caption for a certain image, all these things are done with the help of deep neural network models. The process of generating a description of an image is called image captioning. It requires recognizing the important objects, their attributes, and the relationships among the objects in an image. It generates syntactically and semantically correct sentences. In this paper, we present a deep learning model to describe images and generate captions using computer vision and machine translation. This paper aims to detect different objects found in an image, recognize the relationships between those objects and generate captions. The dataset used is Flickr8k and the programming language used was Python3, and an ML technique called Transfer Learning will be implemented with the help of the caption model, to demonstrate the proposed experiment. This paper will also elaborate on the functions and structure of the various Neural networks involved. Generating image captions is an important aspect of Computer Vision and Natural language processing. Image caption generators can find applications in Image segmentation as used by Facebook and Google Photos, and even more so, its use can be extended to video frames. They will easily automate the job of a person who has to interpret images. Not to mention it has immense scope in helping visually impaired people

Wearable Near-Eye Tracking Technologies for Health: A Review.

With the rapid advancement of computer vision, machine learning, and consumer electronics, eye tracking has emerged as a topic of increasing interest in recent years. It plays a key role across diverse domains including human-computer interaction, virtual reality, and clinical and healthcare applications. Near-eye tracking (NET) has recently been developed to possess encouraging features such as wearability, affordability, and interactivity. These features have drawn considerable attention in the health domain, as NET provides accessible solutions for long-term and continuous health monitoring and a comfortable and interactive user interface. Herein, this work offers an inaugural concise review of NET for health, encompassing approximately 70 related articles published over the past two decades and supplemented by an in-depth examination of 30 literatures from the preceding five years. This paper provides a concise analysis of health-related NET technologies from aspects of technical specifications, data processing workflows, and the practical advantages and limitations. In addition, the specific applications of NET are introduced and compared, revealing that NET is fairly influencing our lives and providing significant convenience in daily routines. Lastly, we summarize the current outcomes of NET and highlight the limitations.

Let pictures speak: hotel selection-recommendation method with cognitive image attribute-enhanced knowledge graphs

PurposeThe purpose of this paper is to study the importance of image data in hotel selection-recommendation using different types of cognitive features and to explore whether there are reinforcing effects among these cognitive features.Design/methodology/approachThis study represents user-generated images “cognitive” in a knowledge graph through multidimensional (shallow, middle and deep) analysis. This approach highlights the clustering of hotel destination imagery.FindingsThis study develops a novel hotel selection-recommendation model based on image sentiment and attribute representation within the construction of a knowledge graph. Furthermore, the experimental results show an enhanced effect between different types of cognitive features and hotel selection-recommendation.Practical implicationsThis study enhances hotel recommendation accuracy and user satisfaction by incorporating cognitive and emotional image attributes into knowledge graphs using advanced machine learning and computer vision techniques.Social implicationsThis study advances the understanding of user-generated images’ impact on hotel selection, helping users make better decisions and enabling marketers to understand users’ preferences and trends.Originality/valueThis research is one of the first to propose a new method for exploring the cognitive dimensions of hotel image data. Furthermore, multi-dimensional cognitive features can effectively enhance the selection-recommendation process, and the authors have proposed a novel hotel selection-recommendation model.

A microdiscectomy surgical video annotation framework for supervised machine learning applications.

Lumbar discectomy is among the most common spine procedures in the US, with 300,000 procedures performed each year. Like other surgical procedures, this procedure is not excluded from potential complications. This paper presents a video annotation methodology for microdiscectomy including the development of a surgical workflow. In future work, this methodology could be combined with computer vision and machine learning models to predict potential adverse events. These systems would monitor the intraoperative activities and possibly anticipate the outcomes. A necessary step in supervised machine learning methods is video annotation, which involves labeling objects frame-by-frame to make them recognizable for machine learning applications. Microdiscectomy video recordings of spine surgeries were collected from a multi-center research collaborative. These videos were anonymized and stored in a cloud-based platform. Videos were uploaded to an online annotation platform. An annotation framework was developed based on literature review and surgical observations to ensure proper understanding of the instruments, anatomy, and steps. An annotated video of microdiscectomy was produced by a single surgeon. Multiple iterations allowed for the creation of an annotated video complete with labeled surgical tools, anatomy, and phases. In addition, a workflow was developed for the training of novice annotators, which provides information about the annotation software to assist in the production of standardized annotations. A standardized workflow for managing surgical video data is essential for surgical video annotation and machine learning applications. We developed a standard workflow for annotating surgical videos for microdiscectomy that may facilitate the quantitative analysis of videos using supervised machine learning applications. Future work will demonstrate the clinical relevance and impact of this workflow by developing process modeling and outcome predictors.

Personalized Drone Interaction : Adaptive Hand Gesture Control with Facial Authentication

This paper presents a novel system for personalized drone interaction, integrating adaptive hand gesture control with facial authentication. Utilizing the DJI Tello drone equipped with a 5 MP camera, the system employs advanced computer vision and machine learning techniques to ensure secure and intuitive control. Facial recognition using the Histogram of Oriented Gradients (HOG) method and FaceNet model verifies user identity, while MediaPipe and a custom convolutional neural network (CNN) facilitate accurate hand gesture recognition. The system’s real-time processing capabilities ensure seamless and responsive user interaction. Experimental results demonstrate the system’s robustness and accuracy in various scenarios, highlighting its potential for diverse applications such as security, entertainment, and personal assistance.

Radiomics of pituitary adenoma using computer vision: a review.

Pituitary adenomas (PA) represent the most common type of sellar neoplasm. Extracting relevant information from radiological images is essential for decision support in addressing various objectives related to PA. Given the critical need for an accurate assessment of the natural progression of PA, computer vision (CV) and artificial intelligence (AI) play a pivotal role in automatically extracting features from radiological images. The field of "Radiomics" involves the extraction of high-dimensional features, often referred to as "Radiomic features," from digital radiological images. This survey offers an analysis of the current state of research in PA radiomics. Our work comprises a systematic review of 34 publications focused on PA radiomics and other automated information mining pertaining to PA through the analysis of radiological data using computer vision methods. We begin with a theoretical exploration essential for understanding the theoretical background of radionmics, encompassing traditional approaches from computer vision and machine learning, as well as the latest methodologies in deep radiomics utilizing deep learning (DL). Thirty-four research works under examination are comprehensively compared and evaluated. The overall results achieved in the analyzed papers are high, e.g., the best accuracy is up to 96% and the best achieved AUC is up to 0.99, which establishes optimism for the successful use of radiomic features. Methods based on deep learning seem to be the most promising for the future. In relation to this perspective DL methods, several challenges are remarkable: It is important to create high-quality and sufficiently extensive datasets necessary for training deep neural networks. Interpretability of deep radiomics is also a big open challenge. It is necessary to develop and verify methods that will explain to us how deep radiomic features reflect various physics-explainable aspects.

The prospect and metaphysical analysis of conscious artificial intelligence

Artificial intelligence, also known as AI, has led the trend of evolution in the past and future decades, and the potential of consciousness artificial intelligence emerges as a renovative field to address. The computer machine aims to process repetitive and tedious tasks for humans since its concept was first developed. Whether AI is conscious does not raise unprecedented discussion before the appearance of the concept of machine learning. After it appears, the machine, instead of merely passing in input and generating output, is able to learn while processing the information, which resembles a human's learning process. Therefore, this paper delves into the complex terrain of AI to explore the theoretical possibility of endowing machines with consciousness and addresses the future concerns and potentials of AI. Illustrating through the aspects of ethical concerns, metaphysical perspectives on consciousness, and the latest advancements in AI, the study critically examines whether machines can possess a consciousness similar to human understanding.

A Comprehensive Review of AI Diagnosis Strategies for Age-Related Macular Degeneration (AMD).

The rapid advancement of computational infrastructure has led to unprecedented growth in machine learning, deep learning, and computer vision, fundamentally transforming the analysis of retinal images. By utilizing a wide array of visual cues extracted from retinal fundus images, sophisticated artificial intelligence models have been developed to diagnose various retinal disorders. This paper concentrates on the detection of Age-Related Macular Degeneration (AMD), a significant retinal condition, by offering an exhaustive examination of recent machine learning and deep learning methodologies. Additionally, it discusses potential obstacles and constraints associated with implementing this technology in the field of ophthalmology. Through a systematic review, this research aims to assess the efficacy of machine learning and deep learning techniques in discerning AMD from different modalities as they have shown promise in the field of AMD and retinal disorders diagnosis. Organized around prevalent datasets and imaging techniques, the paper initially outlines assessment criteria, image preprocessing methodologies, and learning frameworks before conducting a thorough investigation of diverse approaches for AMD detection. Drawing insights from the analysis of more than 30 selected studies, the conclusion underscores current research trajectories, major challenges, and future prospects in AMD diagnosis, providing a valuable resource for both scholars and practitioners in the domain.

Greater benefits of deep learning-based computer-aided detection systems for finding small signals in 3D volumetric medical images.

Radiologists are tasked with visually scrutinizing large amounts of data produced by 3D volumetric imaging modalities. Small signals can go unnoticed during the 3D search because they are hard to detect in the visual periphery. Recent advances in machine learning and computer vision have led to effective computer-aided detection (CADe) support systems with the potential to mitigate perceptual errors. Sixteen nonexpert observers searched through digital breast tomosynthesis (DBT) phantoms and single cross-sectional slices of the DBT phantoms. The 3D/2D searches occurred with and without a convolutional neural network (CNN)-based CADe support system. The model provided observers with bounding boxes superimposed on the image stimuli while they looked for a small microcalcification signal and a large mass signal. Eye gaze positions were recorded and correlated with changes in the area under the ROC curve (AUC). The CNN-CADe improved the 3D search for the small microcalcification signal ( , ) and the 2D search for the large mass signal ( , ). The CNN-CADe benefit in 3D for the small signal was markedly greater than in 2D ( , ). Analysis of individual differences suggests that those who explored the least with eye movements benefited the most from the CNN-CADe ( , ). However, for the large signal, the 2D benefit was not significantly greater than the 3D benefit ( , ). The CNN-CADe brings unique performance benefits to the 3D (versus 2D) search of small signals by reducing errors caused by the underexploration of the volumetric data.

Nenadzirana praktična analiza ponašanja aviona A320 i B738 provedena u međunarodnoj zračnoj luci Sultan Hasanuddin

The purpose of this research was to look at the behavior of two well-known commercial aircraft types in Indonesia (the A320 and the B738) during the take-off phase. This was done to provide new information in the field of aviation, particularly flight safety. Observations were made at Sultan Hasanuddin International Airport by observing aircraft ADS-B data, which defines the behavior of the flight pattern. This ADS-B data is the subject of data analysis, which will subsequently be taught to the machine (computer) so that it can recognize the pattern and construct clusters. The purpose of this study is to utilize unsupervised learning, specifically K-Means clustering, to categorize and identify patterns in unlabeled ADS-B data obtained from AERO-TRACK. To prepare the raw data and create a dataset, data analysis techniques were employed. The machine learning model generates three distinct clusters: cluster 1 represents aircraft take-off on two-thirds of the runway, cluster 2 represents aircraft take-off on the entire runway, and cluster 3 represents aircraft take-off on one-third of the runway. The elbow method is utilized to analyze and interpret the three clusters produced by the model. An interesting observation is that the B738 aircraft dominate in all three clusters, while the A320 aircraft dominate in clusters 1 and 3. Notably, in cluster 2, there is a significant number of commercial planes taking off, accounting for 145 out of 628 flights. Based on the observed data spanning 91 days (September 26 to December 26, 2022), there is a 23% probability of runway excursion (overshooting the runway) in this cluster. Additionally, the research reveals that A320 aircraft demonstrate a safe zone take-off rate of 87%, whereas the B738 aircraft demonstrate a rate of 70.5%. These findings, derived from the analysis of ADS-B data such as GPS-Altitude and Coordinate, are intended to serve as valuable knowledge for aviation authorities, aviation users, and other stakeholders in the aviation industry.

Advanced Systems for Detecting and Recognizing Traffic Objects

Traffic object detection and recognition systems have become critical components in the advancement of intelligent transportation systems (ITS). These systems leverage various technologies such as computer vision, machine learning, and sensor fusion to accurately identify and classify objects on the road, including vehicles, pedestrians, traffic signs, and obstacles. The integration of these technologies enhances traffic management, improves road safety, and facilitates the development of autonomous vehicles. This paper provides an overview of the state-of-the-art methods and technologies used in traffic object detection and recognition. It also discusses the challenges faced in real-world implementations, such as varying weather conditions, lighting changes, and occlusions, and explores potential solutions and future research directions to address these issues.

Computational Machine Learning Analytics for Prediction of Water Quality

In terms of impacts on ecosystems, industry, people, and flora and fauna, water quality is paramount. Contamination and pollution have degraded water quality in recent decades. Predicting WQC and Water Quality Index (WQI) is the problem of this article; WQI is an important measure of water validity. This research use machine learning approaches to forecast WQI and WQC, and it does so by optimizing and tweaking the parameters of several machine learning models. Parameter optimization and tuning for four classification models and four regression models both make use of grid search, an essential tool in both contexts. To forecast WQC, classification models such as Random Forest (RF), Extreme Gradient Boosting (Xgboost), Gradient Boosting (GB), and Adaptive Boosting (Ada-Boost) are used. Predicting WQI is done using regression models such as K-nearest neighbour (KNN), decision tree (DT), support vector regression (SVR), and multi-layer perceptron (MLP). Data normalization and data imputation (mean imputation) were also executed as pretreatment steps to suit the data and make it convenient for any further processing. Seven characteristics and ninety-one cases make up the dataset used for this research. Five evaluation measures were calculated to evaluate the classification systems' effectiveness: accuracy, recall, precision, Matthews' Correlation Coefficient (MCC), and F1 score. A total of four evaluation metrics were calculated to measure the efficacy of the regression models: MAE, MedAE,MSE, and R2. The results of the testing showed that the GB model yielded the most accurate predictions of WQC values (99.50%), making it the top performer in terms of categorization. The experimental findings show that the MLP regressor model got a value of 99.8 percent R2 when predicting WQI values, making it the best performing model in regression.

A genetic algorithm‐based virtual machine scheduling algorithm for energy‐efficient resource management in cloud computing

SummaryTo address the unbalanced resource load of a virtual machine cluster, the author proposes an energy‐saving virtual machine scheduling algorithm based on resource management cloud computing technology. This article analyzes the current cloud computing and virtual machine scheduling research in the cloud computing environment. It discusses the concept, characteristics, classification, application scenarios, and key cloud computing technologies. A genetic algorithm is used to solve the problem of high energy consumption in the data center. The test results show that in the same original configuration scheme, the migration times based on the greedy algorithm adopted by GA2ND are about 1000, and the migration times of GA1ST are between 200 and 500. The GA2ND migration scheme requires fewer virtual machines. In the result analysis, the experiments compare the proposed algorithms—DVFS, IMC, GA1ST, and GA2ND—with a focus on energy consumption and virtual machine migration. Notably, DVFS serves as a reference for energy efficiency, IMC represents the proposed algorithm without genetic optimization, GA1ST denotes the genetic algorithm under a heterogeneous model, and GA2ND signifies the enhanced genetic algorithm introduced in this article. The comparison aims to assess the energy efficiency and virtual machine migration performance of each algorithm in the context of a simulated cloud computing environment. Therefore, the algorithm proposed in this article can effectively reduce energy consumption and avoid frequent migration of virtual machines.

Multi-GPU 3D k-nearest neighbors computation with application to ICP, point cloud smoothing and normals computation

The k-Nearest Neighbors algorithm is a fundamental algorithm that finds applications in many fields like Machine Learning, Computer Graphics, Computer Vision, and others. The algorithm determines the closest points (d-dimensional) of a reference set R according to a query set of points Q under a specific metric (Euclidean, Mahalanobis, Manhattan, etc.). This work focuses on the utilization of multiple Graphical Processing Units for the acceleration of the k-Nearest Neighbors algorithm with large or very large sets of 3D points. With the proposed approach the space of the reference set is divided into a 3D grid which is used to facilitate the search for the nearest neighbors. The search in the grid is performed in a multiresolution manner starting from a high-resolution grid and ending up in a coarse one, thus accounting for point clouds that may have non-uniform sampling and/or outliers. Three important algorithms in reverse engineering are revisited and new multi-GPU versions are proposed based on the introduced KNN algorithm. More specifically, the new multi-GPU approach is applied to the Iterative Closest Point algorithm, to the point cloud smoothing, and to the point cloud normal vectors computation and orientation problem. A series of tests and experiments have been conducted and discussed in the paper showing the merits of the proposed multi-GPU approach.

COMPARISON OF MESSAGE PASSING SYSTEMS IN CONTEXT OF ADAPTIVE LOGGING METHOD

Computer software is an important part of technological progress. As it becomes more and more complex and sophisticated, so does the need to protect it. Apart from typical information security aspects of integrity, availability and confidentiality, the scale and complexity of modern computer systems require a high level of control and observability. The main goal of this research is to build upon the foundations laid by the general idea of an adaptive logging method and introduce the next iteration of its design in the form of an appropriate message passing system to be used to propagate required changes to corresponding implementation in an effective and performant manner. Four different message passing system models are introduced, based on different technologies such as RabbitMQ message broker, communication channels in PostgreSQL database management system, general web server architecture and Linux-based process signaling interface. For each of those an overview description and graphical model is presented. Finally, the resulting comparison is conducted, comparing aspects such as reliance on third-party software, communication medium, error surface increase and authentication related considerations. As a result, the design based on process signaling approach is determined to be the most suitable for adaptive logging method, as it does not introduce any third-party software (and as such affects error surface in a somewhat negligible manner), binds directly to an observed application, is built using low level concepts that should be present in multiple different platforms and programming languages and should be able to reuse authentication logic that is already used when accessing computational machine where observed program is executed.

Rapid species discrimination of similar insects using hyperspectral imaging and lightweight edge artificial intelligence.

Species discrimination of insects is an important aspect of ecology and biodiversity research. The traditional methods based on human visual experience and biochemical analysis cannot strike a balance between accuracy and timeliness. Morphological identification using computer vision and machine learning is expected to solve this problem, but image features have poor accuracy for very similar species and usually require complicated networks that are unfriendly to portable edge devices. In this work, we propose a fast and accurate species discrimination method of similar insects using hyperspectral features and lightweight machine learning algorithm. Feature regions selection, feature spectra selection and model quantification are used for the optimization of discriminating network. The experimental results of six similar butterfly species in the genus of Graphium show that, compared with morphological recognition with machine vision, our work achieves a higher accuracy of 92.36 ± 3.04% and a shorter inference time of 0.6 ms, with the tiny-size convolutional neural network deployed on a neural network chip. This study provides a rapid and high-accuracy species discrimination method for insects with high appearance similarity and paves the way for field discriminations using intelligent micro-spectrometer based on on-chip microstructure and artificial intelligence chip.

Optimization of Pin Fins Using Computational Fluid Dynamics and Machine Learning

This paper presents a two-part study focusing on the optimization of pin-fin arrays for gas turbine blade cooling. The first part of the study examines the thermal performance of various pin-fin shapes and sizes using computational fluid dynamics. The study investigates circular, elliptical, hexagonal, and rectangular cross sections, with emphasis on the hydraulic diameter and Reynolds number. Two-dimensional simulations mimicked a confined, staggered array of uniform-sized pins under different inlet conditions. For a hydraulic diameter of 0.053 m and a Reynolds number of 5500, the rectangular pins showed the highest Nusselt number 8.98, 16.01, and 20.62% larger than circular, elliptical, and hexagonal pins, respectively, but also a pressure increase 68.30% higher on average. For a hydraulic diameter of 0.046 m and a Reynolds number of 1000–15,000, it was shown that all shapes have an exponential increase in pressure and a logarithmic decay in the Nusselt number. Standing out was the rectangular shape, which, at a maximum Reynolds number of 15,000, had a pressure increase of 108% larger than the next in line, the hexagonal pin. In the same range of inlet conditions, the Gee–Webb coefficient was the highest for the circular pin, which was selected as the main shape for the following segment. In the second part of the study, a machine learning framework based on a neural network architecture is presented. The neural network predicts the thermal performance of different pin-fin array configurations. At the end, this framework is used in an optimization process that explores the advantages of nonuniform arrays consisting of differently sized circular pins as opposed to the standard uniform structures of the first part. The model proves to be capable of accurately predicting the characteristic thermal performance coefficients across a wide range of input parameters. The nonuniform array managed a 23% reduction in pressure rise at a 0.2% exit temperature increase compared to a reference standard array of the same hydraulic diameter.

Butterfly valve erosion prediction based on LSTM network

When valves and pipelines are used, erosion wear is a major concern. Erosion wear can lead to equipment downtime, material replacement, and other issues, as well as seal surface failure. The research delves into the phenomenon of erosion in butterfly valves, crucial components utilized across diverse industrial sectors. Erosion primarily affects the valve's disc and seat regions, leading to premature wear and compromised performance. To address this issue, the research employs computational fluid dynamics (CFD) and machine learning techniques, including long short-term memory (LSTM) and BP neural networks, to predict erosion rates under various conditions (different valve openings and particle diameters). Results indicate that erosion escalates with time and larger valve openings, highlighting the need for proactive maintenance strategies. The LSTM model demonstrates superior predictive capabilities compared to the BP neural network, offering valuable insights for improving butterfly valve design and operational efficiency in industrial settings. Furthermore, to seek a more efficient network configuration, the intelligent search capabilities of the particle swarm optimization (PSO) algorithm have been utilized to systematically explore the optimal network structure parameters. The prediction results highlight the advantages of LSTM in handling time series data, particularly in predicting erosion rates with complex dynamic characteristics.