Great Britain Journals Press
Not a member yet
951 research outputs found
Sort by
Evolution of Performance Metrics for Accurate Evaluation of Speech-to-Speech Translation Models: A Literature Review
Full text linkThe translation of speech from a source to speech in a target language with generative artificial intelligence is an area of research that is presently being actively explored. This is aimed at solving global language barriers thereby ensuring seamless communication between the individuals involved. It has been well developed for high-resourced languages like English, Spanish, French and Chinese. Currently, objective evaluation metrics such as Bilingual Evaluation Understudy Scores (BLEUS), and subjective metrics such as Mean Opinion Score Naturalness (MOSN) and Mean Opinion Score Similarity (MOSS) are being used to evaluate the performance of the output of speech-to-speech models. However, low resourced languages are still undeveloped in the area of speech processing applications, especially the African indigenous languages. The output speech in the target language needs to be evaluated to determine the closeness to the ground truth, as well as how natural and intelligible it is to the intended listeners. This paper presents a review of trends from the current metrics to emerging ones such as Recall Oriented Understudy for Gisting Evaluation-L (ROUGE-L) and BLASER. The applications of speech models� metrics on various leaderboards and modern AI platforms were also discussed. The outcome shows that while BLEU score and MOSN metrics are prevalent for speech models, there is a need to explore metrics such as ROUGE-L, and BERTScore which are machine translation metric due to their benefits
A Novel Detail-Enhancement Method for Industrial Digital Radiography via Gaussian-Free Multiscale Laplacian Adaptive Fusion
Full text linkThis study introduces a concise framework for detail enhancement in industrial digital radiography based on the mathematical integration of logarithmic transformation and multiscale Laplacian analysis. The proposed method utilizes multiscale adaptive pixel-level fusion with hyperbolic tangent-based coefficients to preserve microscale defects while enhancing subtle features throughout the dynamic range. Quantitative evaluations of diverse industrial welds, including ship plates, boilers, and oil pipelines, demonstrated substantial improvements. In oil pipeline weld inspections, the Peak Signal-to-Noise Ratio of the method based on Histogram Equalization increased by 133.82%, whereas the Structural Similarity Index Measure and Spatial Frequency metrics exhibited gains of up to 127.27% and 85.81%, respectively. The framework\u27s consistent, albeit moderate, performance gains over state-of-the-art deep learning methods across all benchmarks confirm its value not only as a robust and widely applicable tool but also as a superior preprocessing or integrated solution within nondestructive testing pipelines
Implementation of Generative Artificial Intelligence in a Virtual Reality Exhibition
Full text linkBackground:?Exhibitions are an activity that is often attended by many companies around the world because of its benefits as a promotional event. Companies can build the image of their company and products and interact directly with buyers through an exhibition. With recent advances in technology, virtual exhibitions have begun being created as an alternative to conventional face-to-face exhibitions. This presents an opportunity to implement other technologies within these new type of exhibition, namely generative artificial intelligence.
Methods:?This research involved the use of the Unity game engine to create a virtual environment resembling an exhibition space. Within this environment users can navigate their surroundings and view the products displayed at the exhibition. Generative artificial intelligence was then implemented to generate content based on the products available in the exhibition. A head mounted display and virtual reality controllers were used to view and control the application. Participants were instructed to test the application. Once done, they then filled out a user acceptance test in order to evaluate their experience of using the application and how the use of generative artificial intelligence impacted that experience.
Results:?Five participants tested and evaluated the application. The implementation of generative artificial intelligence had a positive impact on the quality of the information provided by the application. In addition, it did not impact the immersion of the experience.
Conclusions:?Generative artificial intelligence can be used in a virtual exhibition setting to dynamically generate content regarding available products
Advancement in Autonomous Navigation in Space through Artificial Intelligence: A Systematic Review
Full text linkSince the first trip to Mars, rovers have been used to conduct scientific experiments. The use of rovers continues to date due to Mars being uninhabitable for humans at this state and time. Despite the invention of Mars rovers, many limitations have been challenging space exploration, even with improvements in the Curiosity and Perseverance rovers. This study aimed to investigate the advancement in autonomous navigation in space through artificial intelligence. The study used qualitative, desktop, and systematic review research designs. The study\u27s objectives were to determine the types of autonomous navigation technologies in space and examine the role of artificial intelligence in autonomous navigation technologies. Data was collected from secondary sources, which were purely open-access online journals. A total of 61 journals were searched as the target population. The study then conducted judgmental sampling using 9 out of 61 journals. The Preferred Reporting Items for Systematic Reviews and meta-analysis guidelines guided the sampling process. The study used an extraction form to collect data. The study found that star tracker navigation reduces positioning errors and environmental disturbances from sand and dust storms. It was also established that LOS navigation and star trackers ensured highly accurate navigation in challenging conditions for path-planning accuracy. Selecting the Next Coordinate, Obtaining Coordinates of Target Points, Generating Additional Coordinates, and optimising planned paths reduce travel time and energy consumption. On-orbit servicing robotics can extend rover missions up to 10 years. It was also found that 3D OctoMaps improves rovers\u27 navigation accuracy. In addition, the study revealed that unsupervised homography networks, state recursive models, and inertial measurement models reduce localisation errors. Simultaneous Localization and Mapping can improve navigation accuracy and reduce mission delays. The use of RL navigation systems reduces mission delays. It was also found that Convolutional Neural network algorithms advance autonomous navigation accuracy in terms of terrain classification. The study also established that the Nvidia Jetson Nano AI controller and Rapidly-exploring Random Tree (RRT) in MATLAB reduce travel time and energy consumption. Finally, it was found that artificial neural networks advance the accuracy of terrain classification and lower navigation errors
AI-based Sustainable Vehicle Monitoring System for Existing Internal Combustion Vehicles
Full text linkThe transportation industry is a major contributor to carbon� emissions, with internal combustion engines responsible for over� 25% of the total. Despite advances and regulations encouraging the� shift to electric vehicles, the transition from diesel engines remains� slow, as expected. Many countries have heavily relied on diesel� engines, which makes the switch to electric vehicles more difficult� due to the higher costs of buying and replacing internal combustion� engines with electric ones. Therefore, this report suggests a� solution: retrofitting existing ICE vehicles with AI-powered� sustainable vehicle monitoring systems. This upgrade involves� installing sensors that work with OBD-II diagnostics to monitor� emissions, fuel use, and driving habits in real time. Gathering this� data aims to develop personalized, eco-friendly driving� recommendations that help reduce overall emissions. This method� provides a cost-effective, sustainable, and environmentally friendly� alternative to high carbon emissions. It is also scalable, even in� regions with limited financial resources
The Playtech Edu Platform and the Consequences of Technology for Data Monitoring and Improving Educational Indexes in the Municipality of S㯠Miguel Dos Campos - Alagoas
Full text linkThis article aims to evaluate the impact of the PlaytechEdu platform on educational indicators in the municipality of S�o Miguel dos Campos - Alagoas, demonstrating how this platform positively influences data monitoring and demonstrating the importance of these technologies in achieving improvements in municipal education. The research will demonstrate, based on descriptions of the features of the PlaytechEdu platform, how it has been implemented in the municipality of S�o Miguel dos Campos - Alagoas, based on a data analysis and comparison with municipal educational indicators before and after the implementation of the platform. Finally, it will seek to discuss the role of startups and govetechs in public management innovation, and their influence on the improvement of public services. The research uses a mixed research line, graphically demonstrating the improvement resulting from the implementations, based on a documentary analysis of reports, spreadsheets and data provided by the education department of the municipality of S�o Miguel dos Campos. Thus, the research seeks to show how the implementation of PlaytechEdu is a significant factor in the search for educational quality in the municipality of S�o Miguel dos Campos, corroborating the digital technological potential in educational transformation and improvement of local results
Severe Low Vitamin B12 Levels with Macrocytosis and Associated Hemolytic Anemia, Mimicking Thrombocytopenic Thrombotic Purpura: A Case Report and Literature Review
Full text linkThe typical presentation of cobalamin deficiency is macrocytic anemia with or without neurologic symptoms, adding that the most frequent cause is Pernicious anemia, an autoimmune disease. We present a case of a 61year-old man with neurologic symptoms, pancytopenia, and laboratory findings consistent with hemolytic microangiopathic anemia (MAHA), like Thrombocytopenic Thrombotic Purpura (TTP). The lack of response to plasma exchange (PEX) therapy, concomitant with low plasma levels of cobalamin, low reticulocyte count, macrocytosis and remarkably high lactic dehydrogenase (LDH) levels made us suspect a pseudo-Thrombotic Microangiopathy (Pseudo TMA). The diagnosis was confirmed with a normal serum ADAMPTS13 activity and a rapid clinical and laboratory improvement after cobalamin supplementation. We think the internist must know the wide variety of presentations of Cobalamin deficiency, since it is a reversible cause of bone marrow failure, and its� misdiagnosis may result in unnecessary costly procedures
Prevalance of Hpv Infection in Women Living with HIV Attending Waibargi Specialist Hospital
Full text linkCervical cancer remains a significant public health concern, particularly for women living with HIV (WLWH), due to their increased susceptibility to persistent human papillomavirus (HPV) infections.�
This study aims to assess the prevalence of high-risk HPV (hrHPV) infections in WLWH attending Waibargi Specialist Hospital in Myanmar in the year 2024. The cross-sectional analysis involved 234 WLWH, tested with Cobas 4800 system HPV DNA test. Colposcopy directed biopsies were conducted among the participants to detect the presence of cervical intraepithelial neoplasia (CIN) and invasive carcinoma.
The results revealed a high HPV prevalence of 29.9% among the study population, with 70 women tested positive for one or more high-risk HPV types.� Among those, single infection with HPV 16 was found in 9 women (3.8%), HPV 18 in 8 (3.4%) while 35 (15%) of them were infected with other high-risk HPV types. Additionally, 18 women (7.7%) had mixed infections involving multiple hrHPV types.��
The study also identified that women on ART for more than three years exhibited significantly lower HPV infection rates, as did those with undetectable viral loads, suggesting that effective HIV management can mitigate HPV-related cervical cancer risk.
In this study, 41 women (70.7%) out of 58 HPV-positive cohort diagnosed with CIN I or more severe histological abnormalities after colposcopy directed biopsy. Notably, 86.7% of patients with HPV 16, 18, or mixed infections had positive histology results, compared to 53.6% in those with other hrHPV.
In conclusion, this study highlights the high prevalence of hrHPV infections and the association between specific HPV genotypes and the development of cervical pre cancer and cancer among WLWH. The study also emphasizes the need for integrated cervical cancer screening and vaccination programs within HIV frameworks along with the importance of proper HIV treatment. However, since it is a hospital-based study, further research is required to cover the broader populations, particularly in rural and underserved areas of Myanmar
Morbidity and Mortality of Percutaneous Endoscopic Gastrostomies Performed Over A 9-Year Period. Experience of the Pasteur Hospital Endoscopic Center
Full text linkEnteral nutrition is the first method to be considered in patients with nutritional risk and disorders that preclude the oral route. Endoscopic gastrostomy is a fast and safe procedure with a low rate of complications. The aim of this study was to determine the morbidity and mortality of PEG performed at the Endoscopic Center of the Pasteur Hospital from January 1, 2013 to December 31, 2021.� The total number of gastrostomies performed was 241. The most frequent indications were neoplastic and neurological. The frequency of complications observed was 17 %, similar to what is described in the literature (0.4% to 22.5%). The most frequently observed complication was accidental exit (8.9 %), of which the majority managed to recover the trajectory. Among the most important complications were buried dumping syndrome or incarceration (1.6 %) and hemorrhage (1.2 %). Infections accounted for 2.4%. One patient presented implantation of laryngeal neoplasm in the abdominal wall, a rare but described complication. Six patients died within the first 30 days, which is equivalent to 2.4 %, less than that described in the literature. Of these, 4 were due to causes associated with their underlying pathology.�
Prevalence and Determinants of Hearing Loss in Patients with Chronic Rhinosinusitis in a Tertiary Hospital in Nigeria
Full text linkBackground: Chronic rhinosinusitis is a common otorhinolaryngologic condition that is often encountered in daily practice. Nasal obstruction has been found to be the most disturbing symptom in patients with chronic rhinosinusitis which could predispose them to otologic pathologies.
Aim: to assess the prevalence and determinants of hearing loss among patients with chronic rhinosinusitis in the Lagos State University Teaching hospital.
Method: an analytical cross-sectional study which was conducted among 256 patients diagnosed with chronic rhinosinusitis in Lagos State University Teaching Hospital. Participants� audiological profiles was assessed by conducting Pure Tone Audiometry and tympanometry. Data obtained were analyzed with SPSS software version 27.0.
Result: The participants aged 40-49 years constituted the largest age group (30.1%) and most of them were female (69.5%). The prevalence of hearing loss among the participants was 40.2%. There was reduced odds for hearing loss among participants aged 20-29 years (AOR= 0.043, 95% C.I= 0.012- 0.157), 30-39 years (AOR= 0.042, 95% C.I= 0.010- 0.171) and 40-49 years (AOR= 0.075, 95% C.I= 0.027- 0.209). Also there was reduced odds for hearing loss in male (AOR= 0.142, 95% C.I= 0.057- 0.357), but those with facial pain had increased odds for hearing loss (AOR= 5.814, 95% C.I=1.742- 19.231) and those that with nasal polyp had increased odds for hearing loss (AOR= 2.134, 95% C.I= 1.023- 4.451).
Conclusion: the prevalence of hearing loss was high in chronic rhinosinusitis and its determinants were age group, gender, facial pain and nasal polyps