{"title":"Wearable 2.4GHz Antenna on Textile Substrate","authors":"C. Mircea, Svasta Paul","doi":"10.1109/SIITME53254.2021.9663637","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663637","url":null,"abstract":"This paper presents a practical approach and a simple method for the design of a wearable textile substrate antenna especially made for clothing. The design presented focuses on obtaining a usable antenna for the common 2.4GHz band that can be easily made manually or using standard machinery using conductive textile materials and threads, embedded into normal clothing. Experiments are focused on working with UHF band antennas constructed using standard conductive textile fabric, thus demonstrating that good performance can be obtained for household, industrial, telecommunication and medical domains. Several techniques can be used to create an embedded flexible antenna onto textile materials, and performance of the presented wearable antenna is evaluated in a controlled environment and on human-body setups.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123905593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Suciu, Ijaz Hussain, Ioana Esanu, Cristian Beceanu, Robert-Ionut Vatasoiu, Marius Constantin Vochin
{"title":"Role of 5G in Vehicular Network for Smart Vehicles in Smart Cities","authors":"G. Suciu, Ijaz Hussain, Ioana Esanu, Cristian Beceanu, Robert-Ionut Vatasoiu, Marius Constantin Vochin","doi":"10.1109/SIITME53254.2021.9663700","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663700","url":null,"abstract":"The research work aims to design a decentralized decision-making mechanism with the help of data processing capacity and intelligence to the edge, to develop 5G network slicing methods, algorithms, and protocols and implement a proof-of-concept standalone B5G. The V2X and satellite-based maritime low-latency services are targeted. The paper will present how multiple wireless accessing technologies are designed to provide connectivity in vehicular networks and cellular communications using IoT. Recently, cellular V2X was standardized and developed for automotive services. V2X supports two communication modes through a single platform to provide both Wi-Fi and cellular communication. 5G-new radio is expected to address the automotive capabilities, improvement, and services for the 21st century. 5G-NR becomes a competitive technology compared to other wireless technologies due to high reliability, high capacity, extensive coverage, increased and minor delay. We optimize 5G with V2X and analyze the current V2X standards, introducing the development of 5G and considering its challenges, features, requirements, design, and technologies. We use Libelium smart city solutions for traffic measurements to analyze the congestion of vehicles or pedestrians by anonymously detecting and tracking the MAC addresses of the user’s devices on the road.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128486751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cristina Laura Sîrbu, Cristian Tomoiu, Szilvia Fancsali-Boldizsar, Ciprian Orhei
{"title":"Real-time line matching based speed bump detection algorithm","authors":"Cristina Laura Sîrbu, Cristian Tomoiu, Szilvia Fancsali-Boldizsar, Ciprian Orhei","doi":"10.1109/SIITME53254.2021.9663602","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663602","url":null,"abstract":"Active safety is one of the main technologies in the modern automotive industry. Active safety is achieved with advanced sensors that employ Computer Vision algorithms. To assist the driver and eventually to achieve fully autonomous driving, these sensors must be able to perform functions like lane detection, traffic signs recognition, detection of dynamic obstacles and irregularities of the road such as speed bumps. Speed bump detection is an important function for an advanced driver assistance system. In this paper, we present a speed bump detection algorithm that uses a mono-camera sensor as an input. We propose a real-time robust speed bump detection algorithm that first identifies a region of interest, based on semantic segmentation, and later on applies a novel variant of ED Line algorithm.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128631613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive data predictions for the energy sector at national level","authors":"P. V. Vezeteu, A. Morariu, D. Năstac","doi":"10.1109/SIITME53254.2021.9663610","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663610","url":null,"abstract":"Electric load forecasting is a central aspect of power generation planning as it allows the optimization of the production units. To date, no artificial neural network architectures (ANNs) were found that can precisely predict the consumption of energy at national level. In this paper, we propose the implementation of an artificial intelligence forecasting model that focuses on short term predictions. The current version is an enhancement of the previous approach which consisted of a full implementation in MATLAB. The algorithm was transposed in Python, using the new and updated tools such as TensorFlow and Keras, while taking into consideration a performance comparison between the two. To validate our model, we used, data from Romania between years 2008 to 2011. The implementation focuses on four main stages: restructuring and pre-processing the data, finding, and training the optimal model, refining the initial model, and retraining the neural network with new data. In terms of results, the current implementation decreased considerably the training time and returned a good prediction capability. On the other hand, the Python model was prone to overfitting, problem that was solved with techniques such as dropout and regularization layers. Regarding the architecture, it uses classical neurons as compared to other approaches in time series prediction that use LSTM cells. This simpler neural network offered higher efficiency in terms of computational resources while also being able to make accurate predictions.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129950672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automation of Information Exchange Between Neural Networks","authors":"Martin Kaloev, Georgi Krastev","doi":"10.1109/SIITME53254.2021.9663668","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663668","url":null,"abstract":"In recent years, there have been developments in neural networks and machine learning. Numerous platforms and tools for modeling A.I. are published. Compatibility between these platforms and tools is not always smooth because there are no common standards. This article describes the creation of a prototype of protocol that combine multiple neural networks into a common system. This approach offers solutions to machine learning problems related to the processing of large amounts of data.A protocol that allows the automation of the exchange of matrices with weights and bias between neural networks is investigated. The protocol monitors factors such as type of architecture, completeness of training data, network specialization and retraining opportunities. Methods for decentralization of the system and stability of the protocol are considered.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126329617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Development Process of a Quick SMS Auto Responder App for Car Drivers or Busy People","authors":"R. Szabó, A. Gontean, Andrei Burta","doi":"10.1109/siitme53254.2021.9663642","DOIUrl":"https://doi.org/10.1109/siitme53254.2021.9663642","url":null,"abstract":"The aim of this work is to redefine SMS messaging. Sometimes a person cannot respond to an SMS, since has no possibility to do this, because he is driving a car, or he is doing something and has no free hands, for example, when driving a car. To respond to an SMS can be done with an app which has predefined messages and this way the sender can get a quick response, but the receiver can continue his previous task, like driving a car or doing other things. When receiving an SMS message, the receiver can reply to it just by tapping on a predefined message.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126095959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"About narrow band optical digital filters based on metamaterials","authors":"D. Ionescu, G. Apreotesei","doi":"10.1109/SIITME53254.2021.9663696","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663696","url":null,"abstract":"The challenge for our work is setting a band pass filter with the central frequency f0 in visible range, which presents a very narrow band, so it is very selective. The material of the filter is represented by a layered metamaterial with constituents of tens of nanometer order, disposed geometrical in a manner in which can ensure a very precise control of the plasmons propagation at layers interface. We have studied and proposed a set of structures presenting a high tuning level concerning the wave propagation. Dielectric substrate layers with metallic inclusions were considered. Absorption and transmission coefficients were determined in order to find a correlation between the geometrical parameters which ensures a very narrow band of the filter structure. Analysis was performed using a structural simulation technique with help of the HFSS program. The S parameters of the filter structures were determined using a test configuration with the sample in a channel waveguide. For a set of specific wavelengths in the domain of 420 – 580 nm, desired filters were obtained, presenting a bandwidth which represents less than 1 % of the f0 value, depending on the metamaterial properties. The external tuning of the bandwidth is in study, by modifying the propagation direction of the incident field.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"4 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Loredana Buzura, Gabriel Groza, Radu Papara, R. Gălătuș
{"title":"Assisted OCT diagnosis embedded on Raspberry Pi 4","authors":"Loredana Buzura, Gabriel Groza, Radu Papara, R. Gălătuș","doi":"10.1109/SIITME53254.2021.9663686","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663686","url":null,"abstract":"Machine learning in recent years has raised interest in medical imaging application, also on OCT imaging due to the straights to determine clinically significant features for diagnostics and prognostication, with potential to boost biomedical imaging interpretation and medical decision making. Evolution of hardware nowadays made possible to embedded ophthalmology imaging and machine learning techniques for a faster and precise assisted diagnosis. A downside of machine learning is the necessity of powerful hardware to compute, with latest generations of CPU or GPU to run. Low-cost effective calculation is required in this case. In this paper, successfully ported on a Raspberry Pi 4 board and reviewed machine learning algorithms to predict the presence or absence of abnormalities in the retina. A predefined dataset has been used, composed of three different diseases of the retina and a normal case of the retina. The system is portable, making it easy to be used by doctors or resident physician in their knowledge improvement.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"307 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114281102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Student-centred Learning Environments in the Discipline \"Radio Communication Technologies\"","authors":"Ivanka D. Tsvetkova, A. Borodzhieva","doi":"10.1109/siitme53254.2021.9663635","DOIUrl":"https://doi.org/10.1109/siitme53254.2021.9663635","url":null,"abstract":"To engage students in the educational process, different active and interactive methods are mainly used but the core in all methods is that they present student-centred learning environment. But for the engineering students, there is one more important thing about education – the use of real equipment. The paper presents one topic studied in the discipline \"Radio Communication Technologies\" and the students’ opinions about the learning process, used in this discipline.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131815741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A simple High Voltage MOSFET behavioural model for SABER Simulator","authors":"O. Luca","doi":"10.1109/SIITME53254.2021.9663678","DOIUrl":"https://doi.org/10.1109/SIITME53254.2021.9663678","url":null,"abstract":"A behavioral High Voltage MOSFET model was developed by the author as an alternative to the high complex models which requires a huge effort for parameters extraction and to the available limited MOSFET models with tolerances for the model parameters.","PeriodicalId":426485,"journal":{"name":"2021 IEEE 27th International Symposium for Design and Technology in Electronic Packaging (SIITME)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116877956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}