Lecture notes in electrical engineering, Aug 28, 2018
This paper focuses on the design of a WiFi-based tracking and monitoring system that can detect p... more This paper focuses on the design of a WiFi-based tracking and monitoring system that can detect people’s movements in a residential neighbourhood. The proposed system uses WiFi access points as scanners that detect signals transmitted by the WiFi-enabled smartphones that are carried by most people. Our proposed system is able to track these people as they move through the neighbourhood. We implement our WiFi-based tracking system in a prototype and demonstrate that it is able to detect all WiFi devices in the vicinity of the scanners. We describe the implementation details of our system as well as discuss some of the results that we obtained.
Lecture notes in electrical engineering, Aug 28, 2018
In this work, Computed Tomography (CT) brain images are adopted for the annotation of different t... more In this work, Computed Tomography (CT) brain images are adopted for the annotation of different types of hemorrhages. The ultimate objective is to devise the semantics-based retrieval system for retrieving the images based on the different keywords. The adopted keywords are hemorrhagic slices, intraaxial, subdural and extradural slices. The proposed approach is consisted of three separated annotation processes are proposed which are annotation of hemorrhagic slices, annotation of intra-axial and annotation of subdural and extradural. The dataset with 519 CT images is obtained from two collaborating hospitals. For the classification, support vector machine (SVM) with radial basis function (RBF) kernel is considered. On overall, the classification results from each experiment achieved precision and recall of more than 79%. After the classification, the images will be annotated with the classified keywords together with the obtained decision values. During the retrieval, the relevant images will be retrieved and ranked correspondingly according to the decision values.
This paper describes new features for the classification of different types of extra-axial intrac... more This paper describes new features for the classification of different types of extra-axial intracranial hemorrhages namely subdural hemorrhage(SDH) and extradural hemorrhage(EDH) on brain computed tomography(CT) scans. The main objective is to create an automatic retrieval system to reduce the time spent searching manually for the hemorrhagic images. Besides, the challenge is to locate suitable features to differentiate the SDH and EDH. One of the methods to distinguish EDH and SDH is through their shapes. Thus, a shape-based feature extraction is proposed in order to differentiate the SDH and EDH. For the classification part, we present a comparative study of linear discriminant analysis(LDA) and support vector machine(SVM) with linear kernal for the classification of SDH, EDH and normal regions. Both pattern classification techniques map pattern vectors to a high dimensional feature space to construct the optimal margin separating hyperplane. To conclude, SVM outperforms LDA from the obtained classification results.
In this paper, we proposed a new approach for the classification of human gait features with diff... more In this paper, we proposed a new approach for the classification of human gait features with different apparel and various walking speed. The approach consists of two parts: extraction of human gait features from enhanced human silhouette and classification of the extracted human gait features using fuzzy k-nearest neighbours (KNN). The joint angles together with the height, width and crotch
This research work proposes a joint detection approach to detect locations of body joint automati... more This research work proposes a joint detection approach to detect locations of body joint automatically by applying a priori knowledge of body proportion. The joint detection approach does not attempt to detect each lower limb of a human, so it can detect the body joints even from self-occluded silhouettes or those occluded by apparel (long blouses or baggy trousers) or bags (handbag or rucksack). In this research work, an improved perspective correction technique to normalize oblique-view walking sequences to side-view plane has been developed. The silhouettes from oblique-view walking sequences are vertical and horizontal adjusted to fit the sideview.
The primary objective of this research is to develop hybrid decision tree induction methods based... more The primary objective of this research is to develop hybrid decision tree induction methods based on the decision tree C4.5 algorithm and ensemble methods, taking into account cost-sensitivity for the purpose of minimizing either misclassification cost, false negative cost or false positive cost. This paper proposed two cost-sensitive learning methods by modifying the model weight of AdaBoost.M1 for churn analysis in the telecommunication industry. Method 1 applies the ratio of false negative cost over true negative cost to make the weight of false negative heavier than the weight of false positive. While Method 2 combines error rate weighting with false negative cost weighting in order to let examples have heavier weight values for future training in the next learning cycle. The proposed methods have been evaluated with a series of experiments to prove its ability to reduce either false negative cost or misclassification costs. Microsoft Azure Machine Learning Telco Customer Churn and IBM Watson Studio Telecommunication Customer Churn datasets, which include the cost value for each instance, are used for the experiments. The proposed Method 1 able to obtain the lowest false negative cost comparing with the original AdaBoost.M1.
Biometric user authentication is seeing increasing use in access control systems, ranging from a ... more Biometric user authentication is seeing increasing use in access control systems, ranging from a simple employee attendance system to complex application such as an E-passport which utilizes fingerprints as an authenticator. There has been numerous attempts to make use of multiple biometric modality to be fused together in order to enhance the robustness and effectiveness already present in single biometric modality system. These authentication systems are known as multimodal biometric authentication systems (MMBAS). Current multimodal biometric research uses combination of modalities such as facial features, speech, retina patterns, thumb print, palm print, gait , handwriting etc. and so forth to improve on accuracy. This paper presents a research framework for a MMBAS which uses facial features, speech as well as gait. The research framework is intended to analyze how facial features, speech and gait features can be used together for an unobtrusive yet robust authentication system.
Gait as a biometric has received great attention nowadays as it can offer human identification at... more Gait as a biometric has received great attention nowadays as it can offer human identification at a distance without any contact with the feature capturing device. This is motivated by the increasing number of synchronised closed-circuit television (CCTV) cameras which have been installed in many major towns, in order to monitor and prevent crime. This paper proposes a new approach
Lecture notes in electrical engineering, Aug 28, 2018
This paper focuses on the design of a WiFi-based tracking and monitoring system that can detect p... more This paper focuses on the design of a WiFi-based tracking and monitoring system that can detect people’s movements in a residential neighbourhood. The proposed system uses WiFi access points as scanners that detect signals transmitted by the WiFi-enabled smartphones that are carried by most people. Our proposed system is able to track these people as they move through the neighbourhood. We implement our WiFi-based tracking system in a prototype and demonstrate that it is able to detect all WiFi devices in the vicinity of the scanners. We describe the implementation details of our system as well as discuss some of the results that we obtained.
Lecture notes in electrical engineering, Aug 28, 2018
In this work, Computed Tomography (CT) brain images are adopted for the annotation of different t... more In this work, Computed Tomography (CT) brain images are adopted for the annotation of different types of hemorrhages. The ultimate objective is to devise the semantics-based retrieval system for retrieving the images based on the different keywords. The adopted keywords are hemorrhagic slices, intraaxial, subdural and extradural slices. The proposed approach is consisted of three separated annotation processes are proposed which are annotation of hemorrhagic slices, annotation of intra-axial and annotation of subdural and extradural. The dataset with 519 CT images is obtained from two collaborating hospitals. For the classification, support vector machine (SVM) with radial basis function (RBF) kernel is considered. On overall, the classification results from each experiment achieved precision and recall of more than 79%. After the classification, the images will be annotated with the classified keywords together with the obtained decision values. During the retrieval, the relevant images will be retrieved and ranked correspondingly according to the decision values.
This paper describes new features for the classification of different types of extra-axial intrac... more This paper describes new features for the classification of different types of extra-axial intracranial hemorrhages namely subdural hemorrhage(SDH) and extradural hemorrhage(EDH) on brain computed tomography(CT) scans. The main objective is to create an automatic retrieval system to reduce the time spent searching manually for the hemorrhagic images. Besides, the challenge is to locate suitable features to differentiate the SDH and EDH. One of the methods to distinguish EDH and SDH is through their shapes. Thus, a shape-based feature extraction is proposed in order to differentiate the SDH and EDH. For the classification part, we present a comparative study of linear discriminant analysis(LDA) and support vector machine(SVM) with linear kernal for the classification of SDH, EDH and normal regions. Both pattern classification techniques map pattern vectors to a high dimensional feature space to construct the optimal margin separating hyperplane. To conclude, SVM outperforms LDA from the obtained classification results.
In this paper, we proposed a new approach for the classification of human gait features with diff... more In this paper, we proposed a new approach for the classification of human gait features with different apparel and various walking speed. The approach consists of two parts: extraction of human gait features from enhanced human silhouette and classification of the extracted human gait features using fuzzy k-nearest neighbours (KNN). The joint angles together with the height, width and crotch
This research work proposes a joint detection approach to detect locations of body joint automati... more This research work proposes a joint detection approach to detect locations of body joint automatically by applying a priori knowledge of body proportion. The joint detection approach does not attempt to detect each lower limb of a human, so it can detect the body joints even from self-occluded silhouettes or those occluded by apparel (long blouses or baggy trousers) or bags (handbag or rucksack). In this research work, an improved perspective correction technique to normalize oblique-view walking sequences to side-view plane has been developed. The silhouettes from oblique-view walking sequences are vertical and horizontal adjusted to fit the sideview.
The primary objective of this research is to develop hybrid decision tree induction methods based... more The primary objective of this research is to develop hybrid decision tree induction methods based on the decision tree C4.5 algorithm and ensemble methods, taking into account cost-sensitivity for the purpose of minimizing either misclassification cost, false negative cost or false positive cost. This paper proposed two cost-sensitive learning methods by modifying the model weight of AdaBoost.M1 for churn analysis in the telecommunication industry. Method 1 applies the ratio of false negative cost over true negative cost to make the weight of false negative heavier than the weight of false positive. While Method 2 combines error rate weighting with false negative cost weighting in order to let examples have heavier weight values for future training in the next learning cycle. The proposed methods have been evaluated with a series of experiments to prove its ability to reduce either false negative cost or misclassification costs. Microsoft Azure Machine Learning Telco Customer Churn and IBM Watson Studio Telecommunication Customer Churn datasets, which include the cost value for each instance, are used for the experiments. The proposed Method 1 able to obtain the lowest false negative cost comparing with the original AdaBoost.M1.
Biometric user authentication is seeing increasing use in access control systems, ranging from a ... more Biometric user authentication is seeing increasing use in access control systems, ranging from a simple employee attendance system to complex application such as an E-passport which utilizes fingerprints as an authenticator. There has been numerous attempts to make use of multiple biometric modality to be fused together in order to enhance the robustness and effectiveness already present in single biometric modality system. These authentication systems are known as multimodal biometric authentication systems (MMBAS). Current multimodal biometric research uses combination of modalities such as facial features, speech, retina patterns, thumb print, palm print, gait , handwriting etc. and so forth to improve on accuracy. This paper presents a research framework for a MMBAS which uses facial features, speech as well as gait. The research framework is intended to analyze how facial features, speech and gait features can be used together for an unobtrusive yet robust authentication system.
Gait as a biometric has received great attention nowadays as it can offer human identification at... more Gait as a biometric has received great attention nowadays as it can offer human identification at a distance without any contact with the feature capturing device. This is motivated by the increasing number of synchronised closed-circuit television (CCTV) cameras which have been installed in many major towns, in order to monitor and prevent crime. This paper proposes a new approach
Uploads
Papers by Hu Ng