Multiple Instance Mamdani Fuzzy Inference

Amine B. Khalifa,Hichem Frigui 한국지능시스템학회 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.4

A novel fuzzy learning framework that employs fuzzy inference to solve the problem of Multiple Instance Learning (MIL) is presented. The framework introduces a new class of fuzzy inference systems called Multiple Instance Mamdani Fuzzy Inference Systems (MIMamdani). In multiple instance problems, the training data is ambiguously labeled. Instances are grouped into bags, labels of bags are known but not those of individual instances. MIL deals with learning a classifier at the bag level. Over the years, many solutions to this problem have been proposed. However, no MIL formulation employing fuzzy inference exists in the literature. Fuzzy logic is powerful at modeling knowledge uncertainty and measurements imprecision. It is one of the best frameworks to model vagueness. However, in addition to uncertainty and imprecision, there is a third vagueness concept that fuzzy logic does not address quiet well, yet. This vagueness concept is due to the ambiguity that arises when the data have multiple forms of expression, this is the case for multiple instance problems. In this paper, we introduce multiple instance fuzzy logic that enables fuzzy reasoning with bags of instances. Accordingly, a MI-Mamdani that extends the standard Mamdani inference system to compute with multiple instances is introduced. The proposed framework is tested and validated using a synthetic dataset suitable for MIL problems. Additionally, we apply the proposed multiple instance inference to fuse the output of multiple discrimination algorithms for the purpose of landmine detection using Ground Penetrating Radar.

Multiple Instance Mamdani Fuzzy Inference

Khalifa, Amine B.,Frigui, Hichem Korean Institute of Intelligent Systems 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.4

A novel fuzzy learning framework that employs fuzzy inference to solve the problem of Multiple Instance Learning (MIL) is presented. The framework introduces a new class of fuzzy inference systems called Multiple Instance Mamdani Fuzzy Inference Systems (MI-Mamdani). In multiple instance problems, the training data is ambiguously labeled. Instances are grouped into bags, labels of bags are known but not those of individual instances. MIL deals with learning a classifier at the bag level. Over the years, many solutions to this problem have been proposed. However, no MIL formulation employing fuzzy inference exists in the literature. Fuzzy logic is powerful at modeling knowledge uncertainty and measurements imprecision. It is one of the best frameworks to model vagueness. However, in addition to uncertainty and imprecision, there is a third vagueness concept that fuzzy logic does not address quiet well, yet. This vagueness concept is due to the ambiguity that arises when the data have multiple forms of expression, this is the case for multiple instance problems. In this paper, we introduce multiple instance fuzzy logic that enables fuzzy reasoning with bags of instances. Accordingly, a MI-Mamdani that extends the standard Mamdani inference system to compute with multiple instances is introduced. The proposed framework is tested and validated using a synthetic dataset suitable for MIL problems. Additionally, we apply the proposed multiple instance inference to fuse the output of multiple discrimination algorithms for the purpose of landmine detection using Ground Penetrating Radar.

Microencapsulation using aqueous dispersion of lipid matrix by fluidized bed processing technique for stabilization of choline salt

Avinash B. Gangurde,Ritesh A. Fule,Sharadchandra D. Javeer,Rahul K. Patole,Jaywant N. Pawar,Purnima D. Amin 한국약제학회 2015 Journal of Pharmaceutical Investigation Vol.45 No.2

Choline bitartrate (CBT) is a water solubleessential nutrient belongs to vitamin-B family. It is moisturesensitive in nature and marketed formulation has stabilityrelated problems during storage which curtails itseffectiveness. Waxes such as hydrogenated soya bean oil(HSO) reported to be an excellent coating carrier to reducemoisture sensitivity or hygroscopic nature of drug candidates. However, literature dictates HSO applications hasbeen explored mostly using non-aqueous methods or hotmelt techniques of formulation development. In this work,microparticles of choline bitartrate with aqueous coatingdispersion of HSO as primary carrier was successfullydeveloped using fluidized bed coating technique. Aqueousdispersion of HSO was prepared using selected binder in ahomogenizer and formed aqueous dispersion was thensprayed through 0.8 mm gun in fluidized bed processor. The microparticles were evaluated for parameters like flowproperties, morphological characteristics, drug content,encapsulation efficiency and drug release behaviour. Thesolid state characterization of optimized microparticlebased formulation was done by differential scanning calorimetry,X-ray diffractometry, infrared spectroscopy andscanning electron microscopy. The results showed thatmicroencapsulation of choline bitartrate were successfullydone by aqueous wax coating dispersion without using anyorganic solvent or hot melt techniques. Discolouration,fishy odour and drug content variation was not observedafter 6 months stability studies. Choice of proper carrier todrug ratio and selective formulation technique are criticalparameters for dispensing CBT microparticle based formulationwhich might significantly enhance itseffectiveness.

Direct Selection Response to Growth and Correlated Response to Lactation Traits in Black Bengal Goats

Amin, M.R.,Husain, S.S.,Islam, A.B.M.M.,Saadullah, M. Asian Australasian Association of Animal Productio 2001 Animal Bioscience Vol.14 No.7

A field trial on selection for increased live weight in Black Bengal (BB) goat was conducted over two generations. Parents of both sexes were selected (mass selection) based on mature body weight criteria set against age. A parallel randomly mated line was maintained to compare the response (R) of selection at birth. 3, 6, 9 and 12 months of age in both generations. Lactation yield (LY), average per day yield (APDY) and lactation length (LL) were evaluated in the selected line in comparison to randombreds as a result of correlated response. Live weights were significantly improved at onward bir:th in first generation and only at birth in second generation. Improvements (%) in live weight at 3, 6. 9 and 12 months in first generation were 17.6, 18.4, 16.6, and 12.0 at birth in second generation. Significant correlated R were found in LY and APDY. Results suggest that there may be a positive relationship between live weight and lactational traits in BB goats of Bangladesh. It was also concluded that such a field scheme can be effectively used for genetic improvement of goats in subsistence farming, at least for short term gain.

THERMOLUMINESCENCE DOSIMETRIC PROPERTIES OF Ge- AND Er-DOPED OPTICAL FIBRES AND THEIR APPLICATION IN THE MEASUREMENT OF DEPTH -DOSE IN SOLID WATER PHANTHOM

Amin, Y.M.,Abdulla, Y.A.,Khoo, B.H. The Korean Association for Radiation Protection 2001 방사선방어학회지 Vol.26 No.3

The dosimetric properties of Ge- and Er-doped optical fibres are studied. The Ge-doped fibre is found to be more sensitive to radiation and there is little fading of TL signal compared with Er-doped fibre. The Ge- and Er-doped fibres showed a linear response over a range of ${\sim}1\;Gy$ to about 120 Gy and ${\sim}1Gy$ to about 250Gy respectively. The Ge-doped fibre is found to be dose-rate independent both for photons and electron beams of energy ranging from 6 to 10 MeV and 6 to 12 MeV respectively. The fibre is energy independent for energy greater than ${\sim}0.1\;MeV$ for photon or 0.1 MeV for electron beam. From the depth-dose measurement, it was found that the position of maximum dose, dmax, increased with increasing energy ranging from ${\sim}2\;cm$ and ${\sim}2.5\;cm$ for 6 MeV and 10 MeV photons respectively. The central axis percentage depth dose at 10 cm depth was found to be in good agreement with the value obtained using ionization chamber.

Effect of magnetic field on thermal conductivity and viscosity of a magnetic nanofluid loaded with carbon nanotubes

Amin Shahsavar,Mohammad Reza Salimpour,Mohsen Saghafian,M. B. Shafii 대한기계학회 2016 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.30 No.2

The present work examines experimentally the effect of magnetic field on the viscosity and thermal conductivity of a hybrid nanofluid containing tetramethylammonium hydroxide (TMAH) coated Fe 3 O 4 nanoparticles and Gum arabic (GA) coated carbon nanotubes (CNTs). The hybrid nanofluid was prepared by using ultrasonic dispersion method. Magnetic field was created by a pair of spaced apart magnet plates. The effect of temperature on the time variation of thermal conductivity under applied magnetic field was also investigated. According to the results of this study, viscosity of the hybrid nanofluid increases with the strength of magnetic field, while it decreases with the increase of temperature. Additionally, it is found that the hybrid nanofluid behaves as a shear thinning fluid at low shear rates while it exhibits Newtonian behavior at high shear rates. Furthermore, results show that when an external magnetic field is applied to the studied magnetic nanofluids, the thermal conductivity experiences a peak.

A conjugation of stearic acid to apotransferrin, fattigation-platform, as a core to form self-assembled nanoparticles: Encapsulation of a hydrophobic paclitaxel and receptor-driven cancer targeting

Amin, H.H.,Meghani, N.M.,Oh, K.T.,Choi, H.,Lee, B.J. Association de pharmacie galénique industri 2017 Journal of drug delivery science and technology Vol.41 No.-

In this study, apotransferrin (Tf)-stearic acid conjugate was newly synthesized via ''fattigation method'' to form self-assembled nanoparticles (NPs) containing a hydrophobic model drug, paclitaxel (PAC). Then, physicochemical properties and cellular behaviors such as transferrin receptor-driven targeting and cytotoxic efficiencies were evaluated. Scanning electron microscopy (SEM) and transmission electron microscopy (TEM) studies showed that the NPs had spherical shape and smooth surface. The particle size of PAC-loaded NPs was 326.97 +/- 2.03 nm with a loading and encapsulation efficiency of 7.94 +/- 1.60% (w/w) and 71.10 +/- 4.12% (w/w), respectively. In comparison to free PAC, PAC-loaded NPs showed a 7-fold reduction in the LC50 value in breast carcinoma cells (MCF-7), which indicated an increase in cytotoxicity owing to the effective targeting of cells. This observation was confirmed via confocal microscopy images that showed that transferrin receptor blocking inhibited NP uptake. This was further confirmed via flow cytometry data which showed the time-dependent uptake of NPs and their inhibition by transferrin receptor blockage. The results of this study reveal the advantages of NP-based drug delivery systems consisting of Tf as a core of NP for the receptor-driven targeting and subsequent killing of cancer cells.

Effect of Cacao Liquor Extract on Tumor Marker Enzymes During Chemical Hepatocarcinogenesis in Rats

I. Amin,B.K. Koh,R. Asmah 한국식품영양과학회 2004 Journal of medicinal food Vol.7 No.1

This study investigated the effect of cacao liquor extract (CLE) on tumor marker enzymes alkaline phos-phatase (ALP), g-glutamyl transpeptidase (GGT), glutathione-S-transferase (GST), and glutathione reductase (GR) activitiesin plasma and/or liver of hepatocarcinogenic rats, which were induced with diethylnitrosamine and 2-acetylaminofluorene.Twenty-nine male Sprague Dawley rats (weighing 150 330 g) were divided into four groups (n 5 6 8): normal control group(N), normal group 1 CLE (NE), cancer group (C), and cancer group 1 CLE (CE). Analysis of variance showed significantdifferences (P, .05) in the specific activities of ALP, GGT, and GST between the C and N groups. However, GR activityfor the C group was not significantly different compared with the N group. In the CE group, the specific activities of ALP,GGT, GST, and GR were significantly lower (P, .05) compared with the C group. The findings showed that CLE couldlower the activity of tumor marker enzymes of rats during hepatocarcinogenesis. Based on the results obtained, polyphenolcompounds present in the cacao liquor, extracted by using ethanol, have the potential in decreasing the severity of hepato-carcinogenesis.

High-Voltage Performance of Li[Ni[sub 0.55]Co[sub 0.15]Mn[sub 0.30]]O[sub 2] Positive Electrode Material for Rechargeable Li-Ion Batteries

Lee, B.-R.,Noh, H.-J.,Myung, S.-T.,Amine, K.,Sun, Y.-K. The Electrochemical Society 2011 Journal of the Electrochemical Society Vol.158 No.2

Health Fog: a novel framework for health and wellness applications

Ahmad, M.,Amin, M. B.,Hussain, S.,Kang, B. H.,Cheong, T.,Lee, S. Springer Science + Business Media 2016 The Journal of supercomputing Vol.72 No.10

<P>In the past few years the role of e-health applications has taken a remarkable lead in terms of services and features inviting millions of people with higher motivation and confidence to achieve a healthier lifestyle. Induction of smart gadgetries, people lifestyle equipped with wearables, and development of IoT has revitalized the feature scale of these applications. The landscape of health applications encountering big data need to be replotted on cloud instead of solely relying on limited storage and computational resources of handheld devices. With this transformation, the outcome from certain health applications is significant where precise, user-centric, and personalized recommendations mimic like a personal care-giver round the clock. To maximize the services spectrum from these applications over cloud, certain challenges like data privacy and communication cost need serious attention. Following the existing trend together with an ambition to promote and assist users with healthy lifestyle we propose a framework of Health Fog where Fog computing is used as an intermediary layer between the cloud and end users. The design feature of Health Fog successfully reduces the extra communication cost that is usually found high in similar systems. For enhanced and flexible control of data privacy and security, we also introduce the cloud access security broker (CASB) as an integral component of Health Fog where certain polices can be implemented accordingly. The modular framework design of Health Fog is capable of engaging data from multiple resources together with adequate level of security and privacy using existing cryptographic primitives.</P>