International Journal of Soft Computing and Engineering最新文献

Emerging Software and Tools in Higher Education Institutions 高等教育机构中的新兴软件和工具

International Journal of Soft Computing and Engineering Pub Date : 2024-01-30 DOI: 10.35940/ijsce.f3620.13060124

Dr. Shailaj Kumar Shrivastava, Chandan Shrivastava

引用次数: 0

Implications of Deep Compression with Complex Neural Networks 复杂神经网络对深度压缩的影响

International Journal of Soft Computing and Engineering Pub Date : 2023-07-30 DOI: 10.35940/ijsce.c3613.0713323

Lily Young, James Richrdson York, Byeong Kil Lee

{"title":"Implications of Deep Compression with Complex Neural Networks","authors":"Lily Young, James Richrdson York, Byeong Kil Lee","doi":"10.35940/ijsce.c3613.0713323","DOIUrl":"https://doi.org/10.35940/ijsce.c3613.0713323","url":null,"abstract":"Deep learning and neural networks have become increasingly popular in the area of artificial intelligence. These models have the capability to solve complex problems, such as image recognition or language processing. However, the memory utilization and power consumption of these networks can be very large for many applications. This has led to research into techniques to compress the size of these models while retaining accuracy and performance. One of the compression techniques is the deep compression three-stage pipeline, including pruning, trained quantization, and Huffman coding. In this paper, we apply the principles of deep compression to multiple complex networks in order to compare the effectiveness of deep compression in terms of compression ratio and the quality of the compressed network. While the deep compression pipeline is effectively working for CNN and RNN models to reduce the network size with small performance degradation, it is not properly working for more complicated networks such as GAN. In our GAN experiments, performance degradation is too much from the compression. For complex neural networks, careful analysis should be done for discovering which parameters allow a GAN to be compressed without loss in output quality.","PeriodicalId":173799,"journal":{"name":"International Journal of Soft Computing and Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134235783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predictive Insights: using Machine Learning to Determine Your Future Salary 预测性洞察:使用机器学习来确定你未来的薪水

International Journal of Soft Computing and Engineering Pub Date : 2023-05-30 DOI: 10.35940/ijsce.b3605.0513223

Dr. M. Saraswathi, J. Akhila, K. Sireesha

{"title":"Predictive Insights: using Machine Learning to Determine Your Future Salary","authors":"Dr. M. Saraswathi, J. Akhila, K. Sireesha","doi":"10.35940/ijsce.b3605.0513223","DOIUrl":"https://doi.org/10.35940/ijsce.b3605.0513223","url":null,"abstract":"Knowing one's expected salary can be a crucial consideration when deciding whether to change careers or seek higher education in today's fiercely competitive work market. Accurate salary forecasts can give important information about the earning potential of various professions because there are so many students graduating each year and workers looking to switch sectors. In order to forecast a salary range, this paper suggests a computerized method that considers a person's country, level of education, number of years of experience, and area of specialization. This kind of system has obvious benefits because it gives individuals and groups the power to decide wisely about job prospects, wage negotiations, and employee retention. The system's data can be used by researchers, academic institutions, and policymakers to evaluate labor market trends and reach informed decisions. The reliability and correctness of the system's data, the forecasting models employed, and the regularity of system maintenance and updates will all have an impact on these factors. However, it is a promising area for further research and development due to the benefits of having a reliable technique for estimating salaries.","PeriodicalId":173799,"journal":{"name":"International Journal of Soft Computing and Engineering","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132413515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Breast Cancer Prediction Based on Feature Extraction using Hybrid Methodologies 基于混合方法特征提取的乳腺癌预测

International Journal of Soft Computing and Engineering Pub Date : 2023-05-30 DOI: 10.35940/ijsce.b3612.0513223

G. Rajasekaran, D. C. S. Ram

引用次数: 0

Innovations in Healthcare Analytics: A Review of Data Mining Techniques 医疗保健分析的创新:数据挖掘技术综述

International Journal of Soft Computing and Engineering Pub Date : 2023-05-30 DOI: 10.35940/ijsce.b3609.0513223

S. Bhardwaj, Prof. Neeraj Bhargava, Dr. Ritu Bhargava

{"title":"Innovations in Healthcare Analytics: A Review of Data Mining Techniques","authors":"S. Bhardwaj, Prof. Neeraj Bhargava, Dr. Ritu Bhargava","doi":"10.35940/ijsce.b3609.0513223","DOIUrl":"https://doi.org/10.35940/ijsce.b3609.0513223","url":null,"abstract":"This review article provides an overview of the current state of data mining applications in healthcare, including case studies, challenges, and future directions. The article begins with a discussion of the role of data mining in healthcare, highlighting its potential to transform healthcare delivery and research. It then provides a comprehensive review of the various data mining techniques and tools that are commonly used in healthcare, including predictive modelling, clustering, and association rule mining. The article also discusses some key challenges associated with data mining in healthcare, such as data quality, privacy, and security, and suggests possible solutions. Finally, the article concludes with a discussion of the future directions of data mining in healthcare, highlighting the need for continued research and development in this field. The article emphasises the importance of collaboration between healthcare providers, data scientists, and policymakers to ensure that data mining is used ethically and effectively to improve patient outcomes and support evidence-based decision-making in healthcare.","PeriodicalId":173799,"journal":{"name":"International Journal of Soft Computing and Engineering","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121163717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evolutionary Algorithms for Optimization of Drilling Variables for Reduced Thrust Force in Composite Material Drilling 复合材料钻孔减推力钻孔变量优化的进化算法

International Journal of Soft Computing and Engineering Pub Date : 2023-05-30 DOI: 10.35940/ijsce.b3610.0513223

S. Bhardwaj

引用次数: 0

Survival Prediction of Cervical Cancer Patients using Genetic Algorithm-Based Data Value Metric and Recurrent Neural Network 基于遗传算法的数据值度量和递归神经网络的宫颈癌患者生存预测

International Journal of Soft Computing and Engineering Pub Date : 2023-05-30 DOI: 10.35940/ijsce.b3608.0513223

Ojie Deborah Voke, Dr. Akazue M, Dr. Omede E. U, Dr. Oboh E.O, Prof. Imianvan A

{"title":"Survival Prediction of Cervical Cancer Patients using Genetic Algorithm-Based Data Value Metric and Recurrent Neural Network","authors":"Ojie Deborah Voke, Dr. Akazue M, Dr. Omede E. U, Dr. Oboh E.O, Prof. Imianvan A","doi":"10.35940/ijsce.b3608.0513223","DOIUrl":"https://doi.org/10.35940/ijsce.b3608.0513223","url":null,"abstract":"Survival analysis and machine learning has been shown to be an indispensable aspect of disease management as it enables practitioners to understand and prioritize treatment mostly in terminal diseases. Cervical cancer is the most common malignant tumor of the female reproductive organ worldwide. Survival analysis which is a time –to –event analysis for survival prediction is therefore needed for cervical cancer patients. Data Value Metric (DVM) is an information theoretic measure which uses the concept of mutual information and has shown to be a good metric for quantifying the quality and utility of data as well as feature selection. This study proposed the hybrid of Genetic Algorithm and Data Value Metric for feature selection while Recurrent Neural Network and Cox Proportionality Hazard ratio was used to build the survival prediction model in managing cervical cancer patients. Dataset of 107 patients of cervical cancer patients were collected from University of Benin Teaching Hospital, Benin, Edo State and was used in building the proposed model (RNN+GA-DVM). The proposed system outperform the existing system as the existing system had accuracy of 70% and ROC score of 0.6041 while the proposed model gave an accuracy of 75.16% and ROC score of 0.7120 respectively. From this study, It was observed using the GA_DVM features selection that the variables highly associated with cervical cancer mortality are age_at_diagnosis, Chemotherapy, Chemoradiation, Histology, Comorbidity, Menopause, and MENO_Post. Thus, with early diagnosis and proper health management of cervical cancer, the age of survival of cervical cancer patients can be prolonged.","PeriodicalId":173799,"journal":{"name":"International Journal of Soft Computing and Engineering","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131583192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital Text to Users Handwriting (தமிழ்) 数字文本到用户手写(தமிழ்)

International Journal of Soft Computing and Engineering Pub Date : 2023-03-30 DOI: 10.35940/ijsce.a3588.0313123

R. Subash, K. Prasannavenkatesan, Dr. R. Sunitharam

{"title":"Digital Text to Users Handwriting (தமிழ்)","authors":"R. Subash, K. Prasannavenkatesan, Dr. R. Sunitharam","doi":"10.35940/ijsce.a3588.0313123","DOIUrl":"https://doi.org/10.35940/ijsce.a3588.0313123","url":null,"abstract":"Converting digital text to handwriting is a simple process because of the abundance of software and websites that do it, like texttohandwriting.com. The Text to Handwriting Converter is a free artificial intelligence-based tool that translates computer text into handwritten text with ease. An individual's handwriting format is saved as an input, converted into text, and then shown as an output. Image processing techniques can be used to process the handwriting. It is possible to use the alphabets of specific languages, such as Tamil (தமிழ்), English, etc. The text of the input is finally displayed in the user's unique handwriting style. It will be useful in numerous ways, including helping the students who have been injured during an accident and it will also reducing the need for paper. Instead of using paper, we can preserve it and refer to it whenever needed. The primary goal of this project is to convert digital text into user handwriting in Tamil (தமிழ்), as it is the oldest language in India and there are currently no websites or apps that accomplish this specifically in Tamil (தமிழ்). There are 247 Tamil (தமிழ்) letters, which are divided into four groups: uyireluttu (உயிரெழுத்து) (12), meyyeluttu (ரெய்ரயழுத்து) (18), uyirmeyyeluttu (உயிெ்ரெய்ரயழுத்து) (216), and finally ayutha eluttu (ஆய்த எழுத்து) (1). A database is created using the handwriting of the person whose handwriting is being converted. These databases consist solely of 247 letters written in that person's handwriting.","PeriodicalId":173799,"journal":{"name":"International Journal of Soft Computing and Engineering","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127085753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Secure and Light Weight Aodv (Slw-Aodv) Routing Protocol for Resilience Against Blackhole Attack in Manets 安全轻量级Aodv (slow -Aodv)路由协议抗黑洞攻击

International Journal of Soft Computing and Engineering Pub Date : 2023-03-30 DOI: 10.35940/ijsce.a3592.0313123

M. V. D. S. K. Murty, Dr. Lakshmi Rajamani

引用次数: 1

Design and Implementation of an Efficient Smart Digital Energy Meter 高效智能数字电能表的设计与实现

International Journal of Soft Computing and Engineering Pub Date : 2023-03-30 DOI: 10.35940/ijsce.a3600.0313123

Diptarup Paul, O. Pal, Md. Monjurul Islam, Mahathir Mohammad, Riad Mollik Babu

{"title":"Design and Implementation of an Efficient Smart Digital Energy Meter","authors":"Diptarup Paul, O. Pal, Md. Monjurul Islam, Mahathir Mohammad, Riad Mollik Babu","doi":"10.35940/ijsce.a3600.0313123","DOIUrl":"https://doi.org/10.35940/ijsce.a3600.0313123","url":null,"abstract":"In this research, the development of digital prepaid energy meters for homes and businesses that use GSM technology is discussed. The reduction of billing cost electricity wastage is the primary goal of prototype development. The GSM module is used to receive short messaging service (SMS) from the user's mobile phone, which automatically enables the controller to take any further action, such as to help the consumer save money by using prepaid energy meter systems offered by power generation and distribution companies. Embedded C is used to integrate the system's microcontroller and GSM network interface. The integration was carried out using Easy EDA software. When the balance on the energy meter falls too low, the system sends the consumer an SMS. Consumer research is then lacking, leaving power without. After getting the SMS command, the Consumer then balances his or her investigation. Therefore, each item facilitates the usage of electrical power in homes and businesses. The prepaid energy meter is then turned ON or OFF by the microcontroller unit, which subsequently automatically controls the electrical power to homes and businesses. In other words, it responds to the message it receives by reading it from the cell phone and controlling the equipment accordingly.","PeriodicalId":173799,"journal":{"name":"International Journal of Soft Computing and Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129156777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0