JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH <p>Journal of advanced applied scientific research (JOAASR) is an entrenched podium for scientific exchange among applied scientific research. The journal aims to publish papers dealing with novel experimental and theoretical aspects of applied scientific research. The focus is on fundamental and advance papers that understanding of applied scientific research. JOAASR incorporates innovations of the novel theoretical and experimental approaches on the quantitative, qualitative and modeling of advanced scientific concepts.</p> en-US (Editorial Manager) (Softwar Manager ) Thu, 07 Apr 2022 12:20:10 +0000 OJS 60 Automation of Refrigeration Systems for Extending Shelf life of Fruits and Vegetables in Remote Areas for Economically Weaker Section <p>India is an agricultural country. During lockdown, there had been a big problem transporting the production<br>to cold storages. Considering the problem of villagers, a low cost and affordable refrigeration system is proposed<br>here. The time and cost of transportation through the cold chain and the storage are thus saved. This cold storage<br>is automated to control the environmental conditions suitable for extending life of fruits and vegetables. It uses a<br>microcontroller to control humidity, temperature and CO2 level which is appropriate for the commodity to be<br>stored by the farmer. It alerts the farmer before the expiry date of the stored commodity through a message on the<br>phone number linked with the storage. It uses the water obtained from condensation on cooling ducts for humidity<br>control. To maintain the optimum level of CO2 inside the chamber, fresh air is circulated at regular intervals of<br>time. It consumes same power as a refrigerator would consume. It does not require continuous water supply or<br>ammonia as in regular cold storage systems. It can be easily customized for a particular user.</p> Charu Pathak, Shruti Vashist Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 A Competent Convolutional Sparse Representation Model for Pan-Sharpening of Multi-Spectral Images <p>Two types of images are produced by Earth observation satellites, each having complementing spatial and<br>spectral characteristics. Pan-sharpening (PS) is based on remote sensing and image fusion approach that<br>produces a high spatial resolution multi-spectral image by merging spectral information from a low spatial<br>resolution multispectral (MS) image with intrinsic spatial details from a high spatial resolution panchromatic<br>(PAN) image. Traditional pan-sharpening methods continue to seek for a fused image that contains the<br>necessary spatial and spectral information. This work proposes a pan-sharpening method based on a recent<br>invention, convolutional sparse representation (CSR). Geometric structural characteristics are extracted from<br>the PAN image using a CSR-based filtering procedure. The challenge of learning filters, convolutional basis<br>pursuit denoising (CBPDN), is handled using a modified dictionary learning method based on the concept of<br>Alternating Direction Method of Multipliers (ADMM). The retrieved details are put into MS bands using<br>applicable weighting coefficients. Because the proposed fusion model avoids the standard patch-based<br>method, spatial and structural features are preserved while spectral quality is maintained. The spectral<br>distortion index SAM and the spatial measure ERGAS improve by 4.4 and 6.2 percent, respectively, when<br>compared to SR-based techniques. The computational complexity is reduced by 200 seconds when compared</p> <p>to the most recent SR-based fusion technique. The proposed method's efficacy is demonstrated by reduced-<br>scale and full-scale experimental findings utilising the QuickBird and GeoEye-1 datasets.</p> Rajesh Gogineni, Girish Kumar Darisi Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 4-Weighted Fractional Fourier Transform based Multiple Image Encryption Approach with PAN <p>In this manuscript, a new encryption approach for multiple images is proposed based on 4-weighted fractional<br>frequency transform (4-WFRFT) domain. First, the low frequency-components of all the images are obtained by<br>applying Fourier Transform on each image, which positioned at corner position of image, shifted to the central<br>position. Low-frequency component of each individual image is then scrambled with help of Arnold cat map<br>with its parameters and combined all scrambled image to form a single image with the same size that of original<br>image which is now ready for encryption process. Here, parameters of Arnold cat map and transform order of 4-<br>WFRFT treated as secret keys which are converted from Permanent Account Number (PAN) of authorize person.<br>The encrypted image information generated by authorize person can be recovered by applying PAN at receiver<br>side.</p> Arvind Singh Choudhary, Manoj Kumar, Sudhir Keshari Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Boron Nanoparticle Image Analysis using Machine Learning Algorithms <p>The effort of digital image processing involves efficient computation aimed at developing an economical, faster<br>and more accurate, and cost-effective automated system. The objective of this paper is to ascertain and categorize<br>Boron nanoparticles (BNP) using digital image processing techniques. The spatial features are unsheathed from<br>the Boron nanoparticle Transmission Electron Microscope (TEM) images using different segmentation<br>techniques, namely; Fuzzy C -means (FCM) and K-means. The size of Boron nanoparticles is determined and<br>categorized based on the area(size) in the microsize.The synthesization and characterization of Boron<br>nanoparticles play an important role as an elementary procedure for the formation of Boron nanoparticles. The<br>results are analyzed, interpreted and comparison is done with the manual values to observe the efficacy of the<br>results. It is observed that the K-means segmentation technique yields a smaller amountof error (5.87%) as<br>compared with Fuzzy C-mean(16.78%). Hence, it is considered that the K-Means is the most relevant<br>segmentation technique for Boron nanoparticle image analysis and categorization. The statistical test of<br>significance is applied using the Chi-square testing method (at 5% of significance level) to check the relationship<br>between the manual results and the algorithm results.The proposed study also establishes collaborative research<br>work between Chemistry and Computer Science departments to develop computational research on these<br>platforms.</p> Parashuram Bannigidad, Namita Potraj, Prabhuodeyara. M, Gurubasavaraj, Lakkappa.B.Anigol Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Intelligent Medicine Kit for Healthcare Monitoring, An IOT Based Solution <p>Increase in chronic diseases worldwide demands efficient healthcare solutions for maintaining well-being<br>of people. Treatment requires timely in-take of medicines and strict adherence to routine. This lack of adherence<br>is estimated to cause many deaths and hospitalizations. If we can get people to take their medications regularly,<br>they won’t develop complications. In addition to improving patient outcomes, medication adherence will reduce<br>health care costs associated with these conditions. Healthcare monitoring solutions based on Internet of Things<br>(IoT) technology has drawn significant research attention. This paper proposes an IoT based user configurable<br>customized intelligent medicine kit augmented with Wi-Fi and Bluetooth Low Energy technologies. It has<br>capability to detect whether patient is taking all prescribed medicines on fix schedule and intelligently<br>communicates the same to patient and their close relatives using uniquely created Four Tier Notification System<br>(FTNS), thus helping patient to live a healthy life. The paper discusses a novel theme on the functioning of a<br>medical grade device which would consume information from sensor and send it to the central server with a<br>maximum possibility of success using Four Tier Notification System (FTNS). This novel approach discusses<br>handshaking of connection to the central serve with a fallback mechanism to achieve maximum success of data<br>synchronization. This paper also discusses how this useful data from medicine kit can help healthcare sector to<br>closely track patient's physical activities and helps to influence the way healthcare sector operates in future.</p> Shailja Gupta, Sameer Gupta Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 A Systematic Study and Empirical Analysis of Lip Reading Models using Traditional and Deep Learning Algorithms <p>Despite the fact that there are many applications for analyzing and recreating the audio through existing<br>lip movement recognition, the researchers have shown the interest in developing the automatic lip-reading<br>systems to achieve the increased performance. Modelling of the framework has been playing a major role in<br>advance yield of sequential framework. In recent years there have been lot of interest in Deep Neural Networks<br>(DNN) and break through results in various domains including Image Classification, Speech Recognition and<br>Natural Language Processing. To represents complex functions DNNs are used and also they play a vital role<br>in Automatic Lip Reading (ALR) systems. This paper mainly focuses on the traditional pixel, shape and mixed<br>feature extractions and their improved technologies for lip reading recognitions. It highlights the most<br>important techniques and progression from end-to-end deep learning architectures that were evolved during<br>the past decade. The investigation points out the voice-visual databases that are used for analyzing and train<br>the system with the most common words and the count of speakers and the size, length of the language and<br>time duration. On the flip side, ALR systems developed were compared with their old-style systems. The<br>statistical analysis is performed to recognize the characters or numerals and words or sentences in English and<br>compared their performances.</p> R Sangeetha, D. Malathi Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Liver Lesions Classification System using CNN with Improved Accuracy <p>In this paper, the liver lesions classification system for CT images use deep learning (CNN)model with<br>improved accuracy has proposed. The sequential model of CNN architecture with I/P convolution layer, Hidden</p> <p>convolution layer, and O/P convolution layer for CT images have been used to classify liver lesions. TensorFlow-<br>2.0 is used to make an image with varying image qualities.The proposed network is used for CT images with an</p> <p>image size of 65×65, 60×60, 50×50 for which liver lesions classification accuracy of 99%,97%,95% respectively<br>are achieved. The regularization technique used in proposed N/W has helped to improve the accuracy and<br>minimization over fitting problem. The classification accuracy improvement has justified by comparing the<br>proposed research work with other researcher's work.</p> Swapnil V.Vanmore, Sangeeta R.Chougule Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Effect of Microwaves on the pH and °Brix value of Cranberry, Grape, Blackberry and Lemon <p>The microwaves find the potential capability in variety of applications, however the effects of<br>microwaves on the materials plays an important role. It is often discussed about the adverse effects of<br>microwaves on the fruits however this can be verified by considering two characteristics of fruits such as °Brix<br>and pH value.This paper focuses on the effect of microwaves exposure on some fruits. It aims to explain the<br>effect of microwave heating on °Brix and pH value of the Cranberry, Grape, Blackberry and Lemon fruits.<br>Two basic sections are considered here, one without exposure and other with exposure to microwaves.°Brix<br>and pH values of Cranberry, Grape, Blackberry and Lemon are measured before exposure to microwaves.<br>Brix measurement is done by the Aichose Refractometer &amp;pH value is measured by AMT28F pH meter.The<br>change in pH and °Brix value was noted for Cranberry, Grape, Blackberry and Lemon after exposure to<br>microwaves for given time intervals of 5, 10, 15 and 20 seconds of heating at 700 W power. With graphical<br>analysis, USDAstandards(United States Department of Agriculture) are utilized to validate the results.The<br>°Brix and pH values for all fruits have shown the variation when exposed to microwaveshowever the °Brix<br>and pH value were lying in the permissible limits referred by USDA standards after exposure to the<br>microwaves.</p> Anant D. Nimkarde, Shobhika P, Gopnarayan, Kanchan S Vaidya Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Dementia Detection Using LSTM and GRU <p>Neuro-degenerative infections, like dementia, can affect discourse, language, and the ability of correspondence.<br>A new report to work on the precision of dementia identification examined the utilization of conversation analysis<br>(CA) of meetings between patients and nervous system specialists to recognize reformist neuro-degenerative<br>(ND) memory issues patients and those with (non-reformist) FMD (Functional Memory Disorder). In any case,<br>manual CA is expensive for routine clinical use and hard proportional. In this work, we present an early dementia<br>discovery framework utilizing discourse acknowledgment and examination dependent on NLP method and<br>acoustic component handling strategy apply on various element extraction and learning using LSTM (Long<br>Short-Term Memory) and GRU which strikingly catches the transient provisions and long haul conditions from<br>authentic information to demonstrate the abilities of grouping models over a feed-forward neural organization in<br>estimating discourse investigation related issues. Dementia dataset is taken where the audio file is considered for<br>speech recognition analysis on basis of that data is generated and it is predefined given in dementia data databank.<br>That audio file is converted to text based on speech analysis. Using LSTM and GRU gives efficient results.</p> Neha Shivhare, Shanti Rathod, M. R. Khan Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Packrat Parsing with Dynamic Buffer Allocation <p>Packrat parsing is a type of recursive decent parsing with guaranteed liner time parsing. For this,<br>memoization technique is implemented in which all parsing results are memorized to avoid repetitive scanning<br>of inputs in case of backtracking. The issue with this technique is large heap consumption for memoization which<br>out weigh the benefits. In many situations the developers need to make a tough decision of not implementing<br>packrat parsing despite the possibility of exponential time parsing. In this paper we present our developed<br>technique to avoid such a tough choice. The heap consumption is upper bounded since memorized results are<br>stored in buffer, capacity of which is decided at runtime depending on memory available in the machine. This<br>dynamic buffer allocation is implemented by us in Mouse parser. This implementation achieves stable<br>performance against a variety of inputs with backtracking activities while utilizing appropriate size of memory<br>for heap.</p> Nikhil Mangrulkar, Kavita Singh, Mukesh Raghuwanshi Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 On the Real Time Object Detection and Tracking <p>Object detection and tracking is widely used for detecting motions of objects present in images and video.<br>Since last so many decades, numerous real time object detection and tracking methods have been proposed by<br>researchers. The proposed methods for objects to be tracked till date require some preceding information<br>associated with moving objects. In real time object detection and tracking approach segmentation is the initial<br>task followed by background modeling for the extraction of predefined information including shape of the objects,<br>position in the starting frame, texture, geometry and so on for further processing of the cluster pixels and video<br>sequence of these objects. The object detection and tracking can be applied in the fields like computerized video<br>surveillance, traffic monitoring, robotic vision, gesture identification, human-computer interaction, military<br>surveillance system, vehicle navigation, medical imaging, biomedical image analysis and many more. In this<br>paper we focus detailed technical review of different methods proposed for detection and tracking of objects. The<br>comparison of various techniques of detection and tracking is the purpose of this work.</p> Praful V. Barekar, Kavita R. Singh, Shailesh D. Kamble, Bhagyashree V. Ambulkar Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000 Challenges and Approaches in Green Data Center <p>Cloud computing is a fast evolving area of information and communication technologies (ICTs)that has<br>created new environmental issues. Cloud computing technologies have a widerange ofapplications due to their<br>scalability, dependability, and trustworthiness, as well as their abilityto deliver high performance at a low cost.<br>The cloud computing revolution is altering modern networking, offering both economic and technological<br>benefits as well as potential environmental benefits. These innovations have the potential to improve energy<br>efficiency while simultaneously reducing carbon emissions and e-waste. These traits have thepotential tomake<br>cloud computing more environmentally friendly. Green cloud computing is the science and practise of properly<br>designing, manufacturing, using, and disposing of computers, servers,and associated subsystems like displays,<br>printers, storage devices, and networking and communication systems while minimising or eliminating<br>environmental impact. The most significant reason for a data centre review is to understand capacity,<br>dependability, durability,algorithmic efficiency, resource allocation, virtualization, power management, and<br>other elements. The green cloud design aims to reduce data centre power consumption. The main advantage<br>of green cloud computing architecture is that it ensures real-time performance whilereducing IDC’s energy<br>consumption (internet data center).This paper analyzed the difficultiesfaced by data centers such as capacity<br>planning and management, up-time and performance maintenance, energy efficiency and cost cutting, real<br>time monitoring and reporting. The solution for the identified problems with DCIM system is also presented<br>in this paper. Finally, it discusses the market report’s coverage of green data centres, green computing<br>principles, andfuture research challenges. This comprehensive green cloud analysis study will assist native<br>green research fellows in learning about green cloud concerns and understanding future research challenges<br>in the field.</p> Sasi Kumar M, Sasi Kumar V, Samyukthaa L K, Gokul Karthik S, Vinothraja R Copyright (c) 2022 JOURNAL OF ADVANCED APPLIED SCIENTIFIC RESEARCH Thu, 07 Apr 2022 00:00:00 +0000