arXiv subjects

Iuliana Marin

Publications and source records attributed to Iuliana Marin.

At least 19 recordsLinked to original sources

arXiv2026

Effects of Different Attention Mechanisms Applied on 3D Models in Video Classification

Human action recognition has become an important research focus in computer vision due to the wide range of applications where it is used. 3D Resnet-based CNN models, particularly MC3, R3D, and R(2+1)D, have different convolutional filters to extract spatiotemporal features. This paper investigates the impact of reducing the captured knowledge from temporal data, while increasing the resolution of the frames. To establish this experiment, we created similar designs to the three originals, but with a dropout layer added before the final classifier. Secondly, we then developed ten new versions for each one of these three designs. The variants include special attention blocks within their architecture, such as convolutional block attention module (CBAM), temporal convolution networks (TCN), in addition to multi-headed and channel attention mechanisms. The purpose behind that is to observe the extent of the influence each of these blocks has on performance for the restricted-temporal models. The results of testing all the models on UCF101 have shown accuracy of 88.98% for the variant with multiheaded attention added to the modified R(2+1)D. This paper concludes the significance of missing temporal features in the performance of the newly created increased resolution models. The variants had different behavior on class-level accuracy, despite the similarity of their enhancements to the overall performance.

cs.CV↗

arXiv2024

Privacy Management and Interface Design for a Smart House

In today's life, more and more people tend to opt for a smart house. In this way, the idea of including technology has become popular worldwide. Despite this concept's many benefits, managing security remains an essential problem due to the shared activities. The Internet of Things system behind a smart house is based on several sensors to measure temperature, humidity, air quality, and movement. Because of being supervised every day through sensors and controlling their house only with a simple click, many people can be afraid of this new approach in terms of their privacy, and this fact can constrain them from following their habits. The security aspects should be constantly analyzed to keep the data's confidentiality and make people feel safe in their own houses. In this context, the current paper puts light on an alternative design of a platform in which the safety of homeowners is the primary purpose, and they maintain complete control over the data generated by smart devices. The current research highlights the role of security and interface design in controlling a smart house. The study underscores the importance of providing an interface that can be used easily by any person to manage data and live activities in a modern residence in an era dominated by continuously developing technology.

cs.CR↗

arXiv2024

Evaluating Data Augmentation Techniques for Coffee Leaf Disease Classification

The detection and classification of diseases in Robusta coffee leaves are essential to ensure that plants are healthy and the crop yield is kept high. However, this job requires extensive botanical knowledge and much wasted time. Therefore, this task and others similar to it have been extensively researched subjects in image classification. Regarding leaf disease classification, most approaches have used the more popular PlantVillage dataset while completely disregarding other datasets, like the Robusta Coffee Leaf (RoCoLe) dataset. As the RoCoLe dataset is imbalanced and does not have many samples, fine-tuning of pre-trained models and multiple augmentation techniques need to be used. The current paper uses the RoCoLe dataset and approaches based on deep learning for classifying coffee leaf diseases from images, incorporating the pix2pix model for segmentation and cycle-generative adversarial network (CycleGAN) for augmentation. Our study demonstrates the effectiveness of Transformer-based models, online augmentations, and CycleGAN augmentation in improving leaf disease classification. While synthetic data has limitations, it complements real data, enhancing model performance. These findings contribute to developing robust techniques for plant disease detection and classification.

cs.CV↗

arXiv2023

Advancing Medical Education through the cINnAMON Web Application

The cINnAMON EUREKA Traditional project endeavours to revolutionize indoor lighting positioning and monitoring through the integration of intelligent devices and advanced sensor technologies. This article presents the prototypes developed for various project components and explores their potential application in medical education, particularly for aspiring healthcare professionals. The current variant of the intelligent bulb prototype offers a comparative analysis of the project's bulb against commercially available smart bulbs, shedding light on its superior efficiency and capabilities. Furthermore, the initial smart bracelet prototype showcases its ability to collect and analyse data from an array of built-in sensors, empowering medical students to evaluate fragility levels based on accelerometer, gyroscope, orientation, and heart rate data. Leveraging trilateration and optimization algorithms, the intelligent location module enables precise monitoring of individuals' positions within a building, enhancing medical students' understanding of patient localization in healthcare settings. In addition, the recognition of human activity module harnesses data from the bracelet's sensors to classify different activities, providing medical students with invaluable insights into patients' daily routines and mobility patterns. The user's personal profile module facilitates seamless user registration and access to the comprehensive services offered by the cINnAMON system, empowering medical students to collect patient data for analysis and aiding doctors in making informed healthcare decisions. With the telemonitoring system, medical students can remotely monitor patients by configuring sensors in their homes, thus enabling a deeper understanding of remote patient management.

cs.SE↗

arXiv2023

Memory Management Strategies for an Internet of Things System

The rise of the Internet has brought about significant changes in our lives, and the rapid expansion of the Internet of Things (IoT) is poised to have an even more substantial impact by connecting a wide range of devices across various application domains. IoT devices, especially low-end ones, are constrained by limited memory and processing capabilities, necessitating efficient memory management within IoT operating systems. This paper delves into the importance of memory management in IoT systems, with a primary focus on the design and configuration of such systems, as well as the scalability and performance of scene management. Effective memory management is critical for optimizing resource usage, responsiveness, and adaptability as the IoT ecosystem continues to grow. The study offers insights into memory allocation, scene execution, memory reduction, and system scalability within the context of an IoT system, ultimately highlighting the vital role that memory management plays in facilitating a seamless and efficient IoT experience.

cs.SE↗

arXiv2023

From Fake to Hyperpartisan News Detection Using Domain Adaptation

Unsupervised Domain Adaptation (UDA) is a popular technique that aims to reduce the domain shift between two data distributions. It was successfully applied in computer vision and natural language processing. In the current work, we explore the effects of various unsupervised domain adaptation techniques between two text classification tasks: fake and hyperpartisan news detection. We investigate the knowledge transfer from fake to hyperpartisan news detection without involving target labels during training. Thus, we evaluate UDA, cluster alignment with a teacher, and cross-domain contrastive learning. Extensive experiments show that these techniques improve performance, while including data augmentation further enhances the results. In addition, we combine clustering and topic modeling algorithms with UDA, resulting in improved performances compared to the initial UDA setup.

cs.CL↗

arXiv2023

Smart Home Environment Modelled with a Multi-Agent System

A smart home can be considered a place of residence that enables the management of appliances and systems to help with day-to-day life by automated technology. In the current paper is described a prototype that simulates a context-aware environment, developed in a designed smart home. The smart home environment has been simulated using three agents and five locations in a house. The context-aware agents behave based on predefined rules designed for daily activities. Our proposal aims to reduce operational cost of running devices. In the future, monitors of health aspects belonging to home residents will sustain their healthy life daily.

cs.MA↗

arXiv2022

Internet of Things and Health Care in Pandemic COVID-19: System Requirements Evaluation

Technology adoption in healthcare services has resulted in advancing care delivery services and improving the experiences of patients. This paper presents research that aims to find the important requirements for a remote monitoring system for patients with COVID-19. As this pandemic is growing more and more, there is a critical need for such systems. In this paper, the requirements and the value are determined for the proposed system, which integrates a smart bracelet that helps to signal patient vital signs. (376) participants completed the online quantitative survey. According to the study results, Most Healthcare Experts, (97.9%) stated that the automated wearable device is very useful, it plays an essential role in routine healthcare tasks (in early diagnosis, quarantine enforcement, and patient status monitoring), and it simplifies their routine healthcare activities. I addition, the main vital signs based on their expert opinion should include temperature (66% of participants) and oxygenation level (95% of participants). These findings are essential to any academic and industrial future efforts to develop these vital wearable systems. The future work will involve implementing the design based on the results of this study and use machine-learning algorithm to better detect the COVID-19 cases based on the monitoring of vital signs and symptoms.

eess.SP↗

arXiv2021

Oil and Gas Pipeline Monitoring during COVID-19 Pandemic via Unmanned Aerial Vehicle

The vast network of oil and gas transmission pipelines requires periodic monitoring for maintenance and hazard inspection to avoid equipment failure and potential accidents. The severe COVID-19 pandemic situation forced the companies to shrink the size of their teams. One risk which is faced on-site is represented by the uncontrolled release of flammable oil and gas. Among many inspection methods, the unmanned aerial vehicle system contains flexibility and stability. Unmanned aerial vehicles can transfer data in real-time, while they are doing their monitoring tasks. The current article focuses on unmanned aerial vehicles equipped with optical sensing and artificial intelligence, especially image recognition with deep learning techniques for pipeline surveillance. Unmanned aerial vehicles can be used for regular patrolling duties to identify and capture images and videos of the area of interest. Places that are hard to reach will be accessed faster, cheaper and with less risk. The current paper is based on the idea of capturing video and images of drone-based inspections, which can discover several potential hazardous problems before they become dangerous. Damage can emerge as a weakening of the cladding on the external pipe insulation. There can also be the case when the thickness of piping through external corrosion can occur. The paper describes a survey completed by experts from the oil and gas industry done for finding the functional and non-functional requirements of the proposed system.

cs.CV↗

arXiv2021

A Neuroscience Approach regarding Student Engagement in the Classes of Microcontrollers during the COVID19 Pandemic

The process of teaching has been greatly changed by the COVID-19 pandemic. It is possible that studying will not resemble anymore the process known by the previous generations of students. As the current generations learn by doing and use their intuition, new platforms need to be involved in the teaching process. The current paper proposes a new method to keep the students engaged while learning by involving neuroscience during the classes of Microcontrollers. Arduino and Raspberry Pi boards are studied at the course of Microcontrollers using online simulation environments. The Emotiv Insight headset is used by the professor during the theoretical and practical hours of the Microcontrollers course. The analysis performed on the brainwaves generated by the headset provides numerical values for the mood, focus, stress, relaxation, engagement, excitement and interest levels of the professor. The approaches used during teaching were inquiry-based learning, game-based learning and personalized learning. In this way, professors can determine how to improve the connection with their students based on the use of technology and virtual simulation platforms. The results of the test show that the game-based learning was be best approach because students had to become problem solves and start to use the software skills which they will need as future software engineers. The emphasis is put on mastering the mindset by having to choose their actions and to experiment along the way. According to their achievement, students receive experience points in a gamified environment. Professors need to adjust to a new era of teaching and refine their practices and learning philosophy. They need to be able to use virtual platforms with ease, as well as to engage with their students in order to determine and satisfy their needs.

cs.CY↗

arXiv2021

Securing the Network for a Smart Bracelet System

Digital instruments play a vital role in our daily life. It is a routine to produce business papers, watch the news program, write articles and blogs, manage healthcare systems, to purchase online, to send messages and all this is processed by making observations and then manipulating, receiving and availing the diverse data. This electronic data provides the foundation of real time data. All this transmission of data needs to be secured. Security is essential for healthcare systems as the present one where the blood pressure recordings provided by the smart bracelet are sent to the user's mobile phone via Bluetooth. The bracelet monitors the pregnant women, but also other users who wish to have their blood pressure under control. The system's server analyses the recordings and announces the user, as well as the associated persons to the user in case of an emergency. The doctors, the medical staff, user and user's family and caregivers have access to the health recordings belonging to the monitored user. Security is a main feature of the electronic healthcare system based on the smart bracelet.

cs.CY↗

arXiv2021

Brain Performance Analysis based on an Electroencephalogram Headset

Deficit of attention, anxiety, sleep disorders are some of the problems which affect many persons. As these issues can evolve into severe conditions, more factors should be taken into consideration. The paper proposes a conception which aims to help students to enhance their brain performance. An electrocephalogram headset is used to trigger the brainwaves, along with a web application which manages the input data which comes from the headset and from the user. Factors like current activity, mood, focus, stress, relaxation, engagement, excitement and interest are provided in numerical format through the use of the headset. The users offer information about their activities related to relaxation, listening to music, watching a movie, and studying. Based on the analysis, it was found that the users consider the application easy to use. As the users are more equilibrated emotionally, their results are improved. This allowed the persons to be more confident on themselves. In the case of students, the neurofeedback can be studied for the better sport and artistic performances, including the case of the attention deficit hyperactivity disorder. Aptitudes for a subject can be determined based on the relevant generated brainwaves. The learning environment is an important factor during the analysis of the results. Teachers, professors, students and parents can collaborate and, based on the gathered data, new teaching methods can be adopted in the classroom and at home. The proposed solution can guide the students while studying, as well as the persons who wish to be more productive while solving their tasks.

cs.HC↗

arXiv2021

Drone Control based on Mental Commands and Facial Expressions

When it is tried to control drones, there are many different ways through various devices, using either motions like facial motion, special gloves with sensors, red, green, blue cameras on the laptop or even using smartwatches by performing gestures that are picked up by motion sensors. The paper proposes a work on how drones could be controlled using brainwaves without any of those devices. The drone control system of the current research was developed using electroencephalogram signals took by an Emotiv Insight headset. The electroencephalogram signals are collected from the users brain. The processed signal is then sent to the computer via Bluetooth. The headset employs Bluetooth Low Energy for wireless transmission. The brain of the user is trained in order to use the generated electroencephalogram data. The final signal is transmitted to Raspberry Pi zero via the MQTT messaging protocol. The Raspberry Pi controls the movement of the drone through the incoming signal from the headset. After years, brain control can replace many normal input sources like keyboards, touch screens or other traditional ways, so it enhances interactive experiences and provides new ways for disabled people to engage with their surroundings.

cs.HC↗

arXiv2021

Smart Solution for the Detection of Preeclampsia

This paper is written in the context of the international Eurostars project, i-bracelet. The main objective of the i-bracelet project - "Intelligent bracelet for blood pressure monitoring and detection of preeclampsia" is the creation of a portable medical device for uninterrupted monitoring of blood pressure and to detect the blood pressure problems (such as hypertension) and, in particular, preeclampsia. In the current paper is described the software component of this system used for monitoring, viewing and analyzing the blood pressure values coming from a smart bracelet developed in the context of the project. The software solution is available for Android and iOS phone users, as well as it is accessible from a browser. As a conclusion, the blood pressure of the future mothers should be monitored for living a safer and healthier life.

physics.med-ph↗

arXiv2021

Enterprise domain ontology learning from web-based corpus

Enterprise knowledge is a key asset in the competing and fast-changing corporate landscape. The ability to learn, store and distribute implicit and explicit knowledge can be the difference between success and failure. While enterprise knowledge management is a well-defined research domain, current implementations lack orientation towards small and medium enterprise. We propose a semantic search engine for relevant documents in an enterprise, based on automatic generated domain ontologies. In this paper we focus on the component for ontology learning and population.

cs.AI↗

arXiv2021

Benchmarking MD systems simulations on the Graphics Processing Unit and Multi-Core Systems

Molecular dynamics facilitates the simulation of a complex system to be analyzed at molecular and atomic levels. Simulations can last a long period of time, even months. Due to this cause the graphics processing units (GPUs) and multi-core systems are used as solutions to overcome this impediment. The current paper describes a comparison done between these two kinds of systems. The first system used implies the graphics processing unit, respectively CUDA with the OpenMM molecular dynamics package and OpenCL that allows the kernels to run on the GPU. This simulation is done on a new thermostat which mixes the Berendsen thermostat with the Langevin dynamics. The second comprises the molecular dynamics simulation and energy minimization package GROMACS which is based on a parallelization through MPI (Message Passing Interface) on multi-core systems. The second simulation uses another new thermostat algorithm related respectively, dissipative particle dynamics - isotropic type (DPD-ISO). Both thermostats are innovative, based on a new theory developed by us. Results show that parallelization on multi-core systems has a performance up to 33 times greater than the one performed on the graphics processing unit. In both cases temperature of the system was maintained close to the one taken as reference. For the simulation using the CUDA GPU, the faster runtime was obtained when the number of processors was equal to four, the simulation speed being 3.67 times faster compared to the case of only one processor.

physics.comp-ph↗

arXiv2021

Novel Design and Implementation of a Vehicle Controlling and Tracking System

The purpose of this project is to build a system that will quickly track the location of a stolen vehicle, thereby reducing the cost and effort of police. Moreover, the vehicle's computer system can be controlled remotely by the owners of the vehicle or police. More precisely, the goal of this work is to design a, develop remote control of the vehicle, and find the locations with Latitude (LAT) and Longitude (LONG).

cs.RO↗

arXiv2021

User Requirements and Analysis of Preeclampsia Detection done through a Smart Bracelet

Medical students along with the medical staff have to monitor the state of the patients by using modern devices which have to offer precise results in a short amount of time, so that the intervention to be done as soon as possible. E-learning systems for blood pressure monitoring are used and new methods of patient observation, evaluation and treatment are applied compared to classical intervention. Based on this, medical students can improve their knowledge for the practical training. In the medical activities specialized devices occupy an important place. A device that can monitor the blood pressure is a smart bracelet that incorporates a pressure sensor along the wrist for continuous recording of blood pressure values. This enables the prediction of the emergency disorders using a decision support system. It facilitates the learning of new intervention approaches and boosts the responsiveness among learners. According to the World Health Organization, hypertensive disorders affect about 10% of pregnant women worldwide and are an important cause of disability and long-term death among mothers and children. This paper is based on a survey completed by persons of different ages and having various specialization domains regarding the use of smart bracelets for detecting preeclampsia. The aim is to decide upon its popularity among people and to determine the user requirements. The pregnant women will be constantly monitored, doctors can update the diagnosis of the patient. The medical students can learn from the critical situations and benefit from these cases while learning. The results of the survey showed that most of the interviewed persons consider the existence of such a device to be very useful, mostly the female individuals would feel more comfortable to have their blood pressure monitored during pregnancy.

cs.CY↗