The Upper Guinea Forest is subject to heavy deforestation. In this context, many endemic and/or rare plant species are threatened with extinction. This is the case of Aubregrinia taïensis (Aubrév. & Pell...The Upper Guinea Forest is subject to heavy deforestation. In this context, many endemic and/or rare plant species are threatened with extinction. This is the case of Aubregrinia taïensis (Aubrév. & Pellegr.) Heine, a critically endangered Sapotaceae species, endemic to Côte d’Ivoire and Ghana. After 3 years of investigation in and around the Tai National Park (TNP) in the West of Côte d’Ivoire, only one individual of this species was located and no sexual reproductive organs (fruits, seeds) were observed. Woody plant species around this individual were inventoried in order to know the species that can co-occur with Aubregrinia taïensis. For that a plot of 30 m of diameter was established around the individual and all of the woody species of this circle were inventoried. Then, the taxonomic diversity, the chorology of the species, the conservation status and their life-form were recorded. A total of 130 woody plant species belonging to 51 families were collected in the site. The most represented families are Euphorbiaceae (12 spp.), Rubiaceae (10 spp.), Annonaceae (7 spp.), Fabaceae, Moraceae, Malvaceae (6 spp. each) while the most represented genera are Diospyros L. (4 spp.), Cola Schott & Endl. and Vitex L. (3 spp.). Species from the Guineo-Congolese Region (GC) are the most abundant (72%). They are followed by West African endemic species (GCW, 19%). Microphanerophytes (mp) are the most abundant and represent more than 40% of the species. Three vulnerable species were found in this plot: Campylospermum amplectens, Placodiscus boya and Trichoscypha cavalliensis. Thus, the preservation of this forest is more than necessary.展开更多
Background: Participating in working life is important for most peoples’ economy, self-confidence, independence, social life, and feeling of belonging. Persons with co-occurring severe mental health difficulties and ...Background: Participating in working life is important for most peoples’ economy, self-confidence, independence, social life, and feeling of belonging. Persons with co-occurring severe mental health difficulties and substance use problems have challenges in entering working life. Objective: The aim of the study was to explore the importance of work and activity for the recovery of persons with co-occurring severe mental health difficulties and substance use problems and to determine the significant elements that aid them in getting into work and/or meaningful activities. Methods: A professional development program was conducted to explore how following-up on these persons could lead to participation in working life. The data were collected through qualitative interviews with 24 participants, and with 25 of those carrying out the follow-up. Results: The participants described the benefit from the follow-up as well. They expressed enthusiasm for work and vocational training, although they all did not obtain work. Many had a better life, with more daily structure and less substance abuse. The personal encounter between the helper and the participant was ascribed crucial importance— being respected and valued, being relied on, and being able to be honest were considered significant. Conclusions: The participants valued work and regular activities, a more structured life, decreased drug abuse, and altogether a better life. The helpers’ respect, recognition and their ability to see dignity through wretchedness?and broken agreements were important. The participants emphasized the importance of getting help for different problems from different helpers at the same time, and the providers’ interdisciplinary collaboration in teams was essential. It seems that the supported employment philosophy on speedy job seeking ought to be adapted to this target group and that prior social training may be necessary.展开更多
Feature selection（FS） refers to the process of selecting those input attributes that are most predictive of a given outcome. Unlike other dimensionality reduction methods,feature selectors preserve the original mean...Feature selection（FS） refers to the process of selecting those input attributes that are most predictive of a given outcome. Unlike other dimensionality reduction methods,feature selectors preserve the original meaning of the features after reduction. The benefits of FS are twofold：it considerably decreases the running time of the induction algorithm,and increases the accuracy of the resulting model. This paper analyses the FS process in mammogram classification using fuzzy logic and rough set theory. Rough set and fuzzy logic based Quickreduct algorithms are applied for the FS from the features extracted using gray level co-occurence matrix（GLCM） constructed over the mammogram region. The predictive accuracy of the features is tested using NaiveBayes,Ripper,C4.5,and ant-miner algorithms. The results show that the ant-miner produces significant result comparing with others and the number of features selected using fuzzy-rough quick reduct algorithm is minimum,too.展开更多
Automatic segmentation of the vasculature in retinal images is important in the detection of diabetic retinopathy that affects the morphology of the blood vessel tree. In this paper, a hybrid method for efficient segm...Automatic segmentation of the vasculature in retinal images is important in the detection of diabetic retinopathy that affects the morphology of the blood vessel tree. In this paper, a hybrid method for efficient segmentation of multiple oriented blood vessels in colour retinal images is proposed. Initially, the appearance of the blood vessels are enhanced and background noise is suppressed with the set of real component of a complex Gabor filters. Then the vessel pixels are detected in the vessel enhanced image using entropic thresholding based on gray level co-occurrence matrix as it takes into account the spatial distribution of gray levels and preserving the spatial structures. The performance of the method is illustrated on two sets of retinal images from publicly available DRIVE (Digital Retinal Images for Vessel Extraction) and Hoover’s databases. For DRIVE database, the blood vessels are detected with sensitivity of 86.47±3.6 (Mean±SD) and specificity of 96±1.01.展开更多
文摘The Upper Guinea Forest is subject to heavy deforestation. In this context, many endemic and/or rare plant species are threatened with extinction. This is the case of Aubregrinia taïensis (Aubrév. & Pellegr.) Heine, a critically endangered Sapotaceae species, endemic to Côte d’Ivoire and Ghana. After 3 years of investigation in and around the Tai National Park (TNP) in the West of Côte d’Ivoire, only one individual of this species was located and no sexual reproductive organs (fruits, seeds) were observed. Woody plant species around this individual were inventoried in order to know the species that can co-occur with Aubregrinia taïensis. For that a plot of 30 m of diameter was established around the individual and all of the woody species of this circle were inventoried. Then, the taxonomic diversity, the chorology of the species, the conservation status and their life-form were recorded. A total of 130 woody plant species belonging to 51 families were collected in the site. The most represented families are Euphorbiaceae (12 spp.), Rubiaceae (10 spp.), Annonaceae (7 spp.), Fabaceae, Moraceae, Malvaceae (6 spp. each) while the most represented genera are Diospyros L. (4 spp.), Cola Schott & Endl. and Vitex L. (3 spp.). Species from the Guineo-Congolese Region (GC) are the most abundant (72%). They are followed by West African endemic species (GCW, 19%). Microphanerophytes (mp) are the most abundant and represent more than 40% of the species. Three vulnerable species were found in this plot: Campylospermum amplectens, Placodiscus boya and Trichoscypha cavalliensis. Thus, the preservation of this forest is more than necessary.
文摘Background: Participating in working life is important for most peoples’ economy, self-confidence, independence, social life, and feeling of belonging. Persons with co-occurring severe mental health difficulties and substance use problems have challenges in entering working life. Objective: The aim of the study was to explore the importance of work and activity for the recovery of persons with co-occurring severe mental health difficulties and substance use problems and to determine the significant elements that aid them in getting into work and/or meaningful activities. Methods: A professional development program was conducted to explore how following-up on these persons could lead to participation in working life. The data were collected through qualitative interviews with 24 participants, and with 25 of those carrying out the follow-up. Results: The participants described the benefit from the follow-up as well. They expressed enthusiasm for work and vocational training, although they all did not obtain work. Many had a better life, with more daily structure and less substance abuse. The personal encounter between the helper and the participant was ascribed crucial importance— being respected and valued, being relied on, and being able to be honest were considered significant. Conclusions: The participants valued work and regular activities, a more structured life, decreased drug abuse, and altogether a better life. The helpers’ respect, recognition and their ability to see dignity through wretchedness?and broken agreements were important. The participants emphasized the importance of getting help for different problems from different helpers at the same time, and the providers’ interdisciplinary collaboration in teams was essential. It seems that the supported employment philosophy on speedy job seeking ought to be adapted to this target group and that prior social training may be necessary.
文摘Feature selection（FS） refers to the process of selecting those input attributes that are most predictive of a given outcome. Unlike other dimensionality reduction methods,feature selectors preserve the original meaning of the features after reduction. The benefits of FS are twofold：it considerably decreases the running time of the induction algorithm,and increases the accuracy of the resulting model. This paper analyses the FS process in mammogram classification using fuzzy logic and rough set theory. Rough set and fuzzy logic based Quickreduct algorithms are applied for the FS from the features extracted using gray level co-occurence matrix（GLCM） constructed over the mammogram region. The predictive accuracy of the features is tested using NaiveBayes,Ripper,C4.5,and ant-miner algorithms. The results show that the ant-miner produces significant result comparing with others and the number of features selected using fuzzy-rough quick reduct algorithm is minimum,too.
文摘Automatic segmentation of the vasculature in retinal images is important in the detection of diabetic retinopathy that affects the morphology of the blood vessel tree. In this paper, a hybrid method for efficient segmentation of multiple oriented blood vessels in colour retinal images is proposed. Initially, the appearance of the blood vessels are enhanced and background noise is suppressed with the set of real component of a complex Gabor filters. Then the vessel pixels are detected in the vessel enhanced image using entropic thresholding based on gray level co-occurrence matrix as it takes into account the spatial distribution of gray levels and preserving the spatial structures. The performance of the method is illustrated on two sets of retinal images from publicly available DRIVE (Digital Retinal Images for Vessel Extraction) and Hoover’s databases. For DRIVE database, the blood vessels are detected with sensitivity of 86.47±3.6 (Mean±SD) and specificity of 96±1.01.
