BLOOD SMEAR ANALYSIS FOR ACUTE LEUKEMIA DETECTION-MACHINE LEARNING APPROACH

Abstract

Whenever the normal functioning of the body or any of its part becomes impaired, diseases occur and may require medical treatment. In general, diseases can be classified on the basis of their cause and cell of origin i.e. infectious, immunological, endocrine, genetic, neoplastic, and traumatic etc. Among all diseases the quest for understanding leukemia, a malignant neoplastic disorder is in the research forefront for several investigators including biologists, clinicians, and chemists. Physicians across the globe are interested in understanding the biology of diseases, and how it can be prevented, or treated. Studies reveal that excessive workload, shortage of trained pathologist, and use of conventional hematological evaluation methods are some of the leading causes behind delayed or wrong diagnosis in India. Such shortcomings can be overcome by the utilization of quantitative microscopic techniques in the precise characterization of blood test samples facilitating early diagnosis of blood cancers. The development of an automated system for cancer diagnosis in the scanned microscopic images involves four main computational steps i.e. preprocessing, segmentation, feature extraction and detection. The final machine learning approach that locates circles with accuracy even considering complicated conditions and noisy images. Keywords— Neoplastic, preprocessing, segmentation, feature extraction, Machine learning, Leukemia

RESEARCH OF THE MAIN REGULARITIES OF SYNTHESIS AND PROPERTIES OF THE GRAPH OF COPOLYMER COLLAGEN WITH ACRYLIC ACID

Abstract

The main results of the research of the regularities of synthesis and the properties of graft copolymer of collagen with acrylic acid are given.The optimal synthesis parameters: the initial ratio of components, the effect on the process of catalyst concentration, time and temperaturewere found.It was determined that with an increase of the amount of acrylic acid in the copolymerization process, the reaction rate, the viscosity of the solutions and the yield of the formed copolymers increase due to the participation of the double bond acrylate in chain transfer reactions.

FACTORS AFFECTING ONLINE SHOPPING BEHAVIOR OF INTERNATIONAL COLLEGE STUDENTS IN CHINA

Abstract

This study takes a closer look at decision and consumer factors that influence consumer’s online shopping behavior in China from an international college student perspective and to understand what motivates this behavior. To explore the influences of decision factors it was imperative to consider the role of Chinese Language barrier in a cross cultural context. To address the objectives of this study, a conceptual model is proposed along with research propositions. A self-administered questionnaire was used to collect data from 101 international college students. Findings identify and rank key decision factors; price, product variety, convenience, Chinese language barrier to have the most influence on international college students’ online shopping behavior. The results suggest that e-retailers should provide more personalization and consumer socialization options on their websites to target different consumers.

To improve the quality of mortar in the construction field using kota stone waste material as fully replacement of sand

Abstract

Mortar are one of the main part in brick masonary. The strength of mortar depends on the cement and sand properties, however the construction industry is increasing making higher demand of this material and is feared to accommodate the many requests at one time. The test were conducted by partials replacement of Kota stone slurry with sand of 25% ,50%, 75% & 100% for 1:3 mix ratio for mortar of (series -1). One more experimental are done in series-1 in which 100% sand are replace by 66.66% of Kota stone and 33.33% of fly ash are used. In Second Experiment (Series-2) the test were conducted for ratio of 1:6 by adding Kota stone slurry in sand 16.66% ,33.33%, 50% for increase the volume and strength of mortar by ratio of Cement: Kota stone: Sand (1:1:6, 1:2:6, 1:3:6).

STRESS ANALYSIS USING DIFFERENT COMBINATION OF COMPOSITE MATERIAL

Abstract

The report mainly emphasizes on the structural analysis of Hybrid Composite Cylinders which are used for under water respiration using ansys software using Solid45 and Layered46 elements. The results were noted down and a study was carried out to find out the hoop stress developed in the cylinder for different fiber combinations. For optimizing the thickness and hence to reduce the weight of the cylinder filament winding thickness were calculated for different winding angles. A comparison was made between the theoretical results and the analysis results which were found to be satisfactory. The margin of safety was found to be positive in all cases and thus the results are concluded to be satisfactory. The results so obtained were tabulated and conclusions were derived for different fiber combinations of cylinder.

“DESIGN AND ANALYSIS OF BODY FORGE COMPONENT”

Abstract

The Project work involves design & analysis of body forge component which is basically used in aircrafts landing gear hydraulic system as an electro hydraulic valve body designed as per the specification required. The component body forged is a three position, four way,electro hydraulic valve & as two solenoids for electric operation. This valve installed in landing gear bay & is used in hydraulic circuit for extension & retraction for landing gears. The component and die are designed taking into consideration various factors such as final component dimensions and material, grain flow significance, mechanical properties to be achieved etc. this component is manufactured completely by hot forging method using aluminium alloy (AA-2024), and the results are satisfactory.

Effect on Mechanical Properties of Brick Prepared with Granite and Marble Powder

Abstract

Stone manufacturing industries of Rajasthan is spread across the entire region of the state forming the grit of its economy. It produces more than 75 types of rocks and minerals making the state majestic mineral state in the nation. The natural rocks known as aggregates or stones are found in local areas out of which Marble being the one. The desert state itself contributes to 90% of the total marble production all over the country. The rock industries have provided employment opportunities and have used stones in building mesmerizing heritage and monuments of the State. More and more demand for finished and unfinished products are pouring in, exploring of various marble types have increased the growing rate of Marble Industry in the region. As a result, marble processing units and marble quarries had grown in the past ten years. This has lead to generation of waste to a very large amount; hence an alarming situation for the ailing environment and nature. Sustainability and environment friendliness for the industry has become an immediate social need. The motive shown in this report points in finding out a reasonable, viable and viable way to extract out the waste in the form of marble and granite slurry produced from these industries. Many ways are put forward in order to use the waste which is in the form of marble slurry and granite powder stone clay by producing clay bricks. In this report, investigation has been carried out to use such concrete and test the compression strength, water absorption capacity and density of the produced concrete. This study has concluded that the economics of clay would be improved by adding cheap marble and granite waste from stone industry, thus enhancing the quality of clay bricks in all senses. Also, the issue of stone slurry as a waste material would be resolved by integrated marble usage and waste of granite in the clay bricks thus making it a win situation for everyone. Keywords: Brick, clay, granite and marble powder, compressive strength, density.

Review of Surface Roughness Prediction in Cylindrical Grinding process by using RSM and ANN

Abstract

In recent years, one of the innovative technologies which enable automatic computerized devices for the purpose of evaluation, inspection, analyzing of various static and dynamic images is Machine Vision System. MVS provides various benefits in various fields like Surveillance cameras for Security, MAT LAB for analysis of Engineering designs, RSM and ANN for analysis of various parameters for optimizing variables, etc. MVS has some various innovative techniques like automatic capturing of images, evaluation and processing capabilities. This paper is about optimization of various parameters such as depth of cut, feed rate, cutting speed, dressing conditions, etc. For improving the accuracy obtained in Cylindrical (Surface) grinding process. The main objective of our idea is to identify the surface roughness of work piece obtained in Cylindrical grinding process in according to various input parameters like feed rate, depth of cut, dressing speed, etc. The method used here is RSM and ANN which are used to optimize the response of input parameters on output parameters and to provide algorithm for pre-trained model for visualization along with simulation of neural networks.

TRAFFIC STUDY AND DESIGN OF TRAFFIC SINGNAL AT IDENTIFIED INTERSECTIONS IN MANSAROVAR, JAIPUR

Abstract

Transport facility is an important part of growing economy of a country. A good road network is desired for trade and commerce & the system increases development of socioeconomy. An efficient road network is the requirement and needs of commuters by constructing and improvement of road infrastructure. To manage travel demand, the intersection should give least resistance to traffic flow so that the travel time can be minimized. The vehicles are growing at a high rate on roads of Indian cities, so because of that we are facing problems of traffic. As vehicular traffic began to increase, the congestion on the streets began to hamper the safe and efficient movement of traffic. The roads in the Mansarovar of Jaipur has been taken for improvement for delay in the journey time due to congestion at crossings. This is due to conflict, confusion and irritation caused by mixed traffic, which leads to accidents. These can be reduced by introduction of traffic management techniques. In Present Study, four intersections are identified on primary road of Mansarover Jaipur, Mainly Shiprapath, Veer Tejaji Road &Madhyam Marg and its adjoining Cross roads. Remedial measures such as geometric improvement & providing traffic signals are proposed, so that road capacity be utilized with minimum accidents.

DETECTION OF INDIAN COUNTERFEIT BANKNOTES USING NEURAL NETWORK

Abstract

Abstract— Banknotes notes are issued by the Reserve Bank of India (RBI), in the year 1934. They are currently issued in the denomination of Indian rupees ₹10, ₹20, ₹50, ₹100, ₹200, ₹500, ₹2000. In the proposed work, detection of the counterfeit banknotes using multispectral images is implemented by Neural Network technique. It will reduce the cost when neural networks are used. It shows good performance and a low level of complexity. From the results, by using Pattern Recognition algorithm is used to train and test the image at an advanced level to compute the recognition rate level. So that, the performance metrics are increased when compared to the existing work.

Efficient Image Steganography Using Integer Wavelet Transform

Abstract

A Review on An Efficient Singular Value Decomposition Based Filtering For GIF Image Denoising With Ridgelet Approach.

Abstract

Image Denoising has been one of most important area of image processing and very important step in image preprocessing for over several decades. Image denoising is the process by means of which unwanted visual elements in an image is removed to make the image clear as well as better for processing. various image processing algorithms have been proposed and validated over the years. some of the most common image denoising techniques are divided into global and local denoising techniques, examples of denoising techniques are median filter, gaussian filter and so on where as local denoising techniques are moving average filter, trilateral filter and so on. A global filter is essentially faster than local filter where as local filter preserve the local properties of images. however in a sequence of images for example in video frame sequence the local frames are correlated with each other with the help of motion vectors. In such images where the occurrence and the position of the pixels in a frame are dependent on the same of the previous frame, using existing images denoising techniques is extremely difficult. Adaptation of individual image denoising techniques in to the frame based techniques leads to significant amount of image distortion in the means of a blurring and loss of sharpness in the consecutive frames.in order to overcome such problems with existing denoising techniques in this work we proposed a novel image denoising techniques based on image decomposition which can be applied on subsequent image frames extracted out of video which are correlated with each other

Neural Networks based Handwritten Digit Recognition

Abstract

In the field of Artificial Intelligence, scientists have made many enhancements that helped a lot in the development of millions of smart devices. On the other hand, scientists brought a revolutionary change in the field of image processing and one of the biggest challenges in it is to identify data in both printed as well as hand-written formats. One of the most widely used techniques for the validity of these types of document is NEURAL NETWORKS. Neural networks currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing. Handwritten Digit Recognition is an extensively employed method to transform the data of handwritten form into digital format. This data can be used anywhere, in any field, like database, data analysis, etc. There are multitude of techniques introduced now that can be used to recognize handwriting of any form. In the suggested system, we will handle the issue of machine reading numerical digits using the technique of NEURAL NETWORKS. We aim to learn the basic functioning of the neural network and expect to find the correlation between all the parameters i.e. No of layers, Layer Size, Learning Rate, Size of the Training sets and the associated accuracy achieved by the neural net in identifying the handwritten digits, by comparing the accuracy achieved on different sets of the four variable parameters varying in the suitable range.

EFFICIENT APPROACH OF CHANNEL STATE INFORMATION PREDICTION FOR 5G NETWORKS USING CROWD SENSING OPTIMIZATION ALGORITHM

Abstract

In mobile crowdsensing (MCS), among the participants’ main concerns is the cost for 5G data usage, which influences their willingness to take part in a Crowdsensing task. In this paper, present the look and implementation of an MCS info uploading mechanism CSI prediction in reducing additional 5G data cost incurred by the complete crowd of sensing participants. By taking into consideration the two most common real-life 5G price plans-unlimited data plan (Unlimited) and pay as you go (Payout PER), CSI prediction partitions all of the users into two teams corresponding to these two price plans at the beginning of each month, with the aim of minimizing the total refunding budget for all individuals. The partitioning is founded on predicting users’ mobility patterns and sensed info size. The CSI prediction mechanism was created influenced by the observation that during the data uploading cycles, Unlimited users could opportunistically relay Shell out PER users’ info to the crowdsensing server without extra 5G price, pro- vided both types of users will be able to “meet” on a common native cost-no cost network (e.g., Bluetooth or WiFi direct). To carry out the experiments using both Massachusetts Institute of Technology fact mining and the tiny World In Action (SWIM) simulation data sets. Analysis results exhibit that CSI prediction could lessen total 5G data expense by up to ∼50%, in comparison with the direct-assignment approach that assigns each participant to Unlimited or PAY PER directly according to the size of her sensed information.

INTELLIGENT FIRE DETECTION AND VISUAL GUIDED EVACUATION SYSTEM USING ARDUINO AND GSM

Abstract

A prototype capable of detecting fire accident in real time and providing a visual guidance system in case of emergency in parking Area is discussed in presented case. Project has two parts hardware part and software part. The central and intelligent unit of the model is arduino. Hardware design includes arduino, flame sensor, LEDs, liquid crystal display (LCD), buzzer, GSM. And software includes the programming of Arduino according to layout of fire sensor and arrangement of LED panels for guiding evacuation in case of fire. The sensor units are connected via common data line to ATMEL MEGA328P AU1722 Arduino. A SIM 800C GSM kit based network module, capable of operating in standard. GSM Bands has been used to send alert message. The system is implemented on general purpose printed circuit board (PCB).