College Management System using Salesforce

College Management system is Salesforce CRM based application which is the new technical way to manage all department related jobs. Collage management system is helpful for students as well as the colleges. In the existing system all the activities are done manually. It is very costly and time consuming. In our proposed system, students can view results using phones. The data will be stored in the Salesforce. The Admin, Faculty or the student should be a register user. The faculty can login into their college account through the application itself and update the academic result like internal exam marks obtained by the students. In this system students have easy access for viewing the marks; the application will check user authentications. Students are not permitted to manipulate any data. The proposed work has two modules: A. Student B. Teacher C. Admin. In the student’s module, students need to register their university registration number, college registration number, student name. Admin module maintains the student’s marks of internal college exams. Other than this the advanced features are: In case of natural calamities such as floods, etc. notification to students will be sent from admin office through application directly. Any new notice for a particular semester will be uploaded by professor through application notifying to respective semester students. The students can download different subject notes according to their departments. The faculty of particular department is responsible for updating the assignments, updating the attendance of every student, updating the notification related to department.

Banking Management System Using Salesforce

It is felt that Modern Banking has become wholly customer – driven and technology driven. During the last decade, technology has been dramatically transforming the banking activities in India. Driven by challenges on competition, rising customer expectation and shrinking margins, banks have been using technology to reduce cost. Apart from competitive environment, there has been deregulation as to rate of interest, technology intensive delivery channel like Internet Banking, Tele Banking, Mobile banking and Automated Teller Machines (ATMs) etc. have created a multiple choice to user of the bank. The banking business is becoming more and more complex with the changes emanating from the liberalization and globalization. For a new bank, customer creation is important, but an established bank it is the retention is much more efficient and cost effective mechanism. Customer Relationship Management (CRM) would also make Indian bankers realize that the purpose of their business is to create and keep a customer and to view the entire business process as consisting of Highly Integrated effort to discover, create and satisfy customer needs. But it is surprising to note that much of the activities of the banking and financial remain focused on customer creation not retention.

RECRUITMENT APP – A CUSTOM APPLICATION ON SALESFORCE.COM

Cloud Computing is one of the upcoming Internet based technology. It is been considered as the next generation computing model for its advantages. It is the latest computational model after distributed computing, parallel processing and grid computing. To be effective they need to tap all available sources of supply, both internal and external. The system has facilities where prospective candidates can upload their CV’s and other academic achievements. Earlier recruitment was done manually and it was all at a time-consuming work. Now it is all possible in a fraction of second. Better recruitment and selection strategies result in improved organizational outcomes. With reference to this context, the research paper entitled Recruitment and Selection has been prepared to put a light on Recruitment and Selection process.

Crypto-Steganographic Method to Protect Secret Messages

Multiple methods are used to hide secret messages in digital color images, and the most important and most common is the least significant bit (LSB) method. The LSB method is a known and exposed method, and anyone with programming experience can retrieve the secret message embedded in the digital image. In this paper research we will add some enhancements to improve the security level of LSB method to protect the embedded secret message from being hacked. A simple method of secret message cryptography will be used to encrypt the secret message before bedding it using LSB method. The method will be based on using color image as an image_key; this image_key will be resized to generate the needed secret private key used to encrypt-decrypt secret message. The length and the contents of the generated private key will dynamically change depending on the message length and the selected image_key. The selected image_key will be kept in secret without transmission and will be known only by the sender and receiver and it can be changed any time when needed. The proposed crypto_steganographic method will be implemented to show how it will increase the level o secret message protection.

Deep Reinforcement Learning for Cybersecurity Applications

There has been a rapid growth of the devices connected to the internet in the last decade for the various internet (IoT) of things applications. The increase of these smart devices has posed a great security concern in the internet of things ecosystem. The internet of things ecosystem must be protected from these threats. Reinforcement learning has been proposed by the cybersecurity professionals to provide the needed security tools for securing the IoT system since it is able to interact with the environment and learn how to detect the threats. This paper presents a comprehensive research on cybersecurity threats to the IoT system applications. The RL algorithms are also presented to understand the attacks on the IoT. Reinforcement learning is widely employed in cybersecurity because it can learn on its own experience by investigating and capitalizing on the unknown ecosystem, this enables it solve many complex problems. The RL capabilities on dealing with cybercrime challenges are also exploited in this paper.

Automatic Phonemes Segmentation for Quran Verses Using Kaldi Toolkit

In this paper, automatic segmentation system was built using the Kaldi toolkit at phoneme level for Quran verses data set with a total speech corpus of (80 hours) and its corresponding text corpus respectively, with a size of 1100 recorded Quran verses of 100 non-Arab reciters. Initiated with the extraction of Mel Frequency Cepstral Coefficients MFCCs, the proceedings of the building of Language Model LM and Acoustic Model AM training phase continued until the Deep Neural Network DNN level by selecting 770 waves (70 reciters). The testing of the system was done using 220 waves (20 reciters), and concluded with the selection of the development data set which was 280 waves (10 reciters). Comparison was implemented between automatic and manual segmentation, and the results obtained for the test set was 99% and for the Development set was 99% with Time Delay Neural Networks TDNN based acoustic modelling.

Bug Reports and Deep Learning Models

Deep Learning is one of the emerging and trending research area of machine learning in various domains. The paper describes the deep learning approaches applied to the domain of Bug Reports. The paper classifies the tasks being performed for mining of Bug Reports into Bug Report Classification, Bug Localization, Bug Report Summarization and Duplicate Bug Report Detection. The paper systematically discusses about the deep learning approaches being used for the mentioned tasks, and the future directions in this field of research.

Implementing ACT-Based Modalities for Establishing Connectivity among Teachers and Students in the Context of COVID-19

The government aims to make education accessible to all the people of the country can be fulfilled if the online education system is developed enough for all. The country may be benefited by the use of the right type of education system. Learners and teachers get advantages if the education system is reformed using digital technologies like Automatic Call Tree (ACT)-based modalities. Such types of education system has key significant in the pandemic situation which have been facing since two years. This study is assumed to examine the Automatic Call Tree (ACT) based modalities and their utilization for connection between students, teachers, parents and school management committee; and some recommendations are made concerning online education. The main information source for this study is primary. Instruments used are questionnaires, interview with video recording, phone call, and class room observation. The preliminary finding showed that there is a scarcity of orientations of online education to parents, students, teachers, and administrators, though all were found to realize its importance. Likewise, major problems found are lack of digital devices, regular power supply and backup; and network connectivity. Based on the opinions of the respondents and observations of the situations of the different parts of the country running online education during this pandemic period, many recommendations are made. The country needs strategic plans and policy to make online education accessible to all learners specially in urban areas of Nepal and this will ensure online education smooth. It concludes that the Automatic Call Tree (ACT)-based modalities became fruitful for some schools of Nepal during Corona Virus (COVID)-19 pandemic. But many of them are facing different problems while conducting online classes, examination and result processing. Providing practical knowledge and skills about engineering, mathematics, health science, account, computer science subjects are very difficult and to examine them.

A New Prediction Approach for Preventing Default Customers from Applying Personal Loans Using Machine Learning

In the Egyptian banking industry, loan officers use pure judgment to make personal loan approval decisions. In this paper, we develop a new predictive method for default customers' loans using machine learning. The new predictive method uses the available personal data and historical credit data to evaluate the credit trust-worthiness of customers to obtain loans. We used the ABE dataset for training and testing, as we used 10 features from the application form and i- score report class that could give great help to credit officers for taking the right decision through avoiding customer selection using random techniques. The collected dataset was analysed by using various machine learning classifiers based on important selected features, to obtain high accuracy. We compared the performance of several machine learning classifiers before and after feature selection. We have found that in terms of high accuracy, the most important features are (activity – income – loan) and in terms of better performance the decision tree classifier has surpassed any other machine learning classifier with significant prediction accuracy of almost 94.85%.

A Unique Framework for Contactless Estimation of Body Vital Signs using Facial Recognition

As one of the consequences of COVID-19 pandemic, a lot of new technologies are developing in fast-track pace in clinical practices. The main idea of our project is to design contactless technology for the support of patients who suffer from blood pressure disorders and coronary heart diseases using machine learning approach. This may intend people to monitor their heart rate, pulse rate, respiratory life and oxygen saturation levels at an ease. The orientation of this paper is to monitor the blood pressure considering the facial changes and movements in a video to get rid of cuff-based measurement of blood pressure. We analyzed whether blood pressure can be obtained in a contactless way utilizing a novel technologies like image processing and machine learning techniques. This innovation estimates vague facial blood stream changes from video recordings captured by camera with the help of machine learning and image processing techniques.