Computer Users Research Articles

CerviXpert: A multi-structural convolutional neural network for predicting cervix type and cervical cell abnormalities

Objectives Cervical cancer, a leading cause of cancer-related deaths among women globally, has a significantly higher survival rate when diagnosed early. Traditional diagnostic methods like Pap smears and cervical biopsies rely heavily on the skills of cytologists, making the process prone to errors. This study aims to develop CerviXpert, a multi-structural convolutional neural network designed to classify cervix types and detect cervical cell abnormalities efficiently. Methods We introduced CerviXpert, a computationally efficient convolutional neural network model that classifies cervical cancer using images from the publicly available SiPaKMeD dataset. Our approach emphasizes simplicity, using a limited number of convolutional layers followed by max-pooling and dense layers, trained from scratch. We compared CerviXpert’s performance against other state-of-the-art convolutional neural network models, including ResNet50, VGG16, MobileNetV2, and InceptionV3, evaluating them on accuracy, computational efficiency, and robustness using five-fold cross-validation. Results CerviXpert achieved an accuracy of 98.04% in classifying cervical cell abnormalities into three classes (normal, abnormal, and benign) and 98.60% for five-class cervix type classification, outperforming MobileNetV2 and InceptionV3 in both accuracy and computational demands. It demonstrated comparable results to ResNet50 and VGG16, with significantly reduced computational complexity and resource usage. Conclusion CerviXpert offers a promising solution for efficient cervical cancer screening and diagnosis, striking a balance between accuracy and computational feasibility. Its streamlined architecture makes it suitable for deployment in resource-constrained environments, potentially improving early detection and management of cervical cancer.

MLGCN: an ultra efficient graph convolutional neural model for 3D point cloud analysis.

With the rapid advancement of 3D acquisition technologies, 3D sensors such as LiDARs, 3D scanners, and RGB-D cameras have become increasingly accessible and cost-effective. These sensors generate 3D point cloud data that require efficient algorithms for tasks such as 3D model classification and segmentation. While deep learning techniques have proven effective in these areas, existing models often rely on complex architectures, leading to high computational costs that are impractical for real-time applications like augmented reality and robotics. In this work, we propose the Multi-level Graph Convolutional Neural Network (MLGCN), an ultra-efficient model for 3D point cloud analysis. The MLGCN model utilizes shallow Graph Neural Network (GNN) blocks to extract features at various spatial locality levels, leveraging precomputed KNN graphs shared across GCN blocks. This approach significantly reduces computational overhead and memory usage, making the model well-suited for deployment on low-memory and low-CPU devices. Despite its efficiency, MLGCN achieves competitive performance in object classification and part segmentation tasks, demonstrating results comparable to state-of-the-art models while requiring up to a thousand times fewer floating-point operations and significantly less storage. The contributions of this paper include the introduction of a lightweight, multi-branch graph-based network for 3D shape analysis, the demonstration of the model's efficiency in both computation and storage, and a thorough theoretical and experimental evaluation of the model's performance. We also conduct ablation studies to assess the impact of different branches within the model, providing valuable insights into the role of specific components.

Research and application of thermal energy recovery and automatic monitoring system for motor equipment

In order to achieve an automatic monitoring system for the operation status of motor equipment, the author proposes a research and application based on the thermal energy recovery and automatic monitoring system of motor equipment. The author first analyzes the operating characteristics of the motor and collects four basic parameters of the motor, namely voltage, current, speed, and temperature, in order to determine whether the motor is in normal working condition. Secondly, the system combines electrical parameter detection and acquisition, wireless network technology, industrial field bus technology, and computer user software to achieve remote real-time monitoring, control, and management of the motor?s remote travel status. This enables the entire system to achieve intelligent, networked, and systematic management, solving the technical problem of real-time control and system management that cannot be achieved in motor systems distributed in multiple locations. Finally, the monitoring results indicate that after installation and debugging, the data is displayed on the upper computer. This effect is the data collection of the motor during low speed operation, which is reflected in real-time on the control panel. The actual parameters of the motor were compared with the test parameters of this system, and the test basically achieved the desired effect, with accurate detection data.

Chaos and stability of a fractional model of the cyber ecosystem

<p>The widespread use of computer hardware and software in society has led to the emergence of a type of criminal conduct known as cybercrime, which has become a major worldwide concern in the 21st century spanning multiple domains. As a result, in the present setting, academics and practitioners are showing a great deal of interest in conducting research on cybercrime. In this work, a fractional-order model was replaced by involving three sorts of human populations: online computer users, hackers, and cyber security professionals, in order to examine the online computer user-hacker system. The existence, uniqueness and boundedness were studied. To support our theoretical conclusions, a numerical analysis of the influence of the various logical parameters was conducted and we derived the necessary conditions for the different equilibrium points to be locally stable. We examined the effects of the fear level and refuge factor on the equilibrium densities of prey and predators in order to explore and understand the dynamics of the system in a better way. Using some special circumstances, the model was examined. Our theoretical findings and logical parameters were validated through a numerical analysis utilizing the generalized Adams-Bashforth-Moulton technique.</p>

Design of a Cavity Pressure Monitoring System for Plastic Injection Molding

This work aims to create an instrument that allows the measurement of cavity pressure during plastic injection molding. The designed device is intended to contribute to the equipment inventory of the Polymer Technology Laboratory at Sapientia EMTE, Faculty Târgu Mureș. The design criteria were the ease of mounting and use. The system was implemented with two load cells, two HX711 amplifiers, an ESP32-based microcontroller and a corresponding computer user interface. The user interface was developed using National Instruments LabVIEW program and finalized as a stand-alone application. During the design steps, attention was also paid to the practical applicability of the system.

Standardization and Classification of Icons on a Graphical User Interface for Visually Impaired Users

This study aims to establish a universal standard for software application icons, enhancing computer usability for visually impaired and elderly users. It addresses the challenges of graphical interfaces, such as the difficulty in distinguishing between similar icons or understanding complex iconography, and focuses on developing an intuitive, ontology-based classification system for software icons.

Behaviour Based Malware Detection using Machine Learning

Abstract: Considering all the researches done, it appears that over last decade, malware has been growing exponentially and also has been causing significant financial losses to different organizations. Thus, it becomes important to detect if a file contains any malware or not. The malwares can cause a lot of damage to the system such as slowing downthe system and also stealing sensitive information from the system. malware is a executable program specifically to destroy a genuine user's computer by spreading harmful virusin different ways .In the current times, one of the most important assets of the people is their data and information which needs to be protected. Hence, in order to protect the data and information, there is a need for software which couldperform this task and help in ensuring the integrity of our system. Our method for malware detection uses different machine learning algorithms such as decision tree, random forest etc. The algorithm which has the maximum accuracy gets selected which provides a great detection ratio for the system. Furthermore, the performance of the system is detected by calculating the false positive and false negative rates using the confusion matrix.

Trust Framework on Exploitation of Humans as the Weakest Link in Cybersecurity

T he significance of cybersecurity is increasing in our daily digital lives. The reason for this rise is that human interactions take place in computer-mediated environments, or cyberspace, where physical cues from face-to-face interactions are either absent or very minimal. Computer users are becoming increasingly susceptible to cyberattacks as a result of human interactions in cyberspace. Understanding how cybercriminals exploit the human trust, the weakest link in cybersecurity is relevant because cybercriminals focus on attacking the human psychology of trust rather than technical-based controls. To this end, the present paper develops a trust framework on exploitation of humans as the weakest link in cybersecurity. The framework is established by linking the human psychology of trust and techniques used by cybercriminals in deceiving and manipulating users of computer systems. The framework is validated by demonstrating its application using a case study employing real data. Findings show that cybercriminals exploit human trust based on trust development processes and bases of trust, either creating (falsified) expectations or a relationship history to lure the victim in. Furthermore, it is revealed that technical-based controls cannot provide effective safeguards to prevent manipulation of the human psychology of trust.

Improved Image Classification Task Using Enhanced Visual Geometry Group of Convolution Neural Networks

Convolutional Neural Networks (CNNs) have become essential to solving image classification tasks. One of the most frequent models of CNNs for image classification is the Visual Geometry Group (VGG). The VGG architecture is made up of multiple layers of convolution and pooling processes followed by fully connected layers. Among the various VGG models, the VGG16 architecture has gained great attention due to its remarkable performance and simplicity. However, the VGG16 architecture is still prone to have many parameters contributing to its complexity. Moreover, the complexity of VGG16 may cause a longer execution time. The complexity of VGG16 architecture is also more highly prone to overfitting and may affect the classification accuracy. This study proposes an enhancement of VGG16 architecture to overcome such drawbacks. The enhancement involved the reduction of the convolution blocks, implementing batch normalization (B.N.) layers, and integrating global average pooling (GAP) layers with the addition of dense and dropout layers in the architecture. The experiment was carried out with six benchmark datasets for image classification tasks. The results from the experiment show that the network parameters are 79% less complex than the standard VGG16. The proposed model also yields better classification accuracy and shorter execution time. Reducing the parameters in the proposed improved VGG architecture allows for more efficient computation and memory usage. Overall, the proposed improved VGG architecture offers a promising solution to the challenges of long execution times and excessive memory usage in VGG16 architecture.

Improved Image Classification Task Using Enhanced Visual Geometry Group of Convolution Neural Networks

Convolutional Neural Networks (CNNs) have become essential to solving image classification tasks. One of the most frequent models of CNNs for image classification is the Visual Geometry Group (VGG). The VGG architecture is made up of multiple layers of convolution and pooling processes followed by fully connected layers. Among the various VGG models, the VGG16 architecture has gained great attention due to its remarkable performance and simplicity. However, the VGG16 architecture is still prone to have many parameters contributing to its complexity. Moreover, the complexity of VGG16 may cause a longer execution time. The complexity of VGG16 architecture is also more highly prone to overfitting and may affect the classification accuracy. This study proposes an enhancement of VGG16 architecture to overcome such drawbacks. The enhancement involved the reduction of the convolution blocks, implementing batch normalization (B.N.) layers, and integrating global average pooling (GAP) layers with the addition of dense and dropout layers in the architecture. The experiment was carried out with six benchmark datasets for image classification tasks. The results from the experiment show that the network parameters are 79% less complex than the standard VGG16. The proposed model also yields better classification accuracy and shorter execution time. Reducing the parameters in the proposed improved VGG architecture allows for more efficient computation and memory usage. Overall, the proposed improved VGG architecture offers a promising solution to the challenges of long execution times and excessive memory usage in VGG16 architecture.

Adoption of M-Commerce Amongst Pakistani Consumers: By Using TAM with Effect of Social Influence and Mobile Self-Efficacy

M-commerce, or mobile commerce, has gained popularity due to its expanded possibilities over Electronic commerce, which has been growing at a far faster pace because to the Covid-19 outbreak in Pakistan. The utilization of wireless technologies has increased in the M-commerce sector. There are more mobile phone users than personal computer users. In spite of Pakistan's apparent interest in M-commerce as a means of trade, nothing is known about the country's citizens' desire to utilize this new wireless electronic platform. Thus, customers' behavioral intention to use m-commerce has been investigated using an improved technology acceptance model (TAM) that takes into account the consequences of social influence and mobile self-efficacy. The sample size for this study was 220 people from Lahore, Karachi, Islamabad, and Multan, which is a statistically significant number. A variety of statistical techniques, including factor and reliability analysis as well as correlation and regression, were used to examine the data by using SPSS version 19. Customers' attitudes toward adopting M-commerce are positively influenced by their perceptions of its utility, ease of use, social influence, and personal efficacy on their mobile devices, according to this study, which also found a link between these factors and their behavioral intent to use M-commerce.

Cyber Security Challanges for Online Trading

bstract: Today Security is a fundamental component in the computing and networking technology. The first and foremost thing of every network designing, planning, building, and operating a network is the importance of a strong security policy. Network security has become more important to personal computer users, organizations, and the military. With the advent of the internet, security became a major concern. The internet structure itself allowed for many security threats to occur. Online trading facilitates as a financial platform form for buying and selling shares, bidding, product sale or purchase using computers. The vital online trading between B2B, B2C and C2C transaction data may be under siege due to spywares, malwares, Hijackers and intruders. Often trading secrets and portfolios are in risk with network attackers who tracks unauthorizedly the personalized data of business clients. Cyber security is the practice of defending computers, servers, mobile devices, electronic systems, networks, and data from malicious attacks. It's also known as information technology security or electronic information security. The term applies in a variety of contexts, from business to mobile computing, and can be divided into a few common categories.

Comparison of McKenzie and Isometric Exercises on Neck Functions of Computer Users with Forward Head Posture

Introduction: Prolonged use of computer can lead to poor posture such as forward head posture (FHP). This posture is associated with imbalance and stiffness of the neck muscles, lack of postural awareness and inappropriate ergonomics, resulting in work-related musculoskeletal disorders. These disturbances can affect the performance and productivity of office workers. Postural awareness training, neck exercises, and modalities are interventions in FHP management. Research that compares the effectiveness of cervical McKenzie and isometric exercise on neck functional score in computer users with forward head posture has not been conducted.
 Methods: This research was a quasi-experimental. The participants, 24 computer users working at Kariadi Hospital, Semarang, were divided into 2 groups by purposive sampling receiving cervical McKenzie exercise (n=12) and cervical isometric exercise (n=12). Each group received different exercise. Neck functional score was assessed by Neck Disability Index (NDI) questionnaire before and after intervention. The mean differences before and after treatment, as well as between groups was compared statistically using paired t-test.
 Results: The mean NDI score in the McKenzie group after treatment showed an improvement of 7.84 ± 3.54 with p = 0.002. The mean NDI score in the isometric group after treatment also showed an improvement of 3.93 ± 3.75 with p = 0.004. The difference in NDI score improvement in the cervical McKenzie group was greater than the one in isometric group and statistically significant with p = 0.017.
 Conclusion: Cervical McKenzie exercise was proved to be more effective in improving neck functional scores in patients with FHP compared to cervical isometric exercise.

Comparative Evaluation of the Defocus Curve of Monofocal IOL, Extended Depth of Focus IOL, and Trifocal IOL

Purpose. Comparative evaluation of the defocus curve (DC) of monofocal IOLs (MIOLs), extended depth of focus IOLs (EDОF) and trifocal IOLs (TIOLs). Patients and methods. We observed 90 patients (average age 57.8 ± 1.8 years) who underwent standard binocular phacoemulsification of cataracts in both eyes with emmetropic “target” refraction and postoperative monocular uncorrected distance visual acuity (UCVA) of at least 1.0 rel. units. All patients were divided into three groups equal in number of patients, age, gender and visual status, corresponding to three options of implantable IOLs: MIOL (“RayOne Aspheric”, model RAO600C); EDOF (RayOne EMV, model RAO200E) and THYOL (RayOne Trifocal). DC was performed binocularly based on a standard BCVA measurement with an optical load for defocusing from +3.0 D to -4.0 D with a “step” of +1.0 D and -0.5 D. Results. Under conditions of optical defocusing with positive lenses (1.0; 2.0; 3.0 D), all three types of IOLs maintained almost the same average BCVA (at +1.0 D, the BCVA range was 0.72–0.76 rel. units; at +2.0 diopters — 0.66–0.72 relative units; at +3.0 diopters — 0.52–0.56 relative units). In relation to the analysis of BCVA in conditions of defocusing with negative lenses, it was found that visual acuity was significantly better with EDOF than with MIOL, with a load from -1.0 to -4.0 diopters, while these differences were statistically significant and ranged from 0.14 to 0.27 relative units (p < 0.01). Along with this, it was determined that UCVA was significantly better in the group with TIOL than in the group with EDOF, with a load from -2.5 to -4.0 D. Moreover, these differences were statistically significant and ranged from 0.09 to 0.14 rel. units (p < 0.01). Conclusion. The design features of IOLs make it possible to consider implantation of EDOF as an option for an individual approach to the selection of IOLs, especially taking into account the possibility of use in patients whose professional activities involve long-term visual work at intermediate distances (for example, users of personal computers).

Ride comfort oriented integrated design of preview active suspension control and longitudinal velocity planning

Aiming for further improvement in ride comfort, a novel integrated system combining preview active suspension control with longitudinal velocity planning based on road height information is proposed. From the suspension control side, the presented semi-EMPC (Explicit Model Predictive Control)-based controller, which is augmented with preview road information, can make up for the shortcomings of traditional implicit MPC and explicit MPC, and achieve a balance between computational burden and memory usage, thus enhancing the practicality of implementing preview suspension in real-world applications. Adopting dynamic programming and quadratic programming algorithms, a longitudinal velocity planning method based on preview information is provided to overcome the vibration that cannot be effectively suppressed by single suspension control, thus expanding the dimension of ride comfort improvement from the original vertical dimension alone to both longitudinal and vertical dimensions. Throughout the design process, the transformation of pavement information among spatial, time, and frequency domains has been regarded as a bridge to combine two systems, thus handling the complex coupling between above two highly interdependent systems. Experiments in the Quanser active suspension plant have been conducted to verify the superiority of semi-EMPC with preview. The integrated approach is simulated in Carsim and shows a significant improvement over single suspension control.

The Influence of Technological Literacy, Education, and Employment on Poverty in Kalimantan

Poverty is a condition in which individuals or groups lack sufficient resources to meet their basic needs. It is a fundamental issue that can affect the economic growth rate of a region. This study aims to analyze the influence of labor force absorption, percentage of computer users, telecommunications consumption, and education level on the number of poor people in the provinces of Kalimantan Island from 2018 to 2022 using panel data regression analysis. The results from the selected Fixed Effects model indicate that telecommunications consumption has a positive impact on the number of poor people, while the education level has a negative impact on the number of poor people. However, labor force absorption and the percentage of computer users do not significantly influence the number of poor people. Based on the research findings, it is hoped that the government can create an extensive telecommunications network. The expectation is that communication facilities and infrastructure will be widely available, leading to reduced telecommunications expenses for the population, allowing them to allocate their money towards daily essential needs. Additionally, adequate communication facilities are expected to aid the teaching and learning process in Kalimantan Island, as the improvement in educational quality has proven to decrease the poverty rate during the research period.

Feature Extraction in Time-Lapse Seismic Using Deep Learning for Data Assimilation

Summary Assimilation of time-lapse (4D) seismic data with ensemble-based methods is challenging because of the massive number of data points. This situation requires excessive computational time and memory usage during the model updating step. We addressed this problem using a deep convolutional autoencoder to extract the relevant features of 4D images and generate a reduced representation of the data. The architecture of the autoencoder is based on the VGG-19 network, a deep convolutional architecture with 19 layers well-known for its effectiveness in image classification and object recognition. Some advantages of VGG-19 are the possibility of using some pretrained convolutional layers to create a feature extractor and taking advantage of the transfer learning technique to address other related problem domains. Using a pretrained model bypasses the need for large training data sets and avoids the high computational demand to train a deep network. For further improvements in the reconstruction of the seismic images, we apply a fine-tuning of the weights of the latent convolutional layer. We propose to use a fully convolutional architecture, which allows the application of distance-based localization during data assimilation with the ensemble smoother with multiple data assimilation (ES-MDA). The performance of the proposed method is investigated in a synthetic benchmark problem with realistic settings. We evaluate the methodology with three variants of the autoencoder, each one with a different level of data reduction. The experiments indicate that it is possible to use latent representations with major data reductions without impairing the quality of the data assimilation. Additionally, we compare central processing unit (CPU) and graphics processing unit (GPU) implementations of the ES-MDA update step and show in another synthetic problem that the reduction in the number of data points obtained with the application of the deep autoencoder may provide a substantial improvement in the overall computation cost of the data assimilation for large reservoir models.

Twelve tips for applying the think-aloud method to capture cognitive processes

The think-aloud method is an established technique for studying human thought (cognitive) processes. Problem-solving and decision-making are essential skills for medical professionals, and the cognitive processes underlying these skills are complex. Studying these thought processes would enable educators, clinicians, and researchers to modify or refine their approaches and interventions. The think-aloud method has been utilized for capturing cognitive processes in a variety of fields, including computer usability, sports and cognitive psychology. Medical education also recognizes thought processes as valuable data for research and education. This article aims to guide researchers and educators through the preparation and implementation of a think-aloud method to record participants’ thought processes during an activity.

The effects of dual screen layout on neck-shoulder muscle activity and head-neck posture variability during computer tasks.

Larger dual screens have been widely used during office work and their biomechanical exposure should be explored. To investigate the biomechanical effect of two dual screen layouts on neck-shoulder muscle activity and the variability of head-neck posture in computer users. A preliminary study of the user-preferred dual screen angles was carried out in V-shaped and L-shaped layouts. Twenty healthy participants aged 19 to 26 years were recruited and assigned to perform reading, typing, and searching tasks for 30 minutes in both workstation layouts. Electromyography was measured at bilateral cervical erector spinae (CES), sternocleidomastoid (SCM), and upper trapezius (UT). The head-neck lateral bending, rotation, and flexion angles were recorded. The visual analog scale (VAS) was used to evaluate visual strain. The muscle activity at the left UT and right CES sites when using the V-shaped layout was significantly higher than the L-shaped. There were significant differences in head-neck rotation and flexion angles between the two layouts in reading and typing tasks. In the searching task, there was no significant difference in the head-neck rotation and flexion angles between the two layouts. The visual strain score was significantly higher in the V-shaped layout. The CES and UT muscles displayed higher levels of activation while using the V-shaped layout in comparison to the L-shaped layout. The head-neck rotation and flexion angles differed due to varied types of work when using V-shaped and L-shaped layouts.

Prevailing practices for the management of dry eye disease in India: A questionnaire based survey 2023

: Dry eye disease is a common ophthalmic condition which is chronic in nature, It is major health issue especially in the current digital era. Dry eye disease is one of the most common reasons for visiting eye care practitioners. To understand the treatment pattern of medical management of dry eye disease across India.This single visit, cross-sectional, non-interventional, interview-based ophthalmologist survey on dry eye disease (DED) was conducted between 10-13 May 2023 at 81st Annual Conference of All India Ophthalmological Society, Kochi–AIOC 2023. A total of 71 registered ophthalmologist from all over India attending AIOC 2023 who were willing to provide their written consent participated in the survey and completed structured questionnaire on dry eye disease management. Approximately 39.44% ophthalmologist have 20-40% of patients who visiting to daily OPD are suffering from DED, and 40.85% ophthalmologist said the percentage is even more i.e. between 40-60%. 88.73% ophthalmologist responded environmental factors such as digital use specially increased usage of computers and mobile are responsible for dry eye. 49.30% patients suffered from aqueous - deficient dry eye (ADDE) and remaining 50.70% evaporative dry eye (EDE). Artificial Tears (AT) is the first line in management of DED said by all ophthalmologist & in certain cases, depending on type, severity, and cause of dry eye other drugs like cyclosporine, corticosteroids, antioxidant supplements and other medications might be used. Viscosity, pH and osmolarity are important for artificial tear said by 77.46% of ophthalmologist & 23% ophthalmologist opine that viscosity is major factor. 50% ophthalmologist believes that carboxymethylcellulose is the most suitable ingredient followed by sodium hyaluronate (29.58%). 61.43% Ophthalmologists replied, AT should provide continues relief from dry eye symptoms. 42.86% said AT should be used for long terms, it should be preservative free replied by 58.57% Ophthalmologists and 40% replied acceptance from patient should be there in terms of cost. Tear substitutes are the most commonly prescribed medications for the management of dry eye disease. Artificial tears are amongst the first-line agents in the management options for the management of dry eye disease, because of their ease for usage, with a better safety and tolerability profile and their availability in various formulations.