This paper presents a recognition system for handwritten Pashto letters. However, handwritten character recognition is a challenging task. These letters not only differ in shape and style but also vary among individuals. The recognition becomes further daunting due to the lack of standard datasets for inscribed Pashto letters. In this work, we have designed a database of moderate size, which encompasses a total of 4488 images, stemming from 102 distinguishing samples for each of the 44 letters in Pashto. The recognition framework uses zoning feature extractor followed by K-Nearest Neighbour (KNN) and Neural Network (NN) classifiers for classifying individual letter. Based on the evaluation of the proposed system, an overall classification accuracy of approximately 70.05% is achieved by using KNN while 72% is achieved by using NN.
This article proposes and compares the performance of three flexible and bandwidth efficient transceivers. The terminology of Over-Complete Mapping (OCM) is introduced in the first two schemes. All of the schemes, namely Non-Convergent Serial Concatenated OCM Coding (NCSCOC), Convergent Serial Concatenated OCM Coding (CSCOC) and Self-Concatenated Convolutional Coding (SECCC); are simulated for the Rayleigh channel and employing iterative decoding to attain the refined output stream for feeding the video decoder. Specifically, the iterative decoding is beneficial in acquiring the convergence of EXtrinsic Information Transfer (EXIT) curves by repeatedly sharing of the mutual information. The difference between the NCSCOC and CSCOC schemes lies in the inner and outer rates. This change reflects an improvement in the Bit-Error Rate (BER) and improved EXIT convergence of CSCOC scheme, with reference to NCSCOC scheme. Results show that NCSCOC scheme never reaches the point of perfect convergence despite iterative decoding. However, CSCOC and SECCC schemes succeed in securing perfect convergence. Investigating the BER curves, it is deducible that SECCC is the most desirable transceiver system, having the least BER. Furthermore, it is plausible that the overall performance of SECCC is much better than the preceding schemes. Explicitly, our experimental results show that the proposed CSCOC scheme outperforms its identical code rate counterpart NCSCOC scheme by about 3 dB at the Peak Signalto-Noise Ratio (PSNR) degradation point of 1 dB. Additionally, an E b /N 0 gain of 20 dB is attained using SECCC scheme relative to identical code rate NCSCOC benchmarked scheme.
Machine learning in association with remote sensing has assisted agricultural specialists in monitoring, classification and yield estimation of crops. Tobacco is a major taxable crop of Pakistan, however the existing traditional methods for its monitoring and yield estimation are not only expensive and time consuming but also have limitations in terms of accuracy of collected data by a large number of diverse human surveyors. Due to the existence of such loopholes in the employed mechanism for tobacco crop monitoring and yield estimation, its illicit growth and distribution is on the rise. In this paper we have established a sophisticated machine learning mechanism for tobacco crop estimation using temporally stacked sentinel-2 satellite's data of Pakistan. Instead of the conventional approach of using single remotely sensed imagery for the target crop classification, we propose a machine learning based classification algorithm while keeping in view the phonological cycle of the target tobacco crop. Using the proposed mechanism, the temporal variations within the tobacco crop and its association with the variations of other vegetation is considered to improve the classification performance of the employed machine learning algorithm. Furthermore, the impact of stacking the vegetation indices derived from near infrared and vegetation red edge bands of sentinel-2 with the original sentinel-2 datasets, including Normalized Difference Vegetation Index (NDVI) and Normalized Difference Index 45 (NDI45), on the classification performance of the machine learning mechanism is investigated. Ground Truth data for training of our Artificial Neural Networks classifier, was obtained using indigenously developed survey application "GEOSurvey". Experiments were conducted using our proposed mechanism while considering various input data setups-including single date imagery, temporally stacked datasets based on phonological cycle of tobacco crop and different combinations of NDVI and NDI45 stacking. Our proposed experimental setup consisting of temporally stacked imagery along with NDVI stacking results in the best classification performance of 95.81% with reference to the single date imagery stacked with NDVI and NDI45, with performance gain of 07.32%.
In the current age of advanced technologies, there is an escalating demand for reliable wireless systems, catering to the high data rates of mobile multimedia applications. This article presents a novel approach to the concept of Self-Concatenated Convolutional Coding (SECCC) with Sphere Packing (SP) modulation via Differential Space-Time Spreading- (DSTS-) based smart antennas. The two transmitters provide transmit diversity which is capable of recuperating the signal from the effects of fading, even with a single receiving antenna. The proposed DSTS-SP SECCC scheme is probed for the Rayleigh fading channel. The SECCC structure is developed using the Recursive Systematic Convolutional (RSC) code with the aid of an interleaver. Interleaving generates randomness in exchange for extrinsic information between the constituent decoders. Iterative decoding is invoked at the receiving side to enhance the output performance by attaining fruitful convergence. The convergence behaviour of the proposed system is investigated using EXtrinsic Information Transfer (EXIT) curves. The performance of the proposed system is ascertained with the H.264 standard video codec. The perceived video quality of DSTS-SP SECCC is found to be significantly better than that of the DSTS-SP RSC. To be more precise, the proposed DSTS-SP SECCC system exhibits an E b / N 0 gain of 8 dB at the PSNR degradation point of 1 dB, relative to the equivalent rate DSTS-SP RSC. Similarly, an E b / N 0 gain of 10 dB exists for the DSTS-SP SECCC system at 1 dB degradation point when compared with the SECCC scheme dispensing with the DSTS-SP approach.
In this research work, we have presented an iterative joint source channel decoding- (IJSCD-) based wireless video communication system. The anticipated transmission system is using the sphere packing (SP) modulation assisted differential space-time spreading (DSTS) multiple input-multiple output (MIMO) scheme. SP modulation-aided DSTS transmission mechanism results in achieving high diversity gain by keeping the maximum possible Euclidean distance between the modulated symbols. Furthermore, the proposed DSTS scheme results in a low-complexity MIMO scheme, due to nonemployment of any channel estimation mechanism. Various combinations of source bit coding- (SBC-) aided IJSCD error protection scheme has been used, while considering their identical overall bit rate budget. Artificial redundancy is incorporated in the source-coded stream for the proposed SBC scheme. The motive of adding artificial redundancy is to increase the iterative decoding performance. The performance of diverse SBC schemes is investigated for identical overall code rate. SBC schemes are employed with different combinations of inner recursive systematic convolutional (RSC) codes and outer SBC codes. Furthermore, the convergence behaviour of the employed error protection schemes is investigated using extrinsic information transfer (EXIT) charts. The results of experiments show that our proposed R a t e − 2 / 3 SBC-assisted error protection scheme with high redundancy incorporation and convergence capability gives better performance. The proposed R a t e − 2 / 3 SBC gives about 1.5 dB E b / N 0 gain at the PSNR degradation point of 1 dB as compared to R a t e − 6 / 7 SBC-assisted error protection scheme, while sustaining the overall bit rate budget. Furthermore, it is also concluded that the proposed R a t e − 2 / 3 SBC-assisted scheme results in E b / N 0 gain of 24 dB at the PSNR degradation point of 1 dB with reference to R a t e − 1 SBC benchmarker scheme.
The reliable transmission of multimedia information that is coded through highly compression efficient encoders is a challenging task. This article presents the iterative convergence performance of IrRegular Convolutional Codes (IRCCs) with the aid of the multidimensional Sphere Packing (SP) modulation assisted Differential Space Time Spreading Codes (IRCC-SP-DSTS) scheme for the transmission of H.264/Advanced Video Coding (AVC) compressed video coded stream. In this article, three different regular and irregular error protection schemes are presented. In the presented Regular Error Protection (REP) scheme, all of the partitions of the video sequence are regular error protected with a rate of 3/4 IRCC. In Irregular Error Protection scheme-1 (IREP-1) the H.264/AVC partitions are prioritized as A, B & C, respectively. Whereas, in Irregular Error Protection scheme-2 (IREP-2), the H.264/AVC partitions are prioritized as B, A, and C, respectively. The performance of the iterative paradigm of an inner IRCC and outer Rate-1 Precoder is analyzed by the EXtrinsic Information Transfer (EXIT) Chart and the Quality of Experience (QoE) performance of the proposed mechanism is evaluated using the Bit Error Rate (BER) metric and Peak Signal to Noise Ratio (PSNR)-based objective quality metric. More specifically, it is concluded that the proposed IREP-2 scheme exhibits a gain of 1 dB Eb/N0 with reference to the IREP-1 and Eb/N0 gain of 0.6 dB with reference to the REP scheme over the PSNR degradation of 1 dB.
Real-world traffic flow parameters are fundamental for devising smart mobility solutions. Though numerous solutions (intrusive and non-intrusive sensors) have been proposed, however, these have serious limitations under heterogeneous and congested traffic conditions. To overcome these limitations, a low-cost real-time Internet-of-Video-Things solution has been proposed. The sensor node (fabricated using Raspberry Pi 3B, Pi cameral and power bank) has the capability to stream 2 Mbps MJPEG video of 640x480 resolution and 20 frames per second (fps). The Camlytics traffic analysis software installed on a Dell desktop is employed for traffic flow characterization. The proposed solution was field-tested with vehicle detection rate of 85.3%. The novelty of the proposed system is that in addition to vehicle count, it has the capability to measure speed, density, time headway, time-space diagram and trajectories. Obtained results can be employed for road network planning, designing and management.
Underwater Wireless Sensors Networks (UWSNs) use acoustic waves as a communication medium because of the high attenuation to radio and optical waves underwater. However, acoustic signals lack propagation speed as compared to radio or optical waves. In addition, the UWSNs also pose various intrinsic challenges, i.e., frequent node mobility with water currents, high error rate, low bandwidth, long delays, and energy scarcity. Various UWSN routing protocols have been proposed to overcome the above-mentioned challenges. Vector-based routing protocols confine the communication within a virtual pipeline for the sake of directionality and define a fixed pipeline radius between the source node and the centerline station. Energy-Scaled and Expanded Vector-Based Forwarding (ESEVBF) protocol limits the number of duplicate packets by expanding the holding time according to the propagation delay, and thus reduces the energy consumption via the remaining energy of Potential Forwarding Nodes (PFNs) at the first hop. The holding time mechanism of ESEVBF is restricted only to the first-hop PFNs of the source node. The protocol fails when there is a void or energy hole at the second hop, affecting the reliability of the system. Our proposed protocol, Extended Energy-Scaled and Expanded Vector-Based Forwarding Protocol (EESEVBF), exploits the holding time mechanism to suppress duplicate packets. Moreover, the proposed protocol tackles the hidden terminal problem due to which a reasonable reduction in duplicate packets initiated by the reproducing nodes occurs. The holding time is calculated based on the following four parameters: (i) the distance from the boundary of the transmission area relative to the PFNs’ inverse energy at the 1st and 2nd hop, (ii) distance from the virtual pipeline, (iii) distance from the source to the PFN at the second hop, and (iv) distance from the first-hop PFN to its destination. Therefore, the proposed protocol stretches the holding time difference based on two hops, resulting in lower energy consumption, decreased end-to-end delay, and increased packet delivery ratio. The simulation results demonstrate that compared to ESEVBF, our proposed protocol EESEVBF experiences 20.2 % lesser delay, approximately 6.66 % more energy efficiency, and a further 11.26 % reduction in generating redundant packets.
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.