Neural Networks are being used for character recognition from last many years but most of the works were reported to English character recognition. Character recognition is one of the applications of pattern recognition, which has enormous scientific and practical interest. Many scientific efforts have been dedicated to pattern recognition problems and much attention has been paid to develop recognition system that must be able to recognize a character. The main driving force behind neural network research is the desire to create a machine that works similar to the manner our own brain works. Neural networks have been used in a variety of different areas to solve a wide range of problems. A very little work has been reported for Handwritten Hindi Character recognition. In this paper, we have implemented Gradient feature extraction technique, which provides more than 94% recognition accuracy. We have acquired 1000 samples of handwritten Hindi characters by initializing the mouse in graphics mode. The 500 samples have been used for training the network (Train Data) and remaining 500 samples have been used for testing the network (Test Data). The system has been trained using several different forms of handwritings provided by both male and female participants of different age groups. Finally, this rigorous training results an automatic HCR system using MLP network. The error backpropagation algorithm has been used to train the MLP network. A comparative analysis was performed by implementing both global input and Gradient feature input. We have concluded that gradient feature extraction technique provides better recognition accuracy with reduced training time.
The ever-increasing demand of mobile system is posing a great challenge for efficient call delivery due to tremendous surge in numbers of mobile subscribers. In order to scale well with increased users, the efforts are underway to develop the new location management techniques as well as to optimize the existing ones so as to keep up-to-date information about current location of mobile phones without causing much traffic load in cellular network. Various location management optimization approaches are being explored and developed by research community in recent past. This papers sheds light on various such approaches in order to give a comprehensive overview of research registered in this field..
Location management being a major part of cellular network provides mobility to mobile subscribers. The current location information is required to route the call correctly to the recipient irrespective of its current location. The current HLR/VLR architecture for location management in standards like IS-41 & GSM suffers from call setup delay due to network congestion and also prone to failure due to its centralized nature. This paper attempts to make an evaluation of the optimized location management techniques suggesting fully distributed, hierarchical and multi HLR approach against the conventional one and also highlights the pros and cons of all the reviewed techniques.
Background: The World Health Organization (WHO) reported that Air pollution (AP) is prone to the highest environmental risk and has caused numerous deaths. Polluted air has many constituents where Particulate Matter (PM) is majorly reported as a global concern. Currently, the most crucial challenges faced by the globe are the identification and treatment of augmenting AP. The air pollution level was indicated by the Air Quality Index (AQI). It is affected by the concentrations of several pollutants in the air. Many pollutants in the air are harmful to human health. Thus, an efficient prediction system is required. Many security problems and lower classification accuracy are faced by them even though several prediction systems have been formed. A secure air quality prediction system (AQPS) centered upon the energy efficiency of smart sensing is proposed in this paper to overcome these issues. From disparate sensor nodes, the input data is initially amassed in the proposed work. The gathered data is stored in the temporary server. Next, the air-polluted data of the temporary server is offered to the AQPS, wherein preprocessing of the input data along with classification is executed. Methods: Utilizing the Improved Spotted Hyena Optimization-based Deep Convolution Neural Network (ISHO-DCNN) algorithm, the classification is executed. Utilizing the Repetitive Data Coding Based Huffman Encoding (RDC-HE) method, the polluted data attained from the classified output is compressed and encrypted by employing the American Standard Code for Information Interchange based Elliptical Curve Cryptography (ASCII-ECC) method. Results: Afterward, the encrypted and compressed data is saved in the Cloud Server (CS). Finally, for notifying about the AP, the decrypted and decompressed data is offered to the Base Stations (BS). Conclusion: The proposed work is more effective when analogized to the prevailing methods as denoted by the experimental outcomes. Higher accuracy of 97.14% and precision of 91.44% were obtained by the proposed model. Further, lower Encryption Time (ET) and Decryption Time (DT) of 0.565584 sec and 0.005137 sec were obtained by the model.
This study proposes a modification in the de-registration policy of Multi-HLR architecture. This architecture has made an attempt to overcome the drawbacks of Single centralized HLR architecture by introducing multiple HLRs in PCS networks in performing location managements of mobile units using explicit de-registration policy. This paper presents a modification in the de-registration policy of Multi-HLR architecture by applying the concept of implicit deregistration strategies and gives a performance analysis of this modified architecture to show how these implicit deregistration policies outperform the explicit de-registration strategy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.