Saadi Bin Ahmad Kamaruddin

Firearm identification using numerical features of centre firing pin impression image

There are many crime cases such as murders or robberies which frequently involve firearms, especially pistols. The centre firing pin impression image on a cartridge case is one of the important clues for firearms identification. In this study, a total of 16 features of geometric moments up to the sixth order were extracted from centre of firing pin impression images. A total of five pistols of the Parabellum Vector SPI 9mm model, made in South Africa were used. The pistols were labelled as Pistol A, Pistol B, Pistol C, Pistol D, and Pistol E. A total of 747 bullets have been fired from the five pistols. Under preliminary analysis, Pearson correlation coefficients between all pairs of features showed the features were significant and highly correlated among the features. This problematic features were solved by dividing the features into subgroups of variables based on similar characteristics under principle component analysis. The features that highly correlated were combined into meaningful components or factors. Discriminant analysis was applied to identify the types of pistols used based on the factors obtained. Classification results using cross-validation under discriminant analysis showed that 75.4% of the images were correctly classified according to the pistols used. The results of the study had shown a significant contribution towards Royal Malaysian Police Force in handling crime cases which involve firearms in more systematic manner.

Firearm recognition based on whole firing pin impression image via backpropagation neural network

Firearms identification is a vital aim of firearm analysis. The firing pin impression image on a cartridge case from a fired bullet is one of the most significant clues in firearms identification. In this study, a set of data which focused on selected 6 features of firing pin impression images before an entirety of five different pistols of South African made; the Parabellum Vector SPI 9mm model, were used. The numerical features are geometric moments of whole image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of firing pin impression images were then trained and validated using a two-layer backpropagation neural network (BPNN) design with computed hidden layers. A two-layer 6–7–5 connections BPNN of sigmoid/linear transfer functions with ‘trainlm’ algorithm was found to yield the best classification result using cross-validation, where 96% of the images were correctly classified according to the pistols used. Moreover, the network was trained under very small mean-square error (MSE=0.01). This means that neural network method is capable to learn and validate well the numerical features of whole firing pin impression with high precision and fast classification results.

Firearm Classification using Neural Networks on Ring of Firing Pin Impression Images

This paper implements two layer neural networks with different feedforward backpropagation algorithms for better performance of firearm classification us-ing numerical features from the ring image. A total of 747 ring images which are extracted from centre of the firing pin impression have been captured from five different pistols of the Parabellum Vector SPI 9mm model. Then, based on finding from the previous studies, the six best geometric moments numerical fea-tures were extracted from those ring images. The elements of the dataset were further randomly divided into the training set (523 elements), testing set (112 el-ements) and validation set (112 elements) in accordance with the requirement of the supervised learning nature of the backpropagation neural network (BPNN). Empirical results show that a two layer BPNN with a 6-7-5 configura-tion and tansig/tansig transfer functions with ‘trainscg’ training algorithm has produced the best classification result of 98%. The classification result is an improvement compared to the previous studies as well as confirming that the ring image region contains useful information for firearm classification.

Classification of pistol via numerical based features of firing pin impression image

A lot of current crime cases have been reported to involve pistols, among other firearms. The whole firing pin impression image on a cartridge case is one of the most substantial clues for firearms identification. In this study, a total of 16 features of geometric moments up to the sixth order were extracted from the entire firing pin impression images. All five pistols of the Parabellum Vector SPI 9mm model, manufactured in South Africa were used. The pistols were marked Pistol A, Pistol B, Pistol C, Pistol D, and Pistol E. A total of 747 bullets have been launched from the five pistols. Under an initial analysis, Pearson correlation coefficients between all pairs of features have demonstrated that the features were significant and that the features were inter-related. These problematic featureswere solved by dividing the features into subgroups of variables based on the same characteristics under the principle component analysis. The features that are highly correlated were brought together into meaningful components or factors. Discriminant analysis was applied for the identification of the types of pistols used based on the factors obtained. Classification results using cross-validation under the discriminant analysis pointed that 65.7% of the images were rightly classified according to the pistols used.

Determining the best forecasting method to estimate unitary charges price indexes of PFI data in central region Peninsular Malaysia

The concept of Private Financial Initiative (PFI) has been implemented by many developed countries as an innovative way for the governments to improve future public service delivery and infrastructure procurement. However, the idea is just about to germinate in Malaysia and its success is still vague. The major phase that needs to be given main attention in this agenda is value for money whereby optimum efficiency and effectiveness of each expense is attained. Therefore, at the early stage of this study, estimating unitary charges or materials price indexes in each region in Malaysia was the key objective. This particular study aims to discover the best forecasting method to estimate unitary charges price indexes in construction industry by different regions in the central region of Peninsular Malaysia (Selangor, Federal Territory of Kuala Lumpur, Negeri Sembilan, and Melaka). The unitary charges indexes data used were from year 2002 to 2011 monthly data of different states in the central region Peninsula...

Estimating cement price index by regions in Peninsular Malaysia

Malaysia is moving forward towards a developed country by the year 2020. Therefore, implementation of Private Financial Initiative (PFI) in Malaysia is really needed in order to improve the delivery and quality of infrastructure facilities and public services in this nation. The success of this program can only be made possible by healthy participation from both public and private sectors in Malaysia. The most essential aspect that needs to be fulfilled in this program is value for money (VFM) whereby maximum efficiency and effectiveness of every purchase is attained. Hence, at the preliminary stage of this study, estimating materials price index in Malaysia is the main objective. This particular paper aims to discover the best forecasting method to estimate cement price index by different regions in Peninsular Malaysia since cement is the main material used in construction industry. Cement index data used were from year 2005 to 2011 monthly data of different regions in Peninsular Malaysia. It was found that Backpropagation Neural Network with linear transfer function produced the most accurate and reliable results for estimating cement price index in every region in Malaysia. The neural network models selection were based on the Root Mean Squared Errors (RMSE), where the values were approximately zero errors and highly significant at p<;0.01. Therefore, artificial neural network is sufficient to forecast cement price index in Malaysia. The estimated price indexes of cement will contribute significantly to value for money in PFI and soon towards Malaysian economical growth.

Determining the best forecasting model of cement price index in Malaysia

Malaysia is aiming towards a developed country by the year 2020. Therefore, implementation of Private Financial Initiative (PFI) in Malaysia is needed as a procurement method to improve the delivery and quality of infrastructure facilities and public services in this country. The most essential aspect that needs to be fulfilled in this program is value for money (VFM) whereby maximum efficiency and effectiveness of every purchase is attained. Hence, at the preliminary stage of this study, estimating materials price index in Malaysia is the main objective. This particular paper aims to discover the best forecasting method to estimate cement price index by different regions in Malaysia since cement is the main material used in construction industry. Cement index data used were from year 2005 to 2011 monthly data of different regions in Peninsular Malaysia, and year 2003 to 2011 monthly data in both Sabah and Sarawak. It was found that Backpropagation Neural Network (BPNN) with linear transfer function produced the most accurate and reliable results for estimating cement price index in every region in Malaysia. The neural network models selection were based on the Root Mean Squared Errors (RMSE), where the values were approximately zero errors and highly significant at p<0.01. Therefore, artificial neural network is sufficient to forecast cement price index in Malaysia. The estimated price indexes of cement will contribute significantly to value for money in PFI and soon towards Malaysian economical growth.

Authenticating ANN-NAR and ANN-NARMA Models Utilizing Bootstrap Techniques

Neural system procedures have a colossal reputation in the space of gauging. In any case, there is yet to be a sure strategy that can well accept the last model of the neural system time arrangement demonstrating. Thus, this paper propose a way to deal with accepting the said displaying utilizing time arrangement square bootstrap. This straightforward technique is different compared to the traditional piece bootstrap of time-arrangement based, where it was composed by making utilization of every information set in the information apportioning procedure of neural system demonstrating; preparing set, testing set and approval set. At this point, every information set was separated into two little squares, called the odd and even pieces (non-covering pieces). At that point, from every piece, an arbitrary inspecting with substitution in a rising structure was made, and these duplicated tests can be named as odd-even square bootstrap tests. In time, the examples were executed in the neural system preparing for last voted expectation yield. The proposed strategy was forced on both manufactured neural system time arrangement models, which were nonlinear autoregressive (NAR) and nonlinear autoregressive moving normal (NARMA). In this study, three changing genuine modern month to month information of Malaysian development materials value records from January 1980 to December 2012 were utilized. It was found that the suggested bootstrapped neural system time arrangement models beat the first neural system time arrangement models.

The quadriceps muscle of knee joint modelling Using Hybrid Particle Swarm Optimization-Neural Network (PSO-NN)

Neural framework has for quite a while been known for its ability to handle a complex nonlinear system without a logical model and can learn refined nonlinear associations gives. Theoretically, the most surely understood computation to set up the framework is the backpropagation (BP) count which relies on upon the minimization of the mean square error (MSE). However, this algorithm is not totally efficient in the presence of outliers which usually exist in dynamic data. This paper exhibits the modelling of quadriceps muscle model by utilizing counterfeit smart procedures named consolidated backpropagation neural network nonlinear autoregressive (BPNN-NAR) and backpropagation neural network nonlinear autoregressive moving average (BPNN-NARMA) models in view of utilitarian electrical incitement (FES). We adapted particle swarm optimization (PSO) approach to enhance the performance of backpropagation algorithm. In this research, a progression of tests utilizing FES was led. The information that is gotten is utilized to build up the quadriceps muscle model. 934 preparing information, 200 testing and 200 approval information set are utilized as a part of the improvement of muscle model. It was found that both BPNN-NAR and BPNN-NARMA performed well in modelling this type of data. As a conclusion, the neural network time series models performed reasonably efficient for non-linear modelling such as active properties of the quadriceps muscle with one input, namely output namely muscle force.

The quadriceps muscle of knee joint modelling using neural network approach: Part 2

Artificial neural network has been implemented in many filed, and one of the most famous estimators. Neural network has long been known for its ability to handle a complex nonlinear system without a mathematical model and has the ability to learn sophisticated nonlinear relationships provides. Theoretically, the most common algorithm to train the network is the backpropagation (BP) algorithm which is based on the minimization of the mean square error (MSE). Subsequently, this paper displays the change of quadriceps muscle model by using fake savvy strategy named backpropagation neural system nonlinear autoregressive (BPNN-NAR) model in perspective of utilitarian electrical affectation (FES). A movement of tests using FES was driven. The data that is gotten is used to develop the quadriceps muscle model. 934 planning data, 200 testing and 200 endorsement data set are used as a part of the change of muscle model. It was found that BPNN-NARMA is suitable and efficient to model this type of data. A neural network model is the best approach for modelling nonlinear models such as active properties of the quadriceps muscle with one input, namely output namely muscle force.