Enhancing interpretability and explainability for fish farmers: decision tree approximation of DDPG for RAS control

This research paper focused on how knowledge, attitudes, and acceptance of Artificial Intelligence (AI) interrelate among business management students. Spearman Rank Correlation analysis revealed that students' knowledge of AI and attitudes toward it had weak yet statistically significant positive relationship, which means that gaining knowledge contributed to more positive attitudes toward AI. Knowledge and acceptance of AI lacked a weak statistically significant correlation, which means that merely knowing AI does not lay a good foundation for acceptance. On the other hand, attitudes toward AI have been found to have highly positive significant correlation with acceptance, stating that the students' attitudes are important in the process of acceptance. Further, the results support the Technology Acceptance Model (TAM) by asserting that positive attitudes towards AI may be fostered through ethical considerations surrounding AI, awareness-building on AI, and responsible AI use in educational settings. The study recommends that AI be part of the curriculum, that ethical discussions take place, and that increased knowledge and acceptance among students may occur through positive attitudes. Results from this study have practical implications in that educational institutions must engage in imparting technical knowledge concerning AI, while at the same time correcting its perception by means of value instructions, ethical considerations, and exposure to actual applications. Addressing the cognitive and affective domains through this perspective schools might nurture a conducive environment for ushering in the positive integration of AI within academia and future workplace settings.

This study aims to assess Croatian dentists' knowledge, attitudes, and use of artificial intelligence (AI) and modern technology, while also identifying perceived barriers to AI and modern technology adoption and evaluating the need for further education and training. A cross-sectional survey was conducted in February 2024 among general dentists in Croatia using a self-structured questionnaire. A total of 200 respondents filled out the questionnaire. It included five sections: socio-demographic and professional information, self-assessment of AI and modern technology use, knowledge of AI in dentistry, current innovations and devices used in practice, and barriers to AI and modern technology integration in practice. Data were analyzed using descriptive statistics and a regression analysis to explore relationships between socio-demographic factors and AI knowledge. The mean knowledge of AI systems was 3.62 ± 2.56 out of a possible score of 7, indicating relatively poor knowledge, with 47.5% demonstrating knowledge below the median. Most respondents (76.0%) did not use AI systems and modern technology in practice; however, prosthodontics (13.0%) and oral surgery (10.0%) were identified as the primary fields utilizing these technologies. Respondents rated their knowledge of modern technologies and AI as weak or moderate, with 60.5% engaged in continuous education. Despite 76.0% not using AI daily, 71.0% believed that these technologies could enhance patient care. Participants interested in further training showed significantly better knowledge of AI applications (p = 0.030). Major barriers included acquisition and maintenance costs (59.0%) and financial constraints (58.0%). The study revealed that most respondents had poor knowledge of AI systems. Despite this, there is a recognition of AI's and modern technology potential in dentistry, emphasizing the need for enhanced education and training in this field.

PurposeArtificial intelligence (AI) is playing an increasingly important role in healthcare and health professions education. This study explored medical students’ and interns’ knowledge of artificial intelligence (AI), perceptions of the role of AI in medicine, and preferences around the teaching of AI competencies.MethodsIn this cross-sectional study, the authors used a previously validated Canadian questionnaire and gathered responses from students and interns at KIST Medical College, Nepal. Face validity and reliability of the tool were assessed by administering the questionnaire to 20 alumni as a pilot sample (Cronbach alpha = 0.6). Survey results were analyzed quantitatively (p-value = 0.05).ResultsIn total 216 students (37% response rate) participated. The median AI knowledge score was 11 (interquartile range 4), and the maximum possible score was 25. The score was higher among final year students (p = 0.006) and among those with additional training in AI (p = 0.040). Over 49% strongly agreed or agreed that AI will reduce the number of jobs for doctors. Many expect AI to impact their specialty choice, felt the Nepalese health-care system is ill-equipped to deal with the challenges of AI, and opined every student of medicine should receive training on AI competencies.ConclusionThe lack of coverage of AI and machine learning in Nepalese medical schools has resulted in students being unaware of AI’s impact on individual patients and the healthcare system. A high perceived willingness among respondents to learn about AI is a positive sign and a strong indicator of futuristic successful curricula changes. Systematic implementation of AI in the Nepalese healthcare system can be a potential tool in addressing health-care challenges related to resource and manpower constraints. Incorporating topics related to AI and machine learning in medical curricula can be a useful first step.

Artificial intelligence (AI) is rapidly transforming medical practice by enhancing diagnostic accuracy, streamlining workflows, and supporting clinical decision-making. However, the integration of AI into health care largely depends on the preparedness and acceptance of future physicians. Therefore, assessing their knowledge and perceptions of AI is crucial. Notably, no study has yet evaluated these factors among medical students in Morocco. The aim of this study was to describe Moroccan medical students' knowledge and perception of AI. A cross-sectional, observational study was conducted from February to May 2023 at the Faculty of Medicine and Pharmacy, Agadir, Morocco. All undergraduate medical students from the first to the seventh year were eligible, excluding graduate students. A snowball sampling method was used, with a calculated minimum sample size of 385. To account for potential missing data, and given the target population size of 1150, the sample size was increased by 50%. Data were collected through a validated online questionnaire and analyzed using JAMOVI 2.6.2, with significance set at P<.05. A total of 580 medical students (female n=363, 62.6%; mean age 21.3, SD 2.13 years; response rate 50.4%) participated. While 96% (n=557) had heard of AI, 73.1% (n=424) were unfamiliar with key AI terminologies, only 11% (n=64) understood AI functioning, and 14.8% (n=86) were familiar with everyday AI applications. Objectively, 88.1% (n=511) correctly identified deep learning as a method for automated pattern recognition, with 71.5% (n=415) acknowledging its interpretability challenges. First-cycle students demonstrated significantly higher familiarity with AI terms (83/156, 53.2% vs 51/156, 32.7% vs 22/156, 14.1%; P<.001). In terms of perception, 83% (n=482) viewed AI as a collaborative tool, 84.1% (n=488) anticipated a transformative impact on medicine, 39% (n=227) expected noninterventional medicine to be replaced within a decade, and 57.1% (n=331) believed certain specialties could be supplanted by AI. Regarding AI in medical education, 90% (n=522) supported its integration into the curriculum and 94% (n=546) expected enhanced learning conditions, but only 48.1% (n=279) felt ready to use AI tools upon graduation. Additionally, gender and technology familiarity significantly influenced specific perceptions, with technology-savvy students reporting greater readiness (P<.001) and women more likely to view AI as revolutionary (315/488, 64.5% vs 173/488, 35.5%; P=.02). Medical students' knowledge of AI is still limited, but their awareness of the potential impact of this technology on future practice and their openness to its integration into the medical curriculum constitute a promising basis for the successful implementation of these new concepts in our health care system.

Optimizing feeding rates in recirculating aquaculture systems (RAS) is crucial for ensuring fish growth, health, and system efficiency. This research introduces a novel approach to RAS feeding control using a Deep Deterministic Policy Gradient (DDPG) reinforcement learning algorithm. The developed system integrates feeding rate optimization with comprehensive water quality management to improve overall performance and stability. The DDPG controller demonstrated superior tracking accuracy, reduced feed consumption, and improved operational stability compared to traditional control methods such as Model Predictive Control (MPC), PID, and Bang-Bang control. The learned policy-maintained feeding rates within optimal ranges while adapting to dynamic system requirements and environmental conditions. The integration of water quality monitoring and control further enhanced system stability, ensuring critical parameters remained within target ranges. Comparative analysis revealed the DDPG controller’s advantages in terms of faster recovery times after environmental perturbations, improved long-term stability, and significant economic benefits through reduced operational costs and increased efficiency. The robustness and adaptability of the system were validated through comprehensive testing under various fault conditions, growth phases, and system scales. The successful development and evaluation of the DDPG-based RAS feeding control system represents a significant advancement in aquaculture management. The demonstrated improvements in efficiency, stability, and economic performance establish the potential for this approach to revolutionize feeding practices in commercial RAS operations. Further research and development efforts can build upon these findings to advance the state-of-the-art in intelligent aquaculture management systems and promote the sustainability and profitability of the industry.

This study explored physician anesthesiologists' knowledge, exposure, and perceptions of artificial intelligence (AI) and their associations with attitudes and expectations regarding its use in clinical practice. The findings highlight the importance of understanding anesthesiologists' perspectives for the successful integration of AI into anesthesiology, as AI has the potential to revolutionize the field. A cross-sectional survey of 27,056 US physician anesthesiologists was conducted to assess their knowledge, perceptions, and expectations regarding the use of AI in clinical practice. The primary outcome measured was attitude toward the use of AI in clinical practice, with scores of 4 or 5 on a 5-point Likert scale indicating positive attitudes. The anticipated impact of AI on various aspects of professional work was measured using a 3-point Likert scale. Logistic regression was used to explore the relationship between participant responses and attitudes toward the use of AI in clinical practice. A 2021 survey of 27,056 US physician anesthesiologists received 1086 responses (4% response rate). Most respondents were male (71%), active clinicians (93%) under 45 (34%). A majority of anesthesiologists (61%) had some knowledge of AI and 48% had a positive attitude toward using AI in clinical practice. While most respondents believed that AI can improve health care efficiency (79%), timeliness (75%), and effectiveness (69%), they are concerned that its integration in anesthesiology could lead to a decreased demand for anesthesiologists (45%) and decreased earnings (45%). Within a decade, respondents expected AI would outperform them in predicting adverse perioperative events (83%), formulating pain management plans (67%), and conducting airway exams (45%). The absence of algorithmic transparency (60%), an ambiguous environment regarding malpractice (47%), and the possibility of medical errors (47%) were cited as significant barriers to the use of AI in clinical practice. Respondents indicated that their motivation to use AI in clinical practice stemmed from its potential to enhance patient outcomes (81%), lower health care expenditures (54%), reduce bias (55%), and boost productivity (53%). Variables associated with positive attitudes toward AI use in clinical practice included male gender (odds ratio [OR], 1.7; P < .001), 20+ years of experience (OR, 1.8; P < .01), higher AI knowledge (OR, 2.3; P = .01), and greater AI openness (OR, 10.6; P < .01). Anxiety about future earnings was associated with negative attitudes toward AI use in clinical practice (OR, 0.54; P < .01). Understanding anesthesiologists' perspectives on AI is essential for the effective integration of AI into anesthesiology, as AI has the potential to revolutionize the field.

The present contribution seeks to map the development of Artificial intelligence (AI) knowledge as indicated through scientific publications. A set of principal keywords is employed in order to identify those publications that are related to AI in the Web of Science and the metadata provided by the database is then utilised to map the evolution of the field across different scales, such as the national, country, and regional level. This analysis allows for the identification of potential AI “hotspots”, while also establishing places that have been leading in the development of AI knowledge from the onset vis-à-vis those that have managed to catch up over time. In addition, a network that illustrates international collaborative efforts in AI knowledge creation via co-authorships across nations and via the evolution of keywords’ co-occurrence across three decades is illustrated. It is evident that these networks have become denser with time, and that they have changed across regions. The objective of the present analysis is to enhance our understanding about where and how scientific AI knowledge is created, which in turn should encourage and assist future research efforts looking to study AI knowledge and its consequences.

Background: Recirculatory aquaculture system (RAS) is an intensive and sustainable aquaculture system that involves the reuse of water within a closed loop system minimizing water usage and reduces environmental impact. This study compares the growth performance of Climbing Perch (Anabas testudineus) in a low-cost recirculatory aquaculture system (RAS) versus an advanced RAS. The low-cost RAS aims to reduce economic burdens on fish farmers while maintaining sustainability through efficient water reuse. Methods: Climbing perch fingerlings were cultured under Advance RAS, Low cost designed RAS and fiberglass reinforced plastic (FRP) (control) tanks in triplicate with meticulous monitoring of various growth parameters and water quality assessments following standard methods. Result: The study reveals that A. testudineus grew better in advanced RAS, with higher weight and length compared to low-cost RAS and FRP tanks. However, the survival rate was highest in the low-cost RAS (100%) versus advanced RAS (97.61%) and FRP tanks (86.77%). Weight gain, specific growth rate, PER and FCR were statistically similar in both RAS systems. Advanced RAS had a higher temperature (29.02oC) and lower pH (7.56) than the low-cost RAS (28.66oC, 7.82) and FRP tanks (28.46oC, 8.25). The low-cost RAS outperformed in dissolved oxygen levels, lower ammonia, nitrite and nitrate content Low-cost RAS demonstrated superior efficiency in controlling total suspended solids (20.00 mg/l) compared to advanced RAS (58.21 mg/l) and FRP tanks (158.74 mg/l) and superior control of total suspended solids. The low-cost RAS offers comparable performance to advanced RAS, with proper filtration maintenance enhancing fish survival and quality.

Background: The rapid advancement of artificial intelligence (AI) in various sectors has revolutionized problem-solving approaches, particularly in healthcare. Developed countries have invested significantly in AI research and applications in healthcare, while low-income countries such as Somalia lag due to various challenges. This study aimed to assess the knowledge, attitudes, and practices (KAP) of AI among healthcare professionals in Somalia and explore their familiarity with AI technologies and practices. Methods: A cross-sectional study was conducted from January 1, 2024, to March 15, 2024, among 441 healthcare professionals in Somalia, using an online questionnaire. The questionnaire assessed the participants' sociodemographic information, knowledge of AI applications in healthcare, attitudes towards AI capabilities, and practical experience with AI in healthcare. Results: Most participants demonstrated good knowledge of AI (67.6%) and a positive attitude towards its potential in healthcare (80.5%). However, a significant gap was observed in the practical application of AI, with 79.1% of the respondents reporting poor practice. The study also found that sociodemographic factors such as age, gender, and income level did not significantly influence knowledge or attitudes towards AI but did affect its practical use. Professionals in certain fields such as midwifery and public health are more likely to use AI in their work. Knowledge and attitude scores were also significant predictors of practice scores. Conclusion: Healthcare professionals in Somalia demonstrate a good understanding and positive attitudes towards AI but encounter challenges in its practical application. This study emphasizes the necessity of an enhanced infrastructure, technical expertise, and data access to fully utilize AI's potential in healthcare. It also highlights the significance of addressing ethical considerations and implementing regulations to ensure responsible use of AI in healthcare. Efforts are needed to translate awareness and receptiveness into effective practice, which could result in a better healthcare system.

Context: Artificial Intelligence (AI) is revolutionizing dental care, including pediatric dentistry, through advancements in diagnosis, treatment planning, and patient management. Despite its potential, successful AI implementation depends on dental professionals’ awareness, knowledge, and acceptance. Aims: To evaluate the awareness, knowledge, and perception of AI in pediatric dentistry among Indian pediatric dentists. Settings and Design: A descriptive cross-sectional study has been conducted among members of the India Society of Pediatric &amp; Preventive Dentist. (ISPPD) Methods and Material: The study was conducted from March to July 2025. The sample size was calculated as 210 pediatric dentists. The questionnaire captures demographic data, awareness and familiarity with AI, knowledge of AI applications in pediatric dentistry, perceived benefits and limitations, and willingness to integrate AI into practice. The questionnaire was distributed online as google form links. Statistical analysis used: Data has been analysed using SPSS version 23, employing descriptive statistics to determine associations Results: A majority saw value in AI for decision-making, though many felt it should complement—not replace—clinical judgment. Awareness of AI tools varied, with 48.4% recognizing multiple tools, and 19.8% aware of AI-assisted caries detection software. Nearly half (47.4%) believed AI could significantly aid in early caries detection, though cost (51%) and lack of training (41.1%) were key barriers to adoption. Conclusions: AI is an emerging tool in pediatric dentistry with significant potential. Awareness, knowledge, and willingness to adopt AI among practitioners are vital for its effective implementation.

Objective: Healthcare is undergoing a rapid transformation due to artificial intelligence (AI), which has the potential to enhance the nursing profession significantly. Empirical evidence suggests that AI is already influencing nursing practice, encompassing clinical care, nursing responsibilities, and nurse-patient interactions. The goal of the study was to assess nurses' knowledge of artificial intelligence. Methods and Materials: The research was carried out including (354) nurses selected from different departments of the hospitals in Iraq, which include surgical wards, medical, intensive care units, emergency, dialysis, and maternal and child units, using a self-report questionnaire to assess the nurses' Sociodemographic variables (SDVs), and the nurses' AI knowledge. Using statistical tables like Percent (%) and Frequencies (No.). Calculating the overall mean score (M ±), the standard deviation test ±SD. Findings: According to the study's findings, 57.6% of the participants were female, and 94.4% of them were not enrolled in artificial intelligence training programs. Among nurses, 85.6% had a moderate level of understanding of AI. Regarding artificial intelligence, a correlation was found between the nurses' knowledge and specific characteristics (age, educational background, department or unit, and training program) at p ≤ 0.05. Conclusion: The study concluded that nurses' knowledge of artificial intelligence was moderate, varying according to their age, educational background, training, and department of employment.

The implementation of fish farming has been increasing worldwide over the last decades, as well the search for alternative production systems and the treatment of their generated effluent. Recirculating Aquaculture System (RAS) is a compact solution for future intensive fish farming. However, few configurations of treatment technologies were tested in RAS, such as systems with a Membrane Aerated Biofilm Reactor (MABR). In this scene, this study aimed to evaluate the RAS effluent treatment efficiency device for intensive Nile tilapia (Oreochromis niloticus) production, the fish species most cultivated worldwide. The novel RAS configuration was composed of a cultivation tank (CT), a Column Settler, and a MABR. The RAS performance was evaluated by pH, temperature, turbidity, dissolved oxygen (DO), total nitrogen (TN), ammonia, nitrite, nitrate, total solids (TS), and chemical oxygen demand (COD). The obtained results in average values for temperature, pH, and DO inside the CT were 25.22 ± 1.88°C, 7.61 ± 0.33, and 3.80 ± 1.30 mg L−1, respectively, as ideal for tilapias survival. Average removal efficiencies found in the RAS for turbidity, COD, TN, nitrite, nitrate, ammonia, and TS were 50.0, 40.5, 11.7, 40.2, 13.1, 35.0, and 11.4%, respectively. Overall, we observed removals for all parameters studied, with good results, particularly, for COD, turbidity, nitrite, and ammonia. The evaluated system proved an effective alternative for water reuse in RAS capable of maintaining water quality characteristics within the recommended values for fish farming.

The present study was conducted with the aim of examining the most relevant constraints, challenges, and experiences of RAS fish farmers in the state of Haryana state of India. Over the course of a year, extensive surveys were conducted among 20 RAS farms in various districts of the Haryana Region, i.e., Ambala, Bhiwani, Fatehabad, Gurgaon, Hisar, Jind, Kaithal, Karnal, Rohtak, Rewari, and Sonipat. These farmers were interviewed face to face using a questionnaire that combined closed- and open-ended questions to gather valuable insight. The results revealed several common constraints faced by RAS farmers in Haryana. The most significant challenges that farmers faced included disease outbreaks (50%), seed quality issues (45%), lack of knowledge about RAS (35%), and misguidance (5%). Additionally, farmers reported difficulties in seed transportation (10%), and approximately 70% of the farmers emphasized the critical need for specialized training in RAS operations. Moreover, 50% of the farmers considered the lack of information regarding suitable fish species for RAS to be a major problem. In terms of RAS equipment, drum filters (35%) and MBBR media (30%) were the most common malfunctioning components for fish farmers, while 55% of the farmers experienced no default in their RAS systems. Moreover, this research revealed that Haryana farmers are interested in the adoption of RAS technology and are interested in a prototype farm with professional guidance to promote its adoption.

Background: Artificial intelligence (AI) has grown in popularity over the last few decades, and its application in clinical trials is on the rise around the world. Despite Sophie, the world's first humanoid robot to be awarded personality and citizenship by Saudi Arabia, and AI Arabic bots designed to improve customer service, the Saudi region is yet to completely embrace the AI Revolution. Over the last few years, the clinical usage of AI systems in medicine has grown in popularity. Several surgical AI platforms have been tested and found to improve preoperative diagnostic and decision making, outcome prediction, surgical planning, and intraoperative surgical guidance. This study examines clinical researchers' knowledge and attitudes toward Artificial Intelligence (AI) technology in Saudi Arabia. Objective: To find out knowledge about artificial intelligence among clinical researchers of Saudi Arabia and their attitude towards the same. Materials and methods: This study was carried out utilising an online questionnaire-based survey that was created with Google forms and emailed to clinical researchers in the friend circle. A total of 118 people replied to the survey, and the sample population was chosen using a convenience sampling technique. They were asked about their demographics, knowledge of AI, and attitudes toward it.

In the last five years, the state of Haryana has implemented a few high stocking density holding modern fish farming technologies such as Biofloc and Recirculation Aquaculture System (RAS) to boost farmers’ fish production. Besides this, RAS technology has the potential to filter water while reducing the danger of environmental contamination and disease outbreaks due to its unique characteristic of filtration systems. The primary goal of this face-to-face interview-based study was to determine the state of various variables, characteristics, RAS employees’ skills, farmer engagement, and the role of the Pradhan Mantri Matsya Sampada Yojana (PMMSY) in the overall development of this technology in state of Haryana. The majority of RAS farms in Haryana (55%) employed unskilled employees, 25% employed mixed skilled and unskilled workers, and 20% employed just skilled workers. With the implementation of the Pradhan Mantri Matsya Sampada Yojana (PMMSY), the majority of farmers (90%) received government subsidies for the construction of their high-cost RAS projects, while 5% of farmers built their RAS systems under the Blue Revolution scheme and 5% used their own resources to build the farms without any government assistance. On the other side, majority of RAS farmers (45%) sell their production stock to local district markets, while 30% opted to sell their stock inside and beyond the state, compared to 25% who sold their output within their district and State Haryana. All RAS farmers have single units of RAS for fish farming but only 70% RAS farms have 8-6 production tanks on their RAS farms. Whereas 95% of farmers have a power backup (generator) for the appropriate operation of RAS filtration during emergency hours, 35% of RAS farms have four aerators/units for improved filtration and fish survival under high stocking density technology.