International Journal of Soft Computing and Engineering

Journal Information
EISSN : 2231-2307
Total articles ≅ 48
Filter:

Latest articles in this journal

International Journal of Soft Computing and Engineering, Volume 10, pp 1-6; https://doi.org/10.35940/ijsce.f3507.0710621

Abstract:
As software systems evolve, there is a growing concern on how to manage and maintain a large codebase and fully understand all the modules present in it. Developers spend a significant amount of time analyzing dependencies before making any changes into codebases. Therefore, there is a growing need for applications which can easily make developers comprehend dependencies in large codebases. These applications must be able to analyze large codebases and must have the ability to identify all the dependencies, so that new developers can easily analyze the codebase and start making changes in short periods of time. Static analysis provides a means of analyzing dependencies in large codebases and is an important part of software development lifecycle. Static analysis has been proven to be extremely useful over the years in their ability to comprehend large codebases. Out of the many static analysis methods, this paper focuses on static function call graph (SFCG) which represents dependencies between functions in the form of a graph. This paper illustrates the feasibility of many tools which generate SFCG and locks in on Doxygen which is extremely reliant for large codebases. The paper also discusses the optimizations, issues and its corresponding solutions for Doxygen. Finally, this paper presents a way of representing SFCG which is easier to comprehend for developers.
Akshay Daydar
International Journal of Soft Computing and Engineering, Volume 10, pp 12-20; https://doi.org/10.35940/ijsce.f3515.0710621

Abstract:
As the machine learning algorithms evolve, there is a growing need of how to train the algorithm effectively for the large data with available resources in practically less time. The paper presents an idea of developing an effective model that focuses on the implementation of sequential sensitivity analysis and randomized training approach which can be one solution to this growing need. Many researchers focused on the implementation of sensitivity analysis to eliminate the insignificant features ands reduce the complexity in data selection. These sensitivity analysis methods relatively take a large time for validation through modeling and hence found impractical for large data. On the other hand, the randomized training approach was found to be the most popular approach for training the data but there is a very brief explanation available in research articles on how this training method is meaningful in getting higher accuracy. The current work focuses on the use of sequential sensitivity analysis and randomized training in an artificial neural network (ANN) for high dimensionality thermal power plant data. The sequential sensitivity analysis (SSA) technique includes the use of correlation analysis (CA), Analysis of variance (ANOVA), Akaike information criterion (AIC) in a sequential manner to reduce the validation time for all possible feature combinations. Only selected combinations are then tested against different training methods such as downward extrapolation, upward extrapolation, interpolation and randomized training in ANN. The paper also focuses on suggesting the significance of training with randomized training with comparison-based qualitative reasoning. The statistical parameters, mean square error (RMSE), Mean absolute relative difference (MARD) and R Square (R^2)were accessed for validation purposes. The research work mainly useful in the field of Ecommerce, Finance, industry and in facilities where large data is generated.
Mohit Singh, Shobha G
International Journal of Soft Computing and Engineering, Volume 10, pp 21-26; https://doi.org/10.35940/ijsce.f3518.0710621

Abstract:
With the rise of mobile devices and their usage, a lot of development has been made in terms of the development of applications for mobile devices. Traditionally, app development was restricted to the particular operating system, and a separate codebase was required for applications to be developed for multiple operating systems. A new paradigm of development took place in recent years which was of Hybrid app development, leading to the development of multiple frameworks which allowed for a single codebase to be used for multiple operating systems. This paper explores the features and analysis of different hybrid app development frameworks available in the market. A comprehensive analysis has been made to compare the different frameworks which are cross-platform and support web, Android, and iOS platforms. The analysis shows that all the frameworks have their merits and usage of anyone framework over others can vary from case-to-case basis. The detailed analysis of the features will bring a general conclusion over the choice of framework.
International Journal of Soft Computing and Engineering, Volume 10, pp 7-11; https://doi.org/10.35940/ijsce.f3508.0710621

Abstract:
Authentication is a process of verifying the credibility of a user who is trying to access classified or confidential information. There is a vast unfold in the number of internet users, and the demand for IoT devices, cloud services has been increasing; it is now essential more than ever to protect the data hosted on the internet. So, the authentication process cannot be relied on single-factor static authentication methods to verify the user credentials. All devices in the market are not equipped with biometric systems, so a form of multi-factor authentication which is independent of biometrics needs to be adopted for a secure authentication system. This paper portraits a systematic architecture to verify user credentials using specific parameters, trying to unfold patterns using machine learning algorithms based on user's past login records, thus trying to provide a safer and secure authentication process for the users.
Neha Sharma, Aayush Raj, Vivek Kesireddy, Preetham Akunuri
International Journal of Soft Computing and Engineering, Volume 10, pp 20-25; https://doi.org/10.35940/ijsce.f3502.0510521

Abstract:
Client conduct can be addressed from numerous points of view. The client's conduct is distinctive in various circumstances will give his concept of client conduct. From an overall viewpoint, the conduct of the client, or rather any individual around there, is taken to be irregular. When noticed distinctly, it is regularly seen that the future conduct of an individual can rely upon different variables of the current circumstance just as the conduct in past circumstances. This examination establishes the forecast of client beat, for example regardless of whether the client will end buying from the purchaser or not, which relies upon different components. We have chipped away at two sorts of client information. To start with, that is reliant upon the current elements which don't influence the past or future buys. Second, a period arrangement information which gives us a thought of how the future buys can be identified with the buys before. Logistic Regression, Random Forest Classifier, Artificial neural organization, and Recurrent Neural Network has been carried out to find the connections of the agitate with different factors and order the client beat productively. The correlation of calculations demonstrates that the aftereffects of Logistic Regression were somewhat better for the principal Dataset. The Recurrent Neural Network model, which was applied to the time-arrangement dataset, additionally gave better outcomes.
Mohd Sarfraz, Parag Rawal, Chirag Sharma
International Journal of Soft Computing and Engineering, Volume 10, pp 14-19; https://doi.org/10.35940/ijsce.f3493.0510521

Abstract:
Contemplating healthy exercise and well-being are important for everyone. The point of the ebb and flow study was to examine the effect of thinking on living well in real life and in sound behaviour in humans. The benefits of exercise and exercise have been demonstrated throughout life. We are meant to walk and many of our body systems work better when we are physically active. By controlling depressive symptoms, some studies show that high levels of aerobic activity can be associated with a significant reduction in depressive symptoms. Consider engaging in one or two daily exercises that include short periods (30-90 seconds) of high intensity. For some, this can be achieved by exercising in their homes including jumping jugs, mountain climbers, and a series of strength exercises (i.e. standing squats, push-ups, sit-ups). For others, the use of home exercise equipment such as treadmills, elliptical machines, and stationary bicycles may be helpful.It will help people to improve their physical fitness and fitness programs.
Chirag Sharma, Aman Kumar, Akancha Sinha, Meraj Ahmad
International Journal of Soft Computing and Engineering, Volume 10, pp 9-13; https://doi.org/10.35940/ijsce.f3492.0510521

Abstract:
In this era where everything is becoming digital the most challenging topic in front of us is Data Security in every aspect even in the secured communication channel. These issues can be tackled by using strong Data Encryption and the trusted third party who maintains the database. The fast development in Digital Technology also comes with the rapid crimes and the insecurity of data theft. From time to time engineers came up with many encryption techniques like Caser Ciphers, Vernam Ciphers, Vigenère Cipher which helped us in securing the data but with lots of flaws that later were exploited by the cybercriminals. So, they cannot provide sufficient security. In this research paper, we have proposed a new, more efficient encryption algorithm. This algorithm will use multiple keys during encryption or decryption so it will be very less vulnerable against the attacks like Brute force.
Prarthana Mukherjee, Prit Palan, M. V. Bonde
International Journal of Soft Computing and Engineering, Volume 10, pp 26-31; https://doi.org/10.35940/ijsce.f3500.0510521

Abstract:
Studies have shown that new generation of millennials have limited to no knowledge about managing their finances. This lack of awareness has created a need for financial literacy which is not only an essential employ-ability skill but also, a paramount life skill. Not only the younger generation but many individuals already in the corporate field are at their wit’s end when it comes to planning their finances and making correct financial decisions. This is where awareness in wealth management comes in. Wealth management is an investment advisory service. It also combines financial services to address the needs of individuals. It is more than just investment advice; it encompasses all parts of a person's financial life. The users can find all the information of different investments rather than integrating all the information from different places. They can generate a plan themselves or with the help of artificial intelligence and machine learning principles, manage their own and their family's current and future needs.
Samuel Kiilu Mbatha
International Journal of Soft Computing and Engineering, Volume 10, pp 1-8; https://doi.org/10.35940/ijsce.d3485.0510521

Abstract:
Construction projects are predisposed to conflicts. This is attributed to the multiplicity of personnel handling the various phases of the projects. Empirical evidence from previous studies shows that if not properly managed, conflicts affect among others, the project's productivity loss, inadequate time and cost performance levels, loss of profit, and damage in business relations. Identifying the significant causes and major potential impacts of conflicts is crucial to reducing the risk of conflict occurrence in projects. Hence, this study was focused on explaining the classification of conflicts, identifying and assessing their causes and impacts in construction projects in Kenya grounded on the perception of project consultants and contractors. To accomplish the study objectives, a questionnaire was designed to collect data on the experiences of construction professionals on the causes and impacts of conflicts during project implementation. A total of 122 consultants and contractors provided responses, which were analyzed. A total of 42 significant causes of conflicts in the Kenyan context were identified. Based on the survey results, delay in progress payments by the client was identified as the most significant cause of conflicts, followed by poor site management and supervision. The survey also revealed that conflicts can emerge from any of the stakeholders, with contractors contributing the most, accounting for 14 of the 42 conflict factors identified. The study ranked the impacts of these conflicts using the Relative Severity Index (RSI). The results indicated that the biggest impact of conflicts on construction projects is the loss of profitability and perhaps business viability, and delays in project delivery. Expert opinions regarding the best practices and strategies for improving project harmony through effective conflict management were reviewed and grouped into five classes namely; project documentation, stakeholder involvement, value-based procurement, and adoption of ICT. It is concluded that the project manager should develop his leadership role by the adoption of these strategies so that he can use his position to effect positive conflict management on his team members. Furthermore, during the life cycle of the construction project, special attention should be given to the identified cause factors to avoid or effectively manage conflicts. These results, taken together, support clear guidelines on the need for proactive financial obligation on the client-side, as well as the hiring of experienced project professionals. Implementing these suggestions would reduce the risk of conflicts arising during building projects.
Prakash Kanade, Robotics Researcher, Jai Prakash Prasad
International Journal of Soft Computing and Engineering, Volume 10, pp 1-5; https://doi.org/10.35940/ijsce.d3481.0310421

Abstract:
We all depend on farmers in today's world. But is anybody aware of who the farmers rely on? They don't suffer from various irrigation issues, such as over-irrigation, under irrigation, underwater depletion, floods, etc. We are trying to build a project to solve some of the problems that will help farmers overcome the challenges. Owing to inadequate distribution or lack of control, irrigation happens because of waste water, chemicals, which can contribute to water contamination. Under irrigation, only enough water is provided to the plant, which gives low soil salinity, leading to increased soil salinity with a consequent build-up of toxic salts in areas with high evaporation on the soil surface. This requires either leaching to remove these salts or a drainage system to remove the salts. We have developed a project using IoT (Internet of Things) and ML to solve these irrigation problems (machine learning). The hardware consists of different sensors, such as the temperature sensor, the humidity sensor, the pH sensor, the raspberry pi or Arduino module controlled pressure sensor and the bolt IOT module. Our temperature sensor will predict the area's weather condition, through which farmers will make less use of field water. At a regular interval, our pH sensor can sense the pH of the soil and predict whether or not this soil needs more water. Our main aim is to automatically build an irrigation system and to conserve water for future purposes.
Back to Top Top