Improved Classification of Tweet Sentiments with Semantic Features using Convolution Neural Network with Soft-Max Approach
Sentiment analysis is a process of identification of opinion and thought related to any product, people or an organization. The sentiment analysis is mainly done to understand the others opinion related to some entity. This concept is mainly used in the large organizations and E-commerce to track the user’s activity and their response related to the product. The reviews of the product help the other users to know about the product more. If the reviews of other users are positive its sale is enhanced and if reviews are negative, then it affects the product sale. Sentiment analysis is done on the basis of text and images posted by the users on the social media website. In this analysis, sentiments are classified into positive, negative and neutral. sentiment analysis can be characterized as a procedure that helps in mining of feelings, emotions, views, and opinions from content, tweets, database, and speech in an automatic way by mean of NLP i.e. Natural Language Processing. SA examination includes the classification of opinions in content into classifications like "positive" or "neutral" or "negative". It's likewise indicated as opinion-based mining, subjectivity examination, and the extraction based on judgement. This polarity is assigned according to the meaning of words and after these score of all words is combining to understand the total score and then decides the comment is positive or negative. Sentiment analysis is a challenging task because it is not easy to analyses the exact views, opinions, and feeling from the text. The way of writing the feelings are different for every people in different context and topics. This issue solved by combining the text and prior knowledge. This research work proposes the deep convolutional neural network that uses character- to sentence-level information to perform sentiment analysis of tweets. This model presented a new approach for the initialization of the weights of convolutional neural network which helps to train the network effectively and helps to add new features. The model train by using unsupervised neural language and further tuned by deep learning model on a distant supervised corpus.
Published by: Vishal Thakur, Pratibha
Author: Vishal Thakur
Paper ID: V8I4-1146
Paper Status: published
Published: July 7, 2022
Improved work flow scheduling by hybrid optimization using whale optimization in Cloud Computing
Cloud computing is a most recent methodology that is developing quicker step by step because of its compelling component and security. Distributed computing gives an approach to get to the information from wherever whenever. This component makes it famous in light of the fact that it decreases the weight of the clients. Distributed computing gives the administrations like framework, stage and programming as an administration on it. Because of these elements the Size of information on cloud in expanded and it impacts on the productivity of cloud. To defeat the issue like this planning of assignment on information is the best alternative. Work process planning for logical registering frameworks is one of the most testing issues that spotlights on fulfilling client characterized nature of administration necessities while limiting the work process execution cost. So, to lessen the cost, cloud condition, has been conveyed in cloud condition, assets will increment yet its usage is another test. To keep up and use assets in the distributed computing planning component is required. Numerous calculations and conventions are utilized to deal with the parallel employments and assets which are utilized to improve the exhibition of the CPU in the cloud condition. This work Particles swarm Optimization (PSO) and Gray Wolf Optimization (WCA) are utilized for successful booking. This work depends on the advancement of Total execution time and absolute execution cost. The consequences of the proposed methodology are observed to be successful in contrast with existing strategies. Insight advancement Particle Swarm enhancement is utilized which is instated by Pareto circulation. WCA is utilized to merge the choice of Virtual Machine (VM) relocation by its union to limit cost and time as outlined by Total execution time (TET) and Total execution cost (TEC). It is inferred that WCA performs better in contrast with existing FUZZY_HEFT calculation.
Published by: Ashok Kumar Kashyap, Pratibha
Author: Ashok Kumar Kashyap
Paper ID: V8I4-1145
Paper Status: published
Published: July 7, 2022
Maintenance of facilities for women’s safety in hostels
Safety is a state of being “safe”; it is the condition of being protected from harm. A hostel has always been regarded as a smaller, slightly cheaper alternative to a hotel, and a hostel is commonly used by students and working men or women. This study focuses on working women hostels in Hyderabad, India. This study is to re-emphasize the importance of maintenance and safety in hostels. In the last five years, several crimes have come to the notice of schools, hostels, and other areas of stay. With the intention of reducing crimes, one of the steps taken by the Cyberabad police Commissionerate is to enhance “safety” and “security”. This initiative took the form of a project called “Safe stay”. As a part of this initiative, a team of surveyors was appointed from DMS, GCET. They were provided with a checklist of items for audit. These items were regarded as “essential” for safety by Cyberabad Police. After a preliminary survey, the study was extended to studying the importance of maintenance of facilities mentioned in the checklist, in hostels to enhance or ensure safety. The current study focuses on the “MAINTENANCE’’ of facilities in women's hostels
Published by: Jyothi Pulipati
Author: Jyothi Pulipati
Paper ID: V8I4-1138
Paper Status: published
Published: July 7, 2022
Implementation of standard criteria for effective medical equipment preventive maintenance practice in District General Hospital – Nawalapitiya, Sri Lanka.
Implementation of standard criteria for effective medical equipment preventive maintenance practice in District General Hospital – Nawalapitiya, Sri Lanka. ABSTRACT Somaratne, C.J.K.1, Dharmaratne, G.S.K2 1. Director, DGH Nawalapitiya, Sri Lanka 2. Deputy Director General (Laboratory Services), Ministry of Health, Colombo, Sri Lanka. Contact email: [email protected] Background: Scarcity of financial resources has resulted in limited Inspection and preventive maintenance activities for the items of medical equipment in the hospitals of Sri Lanka. There is no standard criteria method applied for selecting items of medical equipment for maintenance strategies such as annual service agreements in public sector hospital of Sri Lanka. Objective: To implement effective medical equipment preventive maintenance practice in relation to service agreements of DGH Nawalapitiya. Methods: The study was carried out in year 2016 and a comprehensive data base for the medical equipment was developed initially. The new method was applied to prioritize the items of medical equipment of District General Hospital Nawalapitiya to select the items of medical equipment for annual service agreements. Results: Total of 642 items of medical equipment were identified in the hospital and 430 (66.9%) items and 212 (33.1%) items were found to be functional and non-functional respectively. According to the Wang - Levenson criteria, AEMR values were calculated, and the functional items of medical equipment were prioritized in a descending order. AEMR values were varying from maximum value of 30 to minimum value of 2. The priority list was utilized for the annual service agreements of the hospital for year 2017 / 2018 and 80 % of the items were selected according to the list. Conclusions: The Provincial Health Department has already taken initiatives to implement the new method at DGH Nawalapitiya and planning to implement it in the other health care institutions of the province. Key Words: DGH Nawalapitiya, Medical equipment, Wang & Levenson criteria, prioritization, Annual service agreements.
Published by: Dr. C. J. K Somaratne, Dr. G.S.K. Dharmaratne
Author: Dr. C. J. K Somaratne
Paper ID: V8I3-1457
Paper Status: published
Published: July 7, 2022
Pests Prediction and Detection of Disease Spreading Frequency in Native crops using Machine Learning Technique
Disease and pest control models can generate information on agrochemical use only if necessary, reducing costs and environmental impacts. With machine learning algorithms, it is possible to develop models that will be used for diseases and pest warning systems to improve the effectiveness of chemical control over coffee tree pests. Therefore, infection rates are linked with climate change and measured and evaluated by machine learning algorithms for predicting the occurrence of diseases. Algorithms that are tested to predict incidence are (a)Multi-line regression (RLM); (b) K Neighbors Regressor (KNN); (c) Random Forest Regressor (RFT), and (d)Artificial Neural Networks. Pearson correlation analysis is to be considered under three different time periods,1-10 days (from 1-10 days before the incidence evaluation),11-20d, and 21-30d, and used to evaluate the unit correlations between the weather variables and infection rates. The number of days, maximum temperature, and relative humidity exceeding 80% are meteorological variables that show a significant correlation with this disease. There is a negative correlation with rainfall, and the severity of pests decreases with increasing rainfall. Machine learning algorithms can be used to predict diseases and pests.
Published by: Impana V., Vanishree K., Hemanth Kumar, Sumit Atram
Author: Impana V.
Paper ID: V8I3-1453
Paper Status: published
Published: July 6, 2022
Resource demand prediction for minimizing power consumption at data centers
Technical progress in servers, systems, and capacity virtualization is empowering the production of resource pools of servers that allows various application workloads to share each server in the pool. This approach proposes and assesses the parts of a capacity management process for creating an efficient utilization of such pools and also facilitates a huge quantity of business administrations. The objective of our approach is to give a capacity management procedure to resource pools that let capacity organizers coordinate-free market activity for resource limits in a given interval of time. In this approach, we will describe the workloads of big business applications to pick up experiences for their conduct. In this paper, we will follow a trace-based approach for capacity management that relies upon the definition of required capacity and portrayal of workload request designs. The exactness of scope quantification expectations relies upon our capacity to describe workload request examples, to perceive patterns for expected changes in future requests, and reflect business conjectures for any sudden changes in future requests. A contextual analysis with 6 months of information that speaks to the asset utilization of 159 workloads in a venture server farm shows the adequacy of the proposed limit administration handle. Our results and conclusion will show that whenever we will use 8 processor systems, we will predict the exact future per-server required capacity to 1 processor every 98 percent of the time. This approach will enable a 38 percent reduction in processor utilization as compared to today’s current best practice for workload placement. This knowledge will help resource pool operators to decide on the best capacity for their server pools.
Published by: Gaurav Thakur
Author: Gaurav Thakur
Paper ID: V8I3-1459
Paper Status: published
Published: July 5, 2022
