This paper explores the application of deep learning techniques in task assessing disaster impact from satellite imagery. Identifying regions impacted by a is critical for effective mobilization relief efforts. Satellite images, with their vast coverage ground surface, are valuable resource that can be leveraged this purpose. However, analysing image to detect challenging. In recent years, increasing availability images place presents an opportunity utilize on these provide preliminary...

Telecommunication industry is one of the major sectors which at higher risk losing revenue due to customer churn. Thus, when churn management done effectively, it provides a competitive advantage telecom company over its competitors by increasing retention rate. Although many machine learning algorithms exist today, few are effective consider imbalanced nature telecommunication's dataset. The real telecommunication data also varies differently from publicly available dataset and hence...

This paper proposes and highlights the need of an online job board system for colleges its effectiveness in bridging gap between college students career opportunities. Traditionally, employment websites have been used HR management finding candidates recruitment. work is based on a portal built one leading engineering campuses Nepal, Pulchowk Campus, which variation such boards designed specifically to serve Campus. With services like recommendations their skills, candidate filtering assist...

There has been an exponential increase in social media users and the amount of time they spend on various sites such as Facebook. As interact these sites, reveal a lot about their characteristics form profile description status updates. This paper describes system to analyze predict personality traits facebook using KNN SVM learning algorithms were used for classification. The well established Big Five model was analysis. different models each dimensions (Openness, Conscientiousness,...

Covid-19, a respiratory disease caused by the SARS-CoV-2 virus, manifests in individuals with varying degrees of severity. Chest X-rays serve as initial screening procedures for suspected Covid-19 infections, aiding detection abnormalities. Various approaches utilizing deep learning models like Convolutional Neural Networks (CNN) have been proposed through analysis chest radiograph images. However, availability radiographic X-ray images remains limited and not easily accessible to global...

Alumni tracking is a difficult task for any institution that has been running long time. The Department of Electronics and Computer Engineering (DOECE), Pulchowk Campus, IOE, offering undergraduate programs since 1994 A.D. masters 2001 existing information about the alumni department unmanaged out date. This paper presents web-based system to integrate data into well-managed database, act as portal where can update their current status view online yearbooks. work aims make easier simpler...

Stemming is an integral part of Natural Language Processing (NLP). It's a preprocessing step in almost every NLP application. Arguably, the most important usage stemming Information Retrieval (IR). While there are lots work done on languages like English, Nepali has only few works. This study focuses creating Rule Based stemmer for text. Specifically, it affix stripping system that identifies two different class suffixes grammar and strips them separately. Only single negativity prefix (Na)...

Spam in Short Message Service(SMS) is a serious issue that impacts mobile phone consumers all around the world. Many strategies have been applied using several deep learning and machine techniques to overcome these issues. The bagging approach used study combine four different algorithms, namely RVM, SVM, Naive Bayes, KNN. Then final prediction calculated from predictions obtained each of algorithms by majority-based voting approach. So, this paper offers research on comparative analysis...

Skills management is one of the key factors to address increasing competitiveness among different companies. Suitable knowledge representation and approach for matching skills competences in job vacancies candidate profiles can support human resources automation through suitable ranking services. This paper presents an matchmaking between demand supply skill enrichment over multiple criteria. work builds upon methods profile modeling, information multi-criteria matching. The main...

Message integrity and authenticity is crucial with ever increasing network communication. Cryptographic Hash Functions are main building block of message integrity. Many types hash functions being used developed. In this paper, a new keyed function proposed described. This algorithm produces code 128 bits for an arbitrary length input. The uses key during hashing, so that any intruder who does not know the cannot forge code, and, thus it satisfies purpose security, authentication in network....

Billions of people across the globe have been using social media platforms in their local languages to voice opinions about various topics related COVID-19 pandemic. Several organizations, including World Health Organization, developed automated analysis tools that classify COVID-19-related tweets into topics. However, these help combat pandemic are limited very few languages, making several countries unable take benefit. While multi-lingual or low-resource language-specific being developed,...

User-generated content can help the growth of linked data. However, we lack interfaces enabling ordinary people to author Secondly, have multiple perspectives on same concept and different contexts. Thirdly, not enough ontologies exist model various Therefore, propose an approach enable share data through easy-to-use social platform. Users define their own concepts conceptualizations are allowed. These consolidated using semi-automatic schema alignment techniques supported by community....

Digital watermarking is one of the best techniques to protect digital data from unauthorized access and provide copyright protection. Imperceptibility robustness are important features watermarking. Color image method based on discrete wavelet transform (DWT), all phase cosine bi-orthogonal (APDCBT) singular value decomposition (SVD) proposed in this paper. In technique we hide a color watermark into cover balancing both imperceptibility robustness. The three level DWT applied Luminance (Y)...

With the rise in internet usage, Nepali individuals have left a flood of opinionated comments their language on YouTube and other social media sites. Such remarks can be subjected to sentiment analysis, which useful for both research business purposes. analysis models extremely understanding user's expectations towards product uplift any organization. Similarly, with Large Language NLP space, there are several large pre-trained BERT architecture upon text corpus. This focuses developing...

Information is abundant in the web. The knowledge graph used for organizing information a structured format that can be retrieved using specialized queries. There are many Knowledge graphs but they differ their ontologies and taxonomies as well property types bind relation between entities, which creates problems while extracting from them. an issue multilingual support. While most of them claim to more suitable querying English language. Most existing existence based on Wikipedia Info box....

Sound Source Localization (SSL) are used to estimate the position of sound sources. Various methods have been for detecting and its localization. This paper presents a system stationary source localization by cubical microphone array consisting eight microphones placed on four vertical adjacent faces which is mounted three wheel omni-directional drive inspection monitoring disaster victims in areas. The proposed method localizes 3D space grid search using Generalized Cross Correlation Phase...