Journal of Advanced Research in Computer Technology & Software Applications

A Deep Learning Framework for Auto Detection of Hate Speech on Social Media

2024-12-06T07:05:14+00:00

Identifying hate speech on social media is important work. Unbridled development of anger can seriously harm marginalized individuals or groups, as well as our society as a whole. Social media is the main platform for spreading hate speech online. This greatly increases the complexity of automatic detection, as social media posts often use poorly written text and paralinguistic characters such as emoticons and hashtags. The context-dependent nature of the task and the lack of consensus on what constitutes hate speech add additional challenges, making it even for humans. This makes the creation of large tagged corpora complex and resource-intensive. The main problem was ungrammatical writing. Recently introduced Deep Neural Network (DNN) models, which have the ability to quickly learn various features, have greatly reduced the problem of grammatically incorrect text. To automatically identify hate speech from social media data, we developed a deep natural language processing (NLP) model that combines convolutional and recurrent layers. Using our model on the HASOC2019 corpus, we were able to detect hate speech in the HASOC test with a macro F1 score of 0.63. However, the ability of DNNs to learn well is also associated with a higher risk of overfitting. especially when there is little training data (e.g., for HASOC). We looked at several techniques to increase the resources needed for this. We considered several options, including using new models, similarly labeled cases, and unlabeled data. Our results have shown that this can significantly increase the final assessment score.

Capacity Utilization of a Single Machine Multi Product Case in Make to Order Manufacturing Organization - A Case Study

2024-12-06T07:07:42+00:00

Capacity planning and control is done for setting the effective capacity of the operation so that it can easily and quickly respond to the demands placed upon it. The purpose of the study was to determine the capacity utilization for a single machine multiple product case in make to order manufacturing organization. The problem was reported in the CNC department as the organization was not able to fulfil the orders by their due dates. The mathematical model prepared was found to be the appropriate for solving this type of problem. Using information of the pre-requisites of model application, the data was collected. The data collected was analysed with the mathematical model. Results investigate significant improvement of 3% production rates and net profit of INR 2 Lacks per annum has been achieved. The results not only validated the model but also showed that the utilization of the machine was found less than as per the specifications of the machine.

Harmonizing Complexity: Unraveling the Tapestry of Modern Software Engineering

2024-12-06T07:10:18+00:00

In the grand concert of technological progress, software engineering plays the role of conductor, wielding the baton of logic and precision to bring forth the symphonies of our digital age. This paper delves into the intricate movements of this discipline, exploring its core principles, diverse methodologies, and profound impact on various domains.

Driven by the unwavering pursuit of problem-solving through digital artistry, software engineering orchestrates the creation of reliable, secure, and maintainable software systems. Its methodology acts as the sheet music, guiding the development process with established approaches like Agile, Waterfall, or DevOps, each offering a unique rhythm to the composition.

At its heart, software engineering is a delicate balance. Resource management, the careful allocation of time and budget, ensures the project stays in tempo. Meanwhile, meticulous testing and security best practices act as the fortifying counterpoint, ensuring the software's robustness and resilience against external threats. Finally, maintainability, the foresight for future modifications, lays the groundwork for the software's enduring performance.

This meticulous composition resonates across diverse domains, each with its own instrumentation. From the interactive melodies of web and mobile applications to the embedded harmonies of smart devices, software engineering weaves its magic. Businesses find their rhythm in enterprise applications, while scientific exploration unlocks new knowledge through software-powered analysis. Even artificial intelligence, the rising star of the technological stage, relies on software engineering to bring its algorithms to life.

Yet, the symphony is never stagnant. Trends like cloud computing act as new instruments, expanding the orchestra's reach and flexibility. Big data and analytics unveil hidden melodies, offering deeper insights into the systems' performance. Meanwhile, artificial intelligence and machine learning inject a novel layer of harmony, automating tasks and amplifying software capabilities. Cybersecurity, the vigilant percussionist, safeguards the composition against ever-evolving threats. Finally, low-code/no-code platforms democratize the creation process, allowing new voices to join the digital chorus.

Software engineering, with its ever-evolving toolkit and unwavering dedication to quality, stands as a testament to human ingenuity. As technology continues to evolve, this discipline will undoubtedly compose even more complex and impactful digital symphonies, shaping the future with every line of code, every innovation, and every carefully orchestrated note.

Retrofitting of Deficient RC Frame Structure

2024-12-06T07:12:15+00:00

RCC-framed structures are the most common and widely accepted form of construction around the globe. The structures have been created with huge investment, and it would not be feasible to build them again out of limited national resources. Therefore, it is very much needed to be maintained and repaired whenever needed. Deterioration of RCC is quite natural, which is clearly visible in many structures. But unfortunately, due to multiple reasons like improper design, faulty construction, change of usage of the building, and change in codal provisions, these structures are often found to exhibit distress even before their service life is over. Since replacement of such deficient elements of structures incurs a huge amount of public money and time, retrofitting has become the acceptable way of improving their load-carrying capacity and extending their service lives. In the present research work, the effect of local retrofitting methods on deficient RCC members of the building has been studied using finite element analysis. The study was done by initially designing a G + 3 RCC frame structure using STAAD Pro. The three types of construction deficiencies are induced in the original columns and beams, which consist of reducing the area of steel and reducing the grade of concrete and steel. Then the retrofitted models are prepared using RC jacketing, steel jacketing, CFRP jacketing, and GFRP jacketing using ANSYS. Then, each type of column and beam are numerically simulated to determine the total deformation and equivalent stress in the members. The cost of each retrofit employed is also calculated and compared. The outcomes of this investigation show that the proposed RC jacketing significantly improves the total deformation of the columns and beams and proves to be cost-effective as compared to the other jacketing methods.