International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Automatic Vehicle Number Plate Recognition Approach Using Color Detection Technique
Get PDFAn Automatic Vehicle Number Plate Recognition System (AVNPR) is a key research area in image processing. Various techniques are developed and tested by researchers to improve the detection and recognition rate of AVNPR system but faced problems due to issues such as variation in format, lighting conditions, scales, and colors of number plates in different countries or states or even provinces of a country. Douglas Peucker Algorithm for shape approximation has been used in this research to detect the rectangular contours and the most prominent rectangular contour is extracted as a number plate (NP) and the connected component analysis is used to segment the characters followed by optical character recognition (OCR) to recognize the number plate characters. A custom dataset of 210 vehicle images with different colors at various distances and lighting conditions was used for the proposed method captured on my smart phone Galaxy J7 Model SM-j700F at roads and parking. The dataset contains various types of vehicles (i.e. Trucks, motorcars, mini-buses, tractors, pick-ups etc). The proposed method shows an average result of 95.5%. The novelty used in this method is that it works for different colors simultaneously because in Pakistan, several colors are used for vehicle NPs.
Full Tex
Asphalt Pavement Potholes Localization and Segmentation using Deep Retina Net and Conditional Random Fields
Get PDFThe main aspect of maintaining the roads and highways\u27 durability and long life is to detect potholes and restore them. A huge number of accidents occur on the roads and highways due to the pothole. It also causes financial loss to vehicle owners by damaging the wheel and flat tire. For the strategies of the road management system and ITS (Intelligent Transportation System) service, it is one of the major tasks to quickly and precisely detect the potholes. To solve this problem, we have proposed a deep learning methodology to automatically detect and segment the pothole region within the asphalt pavement images. The detection of the pothole is a challenging task because of the arbitrary shape and complex structure of the pothole. In our proposed methodology, to accurately detect the pothole region, we used RetinaNet that creates the bounding box around the multiple regions. For the segmentation we used Conditional Random Field that segments the detected pothole regions obtained from RetinaNet. There are three steps in our methodology, image preprocessing, Pothole region localization, and Pothole segmentation. Our proposed methodology results show that potholes in the images were correctly localized with the best accuracy of 93.04%. Conditional Random Fields (CRF) also show good results.
Full Tex
Realization of Presentation layer information of Legacy Java Enterprise Applications Through Design Pattern’s Recovery
Get PDFThe presentation layer is the outermost layer of an application that providesuser interface and communication services. This layer is responsible for session management, controlling client access, and validations within data from the client.In legacy enterprise applications like Java Enterprise Edition Platform (Java EE),thedesign considerations of the presentation layer are spread over different design patterns and cross-language constructs. Resultantly, the analysis of such applications becomes quite challenging due to their heterogeneity, essentially requiredforthe extraction of design-level information and furthermodernization. In this research,a flexible technique is presented to extract presentation tier information based on customizable feature types by recovering instances of presentation tier patterns of the Java Enterprise EditionPlatform.The proposed approach is evaluated on well-operative open-source Enterprise Applications. The validation resultsdemonstratethe extraction of presentation tier information through Design Pattern’s recovery.This prototype is validated on the repository of source code of Java applications as well on open source java applications.
Full Text
Statistical Evaluation of Environmental Factors as Diabetogenic Agent in Type 2 Diabetes Mellitus
Get PDFThe purpose of this study was to analyze the environmental factors affecting individuals with diabetes. A study was conducted among diabetes patients at the Lahore General Hospital\u27s outdoor clinic. Data was collected using a standardized questionnaire after getting approval of patients being interviewed. SPSS 25.0 was utilized for analysis. Total 1000 people were chosen, 500 of whom were diabetic patients and the rest were non-diabetic. Environmental factors were investigated in a 1000-person research of diabetics and non-diabetics. To determine the relationship between patients with diabetes and environmental factors, the Chi-Square test and Mann-Whitney test were used to compare the effects of age, BMI, and sugar level fasting. The findings reveal that environmental factors play crucial effects on patients in term of age, BMI, and sugar level. I also used the odds ratio on diabetic and non-diabetic patients who have the Stroke, TIA, hypertension, and other environmental factors. The study revealed that diabetes is more persistent in industrial and urban region as 60% of the population living in these areas are under risk of diabetes. Moreover, the results showed that nearly 62% tap water consumers in rural areas were diabetic while 38% filtered water consumers in urban areas were diabetic. Smoking caused diabetes in nearly 22% people, 28% people suffered due to utilization of homeopathic medicines while 35% diabetic patients were found multivitamin consumers. Furthermore, the study depicted that among 1000 individuals under study, 56 % females were diabetic due to environmental factors. Diabetes has a direct relationship with the environment experienced by a patient.
Full Tex
Melanoma Detection Using a Deep Learning Approach
Get PDFMelanoma is a skin lesion disease; it is a skin cancer that is caused by uncontrolled growth in melanocytic tissues. Damaged cells can cause damage to nearby cells and consequently spreads cancer in other parts of the body. The aim of this research is the early detection of Melanoma disease, many researchers have already struggled and achieved success in detecting melanoma with different values for their evaluation parameters, they used different machine learning as well as deep learning approaches, and we applied deep learning approach for Melanoma detection, we used publicly available dataset for experimentation purpose. We applied deep learning algorithms ResNet50 and VGG16 for Melanoma detection; the accuracy, precision, recall, Jaccard index, and dice co-efficient of our proposed model are 92.3%, 93.3%, 90%, 9.98%, and 97.7%, respectively. Our proposed algorithm can be used to increase chances of survival for patients and can save the money which is used for diagnosis and treatment of Melanoma every year.
Full Tex
Dual-Band 10-Element MIMO Antenna for Sub-6 GHz MIMO Applications in 5G Smartphones
Get PDFThe dramatic growth of mobile users, IoT-based applications, and astounding channel capacity requirements to connect trillions of devices are some huge challenges of the previous mobile generations, 5G turned up the key solution. Although the 5G MIMO can boost channel capacity and spectrum efficiency, it is very challenging to integrate multiple antennas into a mobile phone with limited space. Therefore, we presented a multi-band 10-elements array antenna operating at the LTE (long term evolution) 42, 43, and 46 frequency spectrum (sub-6 GHz band) for MIMO applications in fourth/fifth generation (4G/5G) modern mobile phones in this paper. A simple T-shaped slot antenna is designed to acquire 10-element MIMO antenna implementation in LTE 42/43 and 46 bands. The presented antenna array is integrated using a low-priced FR-4 substrate which is typically used for 5.7- 6-inch smartphones and possesses dimensions of 150mm × 80mm × 0.8mm. The simulated results show superb impedance matching and isolation between ports (> -12 dB), radiation efficiency (>70 %), and Envelope Correlation Coefficient (ECC< 0.05) over the operational frequency. Consequently, the designed MIMO antenna array is effectively favorable for the 5G MIMO smartphone to enhance data output and the spectrum efficiency.
Full Tex
Estimation of Reference Evapotranspiration using Regionally Calibrated Hargreaves-Samani Equation
Get PDFEvapotranspiration (ETO) is a significant module in water-balance, irrigation scheduling and estimation of crop water requirement models. ETO can be adequately assessed when meteorological data are accessible to implement robust and strong models such as FAO-56 Penman-Monteith (PM). However, due to data insufficiency, substitute methodologies are essential. In this context, this study aims to calculate ETO from regionally calibrated Hargreaves-Samani (HSCAL), Hargreaves-Samani (HS) and Hargreaves methods which base on Land Surface Temperature (LST) and Solar Radiation (SR). SR was calculated from empirical formulas and Shuttle Radar Topography Mission (SRTM) 30m Digital Elevation Model (DEM). HSCAL uses SR which calculated from empirical formulas as an input, whereas HS and Hargreaves uses SR which calculated from the SRTM 30m DEM. LST was calculated from Landsat8 (LS8) thermal band for all three methods. Furthermore, ETO obtained from the HSCAL (ETO,HSCAL) was compared with standard FAO-ETO values and after verification HSCAL treated as standard for the verification of the remaining two methods on various Land Use Land Cover (LULC) types. Results of comparison between ETO,HSCAL and standard FAO-ETO shows that mostly values are within the range but lower side. Comparison also disclose that vegetation and built-up LULC are the best and worst case respectively. Further, ETO,HSCAL values are mostly fall within lower class of the ranges during the monsoon season (August-September). Further, the performance of the HS and Hargreaves are evaluated based on statistical indicators; Root Mean Square Error (RMSE), Mean Bias Error (MBE), Mean Absolute Error (MAE) and Correlation Coefficient (R2). ETO values of HS (ETO,HS) and Hargreaves (ETO,H) are underestimated in the sami-arid climate zone. The mean values of all statistical indicators are lower for ETO,HS in comparison to ETO,H when ETO,HSCAL is used to compare ETO,H with ETO,HS. It indicates that, in comparison to ETO,H, ETO,HS is close to ETO,HSCAL
Multirate Adaptive Equalization
Get PDFFinite Impulse Response (FIR) filter model emulates the Inter Symbol Interference (ISI) in a wireless communication channel. An equalizer, typically an Infinite Impulse Response (IIR) filter, behaves as an inverse filter to the FIR filter to remove the effects of the ISI. IIR filters are generally avoided due to tractability issues, and an FIR filter, with an adaptive signal processing algorithm to minimize the error due to the ISI, is deployed at the receiver. However, the filter is observed to quickly reach a steady state where further iterations do not yield a reduction in the error. This can be attributed to relatively slow variations in the steady state error which prevent further reduction of the errors. This work focuses on converting the low frequency error variations to high frequency variations by the use of multirate signal processing. As such, the steady state error can be damped as well, providing further reduction in the error and an enhanced adaptive filter performance.
Full Tex
Numerical Analysis of Impact of Relative Humidity on Crossflow Heat Exchangers with Staggered Configuration at Maximum Operating Temperature
Get PDFHeat exchangers are employed in numerous applications of industry, automotive and air conditioning systems. The efficacy of heat exchangers depends upon various factors e.g., Reynolds number (Re) of the fluids, geometry of heat exchanging surfaces, and the Prandtl number of the cooling air. In this paper, the working of a crossflow heat exchanger with elliptical tubes is simulated numerically for 5000 < Re < 20000 at its maximum operating temperature of 323K. The tubes were arranged in a staggered way. The radical investigations were done at one-of-a-kind relative humidity ranges within the cooling air ranging from 0% to 80%. The relative humidity was modeled in the shape of mass fractions of water vapors in the air. The thermos-physical properties of dry and moist air were employed for the analysis. The impact of this changing of relative humidity on forced convection heat transfer of heat exchangers is examined in the form of percentage change in Nusselt number. With the increase in moisture content in the air, the Nusselt number was observed increased up to 4.5%. The paper provides a tool to analyze the Nusselt number of the elliptical-shaped heat exchanger while operating in moist atmospheric conditions.
Full Tex
Voice Spoofing Countermeasure Based on Spectral Features to Detect Synthetic Attacks Through LSTM
Get PDFWith the growing number of voice-controlled devices, it is necessary to address the potential vulnerabilities of Automatic Speaker Verification (ASV) against voice spoofing attacks such as Physical Access (PA) and Logical Access (LA) attacks. To improve the reliability of ASV systems, researchers have developed various voice spoofing countermeasures. However, it is hard for the voice anti-spoofing systems to effectively detect the synthetic speech attacks that are generated through powerful spoofing algorithms and have quite different statistical distributions. More importantly, the speedy improvement of voice spoofing structures is producing the most effective attacks that make ASV structures greater vulnerable to stumble on those voice spoofing assaults. In this paper, we proposed a unique voice spoofing countermeasure which is successful to hit upon the LA attacks (i.e., artificial speech and transformed speech) and classify the spoofing structures by the usage of Long Short-Term Reminiscence (LSTM). The novel set of spectral features i.e., Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Cepstral Coefficients (GTCC), and spectral centroid are capable to seize maximum alterations present in the cloned audio. The proposed system achieved remarkable accuracy of 98.93%, precision of 100%, recall of 92.32%, F1-score of 96.01%, and an Equal Error Rate (EER) of 1.30%. Our method achieved 8.5% and 7.02% smaller EER than the baseline methods such as Constant-Q Cepstral Coefficients (CQCC) using Gaussian Mixture Model (GMM) and Linear Frequency Cepstral Coefficients (LFCC) using GMM, respectively. We evaluated the performance of the proposed system on the standard dataset i.e., ASVspoof2019 LA. Experimental results and comparative analysis with other existing state-of-the-art methods illustrate that our method is reliable and effective to be used for the detection of voice spoofing attacks.
Full Tex