In the era of advanced technology and digitalization, the use of machine learning makes it possible to increase the efficiency of the recruitment process. This study aims to identify various variables that directly play a role in recruitment. The study also addresses the HR sphere problems and proposes a solution related to the use of machine learning. The research methodology includes an analysis of the characteristics which are dominated by past candidates. The data obtained suggests that machine learning can bring significant benefits to the recruitment process, such as reducing the cost and time for selection, reducing emotional factors, and increasing accuracy. Overall, this study provides valuable insight into the potential of machine learning in recruitment and highlights how it can be used to facilitate the recruitment process.
This article discusses the potential applications of face-morphing technology, which has become popular in the field of Computer Vision. In this work, we focus on finding the average face of the Kazakh nation by combining different photos of Kazakh men and women separately. We believe that having an average face for our nation will help other nations quickly identify Kazakh people and can provide insight into its culture and characteristics. The project involves finding all face points and placing them in their initial perfect position with the help of face detection. We use OpenCV as a computational platform and the methods of face detection and face morphing by computer vision to accomplish our goal.
The absence of timely and proper intake of medicines can pose great health hazards for patients and elderly persons suffering from critical illnesses. An IoT-based smart pillbox is being proposed to overcome that problem. This pillbox aims to help the patients take the correct medicines at scheduled times in the right amount and also to help keep track of the medical history of the patient. The pillbox can be set up using an app and then it will alert the patient using a buzzer at scheduled times and upon pushing the button after taking particular medicine from the specified drawer, it will update the medicine intake information in the cloud server so that the caregiver can get notified about any unwanted exceptions. It will also keep the count of pills and provide a reminder when the pill count gets low. Thus this smart pillbox aims to ease the life of patients and maintain the well-being of their health.
The increase in network attacks is a serious threat. For the purpose of supporting study in connected areas, researchers provide datasets for network assaults. Following that, other attack detection techniques based on these datasets are suggested. In this paper, we have proposed a Deep Learning (DL) model called DL Dense Classifier with Long Short-Term Memory (LSTM) which is combination of Encoder and classifier modules to identify the type of network attacks from a massive malware dataset with 12 key malware categories and 141 features. Moreover, we have evaluated 3 classifier models on the CCCS-CIC-AndMal-2020 dataset utilizingprecision, recall, F-score, and accuracy metrics. The results of the experiments show that adding an LSTM encoder module to the DL Dense Classifier model successfully improves the accuracy of DL Dense Classifier from %87 to %91 and perform same as the ensemble model of Random Forest, which is one of the best ranked algorithms in the other research.
Considering the extensive utilization of social media platforms, false information is more likely to spread rapidly among users. With the surge of user-generated content, a significant amount of the information being shared is in-accurate and has no connection to reality. It can be chal-lenging to automatically identify and verify the accuracy of textual content. This research project aims to employ B-LSTM deep learning model with dynamic and static pre-trained embeddings to classify news datasets utilizing three fake news benchmarking datasets.
