Neuro-Fuzzy Networks and Their Applications in Medical Fields.

The fusion of artificial neural networks and fuzzy logic systems allows researchers to model real-world problems through the development of intelligent and adaptive systems. Artificial neural networks are able to adapt and learn by adjusting the interconnections between layers, while fuzzy logic inference systems provide a computing framework based on the concept of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. The combined use of those adaptive structures is known as "neuro-fuzzy" systems. In this paper, the basic elements of both approaches are analyzed, noticing that this blending could be applied for pattern recognition in medical applications.

Epidemics Fuzzy Decision-Making Applications and Fuzzy Genetic Algorithms Efficiency Enhancement.

Fuzzy logic is an innovative scientific field with several successful applications. Genetic algorithms and fuzzy logic systems fusion provide real-world problems modeling through the development of intelligent and adaptive systems. Moreover, the statistical analysis of the epidemiology of infectious diseases, which combines fuzzy logic aspects, is vital for perceiving their evolution and control potential. Author's objective is initially to provide a review of the efficiency of fuzzy logic applications. The advanced implementation of fuzzy logic theory in epidemiology and the application of fuzzy logic for controlling genetic algorithms within strategies based on the human experience and knowledge known as fuzzy logic controllers (FLCs) are analyzed. Outcomes of this review study show that not only can fuzzy sets be efficiently implemented in epidemiology but also prove the effectiveness of fuzzy genetic algorithms applications, thus suggesting that fuzzy logic applications are a really promising field of research.

Variables' classification via equivalence relations for the trophic state of a Mediterranean ecosystem.

The trophic state of an aquatic body is influenced by many biotic and abiotic factors. When lots of parameters affect a phenomenon, such as eutrophication, it is difficult to distinguish which are the ones that affect the ecosystem the most. In this paper, we propose an alternative way for data analysis, in order to avoid complex systems with many variables. For the examined Mediterranean shallow lake, the studied parameters are water temperature (°C), ammonia (NH4 -N) (mg/L), dissolved oxygen (mg/L), turbidity (NTU), pH, conductivity (mS/cm), and chlorophyll-a (µg/L). We formed groups with the variables above based on fuzzy equivalence relations and from each group we chose the parameter influence the studied phenomenon the most. Numerical results of fuzzy linear regression showed strong agreement with the proposed method above and pH, NH4 -N, and dissolved oxygen are the variables influence this ecosystem more than the others. PRACTITIONER POINTS: When having many parameters in a studied ecosystem, we propose a way we can distinguish the most representative ones, the parameters that influence more the phenomenon we study each time. Formation of groups in variables can be applied to many case studies in order to have a clear idea of our data and the relevance of each of them in our dependent one. Fuzzy linear regression can be used in order to check the final results and ensure that the equivalence relations are a such a good method used in the data analysis while the researchers save time in long procedures of analyzing parameters not very close involved to the phenomenon investigated every time.

Fuzzy Surrogate Safety Metrics for real-time assessment of rear-end collision risk. A study based on empirical observations.

The present paper discusses two fuzzy Surrogate Safety Metrics (SSMs) for rear-end collision, the Proactive Fuzzy SSM (PFS) and Critical Fuzzy SSM (CFS). The objective is to investigate their applicability for evaluating the real-time rear-end risk of collision of vehicles to support the operations of advanced driver assistance and automated vehicle functionalities (from driving assistance systems to fully automated vehicles). The proposed Fuzzy SSMs are evaluated and compared to other traditional metrics on the basis of empirical observations. To achieve this goal, an experimental campaign was organized in the AstaZero proving ground in Sweden. The campaign consisted of two main parts: a car-following experiment with five vehicles solely driven by Adaptive Cruise Control (ACC) systems and a safety critical experiment, testing the response of the Autonomous Emergency Braking (AEB) system to avoid collisions on a static target. The proposed PFS is compared with the safe distance defined by the well-known Responsibility Sensitive Safety (RSS) model, showing that it can produce meaningful results in assessing safety conditions also without the use of crisp safety thresholds (like in the case of RSS). The CFS outperformed the well-known Time-To-Collision (TTC) SSM in the a-priori identification of the cases, where the tested vehicles were not able to avoid the collision with the static target. Moreover, results show that CFS at the time of the first deceleration is correlated with the velocity of the vehicle at the time of collisions with the target.

Change in preoperative strategy based on intraoperative ultrasound findings.

Forty patients with primary liver carcinoma and 52 with liver secondaries underwent careful preoperative evaluation using computed tomography and magnetic resonance imaging, as well as intraoperative studies using intraoperative ultrasound (IOUS). The results were compared to histological findings. In the 40 patients with primary tumors who underwent hepatic resection, 4 (9.1%) additional lesions were found using IOUS, and in 10 (25%) instances, our preoperative strategy was changed (either a more extensive or more conservative excision was performed). In the 52 cases with metastatic disease who underwent hepatic resection, 14 (21.2%) more lesions were detected, and in 15 (29%) patients, the preoperative strategy was changed. Based on IOUS findings, of 92 patients, a total of 18 (16.4%) additional lesions were detected; in addition, our preoperative strategy changed in 25 (27.2%) of the cases with primary and secondary liver tumors.

Fuzzy logic systems and medical applications.

The combination of Artificial Neural Networks and Fuzzy Logic Systems enables the representation of real-world problems via the creation of intelligent and adaptive systems. By adapting the interconnections between layers, Artificial Neural networks are able to learn. A computing framework based on the concept of fuzzy set and rules as well as fuzzy reasoning is offered by fuzzy logic inference systems. The fusion of the aforementioned adaptive structures is called a "Neuro-Fuzzy" system. In this paper, the main elements of said structures are examined. Researchers have noticed that this fusion could be applied for pattern recognition in medical applications.

A fuzzy multicriteria categorization of the GALDIT method to assess seawater intrusion vulnerability of coastal aquifers.

Groundwater constitutes the primary source of fresh water for >1.2 billion people living in coastal zones. However, the threat of seawater intrusion is widespread in coastal aquifers mainly due to overexploitation of groundwater. In the present study, a modified fuzzy multicriteria categorization into non-ordered categories method was developed in order to modify the standard GALDIT method and assess seawater intrusion vulnerability in a coastal aquifer of northern Greece. The method is based on six parameters: groundwater occurrence, aquifer hydraulic conductivity, groundwater level, distance from the shore, impact of the existing status of seawater intrusion, and aquifer thickness. Initially, the original method was applied and revealed a zone of high vulnerability running parallel to the coastline and covering an area of 8.6km2. The modified GALDIT-F method achieved higher discretization of vulnerability zones which is essential to build a rational management plan to prevent seawater intrusion. The GALDIT-F approach also distinguished an area of the aquifer that is influenced by geothermal fluids. In total, twenty-five categories were produced corresponding to different vulnerability degrees according to the initial method (High, Moderate, Low) as well as the area influenced by geothermal fluids. Finally, a road map was developed in order to adapt management strategies to GALDIT-F categories and prevent and mitigate seawater intrusion. The proposed management strategies of the coastal aquifer include managed aquifer recharge (MAR) implementation, reallocation of existing wells, optimization of pumping rates during the hydrological year, and a detailed monitoring plan.