Papers by sunjida sultana
Effect of Extended Back Gate in GaAs Based DG- JLMOSFET
2022 25th International Conference on Computer and Information Technology (ICCIT)
HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN
Neural Networks
Effect of Sidewall Spacers on the Performance of GaAs Based DG-JLMOSFET
2022 IEEE Region 10 Symposium (TENSYMP), Jul 1, 2022
Performance Analysis of GaAs DG-JLMOSFET: Impact of Gate Oxide and Its Thickness
2022 IEEE Region 10 Symposium (TENSYMP)
Sensors
Automatic leaf disease detection techniques are effective for reducing the time-consuming effort ... more Automatic leaf disease detection techniques are effective for reducing the time-consuming effort of monitoring large crop farms and early identification of disease symptoms of plant leaves. Although crop tomatoes are seen to be susceptible to a variety of diseases that can reduce the production of the crop. In recent years, advanced deep learning methods show successful applications for plant disease detection based on observed symptoms on leaves. However, these methods have some limitations. This study proposed a high-performance tomato leaf disease detection approach, namely attention-based dilated CNN logistic regression (ADCLR). Firstly, we develop a new feature extraction method using attention-based dilated CNN to extract most relevant features in a faster time. In our preprocessing, we use Bilateral filtering to handle larger features to make the image smoother and the Ostu image segmentation process to remove noise in a fast and simple way. In this proposed method, we prepro...
Performance Analysis of Graphene/AlxGa1-xN Schottky Contact at Elevated Temperature
2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2021
The performances of graphene/$Al_{x}Ga_{1-x} N$ contacts have been analyzed for the temperature r... more The performances of graphene/$Al_{x}Ga_{1-x} N$ contacts have been analyzed for the temperature range of 300 to 500 K. Analytical investigation shows that for all the compositions of Aluminium (Al) in $Al_{x}Ga_{1-x} N$, the diodes display good forward characteristics for each temperature. The required forwarding voltage is found to decrease with the increase of temperature. However, deviation of conventional characteristics is found for the graphene/GaN and graphene/$Al_{0.1}Ga_{0.9} N$ Schottky diodes. Moreover, graphene/$Al_{0.2}Ga_{0.8}N$ Schottky diode allows the highest forward current density of $6.5 \times 10^{5} Am^{-2}$ The contact resistivity is obtained smaller when the Al contents are 10% to 40 %. These consequences have been attributed to the low efficiency of Al incorporation in $Al_{x}Ga_{1-x} N$ alloy which is caused by parasitic gas phase reactions during the growth of this alloyed semiconductor. The results obtained here indicate that graphene/ $Al_{x}Ga_{1-x} N$ structure could be a potential candidate to be used as a Schottky rectifier; however, it needs proper investigation.
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 2021
There has been a tremendous increase in internet users and enough bandwidth in recent years. Beca... more There has been a tremendous increase in internet users and enough bandwidth in recent years. Because Internet connectivity is so inexpensive, information sharing (text, audio, and video) has become more popular and faster. This video content must be examined in order to classify it for different purposes for users. Several machine learning approaches for video classification have been developed to save users time and energy. The use of deep neural networks to recognize human behavior has become a popular issue in recent years. Although significant progress has been made in the field of video recognition, there are still numerous challenges in the realm of video to be overcome. Convolutional neural networks (CNNs) are well-known for requiring a fixedsize image input, which limits the network topology and reduces identification accuracy. Despite the fact that this problem has been solved in the world of photos, it has yet to be solved in the area of video. We present a ten stacked three-dimensional (3D) convolutional network based on the spatial pyramidbased pooling to handle the input problem of fixed size video frames in video recognition. The network structure is made up of three sections, as the name suggests: a ten-layer stacked 3DCNN, DenseNet, and SPPNet. A KTH dataset was used to test our algorithms. The experimental findings showed that our model outperformed existing models in the area of video-based behavior identification by 2% margin accuracy.
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 2021
In recent years, there has been a rapid development in web users and sufficient bandwidth. Intern... more In recent years, there has been a rapid development in web users and sufficient bandwidth. Internet connectivity, which is so low cost, makes the sharing of information (text, audio and videos) more common and faster. This video content needs to be analyzed for prediction it class in different purpose for the users. Many machines learning approach has been developed for the classification of video to save people time and energy. There are a lot existing review papers on video classification, but they have some limitations such as limitation of analysis, badly structured, not mention research gaps or findings, not clearly describe advantages, disadvantages, and future work. But our review paper almost overcomes these limitations. This study attempts to review existing video-classification procedures and to examine the existing methods of video-classification comparatively and critically and to recommend the most effective and productive process. First of all, our analysis examines the classification of videos with taxonomical details, latest application, process and datasets information. Secondly, overall inconvenience, difficulties, shortcomings and potential work, data, performance measurements with the related recent relation in science, deep learning and the model of machine learning. Study on video classification systems using their tools, benefits, drawbacks, as well as other features to compare the techniques they have used also constitutes a key task of this review. Lastly, we also present a quick summary table based on selected features. In terms of precision and independence extraction functions, the RNN(Recurrent Neural Network), CNN(Convolutional Neural Network) and combination approach performs better than the CNN dependent method.
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 2021
We present a modern hybrid paradigm for managing tacit semantic awareness and qualitative meaning... more We present a modern hybrid paradigm for managing tacit semantic awareness and qualitative meaning in short texts. The main goals of this proposed technique are to use deep learning approaches to identify multilevel textual sentiment with far less time and more accurate and simple network structure training for better performance. In this analysis, the proposed new hybrid deep learning HARC model architecture for the recognition of multilevel textual sentiment that combines hierarchical attention with Convolutional Neural Network (CNN), Bidirectional Gated Recurrent Unit (BiGRU), and Bidirectional Long Short-Term Memory (BiLSTM) outperforms other compared approaches. BiGRU and BiLSTM were used in this model to eliminate individual context functions and to adequately manage long-range features. Dilated CNN was used to replicate the retrieved feature by forwarding vector instances for better support in the hierarchical attention layer, and it was used to eliminate better text information using higher coupling correlations. Our method handles the most important features to recover the limitations of handling context and semantics sufficiently. On a variety of datasets, our proposed HARC algorithm solution outperformed traditional machine learning approaches as well as comparable deep learning models by a margin of 1%. The accuracy of the proposed HARC method was 82.50 percent IMDB, 98.00 percent for toxic data, 92.31 percent for Cornflower, and 94.60 percent for Emotion recognition data. Our method works better than other basic and CNN and RNN based hybrid models. In the future, we will work for more levels of text emotions from long and more complex text.
A 2-D Double Gate Heterojunction Tunnel-FET Based on AlGaSb/InAs: Analytical Analysis on Electric Field and Capacitance
2021 International Conference on Science & Contemporary Technologies (ICSCT), 2021
An accurate compact model based on the inversion charge mechanism is proposed for AlGaSb/InAs dou... more An accurate compact model based on the inversion charge mechanism is proposed for AlGaSb/InAs double-gate (DG) TFET structure. The surface potential profile is solved under suitable boundary conditions on 2-D Poisson’s equation. This profile is used to derive electric field and an analytical equation of band to band tunneling current is obtained from the Kane’s model. In order to explain the switching phenomenon of this device subthreshold swing (SS) is obtained from the drain current expression. Under different parametric analysis the model clearly mirrors its dependency towards changing gate bias, doping concentration as well as on oxide thickness. The effectiveness is served by adding a simple capacitance model of this structure. Several numerical simulations have revealed a remarkable improvement of the on-current in comparison with its single-gate (SG) structure.
Performance evaluation of GNSS receiver in multi-constellation system
2017 International Conference on Electrical, Computer and Communication Engineering (ECCE), 2017
With the increasing demand of users' multi-constellation will be one of the best modes in fut... more With the increasing demand of users' multi-constellation will be one of the best modes in future satellite navigation system. This basically provides a user the best accuracy in his position, motion and time. For given any positioning information at least four in view satellites are required. In this paper, the main idea is to integrate more satellite system and to achieve higher accuracy by increasing the number of satellites. DOP (Dilution of Precision) factors depending on this available satellites are the most fundamental components in the navigation system which give the timely cautioning for the malfunctioning satellites. From the simulation results, it is evident that all DOPs in multi-constellation are reduced with the combined effects of GNSS systems, which is the first requirement of any positioning accuracy. This availability of more in view satellites and combining signals from different navigation systems will help to minimize DOP and will yield an accurate position with higher precision level.
A Compact Analytical Model of Double Gate Tunnel-FETs AlGaSb/InAs Heterojunction Structure
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
This Paper puts forward a compact analysis of Double Gate (DG) AlGaSb/InAs based Tunnel Field Eff... more This Paper puts forward a compact analysis of Double Gate (DG) AlGaSb/InAs based Tunnel Field Effect Transistor (TFET) for simply modeling its drain current. A 2-D Poisson’s equation is solved to obtain the surface potential considering the boundary conditions. Then the drain current is derived based on the Kane’s model. The model also reflects the impacts of gate biasing, oxide thickness as well as doping concentration on the surface potential and current-voltage characteristics. In the results of the proposed model a remarkable improvement is noticed in the on-current of the DGTFET. Good agreement has revealed by several numerical simulations between AlGaSb/InAs single-gate (SG) and double-gate TFETs structure.
Performance Analysis of Multi-GNSS System Based on Dop, Interoperability and Raim with a New Approach to GNSS Based Tracking System
All praises to the Almighty Allah, the most gracious and the most merciful, who bestowed upon us ... more All praises to the Almighty Allah, the most gracious and the most merciful, who bestowed upon us the will, for the successful competition of our thesis paper within the scheduled time, without which the paper would not have been possible. With due sincerity, we would like to express our heartfelt gratitude and indebtedness to the thesis supervisor Gp Capt Dr. Md Hossam-E-Haider, Head, Department of Electrical, Electronic and Communication Engineering (EECE), Military Institute of Science and Technology (MIST), Dhaka, Bangladesh, whose encouragement, continuous guidance, valuable suggestions, close co-operation and cordial support from the initial to the final level enable us to complete the thesis in a prudent manner. His advice, initiative, moral support and patience are very gratefully acknowledged.
Analysis of DOP and its preciseness in GNSS position estimation
2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2015
Accurate positioning of objects is important for navigation applications which gives rise to many... more Accurate positioning of objects is important for navigation applications which gives rise to many interesting and challenging mathematical problems. These problems involve the relationship between positioning accuracy and satellite geometry in accordance to the user's position. Dilution of precision is an indicator of satellite geometry for constellation of satellites used to determine a position. Better the geometry, better the position accuracy. DOP describes the geometric strength of the visible satellites configuration on the GPS accuracy. Ideally, the visible satellites should be located at wide angles relative to each other. The geometry of such satellite configuration is said to be strong and the DOP values are low.GPS signals from small region of sky gives larger DOP values, and position accuracy will suffer. If we accept lower elevation mask angle, several more satellites are available and DOP values drop to about its ideal value. The main motivation for this work is to introduce with the concept of DOPs: GDOP, PDOP, HDOP, VDOP, TDOP and to derive a comparative conclusion on DOP among GPS, Galileo and combined GPS - Galileo satellite configuration.
An innovative implementation of indoor positioning system using GPS
2016 3rd International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2016
Global Positioning System is used by GPS tracking unit to determine the precise location of vehic... more Global Positioning System is used by GPS tracking unit to determine the precise location of vehicles, persons or other assets and to record their position at regular intervals. The recorded data can be stored within the tracking unit or it may be transmitted to a data base or internet-connected computer device using a cellular, radio or satellite modem embedded in the unit. This will allow the location to be demonstrated as a map backdrop either considered in real time or later analyzing the track depending on different GPS Tracking System. This archetype is a combination of cellular device, Information and Communications Technologies (ICT), indoor and outdoor positioning systems and Server Software giving people information to guide them to their destination. The main motivation of this work is to introduce with a new tracking system which is an innovative additional device that can enable the individual to enjoy the flexibility in motion and develops an advanced sense of confidence and self-reliance.
Uploads
Papers by sunjida sultana