In the world ergonomics is involved everywhere, where is work there is a risk factor. Musculoskeletal disorder (MSDs) is a major risk factor in human life because it affects bones, joints, muscles, and connective tissues of whole human body parts such as the neck, shoulder, arms, wrists, hips, legs, thigh, knee, ankles, etc. so mainly our study focus on musculoskeletal disorders. This study there has used questionnaires in four factors those are socio-demographic, psychological, occupational, and biomechanical. In these factors number of questions were included in the data has been collected. In addition, there was the Nordic section in questions from that we analyzed the pain in different parts of the human body. The study concentrated on the business, education, industry, and healthcare sectors in Hyderabad, Kotri, and Jamshoro. University students and teachers, retail salespeople, manufacturing industry workers, nurses, doctors, nursing assistants, and other health professionals comprised the sample group. The questionnaires were fully completed by 50% of the respondents, resulting in a sample of 116 workers. The majority of the participants were private employees with one to fifteen years of experience in teaching or caring. In this study data has been analyzed through Co-relation between four factors with the Nordic section and ANOVA test through excel and it gives the value of p is also less than 0.05 so we cannot reject the null hypothesis. Over this study it has been analyzed that population is evolving in problems and there should be the proper implementation of ergonomics and safety rules. Test gives the values are not significant and null hypothesis should not reject and it should be improving.

As of late, Automatic speech recognition has advanced on account of instruments, for example, natural language processing, and deep learning, among others. It is a framework or put in another way, a gadget that changes a raw signal into computer comprehensible text. The genuine creation of speech is comprised of changes in air pressure that outcomes in pressure wave that our ear and cerebrum comprehend. The vocal tract is utilized to deliver a human speech, which is adjusted by teeth, tongue, and lips. Speech recognition alludes to a machine's ability to perceive human speech and transform it into a computer comprehensible text. Speech recognition is a magnificent illustration of good interaction between humans and computers. In this paper, we introduce the process to extricate the feature from the signal utilizing Mel-frequency cepstral coefficients. Mel-frequency cepstral coefficients are a genuinely far wide and proficient methodology for feature extraction from a sound file. This technique improved the speech recognition process and removes the distortion in the voice. In this manuscript we applied the Mel-frequency filtration process to improve speech and remove the background noise. the Therefore, the proposed methodology gives better performance in the automated speech recognition system.

As one of the countries situated in the Pacific Ring of Fire, the Philippines suffers from an inexhaustible number of natural disasters every year. One of the most destructible ones is the occurrence of earthquakes. Because of the high damage that earthquakes incur, along with their inevitability and unpredictability, developing effective methods of earthquake damage mitigation as well as disaster preparedness is imperative to lessen the negative impacts it is capable of producing in communities. One efficient way of doing this is by implementing an earthquake early warning (EEW) system that is capable of sending message alerts to receivers to warn them in the event of a hazardous earthquake. With this objective, this study centers on creating an earthquake detector with SMS messaging to function as an EEW system with an added advantage of being low-cost to make it more accessible to the public. Using electronic components based on an Arduino Mega 2560 and a Global System for Mobile Communications (GSM) module, the earthquake detector and its alert message system were created. A series of tests in different locations across Butuan City was then performed to assess the device’s accuracy in measuring different Intensity levels when subjected to surface vibrations. Comparative analysis showed that its recorded values. Corresponded with the values obtained from accelerometer-based mobile applications. In conclusion, the study was deemed functional in its ability to detect low and high surface vibrations, which proves that it is successful in detecting earthquake tremors and vibrations in the event of an earthquake.

The high rate of vehicle theft and the loss of lives occasioned by drunk driving has caused irreparable losses to people and businesses, from a personal, commercial and reputation perspective. Existing systems deployed to mitigate against vehicle theft have all been breached by the ever-adaptive criminals. Drunk driving has been estimated to be a leading cause of deaths on highways and motorways, through preventable accidents. Technology has provided the tools that can aid in mitigating the vices aforementioned with the aim of provisioning lasting solutions. This paper proposes a new architecture for adaptive user authentication in order to mitigate drunk driving and vehicle theft. It considered user authentication in three (3) phases and proposed an authentication architecture for each identified phase, with a step by step description of the implementation method and tools for each phase. The architecture proposed in this study can aid in real time prevention of vehicular theft, unauthorized vehicular access and usage, while also utilizing the benefits of the latest technologies in machine vision and alcohol breadth analyzers to detect and prevent drunk driving, and the associated accidents it causes. 

Facial Expressions are a true and obvious way to represent emotions in human beings. Understanding facial expression recognition (FER) is essential, and it is also useful in the area of Artificial Intelligence, Computing, Medical, Video games, e-Education, and many more. In the past, much research was conducted in the domain of FER using different approaches such as analysis through different sensor data, using machine learning and deep learning framework with static images and dynamic sequence. Researchers used machine learning-based techniques such as the Multi-layer Perceptron Model, k- Nearest Neighbors, and Support Vector Machines were used by researchers in solving the FER. These methods have extracted features such as Local Binary Patterns, Eigenfaces, Face-landmark features, and Texture features. Recently use of deep learning algorithms in FER has been considerable. State-of-the-art results show deep learning-based approaches are more potent than conventional FER approaches. 

This paper focuses on implementing three different Custom CNN Architecture training them on FER13 Dataset and testing them on CK+ and JAFFE Dataset including FER13 after fine-tuning. The three pre-trained models' on FER2013 after fine-tuning have significantly improved the accuracy of the resulting CNN on the target test sets between 65.12 % to 79.07% on the JAFFE dataset and 50.96% to 68.81% on the CK+ dataset.