International Journal on Recent and Innovation Trends in Computing and Communication

Journal Information
EISSN: 23218169
Total articles ≅ 900

Latest articles in this journal

Ashima Uppal, Mahaveer Singh Naruka, Gaurav Tewari
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 52-56;

Generally, it has been observed that due to lack of proper knowledge of disease intensity, the farmer is not able to use the pesticide in proper quantity to treat the diseases. The use of pesticide mostly becomes more than necessary, due to which there is not only a loss of money, but also it causes soil and environmental pollution. If diseases severity-wise labelled data sets are available, it can be used to develop pesticide recommendation systems. Images with least infection severity can be used to train and validate a DL model to capture the plant diseases at very initial stage. Classification techniques may be viewed as variations of detection systems; however, instead of attempting to identify only one particular illness among several diseases, classification methods detect and name the diseases harming the plant. This presents various classification and plant disease detection methods based on image processing with results.
Jitender Singh, Ashish Mani, H.P. Singh, Dinesh Singh Rana
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 01-12;

Economic load dispatch is a complex and significant problem in power generation. The inclusion of emission with economic operation makes it a Multi-objective economic emission load dispatch (MOEELD) problem. So it is a tough task to resolve a constrained MOEELD problem with antagonistic multiple objectives of emission and cost. Evolutionary Algorithms (EA) have been widely used for solving such complex multi-objective problems. However, the performance of EAs on such problems is dependent on the choice of the operators and their parameters, which becomes a complex issue to solve in itself. The present work is carried out to solve a Multi-objective economic emission load dispatch problem using a Multi-objective adaptive real coded quantum-inspired evolutionary algorithm (MO-ARQIEA) with gratifying all the constraints of unit and system. A repair-based constraint handling and adaptive quantum crossover operator (ACO) are used to satisfy the constraints and preserve the diversity of the suggested approach. The suggested approach is evaluated on the IEEE 30-Bus system consisting of six generating units. These results obtained for different test cases are compared with other reputed and well-known techniques.
Shalini Shalini, S. Srinivasan, Nitin Bansal, Piyush Prakash
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 57-63;

Cognitive architecture's purpose is to generate artificial agents with capacities similar to the human mind. Soar Cognitive Architecture is to produce the fixed computational building blocks needed for generally intelligent agents— agents that can outright a variety of tasks and encode, use, and learn all types of knowledge to realize the broad cognitive abilities present in humans. This paper introduced an arithmetic agent that does multicolumn, two-digit addition in SOAR. Here, we show the entire calculating procedure, including all of its operators. We are using episodic memory assistance to enhance the set of cognitive abilities that let the agent learn and reason.
Ravi Kumar Barwal, Neeraj Raheja, Malika Bhiyana, Dimple Rani
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 23-42;

An effective way to identify breast cancer is by creating a prediction algorithm using risk factors. Models for ML have been used to improve the effectiveness of early detection. This article analyses a KNN combined with singular value decomposition and Grey wolf optimization(GWO) method to give a detection of breast cancer(BC) at the early phase depending on risk metrics. The SVD technique was utilized to eliminate the reliable feature vectors, the GW optimizer was used to select the feature vectors, and while KNN model was used to diagnose the BC status. The proposed hybrid recommendation model (SVOF-KNN) for BC prediction's main objective is to give an accurate recommendation for BC prognosis through four different steps such as;BCCD dataset collection, data pre-processing, feature selection, and classification/recommendation. It is implemented to classify the consequence of risk metrics connected withregular blood analysis(BA) in the BCCD database. The aspects of the BC dataset are insulin, glucose, HOMA, Leptin, resistin, etc. The error categories such as RMSE and MAE are used to calculate the exception values for each instance of the BC dataset. It hybrid model has recommended the best score instance having the minimumexception rateas the defined features for BC prediction. It improves significance in automatic BC classification with the optimum solution. The hybrid recommendation model (SVOF-KNN) also recommends the accurateclassification method for BC diagnosis. The results of this work shall enhance the QoS in BC care.
Rajat Verma, Namrata Dhanda, Vishal Nagar
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 13-22;

Technological advancement is a never-ending field that shows its evolution from time to time. In 1832, with the invention of the electromagnetic telegraph, the era of the Internet of Things (IoT) began. Within the time of 190 years, this technological domain has revolutionized IoT and made it omnipresent. However, with this evolved and omnipresent nature of IoT, many drawbacks, privacy, interoperability, and security issues have also been generated. These different concerns should be tackled with some newer technologies rather than the conventional ones as somehow, they are only the generator of those issues. Outdated Security could be an appropriate issue of IoT along with the centralized point of failure. It also possesses more concerns and challenges to tackle. On the other side, there is a visible solution to address the challenges of IoT in this developing domain of technology. The visible approach is Blockchain which acted as the backbone in securing Bitcoin in 2008, which was created by the pseudo group named Satoshi Nakamoto. Blockchain has evolved from Blockchain 1.0 to Blockchain 4.0 as the latest one depicts its amalgamation with another component of Industry 4.0 i.e., Artificial Intelligence (AI). AI will give the ability to think logically and like humans. In addition to this SMART solution, there is also an advanced cryptographical technique known as the Elliptic Curve Digital Signature Algorithm (ECDSA) which can enhance the security spectrum of IoT if applied appropriately. This paper produces a vision to enhance and optimize the security of IoT using a network peer-to-peer technology Blockchain along with advanced cryptography.
M Jahir Pasha, K Sreenivasulu, B Roja Ramani, M Jaya Sunitha, K. Swetha, K Samunnisa
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 64-70;

This research article emphasises on use of algorithmic approach to activate sensors to optimize waste disposal and internet of things technology to notify the trash collectors when it is time to clean the trash cans. Here, a heuristic algorithmic approach will serve as the universal alarm and an SMS will be sent to the cleaners' registered mobile numbers as the local alert. The registered higher officials will receive an SMS alert if cleaners don't finish cleaning by the deadline. The top and bottom of a trashcan are where the ultrasonic sensors will be placed as part of the research goals. Every second, the value of the sensed ultrasonic sensor will be stored in the cloud. If the trash can is full, the lid will automatically close as a local warning. There will be a global alert sent via SMS to the authorised cleaners and higher officials. The research objectives include placing the ultrasonic at top and bottom of a dustbin. The sensed ultrasonic sensor value will store in a cloud at every second. As a local alert the lid of the garbage will be closed automatically if the dustbin is full. Global alert as a SMS will send to the authorized cleaners and higher officials. To know where the trash can is, attach a GPS sensor there. The existing intelligent dustbin is equipped with a voice controller that is used to classify the garbage but is not connected to the internet. In the existing system, an IoT platform was used with the assistance of a computer terminal, an infrared sensor, and continuous monitoring of the root plan to empty the dustbin. The lead of a dustbin is closed and opened by a vibration switch in smart homes. Whether the trash is full or not, the intelligent trash can will only locally but not worldwide transmit an alarm. The smart waste tank will communicate with smart phones by sending local dustbin values but was not stored in the cloud for every second. In this garbage narrow band IoT module was used but not internet. Accordingly the IoT enabled dustbin by placing the ultrasonic sensors, GPS sensor it is capable to know whether the dustbin is full or empty and the status will be indicated as local alert and global alert. The local alert will be the automatic lid closing of a dustbin and the global alert will be a SMS with the location of a dustbin and the status as full.
Patil Vinodkumar Ramesh, Jaware Tushar Hrishikesh, Manisha S. Patil
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 71-79;

Infant MRI brain soft tissue segmentation become more difficult task compare with adult MRI brain tissue segmentation, due to Infant’s brain have a very low Signal to noise ratio among the white matter_WM and the gray matter _GM. Due the fast improvement of the overall brain at this time , the overall shape and appearance of the brain differs significantly. Manual segmentation of anomalous tissues is time-consuming and unpleasant. Essential Feature extraction in traditional machine algorithm is based on experts, required prior knowledge and also system sensitivity has change. Recently, bio-medical image segmentation based on deep learning has presented significant potential in becoming an important element of the clinical assessment process. Inspired by the mentioned objective, we introduce a methodology for analysing infant image in order to appropriately segment tissue of infant MRI images. In this paper, we integrated random forest classifier along with deep convolutional neural networks (CNN) for segmentation of infants MRI of Iseg 2017 dataset. We segmented infants MRI brain images into such as WM- white matter, GM-gray matter and CSF-cerebrospinal fluid tissues, the obtained result show that the recommended integrated CNN-RF method outperforms and archives a superior DSC-Dice similarity coefficient, MHD-Modified Hausdorff distance and ASD-Average surface distance for respective segmented tissue of infants brain MRI.
Anubhav Kumar, Dileep Kumar M, Víctor Daniel Jiménez Macedo, B R Mohan, Achyutha Prasad N
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 11, pp 43-51;

The deployment of self-learning computer algorithms that can automatically enhance their performance via experience is referred to as machine learning in ecommerce and is a crucial trend of the retail digital transformation. Machine learning algorithms can be unambiguously trained by analysing big datasets, identifying repeating patterns, relationships, and anomalies among all of this data, and creating mathematical models resembling such associations. These models are improved when the algorithms analyse ever-increasing amounts of data, providing us with useful insights into specific ecommerce-related events and the links between all the variables that underlie them. A tool that has been quite effective in studying current affairs, predicting future trends, and making data-driven decisions. The present work investigates the implementation of machine learning algorithms to predict the user intention for purchasing a product on a specific store's website. An Online Shoppers Purchasing Intention data set from the UC Irvine Machine Learning Repository was used for this investigation. In this study, two classification-based machine learning algorithms i.e. Stochastic Gradient Descent (SGD) algorithm and Random Forest algorithm were used. SGD algorithm was used for first time in prediction of the online user intention. The results showed that the Random Forest resulted in the highest F1-Score of 0.90 in contrast to the Stochastic Gradient Descent algorithm.
Lakshmikanth Paleti, Ramakrishna Badiguntla, H. Venkateshwara Reddy, K. Prabhakar, Ch. Suresh Babu, K. Vamsi Krishna
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 10, pp 76-82;

Photographic training can result in new photographs that, to human observers, appear to be at least superficially authentic, with many realistic features. will discuss a number of intriguing GAN applications in order to help you develop an understanding of the types of problems where GANs can be used and useful. It is not an exhaustive list, but it includes numerous examples of GAN applications that have garnered media attention. This Paper Proposes a Framework for Generating Photorealistic Photos of real time objects (FGPPO) using Adam Optimizer by Generative Adversarial Networks.
Ch. N. Santhosh Kumar, M. Sailaja, Ali Hussain, Syed Ziaur Rahman
International Journal on Recent and Innovation Trends in Computing and Communication, Volume 10, pp 146-150;

The value of online media for getting news is questionable. People seek out and devour news from online media because it is convenient, inexpensive, and widely disseminated. In contrast, it facilitates the widespread distribution of "counterfeit news," or news of lower quality that includes fabricated data. Many people and institutions are negatively impacted by the widespread circulation of false information. As a result, detecting fake news via social media has emerged as a topic of interest for academics. Searching for and reading the news is becoming increasingly convenient as a result of the widespread availability, quick expansion, and widespread dissemination of traditional news outlets and social media. Nowadays, there is a plethora of information that can be found on social media, and it can be difficult to tell what is real and what is not. The distribution costs of releasing news via social media are inexpensive, and anyone can do it. The widespread circulation of false information could have devastating effects on both individuals and communities. Developing a reliable machine learning method for spotting fake news is the focus of this work.
Back to Top Top