International Conference on Innovations in Science, Engineering and Technology 2016 (ICISET 2016)

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 20 of 38
  • Item
    International Conference on Innovations in Science, Engineering and Technology 2022 (ICISET-2022)
    (Faculty of Science & Engineering, 2022-02-24) Editor: Karim, Rezaul
  • Item
    Human Activity Recognition using Depth Body Part Histograms and Hidden Markov Models
    (IEEE, 2016-10-28) Uddin, Md. Zia; Torresen, Jim; Jabid, Taskeed
    This paper proposes a novel approach for human activity recognition based on body part histograms and Hidden Markov Models. From a depth video frame, body parts are segmented first using a trained random forest. Then, a histogram for each body part is combined to represent histogram features for a depth image. The depth video activity features are then applied on hidden Markov models for training and recognition. The proposed method was superior when compared with other conventional approaches.
  • Item
    Development of a telemedicine model with low cost portable tool kit for remote diagnosis of rural people in Bangladesh
    (IEEE, 2016-10-28) Prodhan, Uzzal Kumar; Rahman, Mohammad Zahidur; Abid, Ahsin; Bellah, Mohtasim
    In this paper we have developed a Telemedicine model with portable tool kit for remote patients to collect vital signs of patients which are used for Telemedicine services. This developed system is low cost, portable, and easily maintainable and can be integrated with any complex health system. We have used the GNU health where local doctors can communicate with a low cost terminal. Expert doctors can also take part through this terminal and deliver treatment to the patients. The patient’s medical history is stored in GNU health database and accessed from the remote terminal. We have successfully designed the system and collected the patient's data. Through our developed android apps, the data will be stored in the staging server. From the staging server, any health system can collect the data and give the services to the rural people. Finally we can conclude that, Telemedicine service can be given effectively by using our portable tool kit in a cost effective manner which improves the quality and accessibility especially in rural areas.
  • Item
    A Compact Patch Antenna for Ultrawideband Application
    (IEEE, 2016-10-28) Islam, M. Tarikul; Samsuzzaman, M.; Islam, M. M.; Mahmmud, M.Z.; Islam, M.T.
    A compact microstrip line fed tapered-shaped slotted ultra-wideband(UWB) antenna is presented. The new design is composed of a rectangular slotted patch with a compact size of 21.44 × 23.53 mm2 and fed by microstrip transmission line of 50 Ω. The proposed antenna is simulated onto a less expensive FR4 substrate which has a height of 1.6 mm. There achieved a wider bandwidth of 8.51 GHz (3.49-12 GHz) with good impedance matching, constant gain, 5.76 dBi of maximum gain and stable radiation pattern results in the proposed antenna more appropriate for using UWB communication applications compared to existing antennas. The proposed antenna is designed and simulated in HFSS and CST Microwave Studio software to see the antenna performance.
  • Item
    Structural, Dielectric and Conductivity Studies of Ni-Cu-Cd Ferrite Nanoparticles
    (IEEE, 2016-10-28) Arifuzzaman, M.; Abden, M.J.; Ahmed, S.K.; Belal Hossen, M.
    In this study, the nanoparticles (NPs) of Ni0.6Cu0.1Cd0.3Fe2O4 (NCCF) ferrite was successfully synthesized by sol-gel auto combusted process. The effects of temperature and size on the structural, dielectric and conductivity properties of NCCF ferrite nanoparticles were investigated. X-ray diffraction (XRD) analysis of the NPs annealed at 550 and 700 ºC displayed the single phase cubic spinel structure with the particle size of 11 and 17 nm, respectively. The surface morphology of the annealed NCCF ferrite nanoparticles was studied by using field emission scanning electron microscopy (FESEM). Dielectric constant of larger particles shows higher values at low frequency as well as lower dielectric loss tangent. Ac conductivity shows conventional trend with size effects.
  • Item
    Bomb disposal Robot Discarding explosive through wireless controlled method
    (IEEE, 2016-10-28) Motaleb, Abdul Kadir Bin; Hoque, Mohammad Busayeed; Hoque, Md. Ahsanul
    Bomb disposal robot has been developed by different experts around the world to make an affordable and safe device which will be useful for emergency rescue support. A 6 DOF articulated robotic arm mounted on a moveable base is been developed to help bomb disposal squad to dispose bomb safely from distance. The whole operation of the robot can be performed wirelessly from a computer. DC servo motor is used as actuator of the arm, and the servo is controlled by the PWM signal generated by microcontroller. This report is concerned with the mathematical modeling of a 6 DOF robotic arm along with the methodology of the entire prototype development. Architectural and circuitry development are separately deliberated. Lastly, the performance of the developed robot has been discussed.
  • Item
    Automated Weather Event Analysis with Machine Learning
    (IEEE, 2016-10-28) Hasan, Nasimul; Uddin, Md. Taufeeq; Chowdhury, Nihad Karim
    Weather forecasting has numerous impacts in our daily life from cultivation to event planning. Previous weather forecasting models used the complicated blend of mathematical instruments which was insufficient in order to get higher classification rate. In contrast, simple analytical models are wellsuited for weather forecasting tasks. In this work, we focus on the weather forecasting by means of classifying different weather events such as normal, rain, and fog by applying comprehensible C4.5 learning algorithm on weather and climate features. The C4.5 classifier classifies weather events by building the decision tree using information entropy from the set of training samples. We conducted experiments on LA weather history dataset; from evaluation results, it is revealed that C4.5 classifier classifies weather events with f-score of around 96.1%. This model also indicates that climate features such as rainfall, visibility, temperature, humidity, and wind speed are highly discriminative toward events classification.
  • Item
    Frequency Domain Linear Prediction-Based Robust Text-Dependent Speaker Identification
    (IEEE, 2016-10-28) Islam, M. A.
    Speaker identification is a biometric technique of determining an unknown speaker's identity among a number of speakers using distinguish latent information of uttered speech. Crime investigation, security control, telephone banking and trading, and information reservation are some applications of this technique. Frequency Domain Linear Prediction (FDLP) is a time-frequency-based feature has been derived using 2-D autoregressive model. This feature was constructed from sub-bands short frame energies estimation. FDLP has been used in this study to propose a robust text-dependent speaker identification technique. The clean features were used to obtain speaker behavioural model. Support vector machine has been used to train the proposed method. This presented study was tested in both clean and noisy conditions to validate the method extensively. The proposed method got significant improved performance over all traditional methods performances in noisy conditions. The obtained performance was indicated; the proposed method was very robust to noises and showed consistent performance irrespective to noises.
  • Item
    GFCC-Based Robust Gender Detection
    (IEEE, 2016-10-28) Islam, M. A.
    Gender classification technique is a part of the signal processing comprises with feature extraction and behavioural gender modelling. Fundamental frequency and pitch are mostly used as feature for gender detection due to their unique characteristics in voice source. In this study, Gammatone Frequency Cepstral Coefficient (GFCC)-based robust gender classification method has been presented. This study was accomplished using speech samples from a text-dependent data set. The prototype gender behavioural modelling was done using Gaussian mixture model (GMM) to obtain better performance and only clean signal was used to train the model. The performance of the proposed method was tested under both clean and contaminated conditions. The clean signal was contaminated using nine different noises at a range of signal-to-noise ratios (SNRs) from 0 dB to 10 dB. The obtained performance showed the proposed method was very robust against noise and the average performance at 0 dB SNR was almost 100% for female and 92% for male irrespective to noises. So, it could be said the proposed method performance was almost noise invariant.
  • Item
    Bio Inspired Cyber Security Architecture for Smart Grid
    (IEEE, 2016-10-28) Faisal, Muhammad Mostafa Amir; Chowdhury, Muhammad Ariful Islam
    Smart grid is an advanced and intelligent form of conventional power grid with high fidelity power-flow control, self-healing, and energy reliability using advance computer and communication technologies. The idea of integrating power systems with complex computer communication has introduced serious cyber security concerns as it requires significant dependence on secured communication infrastructures. Because of the wide nature of smart grid, it is very risky to compromise any component of the grid which may lead to serious damage to the electrical infrastructure, energy theft and unnecessary expenditure. Studying various smart grid security architectures, efficient bio-inspired complete security architecture for smart grid is proposed in this work which can be easily implemented in the smart grid without changing any element of its infrastructure. Bio-inspired cyber security architecture for smart grid is developed with discussion on the core elements of the architecture. The threat detection is tested with simulation using popular KDDDump dataset and real time gas pipe line SCADA data.
  • Item
    Logical Clipper and De-clipper Technique to Reduce PAPR from OFDM Signal
    (IEEE, 2016-10-28) Raza, Md. Salim; Hasan, Md. Mhedi; Islam, Md. Obidul; Ali, Md. Shahjahan
    Orthogonal frequency-division multiplexing (OFDM) is the most effective technique for high speed wireless communication systems. The key challenge of OFDM based transceiver is its large peak to average power ratio (PAPR) due to non-linearity effects of power amplifier at final stage of OFDM transmitter. In this work performance of OFDM system using logical clipper and de-clipper in the OFDM transmitter and receiver respectively has been studied. In the proposed method the clipped portion of the signal is transmitted as side information which is subsequently used by the receiver to reproduce the original signal. The whole system was simulated in MATLAB environment considering AWGN channel. It is observed that the proposed system can significantly reduce PAPR of OFDM signal.
  • Item
    Design of a low-cost lighting system for the rural areas of Bangladesh
    (IEEE, 2016-10-28) Yasin, Mohammad Salman; Islam, Mohammad Sharier; Biswas, Tanmoy; Rahman, M. Saidur
    This study was conducted to find a solution to solve the problem of deprivation of light present in the rural society of Bangladesh. More than 50percent of our rural population are deprived of electricity. This in turns results in absence of light in houses. A device was designed using bottles, Light Emitting Diode, solar panel and battery for an alternative lighting system. This device is not so costly and can be reproduced very easily. Different variations of this device was tested using a light meter (Model-LX 1102). A brief overview of this newly proposed lighting system is discussed in the study.
  • Item
    Adopting Factors of Electronic Human Resource Management: Evidence from Bangladesh
    (IEEE, 2016-10-28) Masum, Abdul Kadar Muhammad; Alam, Md. Golam Rabiul; Alam, Mohammed Shamsul; Azad, Md. Abul Kalam
    The incorporation of information technology (IT) instincts the legacy of human resource management (HRM) towards agile HRM. To achieve agility, this paper explores the factors or determinants inducing the organisation decisions to adopt electronic human resource management (eHRM) in organisations of Bangladesh through structural equation modeling (SEM) of data science. To realize the influencing determinants, a research model was developed based on technology-organisation-environment (TOE) model. A total number of 320 respondents were participated from 48 organisations in Bangladesh using simple random sampling. The SEM results indicate that perceived compatibility, perceived cost, top management support, organisational culture, centralisation, IT vendor support, and government support have significant influence on management decision of e-HRM adoption. The applied implication of the findings and the scope of future studies are deliberated at the end of this paper.
  • Item
    Effects of Buffer Size and Mobility Models on the Optimization of Number of Message Copies for Multi-Copy Routing Protocols in Scalable DelayTolerant Networks
    (IEEE, 2016-10-28) Hossen, Md. Sharif; Ahmed, Md. Tofael; Rahim, Muhammad Sajjadur
    In Delay-Tolerant Network (DTN), there exists a lack of direct path from source to destination, and it is also featured by extremely high bit error rate, unwanted delay, limited resource, etc. For such network, we have investigated the effects of buffer size and mobility models on the optimization of the number of message copies for multi-copy routing protocols such as Spray-and-Focus (SNF) and Spray-and-Wait (SNW). This investigation is essential for providing us with the insight on the number of message copies that would provide better delivery, lower latency and lower overhead considering the effects of buffer size and mobility models in scalable delay-tolerant networks. In this investigation, we have considered three performance metrics, namely delivery probability, average latency, and overhead ratio. Simulation is done using Opportunistic Network Environment (ONE) simulator, which is designed basically for evaluating the performance of DTN routing strategies. Here we have considered three mobility models, namely Shortest Path Map Based (SPMB) movement, Random Walk, and Random Direction. Simulation results show that for increasing buffer size and number of nodes on these considered mobility models for a particular value of number of message copies, indicated by L, SNF routing exhibits satisfactory performance, especially in the case of SPMB movement using only L = 2 copies. Since our purpose is to provide a satisfactory performance, i.e., higher delivery, lower latency and lower overhead, SNW routing shows overall good performance using L = 10 copies. Therefore, it would be a good optimization using Shortest Path Map Based movement model using L = 2 copies for SNF routing, and L = 10 copies for SNW in scalable DTN scenario, where there may be a high possibility of varying buffer size with number of mobile nodes.
  • Item
    Selection of Better Strategy for Self Organized Data Aggregation Techniques using Evolutionary Game Theory
    (IEEE, 2016-10-28) Kader, Md. Salehin Ferdous; Hossain, Mir Muntasir; Ghose, Sanchita; Zafreen, Kazi Rehnuma
    Self Organized Data Aggregation Technique applying Evolutionary Game Theory is one of the most effective methods to select the optimum strategy for Delay Tolerant Network (DTN). In DTN, reliable end-to-end data transfer is provided by custody transfer mechanism where special nodes (custodians) exchange information with custody following hopby-hop manner. For multi cluster Delay Tolerant Network, message ferrying approach is considered here. Now, the strategy selection (to become an aggregator or sender) is considered as a game in Evolutionary Game Theory, where, each node will draw result after interaction. For strategy selection, Imitation Update Rule of Evolutionary Game Theory has been utilized. We will focus mainly on the Birth-Death and Death-Birth Update Rules of Evolutionary Game Theory and select the better Update rules among three update rules.
  • Item
    Design, Fabrication and Performance Evaluation of a Three Electrode ECG Recorder
    (IEEE, 2016-10-28) Chowdhury, Mehdi Hasan; Hossain, Quazi Delwar; Saha, Pradipta; Rahaman, Md. Mushfiqur
    Frequent monitoring is required for chronically ill cardiac patients to ensure superior treatment. This paper presents a low-cost, novel wearable electrocardiogram (ECG) measuring unit for consistent use. In this study, the ECG signal is accumulated by a three-electrode data acquisition system and measured by an integrated signal conditioning block AD8232. The analog signal from AD8232 is converted to digital data and recorded on a computer using unique software developed for this study. This automated software can store electronic records of the patients. These patient particulars can be forwarded to a proper medical support system if needed. To confirm the quality of ECG recorded by this prototype, clinical tests are conducted. The results of these assessments demonstrate the viability and efficacy of this system.
  • Item
    Combining a Rule-based Classifier with Weakly Supervised Learning for Twitter Sentiment Analysis
    (IEEE, 2016-10-28) Siddiqua, Umme Aymun; Ahsan, Tanveer; Chy, Abu Nowshed
    Microblog, especially Twitter, have become an integral part of our daily life, where millions of user sharing their thoughts daily because of its short length characteristics and simple manner of expression. Monitoring and analyzing sentiments from such massive amount of twitter posts provide enormous opportunities for companies and other organizations to learn about what user think and feel about their products and services. But the ever-growing unstructured and informal user-generated posts in twitter demands sentiment analysis tools that can perform well with minimum supervision. In this paper, we propose an approach for sentiment analysis on twitter, where we combine a rule-based classifier with weakly supervised NaiveBayes classifier. To classify the tweets sentiment, we introduce a set of rules for the rule-based classifier based on the occurrences of emoticons and sentiment-bearing words, whereas several sentiment lexicons are applied to train the Naive-Bayes classifier. We conducted our experiments based on the Stanford sentiment140 dataset. Experimental results demonstrate the effectiveness of our method over the baseline in terms of recall, precision, F1 score, and accuracy.
  • Item
    Predicting the Popularity of Online News from Content Metadata
    (IEEE, 2016-10-28) Md. Taufeeq Uddin, Md. Taufeeq; Patwary, Muhammed Jamshed Alam; Ahsan, Tanveer; Alam, Mohammed Shamsul
    Popularity prediction of online news aims to predict the future popularity of news article prior to its publication estimating the number of shares, likes, and comments. Yet, popularity prediction is a challenging task due to various issues including difficulty to measure the quality of content and relevance of content to users; prediction difficulty of complex online interactions and information cascades; inaccessibility of context outside the web; local and geographic conditions; social network properties. This paper focuses on popularity prediction of online news by predicting whether users share an article or not, and how many users share the news adopting before publication approach. This paper proposes the gradient boosting machine for popularity prediction using features that are known before publication of articles. The proposed model shows around 1.8% improvement over previously applied techniques on a benchmark dataset. This model also indicates that features extracted from articles keywords, publication day, and the data channel are highly influential for popularity prediction.
  • Item
    Optoelectronic Performance of Vertical Cavity Surface Emitting InGaAs/InP QW Laser in non-conventional orientation
    (IEEE, 2016-10-28) Roy, Sourav; Kabir, Md. Imtiaz; Mamun, K.M Abdullah Al
    Here, the optoelectronic performance of lattice matched InGaAs/InP vertical cavity surface emitting LASER is numerically simulated using MATLAB in (100), (110), (111), (113) and (131) crystal orientation by solving an eight-band k.p Hamiltonian using finite difference scheme including spin-orbit coupling. Tensor plane rotation formulae is applied to change the wave-vector k and Hamiltonian from orthodox (100) plane orientation. It is shown that there is a notable interrelationship between optical emission spectra and crystal plane orientations. The highest and lowest gains are estimated in (111) and (100) orientations with their respective peak emission wavelengths of 1770nm and 1680 nm at the carrier injection density of 2.5 × 1018 cm-3. The outcome of this paper would be a stimulus to design ultra-speed optoelectronic devices with performance amelioration by using non-100 oriented epitaxial layers.
  • Item
    A Comparative Analysis among PWM Control Z-source Inverter with Conventional PWM Inverter for Induction Motor Drive
    (IEEE, 2016-10-28) Islam, Md. Khurshedul; Zaved, Md. Mustafa; Siddiky, Air Mohammad; Mamun, Khandakar Abdulla Al
    The uses of induction motor is ever-growing day by day because of its superiority and high efficiency over dc machine. So for wide range of use in the industry, this machine requires an efficient driver circuitry arrangement. Currently conventional Voltage Source Inverter (VSI) or Current Source Inverter (CSI) is dealing as key part in the field of induction motor driver circuit. These converters fail to perform at our desire level due to some crucial drawbacks like they can perform as either buck or boost operation and they contain considerable amount of harmonics as well as EMI noise. So we are trying to replace these traditional inverters by PWM control Z-Source Inverter (ZSI) which offers buck-boost operation capability by utilizing shoot through state and provides less EMI noise. This paper presents a comparative study among these three inverters. Firstly three MATLAB simulation model of Induction motor driver by using VSI, CSI and ZSI (having almost same environment) have arranged. Then some important motor characteristics such as rotor speed, electromagnetic torque, rotor current and stator current have observed for three system models at various loading conditions. The model using Z-source inverter exhibits efficient performance in all cases compared to the other models.