In present technological era, healthcare providers generate huge amount of clinical data on daily basis. Generated is stored digitally in the form Electronic Health Records (EHR) as a central repository hospitals. Data contained EHR not only used for patients' primary care but also various secondary purposes such research, automated disease surveillance and audits quality enhancement. Using without consent or some cases even with creates privacy issues individuals. Secondly, made accessible...

Abstract At present, voice biometrics are commonly used for identification and authentication of users through their voice. Voice based services such as mobile banking, access to personal devices, logging into social networks the common examples authenticating biometrics. In Pakistan, voice-based very in banking mobile/cellular sector, however, these do not use features recognize customers. Therefore, chance with false identity is always high. It essential design a recognition system...

Mental illness is a common disease that at its extremes leads to personal and societal suffering. A complicated multi-factorial disease, mental influenced by number of socioeconomic clinical factors, including individual risk factors. Traditionally, approaches relying on interviews filling out questionnaires have been employed diagnose illness; however, these manual procedures found be frequently prone errors unable reliably identify individuals with illness. Fortunately, people illnesses...

Speaker recognition plays a significant role in the field of human computer interaction. In recent years, several researchers have contributed this and successfully build machine learning models for automatic speaker systems. paper, we propose an identification system qaries (Quran reciter) Arabic Language. For feature extraction discrete Wavelet Transform (DWT) Linear Predictive Coding (LPC) techniques were used. Classification was performed by Random Forest (RF). order to improve accuracy...

The present research is an effort to enhance the performance of voice processing systems, in our case speaker identification system (SIS) by addressing variability caused dialectical variations a language. We effective solution reduce dialect-related from systems. proposed method minimizes system’s complexity reducing search space during testing process identification. searched set speakers identified dialect instead all training. study conducted on Pashto language, and data samples are...

Today, various mobile applications and wearable devices support the management of diabetes by offering early remote monitoring facilities. However, most available products recommend activity/exercise level for patients based on standard data about impact exercise calories burnt blood Glucose levels. There is a risk associated with such due to lack customization individual patients. In this paper, we propose use an Internet Medical Things (IoMT) architecture predict activity required each day...

This study investigates the use of Large Language Models (LLMs) for improved depression detection from users social media data. Through fine-tuned GPT 3.5 Turbo 1106 and LLaMA2-7B models a sizable dataset earlier studies, we were able to identify depressed content in posts with high accuracy nearly 96.0 percent. The comparative analysis obtained results relevant studies literature shows that proposed LLMs achieved enhanced performance compared existing state the-art systems. demonstrates...

Environmental monitoring and predictive modeling of the Water Quality Index (WQI) through assessment water quality.

COVID-19 is extremely contagious and its rapid growth has drawn attention towards early diagnosis. Early diagnosis of enables healthcare professionals government authorities to break the chain transition flatten epidemic curve. With number cases accelerating across developed world, induced Viral Pneumonia a big challenge. Overlapping with other lung infections limited dataset long training hours serious problem cater. Limited amount data often results in over-fitting models due this reason,...

Visual impairment affects the ability of people to live a life like normal people. Such face challenges in performing activities daily living, such as reading, writing, traveling and participating social gatherings. Many traditional approaches are available help visually impaired people; however, these limited obtaining contextually rich environmental information necessary for independent living. In order overcome this limitation, paper introduces novel wearable vision assistance system that...

A small scale Pashtu speakers' database with multiple accents and dialects has been developed to use in Speaker Identification Systems (SIS) dialect identification systems. is a major spoken language of Pakistan Afghanistan. At present, it become very prominent worldwide due its regional importance. The regions Afghanistan where are mostly occupied by the extremists who for their communication. In order design voice-based systems security other applications, designed which voice data...

Context-awareness is a pervasive computing enabling technology that allows context-aware applications to respond multiple contexts such as activity, location, temperature, and so on. When many users attempt access the same application, user conflicts may emerge. This issue emphasized, conflict resolution approach presented address it. Although there are other approaches in literature, one here unique it considers users' special cases their sickness, examinations, on when resolving conflicts....

Image segmentation is the most important and significant aspect of image processing analysis. Medical imaging critical for providing noninvasive information about human body structure that assists physicians to analyze anatomies efficiently. Until recently, various approaches medical have been presented; however, these are deficient in segmenting abdominal organs because similarity their intensity levels. The purpose this research propose a method facilitate improve performance existing...

Breast cancer is one of the leading causes death among women across globe. It difficult to treat if detected at advanced stages, however, early detection can significantly increase chances survival and improves lives millions women. Given widespread prevalence breast cancer, it utmost importance for research community come up with framework detection, classification diagnosis. Artificial intelligence in coordination medical practitioners are developing such frameworks automate task...