In this paper several probabilistic search techniques are developed for global optimization under... more In this paper several probabilistic search techniques are developed for global optimization under three heuristic classi"cations: simulated annealing, clustering methods and adaptive partitioning algorithms. The algorithms proposed here combine di!erent methods found in the literature and they are compared with well-established approaches in the corresponding areas. Computational results are obtained on 77 small to moderate size (up to 10 variables) nonlinear test functions with simple bounds and 18 large size test functions (up to 400 variables) collected from literature. Scope and purpose Global optimization techniques aim at identifying the global optimum solution of a function which need not be convex or di!erentiable. In this paper, we consider stochastic global optimization search techniques. Among them, one can name probabilistic search methods such as simulated annealing, genetic algorithms, controlled random search and clustering methods. Another class of global optimization methods considered here are adaptive partitioning algorithms which aim at reducing the search space around the global optimum by consecutive partitioning iterations of a promising subregion into smaller and smaller subspaces. Here, we speci"cally investigate simulated annealing, clustering methods and adaptive partitioning algorithms. Besides implementing some well-established techniques in these "elds, we develop new techniques which also lead to hybrid methods combined with existing ones. In an adaptive partitioning algorithm proposed here a new partition evaluation measure of fuzzy nature is developed. Furthermore, both simulated annealing and random search are used for collecting samples in the adaptive partitioning algorithm. We conduct a study on
We propose a new metaheuristic, FRACTOP, for global optimization. FRACTOP is based on the geometr... more We propose a new metaheuristic, FRACTOP, for global optimization. FRACTOP is based on the geometric partitioning of the feasible region so that search metaheuristics such as Simulated Annealing (SA), or Genetic Algorithms (GA) which are activated in smaller subregions, have increased reliability in locating the global optimum. FRACTOP is able to incorporate any search heuristic devised for global optimization. The main contribution of FRACTOP is that it provides an intelligent guidance (through fuzzy measures) in locating the subregion containing the global optimum solution for the search heuristics imbedded in it. By executing the search in nonoverlapping subregions, FRACTOP eliminates the repetitive visits of the search heuristics to the same local area and furthermore, it becomes amenable for parallel processing. As FRACTOP conducts the search deeper into smaller subregions, many unpromising subregions are discarded from the feasible region. Thus, the initial feasible region gains a fractal structure with many space gaps which economizes on computation time. Computational experiments with FRACTOP indicate that the metaheuristic improves significantly the results obtained by random search (RS), SA and GA.
This article describes a new fuzzy areal site assessment approach in the detection of contaminate... more This article describes a new fuzzy areal site assessment approach in the detection of contaminated zones within a site which is under environmental investigation. Conventional techniques utilized in this field are mostly interpolation based. These methods interpolate the contaminant concentration values at unobserved locations using observed values. Unlike these interpolation techniques, the motivation of the approach introduced here consists of
ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrial... more ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrially contaminated sites. In this study, an information retrieval approach involving a fuzzy partitioning scheme is proposed to identify the topology of polluted areas in a given industrial site. While its primary objective is to locate contaminated zones accurately with a minimal number of samples, the second target is to reduce the size of the investigation area subjected to re-sampling in the next phase. The performance of the mentioned approach is demonstrated here, using results from real industrially contaminated sites.
Bulletin (Hospital for Joint Diseases (New York, N.Y.))
Twenty consecutive patients (17 male, 3 female) with a diagnosis of traumatic recurrent anterior ... more Twenty consecutive patients (17 male, 3 female) with a diagnosis of traumatic recurrent anterior instability of the shoulder were treated by a modified Bankart procedure using suture anchors. The technique consists of vertical incision of the capsule, just medial to the lateral insertion on the humerus and anatomic repair of the Bankart lesion. Humeral-based capsular shifting was performed in patients with anterior-inferior instability. The average age was 24 years (range: 14 to 39 years), and average follow-up period 68 months (range: 2 to 8 years). The average Bankart rating score was 92.5 (range: 70 to 100); with 16 (80%) excellent (score 90 to 100), 2 (10%) good (score 75 to 89), and 2 (10%) fair results. Failure in terms of recurrent dislocation was not reported. Eleven patients (55%) had a loss of 5 degrees to 10 degrees of external rotation either with the extremity at the side or at 90 degrees of abduction. Nine (45%) patients had external rotation equal to the contralateral...
The Site Characterization Approach for Recovery of contaminated industrial sites (SCAR) is being ... more The Site Characterization Approach for Recovery of contaminated industrial sites (SCAR) is being developed to enable the results of the Project “Protection of groundwater resources at industrially contaminated sites (PURE project)” to be integrated and efficiently used by site owners to take the relevant decisions for site management. SCAR has been tested and detailed in the last year of the PURE project. The project results show what input, activity and criteria are needed to obtain an output that meets the expectations of both the developers and end-users of the project as much as possible. The approach is divided in three main phases. Phase 1 gives a first fast, relatively cheap, impression of the risks, benefits and cost of the remediation of the contamination involved. Phase 2 gives the risks (technical, economical, HSE, political), benefits and costs more detailed. In phase 3 field test are carried out at the site and the site is actually remediated. It is the goal of the PURE...
PURE is aimed at preventing contamination of groundwater from industrial sites from priority poll... more PURE is aimed at preventing contamination of groundwater from industrial sites from priority pollutants, including recalcitrant chloroorganics, BTEX and PAH compounds and heavy metals. The overall structure of the project is summarised in Figure 1. Sub-project SICHAMORE is designed to generate data and give added value to site owners to allow a decision to be reached regarding the remediation of a contaminated site. The integration of these work packages forms the basis of SCAR: Site Characterisation Approach for Recovery of contaminated industrial sites. SCAR is designed to: • give an overview of the different steps of site characterisation that could be applied on different sites and could be adapted to the needs of the site owner; • contribute to the formulation of a comprehensive and structured overview for the sites in the PURE project; • provide an inventory of existing and historical site development; • indicate possible site remediation scenarios with associated technical an...
Entrapment of the suprascapular nerve by the inferior transverse scapular ligament or spinoglenoi... more Entrapment of the suprascapular nerve by the inferior transverse scapular ligament or spinoglenoid ligament (SGL) has been discussed frequently in the literature, but it has not been well documented anatomically. Therefore the mechanism of entrapment is not well understood. When isolated atrophy and denervation of the infraspinatus muscle have been noted, compression of the muscle's motor branch at the spinoglenoid notch has been implicated. This anatomic and morphologic study investigates the role of the SGL in entrapment neuropathy of the infraspinatus. We used 23 shoulders from 19 cadavers, 5 women (8 shoulders) and 14 men (15 shoulders), with a mean age of 67.9 (54 to 78) years. The presence or absence of the SGL was noted. The length, width, and orientation of the SGL; size and shape of the tunnel to the infraspinatus fossa; and distance of the notch to the posterior glenoid rim were determined. The SGL was present in 14 (60.8%) shoulders, 5 (36%) women and 9 (64%) men. The SGL was wider at the superior entrance of the tunnel and fanned and twisted toward the inferior aspect. In all specimens the SGL fibers inserted into the posterior shoulder capsule. The mean length for the upper part of the SGL was 17.5 +/- 2.6 mm in men and 15.8 +/- 1.8 mm in women, and the lower part was 14.1 +/- 2.4 mm and 12.9 +/- 1.8 mm, respectively. The widths of the SGL at the origin of the scapular spine were 12.2 +/- 3.9 mm for men and 10.4 +/- 2.7 mm for women, whereas the insertion site widths were 15.8 +/- 2.2 mm for men, and 16.1 +/- 3.8 mm for women. The midportion width of the SGL was 6.8 +/- 1.9 mm in men and 5.8 +/- 2.1 mm in women. During cross-body adduction and internal rotation of the glenohumeral joint, the interaction of the SGL and the posterior capsule resulted in a tightening of the SGL. The suprascapular nerve moved laterally and stretched underneath the SGL in this position.
Synovial chondromatosis, is the chondroid metaplasia of the synovial membrane. Large joints such ... more Synovial chondromatosis, is the chondroid metaplasia of the synovial membrane. Large joints such as the knee and hip are most commonly involved. Extraarticular involvement is rarely described. Synovial chondromatosis may be associated with impingement syndrome of the shoulder. We report a case of synovial chondromatosis of the subcoracoid bursa, which resulted in impingement symptoms.
Bilateral posterior fracture-dislocation of the shoulder is a very rare injury. Almost 50% of bil... more Bilateral posterior fracture-dislocation of the shoulder is a very rare injury. Almost 50% of bilateral posterior dislocations are due to a convulsive seizure, rising to 90% if the dislocations are associated with fractures. Electric shock accounts for less than 5% of bilateral posterior dislocations of the shoulder. A systematization of the clinical and radiological approach, followed by an early diagnosis and proper surgical treatment is essential. Authors report 2 cases of bilateral posterior fracture-dislocation of the shoulder, one caused by a convulsive seizure and the other by an electric shock. A review of literature and a treatment protocol are also presented.
Dislocation of the shoulder is a common injury and may be associated with a variety of complicati... more Dislocation of the shoulder is a common injury and may be associated with a variety of complications. We report six cases of primary replacement of the humeral head where closed reduction of a shoulder dislocation associated with an undisplaced fracture of the humeral neck led to displacement of the neck fracture. All dislocations examined were anterior with a displaced greater tubercle fracture. The patients had undergone closed reduction at other medical centres and were referred to us because of iatrogenically displaced fracture-dislocations of the shoulder. Three were women and three were men with a mean age of 52.8 years (range38-72).
IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2001
ABSTRACT The site characterization issue is the most essential task to be undertaken prior to the... more ABSTRACT The site characterization issue is the most essential task to be undertaken prior to the reclamation of a potentially contaminated site and it is composed of sampling, laboratory analysis, and data evaluation phases. We are primarily concerned with the data evaluation phase and we utilize a recently developed adaptive areal partitioning algorithm to characterize the site. Here, we enhance this approach by integrating expert knowledge (expert belief) into the fuzzy areal assessment scheme which derives information from sample data. We propose to allocate an adaptive weight to expert belief during the assessment. We compare the belief-integrated approach with the nonintegrated one on synthetically generated sites where both uniform and biased sampling have been applied independently. In biased sampling, the zones claimed to be highly contaminated (by the expert) are allocated a higher sampling density. We demonstrate that the belief-integrated approach outperforms the nonintegrated one both when the expert is correct or mistaken in his/her judgment irrespective of the sampling methodology
IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2005
ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrial... more ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrially contaminated sites. It is required to take samples and analyze the laboratory reports to find out the distribution of contaminants over the site. In this study, an algorithm based on fuzzy assessment and overlapped partitioning is proposed to identify the topology of polluted areas in a given industrial site. The primary objective is to locate contaminated zones accurately with sparse data in a preliminary investigation and the second is to reduce the size of the area that is resubjected to expensive sampling methods (such as deep drilling) in the detailed phase of the investigation. If these objectives are achieved, a considerable cost reduction occurs in the process of site characterization.
ABSTRACT In global optimization, adaptive partitioning algorithms (APA) operate on the basis of p... more ABSTRACT In global optimization, adaptive partitioning algorithms (APA) operate on the basis of partitioning the feasible region into subregions, sampling and evaluating each subregion, and selecting one or more subregions for repartitioning. The purpose of the repartitioning process is to locate a narrow neighborhood around the global optimum. In this correspondence, we propose to use a fuzzy approach in the assessment of subregions using random samples taken from these subregions. We discuss different types of uncertainties involved in APA and we conclude that the use of a fuzzy approach in the assessment of subregions is in concurrence with APA's convergence property. We provide numerical results for the fuzzy approach on 13 test functions from the literature
ABSTRACT This paper briefly describes a partitioning algorithm (FRACTOP) for global optimization,... more ABSTRACT This paper briefly describes a partitioning algorithm (FRACTOP) for global optimization, which in the search for the global optimum of simple bounded multimodal functions evaluates nonoverlapping partitions of the feasible region by random search. Fuzzy measures are used in the assessment of samples taken from all partitions, and the partition with the highest tendency of containing the global optimum is repartitioned to refine the search in that region. The performance of FRACTOP where fuzzy measures are embedded is compared with a statistical promise measure proposed by Tang (1994). Computational results are reported on an extensive set of 77 test functions collected from the literature
An adaptive partitioning algorithm with random search is proposed to locate the global optimum of... more An adaptive partitioning algorithm with random search is proposed to locate the global optimum of multimodal functions. Partitioning algorithms divide the feasible region into nonoverlapping partitions in order to restrict and direct the search to the most promising region expected to contain the global optimum. In such a scheme a partition evaluation measure is required to assess sub-regions in order to re-partition the most promising sub-region and intensify the search within that area. This study provides computational results on several classes of partition evaluation measures used in the assessment of samples taken from all partitions. Among the partition evaluation classes used in our comparison are fuzzy, statistical, and deterministic interval estimation measures. Performance in terms of solution quality is reported on an extensive set of 77 test functions collected from the literature.
ABSTRACT This study aims to evaluate various well-known spatial interpolation methods used in ide... more ABSTRACT This study aims to evaluate various well-known spatial interpolation methods used in identifying hot-spots during site investigations on brownfields. Before any reclamation is carried out zones within a site with contaminant levels above the threshold limits should be identified correctly with minimum reclamation costs. The latter implies that all contaminated areas are to be determined while minimizing the space claimed for reclamation. In other words, clean areas should not be declared as contaminated. This issue is crucial both with respect to minimizing health hazards in human use after reclamation and also with respect to minimizing reclamation costs. Here, we conduct a numerical survey on the performance of spatial interpolation techniques on 360 hypothetical sites which are generated according to a given experimental design. The effects of the number of non-overlapping hot-spots in a site, the percentage of the area contaminated, and the effects of the sampling pattern are observed during the experimentation. Furthermore, as an alternative site evaluation scheme, we propose a new fuzzy areal site assessment scheme (FASA) which is independent of the assumptions implied by spatial statistics and compare its performance with those of spatial interpolation methods.
In this paper several probabilistic search techniques are developed for global optimization under... more In this paper several probabilistic search techniques are developed for global optimization under three heuristic classifications: simulated annealing, clustering methods and adaptive partitioning algorithms. The algorithms proposed here combine different methods found in the literature and they are compared with well-established approaches in the corresponding areas. Computational results are obtained on 77 small to moderate size (up to 10 variables) nonlinear test functions with simple bounds and 18 large size test functions (up to 400 variables) collected from literature.
In this paper several probabilistic search techniques are developed for global optimization under... more In this paper several probabilistic search techniques are developed for global optimization under three heuristic classi"cations: simulated annealing, clustering methods and adaptive partitioning algorithms. The algorithms proposed here combine di!erent methods found in the literature and they are compared with well-established approaches in the corresponding areas. Computational results are obtained on 77 small to moderate size (up to 10 variables) nonlinear test functions with simple bounds and 18 large size test functions (up to 400 variables) collected from literature. Scope and purpose Global optimization techniques aim at identifying the global optimum solution of a function which need not be convex or di!erentiable. In this paper, we consider stochastic global optimization search techniques. Among them, one can name probabilistic search methods such as simulated annealing, genetic algorithms, controlled random search and clustering methods. Another class of global optimization methods considered here are adaptive partitioning algorithms which aim at reducing the search space around the global optimum by consecutive partitioning iterations of a promising subregion into smaller and smaller subspaces. Here, we speci"cally investigate simulated annealing, clustering methods and adaptive partitioning algorithms. Besides implementing some well-established techniques in these "elds, we develop new techniques which also lead to hybrid methods combined with existing ones. In an adaptive partitioning algorithm proposed here a new partition evaluation measure of fuzzy nature is developed. Furthermore, both simulated annealing and random search are used for collecting samples in the adaptive partitioning algorithm. We conduct a study on
We propose a new metaheuristic, FRACTOP, for global optimization. FRACTOP is based on the geometr... more We propose a new metaheuristic, FRACTOP, for global optimization. FRACTOP is based on the geometric partitioning of the feasible region so that search metaheuristics such as Simulated Annealing (SA), or Genetic Algorithms (GA) which are activated in smaller subregions, have increased reliability in locating the global optimum. FRACTOP is able to incorporate any search heuristic devised for global optimization. The main contribution of FRACTOP is that it provides an intelligent guidance (through fuzzy measures) in locating the subregion containing the global optimum solution for the search heuristics imbedded in it. By executing the search in nonoverlapping subregions, FRACTOP eliminates the repetitive visits of the search heuristics to the same local area and furthermore, it becomes amenable for parallel processing. As FRACTOP conducts the search deeper into smaller subregions, many unpromising subregions are discarded from the feasible region. Thus, the initial feasible region gains a fractal structure with many space gaps which economizes on computation time. Computational experiments with FRACTOP indicate that the metaheuristic improves significantly the results obtained by random search (RS), SA and GA.
This article describes a new fuzzy areal site assessment approach in the detection of contaminate... more This article describes a new fuzzy areal site assessment approach in the detection of contaminated zones within a site which is under environmental investigation. Conventional techniques utilized in this field are mostly interpolation based. These methods interpolate the contaminant concentration values at unobserved locations using observed values. Unlike these interpolation techniques, the motivation of the approach introduced here consists of
ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrial... more ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrially contaminated sites. In this study, an information retrieval approach involving a fuzzy partitioning scheme is proposed to identify the topology of polluted areas in a given industrial site. While its primary objective is to locate contaminated zones accurately with a minimal number of samples, the second target is to reduce the size of the investigation area subjected to re-sampling in the next phase. The performance of the mentioned approach is demonstrated here, using results from real industrially contaminated sites.
Bulletin (Hospital for Joint Diseases (New York, N.Y.))
Twenty consecutive patients (17 male, 3 female) with a diagnosis of traumatic recurrent anterior ... more Twenty consecutive patients (17 male, 3 female) with a diagnosis of traumatic recurrent anterior instability of the shoulder were treated by a modified Bankart procedure using suture anchors. The technique consists of vertical incision of the capsule, just medial to the lateral insertion on the humerus and anatomic repair of the Bankart lesion. Humeral-based capsular shifting was performed in patients with anterior-inferior instability. The average age was 24 years (range: 14 to 39 years), and average follow-up period 68 months (range: 2 to 8 years). The average Bankart rating score was 92.5 (range: 70 to 100); with 16 (80%) excellent (score 90 to 100), 2 (10%) good (score 75 to 89), and 2 (10%) fair results. Failure in terms of recurrent dislocation was not reported. Eleven patients (55%) had a loss of 5 degrees to 10 degrees of external rotation either with the extremity at the side or at 90 degrees of abduction. Nine (45%) patients had external rotation equal to the contralateral...
The Site Characterization Approach for Recovery of contaminated industrial sites (SCAR) is being ... more The Site Characterization Approach for Recovery of contaminated industrial sites (SCAR) is being developed to enable the results of the Project “Protection of groundwater resources at industrially contaminated sites (PURE project)” to be integrated and efficiently used by site owners to take the relevant decisions for site management. SCAR has been tested and detailed in the last year of the PURE project. The project results show what input, activity and criteria are needed to obtain an output that meets the expectations of both the developers and end-users of the project as much as possible. The approach is divided in three main phases. Phase 1 gives a first fast, relatively cheap, impression of the risks, benefits and cost of the remediation of the contamination involved. Phase 2 gives the risks (technical, economical, HSE, political), benefits and costs more detailed. In phase 3 field test are carried out at the site and the site is actually remediated. It is the goal of the PURE...
PURE is aimed at preventing contamination of groundwater from industrial sites from priority poll... more PURE is aimed at preventing contamination of groundwater from industrial sites from priority pollutants, including recalcitrant chloroorganics, BTEX and PAH compounds and heavy metals. The overall structure of the project is summarised in Figure 1. Sub-project SICHAMORE is designed to generate data and give added value to site owners to allow a decision to be reached regarding the remediation of a contaminated site. The integration of these work packages forms the basis of SCAR: Site Characterisation Approach for Recovery of contaminated industrial sites. SCAR is designed to: • give an overview of the different steps of site characterisation that could be applied on different sites and could be adapted to the needs of the site owner; • contribute to the formulation of a comprehensive and structured overview for the sites in the PURE project; • provide an inventory of existing and historical site development; • indicate possible site remediation scenarios with associated technical an...
Entrapment of the suprascapular nerve by the inferior transverse scapular ligament or spinoglenoi... more Entrapment of the suprascapular nerve by the inferior transverse scapular ligament or spinoglenoid ligament (SGL) has been discussed frequently in the literature, but it has not been well documented anatomically. Therefore the mechanism of entrapment is not well understood. When isolated atrophy and denervation of the infraspinatus muscle have been noted, compression of the muscle's motor branch at the spinoglenoid notch has been implicated. This anatomic and morphologic study investigates the role of the SGL in entrapment neuropathy of the infraspinatus. We used 23 shoulders from 19 cadavers, 5 women (8 shoulders) and 14 men (15 shoulders), with a mean age of 67.9 (54 to 78) years. The presence or absence of the SGL was noted. The length, width, and orientation of the SGL; size and shape of the tunnel to the infraspinatus fossa; and distance of the notch to the posterior glenoid rim were determined. The SGL was present in 14 (60.8%) shoulders, 5 (36%) women and 9 (64%) men. The SGL was wider at the superior entrance of the tunnel and fanned and twisted toward the inferior aspect. In all specimens the SGL fibers inserted into the posterior shoulder capsule. The mean length for the upper part of the SGL was 17.5 +/- 2.6 mm in men and 15.8 +/- 1.8 mm in women, and the lower part was 14.1 +/- 2.4 mm and 12.9 +/- 1.8 mm, respectively. The widths of the SGL at the origin of the scapular spine were 12.2 +/- 3.9 mm for men and 10.4 +/- 2.7 mm for women, whereas the insertion site widths were 15.8 +/- 2.2 mm for men, and 16.1 +/- 3.8 mm for women. The midportion width of the SGL was 6.8 +/- 1.9 mm in men and 5.8 +/- 2.1 mm in women. During cross-body adduction and internal rotation of the glenohumeral joint, the interaction of the SGL and the posterior capsule resulted in a tightening of the SGL. The suprascapular nerve moved laterally and stretched underneath the SGL in this position.
Synovial chondromatosis, is the chondroid metaplasia of the synovial membrane. Large joints such ... more Synovial chondromatosis, is the chondroid metaplasia of the synovial membrane. Large joints such as the knee and hip are most commonly involved. Extraarticular involvement is rarely described. Synovial chondromatosis may be associated with impingement syndrome of the shoulder. We report a case of synovial chondromatosis of the subcoracoid bursa, which resulted in impingement symptoms.
Bilateral posterior fracture-dislocation of the shoulder is a very rare injury. Almost 50% of bil... more Bilateral posterior fracture-dislocation of the shoulder is a very rare injury. Almost 50% of bilateral posterior dislocations are due to a convulsive seizure, rising to 90% if the dislocations are associated with fractures. Electric shock accounts for less than 5% of bilateral posterior dislocations of the shoulder. A systematization of the clinical and radiological approach, followed by an early diagnosis and proper surgical treatment is essential. Authors report 2 cases of bilateral posterior fracture-dislocation of the shoulder, one caused by a convulsive seizure and the other by an electric shock. A review of literature and a treatment protocol are also presented.
Dislocation of the shoulder is a common injury and may be associated with a variety of complicati... more Dislocation of the shoulder is a common injury and may be associated with a variety of complications. We report six cases of primary replacement of the humeral head where closed reduction of a shoulder dislocation associated with an undisplaced fracture of the humeral neck led to displacement of the neck fracture. All dislocations examined were anterior with a displaced greater tubercle fracture. The patients had undergone closed reduction at other medical centres and were referred to us because of iatrogenically displaced fracture-dislocations of the shoulder. Three were women and three were men with a mean age of 52.8 years (range38-72).
IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2001
ABSTRACT The site characterization issue is the most essential task to be undertaken prior to the... more ABSTRACT The site characterization issue is the most essential task to be undertaken prior to the reclamation of a potentially contaminated site and it is composed of sampling, laboratory analysis, and data evaluation phases. We are primarily concerned with the data evaluation phase and we utilize a recently developed adaptive areal partitioning algorithm to characterize the site. Here, we enhance this approach by integrating expert knowledge (expert belief) into the fuzzy areal assessment scheme which derives information from sample data. We propose to allocate an adaptive weight to expert belief during the assessment. We compare the belief-integrated approach with the nonintegrated one on synthetically generated sites where both uniform and biased sampling have been applied independently. In biased sampling, the zones claimed to be highly contaminated (by the expert) are allocated a higher sampling density. We demonstrate that the belief-integrated approach outperforms the nonintegrated one both when the expert is correct or mistaken in his/her judgment irrespective of the sampling methodology
IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2005
ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrial... more ABSTRACT Environmental site investigations are carried out prior to the reclamation of industrially contaminated sites. It is required to take samples and analyze the laboratory reports to find out the distribution of contaminants over the site. In this study, an algorithm based on fuzzy assessment and overlapped partitioning is proposed to identify the topology of polluted areas in a given industrial site. The primary objective is to locate contaminated zones accurately with sparse data in a preliminary investigation and the second is to reduce the size of the area that is resubjected to expensive sampling methods (such as deep drilling) in the detailed phase of the investigation. If these objectives are achieved, a considerable cost reduction occurs in the process of site characterization.
ABSTRACT In global optimization, adaptive partitioning algorithms (APA) operate on the basis of p... more ABSTRACT In global optimization, adaptive partitioning algorithms (APA) operate on the basis of partitioning the feasible region into subregions, sampling and evaluating each subregion, and selecting one or more subregions for repartitioning. The purpose of the repartitioning process is to locate a narrow neighborhood around the global optimum. In this correspondence, we propose to use a fuzzy approach in the assessment of subregions using random samples taken from these subregions. We discuss different types of uncertainties involved in APA and we conclude that the use of a fuzzy approach in the assessment of subregions is in concurrence with APA's convergence property. We provide numerical results for the fuzzy approach on 13 test functions from the literature
ABSTRACT This paper briefly describes a partitioning algorithm (FRACTOP) for global optimization,... more ABSTRACT This paper briefly describes a partitioning algorithm (FRACTOP) for global optimization, which in the search for the global optimum of simple bounded multimodal functions evaluates nonoverlapping partitions of the feasible region by random search. Fuzzy measures are used in the assessment of samples taken from all partitions, and the partition with the highest tendency of containing the global optimum is repartitioned to refine the search in that region. The performance of FRACTOP where fuzzy measures are embedded is compared with a statistical promise measure proposed by Tang (1994). Computational results are reported on an extensive set of 77 test functions collected from the literature
An adaptive partitioning algorithm with random search is proposed to locate the global optimum of... more An adaptive partitioning algorithm with random search is proposed to locate the global optimum of multimodal functions. Partitioning algorithms divide the feasible region into nonoverlapping partitions in order to restrict and direct the search to the most promising region expected to contain the global optimum. In such a scheme a partition evaluation measure is required to assess sub-regions in order to re-partition the most promising sub-region and intensify the search within that area. This study provides computational results on several classes of partition evaluation measures used in the assessment of samples taken from all partitions. Among the partition evaluation classes used in our comparison are fuzzy, statistical, and deterministic interval estimation measures. Performance in terms of solution quality is reported on an extensive set of 77 test functions collected from the literature.
ABSTRACT This study aims to evaluate various well-known spatial interpolation methods used in ide... more ABSTRACT This study aims to evaluate various well-known spatial interpolation methods used in identifying hot-spots during site investigations on brownfields. Before any reclamation is carried out zones within a site with contaminant levels above the threshold limits should be identified correctly with minimum reclamation costs. The latter implies that all contaminated areas are to be determined while minimizing the space claimed for reclamation. In other words, clean areas should not be declared as contaminated. This issue is crucial both with respect to minimizing health hazards in human use after reclamation and also with respect to minimizing reclamation costs. Here, we conduct a numerical survey on the performance of spatial interpolation techniques on 360 hypothetical sites which are generated according to a given experimental design. The effects of the number of non-overlapping hot-spots in a site, the percentage of the area contaminated, and the effects of the sampling pattern are observed during the experimentation. Furthermore, as an alternative site evaluation scheme, we propose a new fuzzy areal site assessment scheme (FASA) which is independent of the assumptions implied by spatial statistics and compare its performance with those of spatial interpolation methods.
In this paper several probabilistic search techniques are developed for global optimization under... more In this paper several probabilistic search techniques are developed for global optimization under three heuristic classifications: simulated annealing, clustering methods and adaptive partitioning algorithms. The algorithms proposed here combine different methods found in the literature and they are compared with well-established approaches in the corresponding areas. Computational results are obtained on 77 small to moderate size (up to 10 variables) nonlinear test functions with simple bounds and 18 large size test functions (up to 400 variables) collected from literature.
Uploads
Papers by Melek Demirhan