scholarly journals Design of Effective Smart Communication System for Impaired People

2021 ◽  
Vol 2 (4) ◽  
pp. 181-194
Author(s):  
Akey Sungheetha ◽  
Rajesh Sharma R
Keyword(s):  
Research Work ◽  
Recognition Rate ◽  
Difficulty Level ◽  
Normal Person ◽  
Research Article ◽  
Input Control ◽  
Proposed Model ◽  
Challenging Tasks ◽  
Output Module ◽  
Flex Sensors

In communication medium, sharing a conversation dialogue between the normal person and deaf and dumb person is one of the challenging tasks still. The dumb person can practice hand gesture language in their community but not to others. This research article focuses to minimize the difficulty level between these two communities with smart glove devices. Besides, the author believes that result of the proposed model provides a good impact on the dump community. The smart glove contains input, control, and output module to get, process, and display the data respectively. Our proposed model is used to help these communities to interact with each other continuously without any error. The proposed model is constructed with good specification flex sensors. Little change of resistance in flex sensor is providing changes in their gesture language. So this orientation direction is calculated well and gives better results over existing methods. The wireless set can be made with Bluetooth technologies here. Here the gestures are assigned based on the alphabet letter. The sign language performs and gives audible output in the display section of the proposed model. It gives good results in our experimental setup. This research work focuses on good recognition rate, accuracy, and efficiency. The good recognition rate shows the continuous conversation between the two persons. Moreover, this research article compares the recognition rate, accuracy, and efficiency of the proposed model with an existing model.

scholarly journals Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks

2020 ◽  
pp. 002029402096482
Author(s):  
Sulaiman Khan ◽  
Abdul Hafeez ◽  
Hazrat Ali ◽  
Shah Nazir ◽  
Anwar Hussain
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Research Work ◽  
Recognition Rate ◽  
Recognition Task ◽  
Convolution Neural Network ◽  
Medium Size ◽  
Support Vector ◽  
Artificial Neural

This paper presents an efficient OCR system for the recognition of offline Pashto isolated characters. The lack of an appropriate dataset makes it challenging to match against a reference and perform recognition. This research work addresses this problem by developing a medium-size database that comprises 4488 samples of handwritten Pashto character; that can be further used for experimental purposes. In the proposed OCR system the recognition task is performed using convolution neural network. The performance analysis of the proposed OCR system is validated by comparing its results with artificial neural network and support vector machine based on zoning feature extraction technique. The results of the proposed experiments shows an accuracy of 56% for the support vector machine, 78% for artificial neural network, and 80.7% for the proposed OCR system. The high recognition rate shows that the OCR system based on convolution neural network performs best among the used techniques.

Combination of gated recurrent unit and Network in Network for underwater acoustic target recognition

2021 ◽  
Vol 263 (6) ◽  
pp. 486-492
Author(s):  
Shuang Yang ◽  
Xiangyang Zeng
Keyword(s):  
Information Acquisition ◽  
Target Recognition ◽  
Recognition Rate ◽  
Temporal Correlation ◽  
Feedback Mechanism ◽  
Underwater Acoustic ◽  
Acoustic Information ◽  
Proposed Model ◽  
Acoustic Target ◽  
Gated Recurrent Unit

Underwater acoustic target recognition is an important part of underwater acoustic signal processing and an important technical support for underwater acoustic information acquisition and underwater acoustic information confrontation. Taking into account that the gated recurrent unit (GRU) has an internal feedback mechanism that can reflect the temporal correlation of underwater acoustic target features, a model with gated recurrent unit and Network in Network (NIN) is proposed to recognize underwater acoustic targets in this paper. The proposed model introduces NIN to compress the hidden states of GRU while retaining the original timing characteristics of underwater acoustic target features. The higher recognition rate and faster calculation speed of the proposed model are demonstrated with experiments for raw underwater acoustic signals comparing with the multi-layer stacked GRU model.

scholarly journals Design of Cascaded CNN for Medical Image Super Resolution

2021 ◽  
Vol 7 (3) ◽  
pp. 22-29
Author(s):  
Kajol Singh ◽  
Manish Saxena
Keyword(s):  
Neural Networks ◽  
Medical Image ◽  
Research Work ◽  
Super Resolution ◽  
Primary Objective ◽  
Lighting Conditions ◽  
Proposed Model ◽  
Filter Size ◽  
Medical Image Reconstruction ◽  
Image Super Resolution

The images captured through a camera usually belong to over or under exposed conditions. The reason may be inappropriate lighting conditions or camera resolution. Hence, it is of utmost importance to have a few enhancement techniques that could make these artefacts look better. Hence, the primary objective pertaining to the adjustment and enhancement techniques is to enhance the characteristics of an image. The initial numeric values related to an image get distorted when an image is enhanced. Therefore, enhancement techniques should be designed in such a way that the image quality isn’t compromised. This research work is focused on proposed a network design for deep convolution neural networks for application of super resolution techniques. To improve the complexity of existing techniques this work is intended towards network designs, different filter size and CNN architecture. The CNN model is most effective model for detection and segmentation in image. This model will improve the efficiency of medical image reconstruction from LR to HR. The proposed model showed its efficiency not only PET medical images but also on retinal database and achieved advance results as compared to existing works.

scholarly journals SOLF - A SOFTWARE DEVELOPMENT LIFECYCLE BASED ON GOLF

2020 ◽  
Author(s):  
CRS Kumar
Keyword(s):  
Software Development ◽  
Development Project ◽  
Difficulty Level ◽  
Golf Course ◽  
Skill Levels ◽  
Development Lifecycle ◽  
Proposed Model ◽  
Development Life Cycle ◽  
Software Development Lifecycle ◽  
Engineering Models

In the game of Golf, a player is challenged to take the minimum strokes to complete a round of 18 holes under varying playing conditions. Players use different clubs depending on their skill levels to achieve the desired distance while taking shots at the golf ball from the start (tee off) to the hole (pin). Unlike other games which have a standardized playing area, the terrain in a golf course comprises of various natural and manmade features viz. fairways, bunkers, trees, water bodies etc, which increase the difficulty level of the game and keep the players challenged.The game of golf has a fascinating similarity to a software development life cycle. If the holes on a golf course are considered akin to milestones in a development project then most of the Software Engineering models focus on software development in groups. Thus, we propose SOLF i.e Software Development Lifecycle model based on Golf, as a SDLC ideal for individuals or a small group of 2-3 developers. The proposed model is easy to comprehend, flexible and optimally adjustable in a dynamic environment.SOLF divides the project into 18 stages wherein each stage of the project will have 3 to 6 tasks which are required to be completed within a fixed timeline. The stages are managed by creating checklists at the start akin to the pre-shot routines in golf and the customer feedback is received on reaching each of the milestones similar to applause in the game of golf. Terrain of the golf course is reflected as risk list which are varying for each of the stages.SOLF achieves 10x speedup in software development and research projects as it creates an environment of challenges and drives the developer towards self excellence. It also inculcates a spirit of competition and sportsmanship by challenging the developers on various 'terrains' of development.

scholarly journals Multimodal biometrics of fingerprint and signature recognition using multi-level feature fusion and deep learning techniques

2021 ◽  
Vol 22 (1) ◽  
pp. 187
Author(s):  
Arjun Benagatte Channegowda ◽  
H N Prakash
Keyword(s):  
Deep Learning ◽  
Feature Fusion ◽  
Research Work ◽  
Recognition Rate ◽  
Recognition System ◽  
Multimodal Biometrics ◽  
Histograms Of Oriented Gradients ◽  
Multi Level ◽  
Deep Learning Neural Network ◽  
Hidden Neurons

Providing security in biometrics is the major challenging task in the current situation. A lot of research work is going on in this area. Security can be more tightened by using complex security systems, like by using more than one biometric trait for recognition. In this paper multimodal biometric models are developed to improve the recognition rate of a person. The combination of physiological and behavioral biometrics characteristics is used in this work. Fingerprint and signature biometrics characteristics are used to develop a multimodal recognition system. Histograms of oriented gradients (HOG) features are extracted from biometric traits and for these feature fusions are applied at two levels. Features of fingerprint and signatures are fused using concatenation, sum, max, min, and product rule at multilevel stages, these features are used to train deep learning neural network model. In the proposed work, multi-level feature fusion for multimodal biometrics with a deep learning classifier is used and results are analyzed by a varying number of hidden neurons and hidden layers. Experiments are carried out on SDUMLA-HMT, machine learning and data mining lab, Shandong University fingerprint datasets, and MCYT signature biometric recognition group datasets, and encouraging results were obtained.

scholarly journals IBPS: iBeacons Based Improved Indoor Positioning System

2020 ◽  
Vol 8 (5) ◽  
pp. 3792-3797
Keyword(s):  
Research Work ◽  
Energy Resource ◽  
Smart Phone ◽  
Indoor Positioning ◽  
Small Scale ◽  
Positioning System ◽  
Human Organ ◽  
Proposed Model ◽  
Small Hand ◽  
Indoor Positioning System

Smartphone plays a key role in integrating the entire world into a small hand. This feature made these smartphones as another human organ of many people. One of the main feature in every smart phone is GPS which used to travel new places, to locate and find optimized way to reach their destination. As we aware GPS is an outdoor application, GPS location is not accurate in indoor and small scale areas. This leads to an advanced research to improve the accuracy in GPS positing for the benefit of indoor applications. This research proposes a new iBeacons based Improved Indoor Positioning System for indoor positing application using Bluetooth low energy (BLE) beacons. This model helps the mobile application to find the exact location at micro-level scale. The objective of this research work is to design a potable indoor positing system (IPS) for indoor applications with at least 100m accuracy with in the inbuilt energy resource limitations. The proposed model has been built and verified in all the aspects. The location accuracy and energy efficiency of the proposed model is compared and found better than the existing models

scholarly journals Design of Vibration Frequency Method with Fine-Tuned Factor for Fault Detection of Three Phase Induction Motor

2021 ◽  
Vol 3 (1) ◽  
pp. 52-65
Author(s):  
Thomas Amanuel ◽  
Amanuel Ghirmay ◽  
Huruy Ghebremeskel ◽  
Robel Ghebrehiwet ◽  
Weldekidan Bahlibi
Keyword(s):  
Induction Motor ◽  
Vibration Frequency ◽  
Vibration Monitoring ◽  
Slight Variation ◽  
Frequency Method ◽  
Monitoring Method ◽  
Stator Current ◽  
Research Article ◽  
Proposed Model ◽  
Fault Parameters

This research article focuses on industrial applications to demonstrate the characterization of current and vibration analysis to diagnose the induction motor drive problems. Generally, the induction motor faults are detected by monitoring the current and proposed fine-tuned vibration frequency method. The stator short circuit fault, broken rotor bar fault, air gap eccentricity, and bearing fault are the common faults that occur in an induction motor. The detection process of the proposed method is based on sidebands around the supply frequency in the stator current signal and vibration. Moreover, it is very challenging to diagnose the problem that occur due to the complex electromagnetic and mechanical characteristics of an induction motor with vibration measures. The design of an accurate model to measure vibration and stator current is analyzed in this research article. The proposed method is showing how efficiently the root cause of the problem can be diagnosed by using the combination of current and vibration monitoring method. The proposed model is developed for induction motor and its circuit environment in MATLAB is verified to perform an accurate detection and diagnosis of motor fault parameters. All stator faults are turned to turn fault; further, the rotor-broken bar and eccentricity are structured in each test. The output response (torque and stator current) is simulated by using a modified winding procedure (MWP) approach by tuning the winding geometrical parameter. The proposed model in MATLAB Simulink environment is highly symmetrical, which can easily detect the signal component in fault frequencies that occur due to a slight variation and improper motor installation. Finally, this research article compares the other existing methods with proposed method.

scholarly journals LEVEL OF EMOTIONAL INTELLIGENCE AND ITS IMPACT ON ACCEPTANCE TO TECHNOLOGY IMPLEMENTATION: A STUDY ON EMPLOYEES OF PRIMARY COOPERATIVE CREDIT SOCIETIES IN IDUKKI DISTRICT

2021 ◽  
pp. 333-337
Author(s):  
Mrs. Maya Murali ◽  
Dr. Well Haorei
Keyword(s):  
Emotional Intelligence ◽  
Technology Implementation ◽  
Self Regulation ◽  
Research Work ◽  
Social Awareness ◽  
Self Awareness ◽  
Independent Variables ◽  
Research Article ◽  
Five Factors ◽  
Bank Employees

This research article is an extract of Ph.D. thesis research work. The present paper analyses the level of emotional intelligence and its impact on acceptance to technology implementation among the employees of primary cooperative credit societies in Idukki District. The study concluded that multiple regression analysis indicated independent variables, namely; social skills factor, social awareness factor, self-regulation factor, and self-awareness factor were highly significant in supplementing emotional intelligence among the bank employees in the study area. Further, from the analysis of Pearson’s correlation coefficient of emotional intelligence index and emotional intelligence factors, the study concludes that all the five emotional intelligence factors are statistically significant and has a positive correlation to emotional intelligence index. So, to increase the emotional intelligence level of the sample bank employees the higher authorities of the study banks should impart training in those five factors. KEY WORDS: Level of Emotional Intelligence and Impact, Employees, Idukki District

scholarly journals An Efficient FPGA-Based Convolutional Neural Network for Classification: Ad-MobileNet

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2272
Author(s):  
Safa Bouguezzi ◽  
Hana Ben Fredj ◽  
Tarek Belabed ◽  
Carlos Valderrama ◽  
Hassene Faiedh ◽  
...  
Keyword(s):  
Recognition Rate ◽  
Hardware Acceleration ◽  
Implementation Model ◽  
Gate Arrays ◽  
Proposed Model ◽  
Field Programmable ◽  
Programmable Gate Arrays ◽  
Computer Vision Applications ◽  
On Chip ◽  
Segmentation Image

Convolutional Neural Networks (CNN) continue to dominate research in the area of hardware acceleration using Field Programmable Gate Arrays (FPGA), proving its effectiveness in a variety of computer vision applications such as object segmentation, image classification, face detection, and traffic signs recognition, among others. However, there are numerous constraints for deploying CNNs on FPGA, including limited on-chip memory, CNN size, and configuration parameters. This paper introduces Ad-MobileNet, an advanced CNN model inspired by the baseline MobileNet model. The proposed model uses an Ad-depth engine, which is an improved version of the depth-wise separable convolution unit. Moreover, we propose an FPGA-based implementation model that supports the Mish, TanhExp, and ReLU activation functions. The experimental results using the CIFAR-10 dataset show that our Ad-MobileNet has a classification accuracy of 88.76% while requiring little computational hardware resources. Compared to state-of-the-art methods, our proposed method has a fairly high recognition rate while using fewer computational hardware resources. Indeed, the proposed model helps to reduce hardware resources by more than 41% compared to that of the baseline model.

Automated monitoring and assessment of productivity in earthmoving projects

2018 ◽  
Vol 45 (11) ◽  
pp. 958-972 ◽  
Author(s):  
Ashraf Salem ◽  
Osama Moselhi
Keyword(s):  
Data Fusion ◽  
Continuous Monitoring ◽  
Research Work ◽  
Sensor Data ◽  
Fusion Algorithm ◽  
Cost Overruns ◽  
Knowledge Based ◽  
Monitoring Model ◽  
Multi Sensor Data Fusion ◽  
Proposed Model

Continuous monitoring of productivity and assessment of its variations are crucial processes that significantly contribute to success of earthmoving projects. Numerous factors may lead to productivity variations. However, these factors are subjectively identified using manual knowledge-based expert judgment. Such manual recognition process is not only subject to errors but also time-consuming. There is a lack of research work that focuses on near real-time assessment of productivity variation and its effect on cost, schedule and effective utilization of resources in earthmoving projects. This paper presents a customized multi-source automated data acquisition model that acquires data from a variety of wireless sensing technologies. The acquired multi-sensor data are transmitted to a central MySQL database. Then a newly developed data fusion algorithm is applied for truck state recognition, and hence the duration of each earthmoving state. Multi-sensor data fusion facilitates measurement of actual productivity, and consequently the assessment of productivity ratios that support continuous monitoring of productivity variation in earthmoving operations. The developed tracking and monitoring model generates an early warning that supports proactive decisions to avoid schedule delays, cost overruns, and inefficient depletion of resources. A case study is used to reveal the applicability of the proposed model in monitoring and assessing actual productivity and its deviations from planned productivity. Finally, results are discussed and conclusions are drawn highlighting the features of the proposed model.

Sign in / Sign up

Export Citation Format

Share Document