• Send Your paper at :
  • ijirtm@gmail.com
  • editor@ijirtm.com

Impact Factor - 5.445


IJIRTM: Volume-6, Issue-3, 2022

Paper Title : Fast Beam Training in FDD Multi-User Massive MIMO for Client Coordination as a Review
Author Name : Chetna Singh, Prof.Anoop Kumar Khambra
Keywords : Beam selection, FDD massive MIMO, covari- ance shaping, training overhead, device-to-device.
Abstract :

A quick bar preparing plan for the gigantic recieving wire exhibits is a key to recurrence division duplex (FDD) mmWave frameworks, as channel correspondence between the down-connect (DL) and up-connect (UL) diverts doesn't hold as a rule, requiring input component for DL pillar choice. Because of the enormous number of radio wires in a huge exhibit, it isn't exceptionally pragmatic to lead a thorough hunt, particularly while thinking about the little precise inclusion of one directional limited pillar (thus the quantity of up-and-comer radiates). To address such a test, we consider the 3D pillar matching issue for a multi-client gigantic different information numerous result (MIMO) framework, and propose a two-stage hierachical codebook alongside the comparing quick bar preparing plan. The proposed codebook contains an essential codebook for progressive bars and a helper codebook for tight shafts following the restricted goal of the stage shifters (PSs). The quick pillar preparing plan in light of the codebook lessens shaft preparing above, yet additionally is material to the situation where there exist various engendering ways for one versatile station (MS). Mathematical outcomes show that the proposed plot not just partakes in a lower pillar matching intricacy (for example the preparation above), yet additionally accomplishes a similar exhibition to the comprehensive pursuit conspire.

Download IJIRTM-6-3-0603202204
Paper Title : Computational Modeling of Hippocampus to Store and Retrieve Patterns using Spiking Neural Network
Author Name : Manonit Utkarsh, Prof.Ratnesh Kumar Dubey, Dr.Sadhna K. Mishra
Keywords : Hippocampus modeling, Spiking Neural Network, Recalling.
Abstract :

In this research article, a computational model is proposed for DG and CA3 region of the hippocampus. Model is designed to store overlapped patterns, and to retrieve a complete pattern from a cue. In Proposed model, DG and CA3 region of the hippocampus is designed as pattern separator and as pattern storage respectively, where firing-rate based pattern separator is used. Here, DG and CA3 is combinedly described as two sequential associative networks. First network is used as a pattern separator and other one is used as a memory for storage of pattern to perform pattern completion from the incomplete pattern. Whole model is designed using Spiking neural network which makes it more realistic in nature. Model is deployed to store the grid patterns of black white blocks, and also recalling has been done successfully. Also, the architecture of proposed model follows the major phenomena of hippocampus like sparse connectivity and activation in DG.

Download IJIRTM-6-3-0603202205
Paper Title : Grouping In Wireless Sensor Network Utilizing K-MEANS and Map Reduce
Author Name : Chetna Singh, Prof.Anoop Kumar Khambra, Prof.Jitendra Mishra
Keywords : Beam selection, FDD massive MIMO, covariance shaping, training overhead, device-to-device.
Abstract :

A remote sensor organization (WSN) comprises of countless little sensors with restricted energy. Delayed network lifetime, adaptability, hub portability and burden adjusting are significant prerequisites for the vast majority WSN applications. Bunching the sensor hubs is a compelling procedure to accomplish these objectives. The different grouping calculations additionally contrast in their goals. We have proposed another technique to accomplish these objectives and the proposed strategy relies upon MAP-REDUCE programming model and K-MEANS grouping calculation. Thus, new grouping calculation has been proposed to bunch the sensor hubs of an organization. It utilizes MAP Diminish and K MEANS calculation for bunching. Network is partitioned into number of bunches, which we have taken as 5% of the all out number of hubs of an organization. Hubs are doled out to the bunch having least distance to the group head having most extreme energy. The distance is determined utilizing Euclidean Distance Recipe. We have additionally determined the intra bunch and bury group distance for the group. We additionally found the start to finish postponement of bundle transmission, energy utilization for the transmission. Introductory reproductions are performed to check the amount we can bring down the energy utilization by setting the group heads over the network. We have thought about two ways with which group heads can be set over the network, either place them arbitrarily or keep some distance among them. For this results are found and checked. These outcomes show that putting the group heads utilizing some negligible distance performs well than setting them arbitrarily.

Download IJIRTM-6-3-0603202206
Paper Title : Fatigue and Fractography Analysis of Artificially Age-hardened Al2016 High strength Aluminium Alloy
Author Name : Arivumani Ravanan, Ilamathi P, Balamurugan K
Keywords : Al2016, T6, Al-Cu alloy, fatigue strength, Fractography, Fracture mechanism, SEM.
Abstract :

Objectives of this experimental work are to determine the fatigue strength and to examine the fatigue fractured surface of the broken specimens of the Al2016-T6 alloy. Twin rolled Al-Cu alloy was received as cylindrical bar after the artificial aging under T6 condition. Specimens were prepared according to ASTM E606 standard and subjected to fatigue testing. Fatigue tests were conducted under the stress amplitude with an upper range of 250 MPa to a lower bound to fix the fatigue limit. SEM images were taken for the broken specimens where a high-cycle fatigue broken specimen images were chosen and investigated to understand its fracture, origin of fracture, surface morphology of fractured surface and the mechanism of failure.

Download IJIRTM-6-3-0603202208
Paper Title : Throughput Maximization with Energy Harvesting in Cognitive Radio Network
Author Name : Rajesh Sahu, Prof.Jitendra Mishra
Keywords : Energy harvesting, Throughput, False alarm probability, Cognitive radio network, Software defined radio, Primary user, Secondary user.
Abstract :

Recently, the conception of Internet of Things (IoT) has been widely applied in many areas, and brings great benefits to our daily life. According to Cisco annual internet report, IoT devices will account for 60% of all global networked devices in 2024, and the ever-increasing number of IoT devices has led to a significant growth of mobile data. The huge data traffic has led to scarcities of both spectrum and energy. The cognitive radio (CR) technology is emerging as one of the solutions to address the well-known spectrum scarcity problem. CR allows unlicensed users to opportunistically access the licensed (unused or under-utilized) frequency bands, thus improving the efficiency of the current radio spectrum usage. This paper present the comparative performance analysis for the throughput and false alarm probability in cognitive radio network with energy harvesting mechanism, Simulated study show that our presents work give better results than the existing work.

Download IJIRTM-6-3-0603202209
Paper Title : An Educational AR/VR System for Predicting Right Career Using Data Mining
Author Name : Kalyani Kanade, Himanshu Yadav
Keywords : Virtual Reality, Education, Data Mining, Prediction Models, Unreal Engine.
Abstract :

Virtual reality is an emerging technology which could potentially shape the future of education. According to actual demand for system analysis, this paper designs and develops data mining analysis system of college students’ data that can help them to predict right career on the basis of their ability test data. Data mining technologies are well grown and able to analyze any data. Proposed system will take students’ test data from the virtual reality devices and analyses their activities in real time. However, prediction is performed later when data is collected in the system for the processing with different data mining algorithms. Finally, through example test and analysis, the system is verified to be accuracy in related functions and it has practical application value to use data mining-based method to solve these problems.

Download IJIRTM-6-3-0603202210
Paper Title : A Wavelet Transformation based Performance Analysis on Image Denoising
Author Name : Aarti Gupta, Prof.Jitendra Mishra
Keywords : Edge detection, Wiener filter, Wavelet transformation, Image denoising, Matlab.
Abstract :

Visual information transmitted in the form of digital images is becoming a major method of communication in the modern age, but the image obtained after transmission is often corrupted with noise. The received image needs processing before it can be used in applications. Image denoising involves the manipulation of the image data to produce a visually high quality image. This process of image denoising is done by using methods that are with like wavelet transformation, wiener filter and mean filter. This all methods implemented in MATLAB. The input images are used here for the measured of image denoising techniques comparative performance used barbara image, cameraman image and house image, here proposed method gives better results than the existing work.

Download IJIRTM-06-03-202207
Paper Title : Computational Fluid Dynamic Thermal Simulation on Double Pipe Heat Exchanger
Author Name : Sharad Kumar Jain, Prof.P K Sharma
Keywords : CFD, Helical baffle, ANSYS, Heat exchanger.
Abstract :

The double tube or tube in the tube heat exchanger consists of a tube which is arranged concentrically in another tube of larger diameter. There are two types of flow in this configuration: parallel flow and counter flow. It can be organized into multiple series and parallel configurations to meet different heat transfer needs. The spiral arrangement stands out because it has found its place in various industrial applications. Since this configuration is widespread, knowledge of the heat transfer coefficient, pressure drop and various flow patterns has been of great importance. this analysis double pipe heat exchangers are divided into three different domains such as two fluid domains hot fluid in the inner tube and cold fluid in the outer pipe and a solid domain as helical baffles on inner tube of hot fluid. Mass flow rate cold fluid was varied from 0.1 kg/s to 0.3 kg/s while the flow rate in the inner tube i.e. hot water was kept constant at 0.1 kg/s.

Download IJIRTM-6-2-0603202201
Paper Title : Turning Process Parameter for Lathe Machine Optimization By Using Taguchi Method
Author Name : Manish Kumar, Prof.Swapnil Singh
Keywords : Turning Process, Parameters of machining, EN-8 steel, Taguchi Method, Experiments.
Abstract :

This paper investigates the parameters affecting the roughness of surfaces produced in the turning process for the various materials studied by researchers. Design of experiments were conducted for the analysis of the influence of the turning parameters such as cutting speed, feed rate and depth of cut on the surface roughness. The results of the machining experiments were used to characterize the main factors affecting surface roughness by the Analysis of Variance (ANOVA) method Taguchi’s parametric design is the effective tool for robust design it offers a simple and systematic qualitative optimal design to a relatively low cost. From the response graph plotted between turning parameters and hardness of EN 8, it is observed that there is increase in hardness as the speed is increased at 850 rpm but when speed is further increased hardness goes decreased. The hardness increases when feed rate is changed from 0.2 mm/rev to 0.3 mm/rev and 0.3 to 0.4 mm/rev, but when depth of cut is 1 mm then hardness increases, but as the depth of cut is further increased then hardness decrease considerably.

Download IJIRTM-6-3-0603202202
Paper Title : A Review on Energy Harvesting and Quality of Services in Cognitive Radio Network
Author Name : Rajesh Sahu, Prof.Jitendra Mishra
Keywords : Energy harvesting, Wireless communication, Cognitive radio network, Energy, Smart grid.
Abstract :

To fulfill ever-increasing demands for wireless services and applications, cognitive radio (CR) technology has been emerged to lighten severe shortage of spectrum resources. CR technology allows the secondary users (SUs) to access the spectrum licensed to the primary users (PUs), based on the premise that the quality of service (QoS) requirement of the PUs must be guaranteed. Radio-frequency (RF) energy-harvesting technology is a good candidate solution for charging the low-power wireless devices, which can conquer the uncontrollability and intermittency of wireless devices powered by the renewable energy sources, such as wind, solar and vibrational energy. This paper addresses the review work of energy harvesting in wireless communication and cognitive radio network. To improve the energy efficiency and spectrum efficiency mentioned above, the use of RF energy-harvesting technology in CR networks has been studied extensively in this paper.

Download IJIRTM-6-3-0603202203
Paper Title : Plant Disease Detection Techniques Based on Deep Learning Models: A Review
Author Name : Noorain Naaz, Prof.Himanshu Yadav
Keywords : Plant disease detection, image processing, image acquisition, segmentation, feature extraction, classification.
Abstract :

To avoid these diseases, plants need to be monitored at a very early stage in their life cycle. The traditional method used for this monitoring is visual observation, which requires more time and expensive expertise. Therefore, to accelerate this process, disease detection systems must be automated. Disease detection systems should be developed using image processing techniques. Many researchers have developed systems based on various techniques of image processing. This paper examines the potential of methods of plant leaf disease detection systems to promote the development of agriculture. It includes various steps such as image retrieval, image segmentation, feature extraction, and classification. Plant disease detection is a technique applied to detect disease in infected plants. Plant disease detection technology consists of two steps: segmentation of the first stage of an open input image to detect a sick part in the input image. A feature extraction technique is applied that extracts the features of the image and classifies the extracted features using various classifiers. In this paper, we will examine and explain various techniques of segmentation, feature extraction and classification from the viewpoint of various parameters.

Download IJIRTM-6-3-0603202211
Paper Title : Performance Analysis of Cancer Disease Diagnosis using Classification Technique
Author Name : Anil Paswan, Prof.Jitendra Mishra
Keywords : Health care, Accuracy, Support vector machines, Classification techniques, Multi layer neural network.
Abstract :

In the human body, there are several types of tissues formed by a plurality of cells. The inharmonious and vertiginous growth of these cells can cause a tumor, being able to be benign or malignant thus originating the cancer. Many researchers proposed many solutions and challenges of different phases of computer aided system to detect the lung cancer in early stages and give the facts about the lung cancer, breast cancer and other types of cancer. Breast cancer is the type of cancer that affects women more; however, there is a small possibility of occurring in men, even in a very unusual way, since according to statistics, for every 1 man diagnosed with cancer 100 women present the disease. Breast cancer accounts for more than 1 in 10 new cancer diagnosis each year and is the leading cause of cancer death in women. Cancer detection and diagnosis is one of the most important areas of research in medical field. Neural networks have been used for medical sciences by many researchers, for different classes of cancer. In this paper we present the feed forward neural network classifier for the breast cancer detection and improved the accuracy rate over the previous approach.

Download IJIRTM-6-3-0603202212
Paper Title : A Cascaded Method for Real Face Image Restoration using GFP-GAN
Author Name : Anamika Kumari, Prof.Ratnesh Kumar Dubey, Dr.Sadhna K. Mishra
Keywords : Face image restoration, GFP-GAN, Cascaded, Resolution, FID, NIQE, Celeb Child.
Abstract :

Blind face restoration is referred as the process which recovers the high quality images (HQ) from images having low quality (LQ) input. Generally LQ images experience defects of obscure degradation like low resolution, noise, blur as well as lossy compression. Latest restoration strategies actually centered on particularly super resolution method. Very few image restoration techniques work well to real LQ images except the same. When applied to genuine situations, it turns out to be really difficult, because of more convoluted degradation, different poses and articulations. In this paper, a cascaded method for real face image restoration using GFP-GAN has been proposed. For experiment on combined approach of GFP-GAN, FFHQ dataset has been used. All images which are used here are much authentic in the terms of their feature originality, hence it improves the results. Our GFP-GAN method has been trained on synthetic data which estimates LQ images. Training data have been generated by degradation model by passing high quality images through Gaussian blur kernel. At time of training for color enhancement color jittering has been used. FID and NIQE metrics was calculated on CelebChild image dataset for strongly verify our proposed work against available restoration model. Based on evaluation metrics it is shown that GFP-GAN works well comparative to other existing methods and can be adapted by different face image restoration applications.

Download IJIRTM-6-3-0603202213
Paper Title : Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios as a Review
Author Name : Ramdas, Prof.Anoop Kumar Khambra
Keywords : Face convolutional neural network, In-phase and quadrature (IQ) constellation diagrams, Samples Automatic modulation recognition (AMR), cognitive radio (CR), deep learning.
Abstract :

Programmed regulation acknowledgment (AMR) is a fundamental and chickening point in the improvement of the mental radio (CR), and it is a foundation of CR versatile balance and demodulation capacities to detect and learn conditions and make relating changes. AMR is basically an order issue, and profound learning accomplishes outstand-ing exhibitions in different characterization undertakings. Thus, this paper proposes a profound learning-based strategy, joined with two convolutional brain organizations (CNNs) prepared on various datasets, to accomplish higher precision AMR. A CNN is prepared on examples made out of in-stage and quadrature part flags, also called in-stage and quadrature tests, to recognize balance modes that are somewhat simple to distinguish. We embrace dropout as opposed to pooling activity to accomplish higher acknowledgment exactness. A CNN in light of star grouping charts is likewise intended to recognize balance modes that are hard to recognize in the previous CNN, like 16 quadratic-plentifulness regulation (QAM) and 64 QAM, evil presence starting the capacity to characterize QAM flags even in situations with a low sign to-commotion proportion.

Download IJIRTM-6-3-0603202214
Paper Title : Design of Railingwire Rope by Finite Element Method
Author Name : Shailendra Singh, Ranjeet Kumar, Dr.R S Sikarwar
Keywords : hoisting, 3D, stainless steel, deformation and shear stress.
Abstract :

Crane is a hoisting device use for lifting and lowering load with means of drum or lift wheel around which there will be rope or chain wraps. EOT crane is a mechanical devices used for lowering or lifting material, also used for making the material move vertically or horizontally. The results reveal that all three wire rope is bearing almost equal amount of stress on applying same load, this may be because the effective area of the WR are almost same or all three wire ropes. The results reveal that Seale type wire rope is bearing more shear stress on the same amount of load, the stress generated is almost 80% more than the ordinary wire rope, the torsion stresses act more on the first layer and this may be the reason as less diameter of the wires to resist stresses.

Download IJIRTM-6-3-0603202215
Paper Title : Design & Analysis on Truck Chassis By Using Fem
Author Name : Abhay Shrivastava, Prof.Trapti Sharma, Prof.Mamta Singh
Keywords : Chassis, FEA, LCV, Aluminum Alloy, Engine, Vehicle.
Abstract :

The automotive chassis is the backbone of the entire vehicle. A good chassis absorbs all sudden loads, torsional loads and impacts without damaging other parts of the chassis and offers the driver the best driving behavior and handling. Now the Indian auto market is growing and with it the demand for light commercial vehicles. Determined the stresses and deformation at various stacking conditions. Proposed the best reasonable material for undercarriage plan. Furthermore, all out deformation and comparable stresses was 2.6 mm and 25 mpa. The FEA Analysis Of Tata Ace Chassis configuration is worked with low thickness AL 7050- T7451 (2690Kg/m3) since it is a less weight and has a superb strength weight proportion and shows great bowing and twist firmness contrasting and other material thus FEA Analysis of truck with fiber material is a best elective plan for the light weight undercarriage plan.

Download IJIRTM-6-3-0603202216
Paper Title : Shell And Tube Type Heat Exchanger CFD Analysis by Using Different Baffle Inclination Angle
Author Name : Samshad Ansari, Prof.Neeraj Agrawal, Dr.Gurjeet Singh
Keywords : CFD, Solid Work, Heat exchanger, Heat, Inclination.
Abstract :

Heat Exchangers are components that allow the transfer of heat from one fluid (liquid or gas) to another fluid. In a heat exchanger there is no direct contact between the two fluids. Here modeling of heat exchanger has done on Solid work ver 2021 software and simulation has performed on Solid work 2021 CFD platform. Hence the design can be changed for higher heat transfer rate results through positioning of baffles changing in our new design. So we are able to visible that when angle of inclination baffle might be extended then heat transferred .we located that most. Right here we use 90 circular baffles, 10 degree inclination attitude with circular baffles, oval shape baffles and rectangular shape baffle. Here determined most heat transfer examine to 10 degree inclination of baffles is best compare to all design.

Download IJIRTM-6-3-0603202217
Paper Title : Techniques for the Detection of Plant Diseases Using Deep Learning Models: An Analysis and Review
Author Name : Mrinal Raj, Prof.Chetan Agrawal, Prof.Pooja Meena
Keywords : Machine Learning, Deep Learning, Plant Disease, image processing.
Abstract :

Monitoring the plants at a very early stage in their life cycle is necessary in order to protect them from these illnesses. Visual observation, which is the usual approach for carrying out this monitoring, is laborious, time-consuming, and requires specialized knowledge at a high cost. Because of this, disease detection systems really need to be automated in order to hasten the process. The development of disease detection systems that utilize image processing techniques is recommended. A large number of researchers have built systems that are based on a variety of image processing approaches. In this study, we investigate whether or not there is a connection between the methods of plant leaf disease detection systems and the advancement of agriculture. It covers a variety of stages like as retrieving images, segmenting those images, obtaining feature information, and classifying the data. The method known as plant disease detection is used to identify diseases that are present in plants that have already been affected. The segmentation of the first stage of an open input image to detect a sick region in the input image is the first stage of the technology used to detect plant diseases. The second stage is the analysis of the input image. An application of a feature extraction method is made, which extracts the features of the image and then classifies those recovered features utilizing a number of different classifiers. In this work, we will investigate and discuss a number of different methods of segmentation, feature extraction, and classification from the perspective of a number of different parameters.

Download IJIRTM-6-3-0603202218