Search

Matlamat pengurangan emisi karbon global sebanyak 50% menjelang tahun 2050 memerlukan penyertaan daripada pelbagai komponen masyarakat. Kajian telah dijalankan untuk meneroka prospek kawasan Lembah Klang ke arah Bandaraya Rendah Karbon (BRK) dari dimensi persepsi, tahap kesediaan dan limitasi penyertaan masyarakat. Kawasan Lembah Klang telah dipilih sebagai kawasan penelitian kajian kerana ia mempunyai kepadatan penduduk yang tinggi dan sektor ekonomi yang berkembang pesat. Kajian telah dijalankan secara kualitatif menggunakan instrumen temubual semi-struktur mendalam dan data yang diperoleh telah dianalisa secara analisa tema. 8 tema telah ditemui dalam kajian ini iaitu tema definisi, kriteria dan sumber emisi karbon di bawah dimensi persepsi; tema amalan dan kesedaran di bawah dimensi kesediaan masyarakat; dan tema insentif, politik dan hebahan di bawah dimensi limitasi penyertaan masyarakat. Semua tema yang ditemui dalam kajian ini menegaskan tentang keperluan mengubah gaya hidup kepada penjimatan tenaga dalam aktiviti harian tanpa mengurangkan keselesaan hidup. Maka secara prinsipnya, penyelidik merumuskan bahawa prospek kawasan Lembah Klang untuk mencapai bandar rendah karbon dari dimensi persepsi, kesediaan dan limitasi penyertaan masyarakat pada masa akan datang adalah sangat berpotensi. Kata kunci: Bandar rendah karbon; Persepsi; Kesediaan; Limitasi; Masyarakat ABSTRACT The goals to reduce 50% of global carbon emissions by 2050 require fully participation from various components of the local community. Therefore, this study has been conducted to explore the prospects of the Klang Valley area towards Low Carbon Cities (LCC) based on the perception, level of readiness and limitations in community participation. Klang Valley is selected as the area of observation due to its rapidly growing population and economic sector. This study adopted qualitative approach using in-depth semi-structured interview instrument and the data was analyzed using thematic analysis. 8 themes appeared in the analysis which are the themes of definition, criteria and sources of carbon emissions under the dimension of public perception; the themes of practice and awareness under the dimension of community readiness; and the themes of incentives, politics and awareness under the dimension of the limitation of community participation. All themes indicated that changing of the lifestyle of the individual towards energy saving in daily activities is prime important to achieve the LCC goal. In conclusion, the prospect for Klang Valley to become a low carbon city in regard to the dimensions of community perception, awareness and partipation limitation is high. Keywords: Low carbon cities; Perception; Readiness; Limitations; Community

Soil is of particular interest to the forensic community because it can be used as valuable associative evidence to link a suspect to a victim or a crime scene. Liquid chromatography is a powerful analytical tool for organic compound analysis. Recently, high-performance liquid chromatography (HPLC) has proven to be an efficient method for forensic soil analysis, especially in discriminating soils from proximity locations. However, ultra-performance liquid chromatography (UPLC), which is much more sensitive than HPLC, has never been explored in this context. This study proposed a UPLC method for profiling non-volatile organic compounds in three Malaysian soils (red, brown and yellowish-brown soils). The three soils were analysed separately to assess the effects of individual chromatographic parameters: (a) elution programme (isocratic vs. two gradient programmes); (b) flow rate (0.1 vs. 0.2 mL/min); (c) extraction solvent (acetonitrile vs. methanol) and (d) detection wavelength (230 vs. 254 nm). The injection volume and total run time were set to 5 µL and 35 min, respectively. Consequently, each soil sample gave 24 different chromatograms. Results showed that the most desirable chromatographic parameters were (a) isocratic elution; (b) flow rate at 0.2 mL/min and (c) acetonitrile extraction solvent. The proposed UPLC system is expected to be a feasible method for profiling non-volatile organic compounds in soil, and is more chemical-efficient than a comparable HPLC system. Key PointsUPLC is a chemical-efficient analytical method for profiling non-volatile organic compounds in soil.Mobile phase rich in acetonitrile promotes separation of non-volatile organic compounds in soil.Isocratic elution is more desirable than gradient elution in producing a high-quality chromatogram.

Forensic ink analyst is frequently asked to determine the source of questioned ink entries. Ultra-performance liquid chromatography (UPLC) technique is useful for profiling organic compounds of pen...

Forensic soil analysis is commonly used to establish a link between soil collected from a suspect (known samples) and soil collected from a crime scene (questioned sample) (1). Taman Tasik Permaisuri is located about 7km from Kuala Lumpur, one of the capital cities of Malaysia. Being a densely populated residential place, the rate of crime reported is also high. Soil is one of the most common types of evidence encountered in various types of crimes (2). The understanding of the variability of soil of a place is of fundamental importance to assess reliable evidence on forensic investigations (3). Therefore, this work aimed to evaluate the physico-chemical variability of soils collected from the urban park of Taman Tasik Permaisuri. A total of 20 soil samples were collected from several proximate sites around the park. The pH of all the samples dissolved in distilled water were measured using a pH meter. Meanwhile, colour of the samples in dried and wet conditions were recorded based on the Munsell Soil Color Chart. The variability of the physico-chemical properties was first explored using levelplot and then assessed via one-way ANOVA test). Fig. 1 illustrates the variability of the 20 soil samples by pH and soil color observed under dried condition using levelplot. In overall, the soils were mainly slight acidic or neutral. The soils exhibited rather low variability in pH value despite the one-way ANOVA coupled with LSD test (Fig. 2) denoted that the samples can be divided into ten subgroups. In conclusion, the physico-chemical properties of soils collected from the urban park of Taman Tasik Permaisuri were rather homogenous with mild variability.

Partial least squares-discriminant analysis (PLS-DA) is a favored modeling tool for high-dimensional data, e.g. infrared and Raman spectra. Prior to prediction, one needs to pre-select one decision rule (DR) for the PLS-DA model. The purpose of this work is to evaluate statistical differences of four novel DRs and the naive DR in PLS2-DA prediction models for classification of blue gel pen inks based on attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectra. The performances of the DRs have been estimated using forty sub-datasets that were prepared from the principal ATR-FTIR spectra. The global region together with three mutually exclusive spectral windows were preprocessed independently via nine different data preprocessing methods (i.e. mean centering, autoscaling, Pareto scaling, robust scaling, multiplicative scatter correction, normalization to sum, normalization to constant vector length, standard normal variate and asymmetric least squares). Then a series of 50 models (i.e. by including the first 50 PLS components incrementally) was constructed using the forty sub-datasets independently. Each model was evaluated using six different variants of v-fold cross-validation and external testing; and selected models were also assessed using iterative random sampling approach. Eventually, each DR was presented with a number of model estimates that describe the model accuracy and stability. Performances of the DRs were discussed according to summary statistics and ANOVA tests that were derived from the model estimates. Results show that the novel DRs are more accurate but relatively less stable than the naive DR. The differences are statistically significant at the 0.05 significance level. In conclusion, both novel and naive DRs are competitive with each other; and one has to decide on a trade-off between model stability and model accuracy.

In response to our review paper [L. C. Lee et al., Analyst, 2018, 143, 3526-3539], we present a study that compares empirical differences between PLS1-DA and PLS2-DA algorithms in modelling a colossal ATR-FTIR spectral dataset. Over the past two decades, partial least squares-discriminant analysis (PLS-DA) has gained wide acceptance and huge popularity in the field of applied research, partly due to its dimensionality reduction capability and ability to handle multicollinear and correlated variables. To solve a K-class problem (K > 2) using PLS-DA and high-dimensional data like infrared spectra, one can construct either K one-versus-all PLS1-DA models or only one PLS2-DA model. The aim of this work is to explore empirical differences between the two PLS-DA algorithms in modeling a colossal ATR-FTIR spectral dataset. The practical task is to build a prediction model using the imbalanced, high dimensional, colossal and multi-class ATR-FTIR spectra of blue gel pen inks. Four different sub-datasets were prepared from the principal dataset by considering the raw and asymmetric least squares (AsLS) preprocessed forms: (a) Raw-global region; (b) Raw-local region; (c) AsLS-global region; and (d) AsLS-local region. A series of 50 models which includes the first 50 PLS components incrementally was constructed repeatedly using the four sub-datasets. Each model was evaluated using six different variants of v-fold cross validation, autoprediction and external testing methods. As a result, each PLS-DA algorithm was represented by a number of figures of merit. The differences between PLS1-DA and PLS2-DA algorithms were assessed using hypothesis tests with respect to model accuracy, stability and fitting. On the other hand, confusion matrices of the two PLS-DA algorithms were inspected carefully for assessment of model parsimony. Overall, both the algorithms presented satisfactory model accuracy and stability. Nonetheless, PLS1-DA models showed significantly higher accuracy rates than PLS2-DA models, whereas PLS2-DA models seem to be much more stable compared to PLS1-DA models. Eventually, PLS2-DA also proved to be less prone to overfitting and is more parsimonious than PLS1-DA. In conclusion, the relatively high accuracy of the PLS1-DA algorithm is achieved at the cost of rather low parsimony and stability, and with an increased risk of overfitting.

This paper presents a comparison between self-organizing maps (SOMs) and principal component analysis (PCA) on investigating the temporal variation characteristics of air pollution. The concentrations of particulate matters (PM10, PM2.5), sulfur dioxide (SO2), nitrogen oxides (NO2), ozone (O3) and carbon monoxide (CO) were measured by the monitoring station at Nilai, an industrial and residential area in Negeri Sembilan, Malaysia. The data were collected from January 2018 to December 2019. Both the SOM and PCA were employed to reveal the patterns of the monthly and hourly variability of air pollutants in 2018 and 2019, respectively, and then in both the two years. Generally, the scores plots of PCA and mapping plot of SOMs gave comparable clustering results. However, visualization of the patterns was much feasible in SOM than PCA when the number of samples increased. In conclusion, SOM appears to be much appropriate than PCA in revealing temporal characteristics of air quality data.

Latent fingerprint is one of the most encountered evidence in a crime scene and is useful for personal identification. In forensic investigation, reliability of the identification process is greatly affected by the visibility of the minutiae features. This is because the matching of known and unknown fingerprints achieved according to the types and locations of the minutiae features. However, most of the fingerprints recovered from the crime scene are of low quality, i.e. incomplete print or minutiae features. Under such circumstances, forensic analyst can try to determine gender of donor of the latent fingerprint. This piece of information could help to narrow down the scope of searching of suspect. Forensic discrimination of gender based on ridge counts has been proposed for a few decades ago. Despite multiple works have reported the use of machine learning methods in gender classification using fingerprints, the fingerprint features were mainly extracted from the images. In this work, the diagonal ridge counts were calculated manually within a well-defined region, i.e. 25 centimetres squared. This approach is more relevant to a real crime scene investigation. This work employed two well-known machine learning algorithms, i.e. naive Bayes (NB) and Classification and Regression Trees (CART) algorithms, in discriminating gender based on the ridge counts. The performances of predictive models have been assessed by ethnicity and finger digit via bootstrapping without replacement approach. Results showed one-digit samples can perform as good as the five-digit or ten-digit samples. Comparing to the global predictive model, ethnicity-specific models of Indian and Malay subjects, respectively, showed better improvement. Moreover, by considering all five digits of a particular hand as input data, NB tended to outperform CART; whilst the relative performances reversed when only one digit was considered as input data. In conclusion, fingerprint ridge counts can be a potential indicator of gender in the Malaysian population.

Forensic ink analysis is aiming to determine source of an unknown ink entry found on a questioned document. A forgery indicator is established if the source of a questioned ink entry is different from the other ink entries on the same document. A statistical predictive model built from a chemical data of pen ink is useful in accomplishing the goal. Multiple statistical prediction model could be constructed from a chemical data after it was preprocessed via multiple data preprocessing techniques. Commonly, hypothesis test is employed to choose the best prediction model. However, when the number of models and model performance metric are overwhelming, this can be a laborious task. This work aims to explore the feasibility of Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for selecting the best predictive model. A total of 40 models have been constructed using an attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectral data of blue gel pen inks via Partial Least Squares-Discriminant Analysis (PLS-DA) technique. The ATR- FTIR spectral data was preprocessed using nine different data preprocessing techniques by considering the global and three different sub-spectral regions. The results showed that TOPSIS produced similar ranking model performances to that derived via conventional approach, i.e. univariate hypothesis test. The advantages of TOPSIS method in this context are no statistical assumptions compliance, e.g. normality; and numerical score presenting together with a rank allows inference of relative difference between the models.

In response to our review paper [L.C. Lee et al., Chemom. Intell. Lab. Systs. 163 (2017) 64–75], we present a study that explores practical impacts of data preprocessing (DP) methods in ATR-FTIR spectra. Nine common DP methods, i.e. mean centering (MC), autoscaling (AS), Pareto scaling, robust scaling, multiplicative scatter correction (MSC), normalization to sum (NS), normalization to constant vector length (NV), standard normal variate and asymmetric least squares (AsLS), were chosen on the sake of their availability in the R software and the rather simple computation steps. An ATR-FTIR spectral dataset of blue gel pen inks that is originated from 10 different manufacturers (i.e. brands) was used in this work. The dataset is colossal (N = 1361), high dimensional (J = 5401), multi-class (C = 10), and imbalanced. In order to examine the impacts of substrate interferences, the global spectral region was further divided, arbitrarily, into three mutually exclusive local regions and analyzed independently. Following that, the resulting four sub-datasets (i.e. one based on global and three based on local regions) were preprocessed via the DP methods independently to produce 40 different sub-datasets including the raw counterparts. Partial least squares-discriminant analysis (PLS-DA) was chosen to construct a series of 50 models by including the first 50 PLS components incrementally. The modeling was performed independently for each of the 40 sub-datasets. Each model was evaluated repeatedly using autoprediction, six variants of v-fold cross validation (v = 2, 4, 5, 7, 10, 15) and external testing schemes. As a results, empirical performances of each DP methods are represented by 400 different error rates (8 model validation schemes × 50 models). Performances of each DP method was then compared against its raw counterparts according to summary statistics and hypothesis tests. In addition, principal component analysis and hierarchical clustering analysis were also employed, respectively, to illustrate the spatial distribution and the similarity between the nine DP methods and the raw counterparts. Several important remarks have been drawn from the rigorous comparative analyses. First, due to the inherent properties of ATR-FTIR spectra, DP methods that handling slope, e.g. MSC and AsLS, have appeared to be the most excellent DP methods. Second, normalization methods, either NS or NV, ranked the second best-performing DP method. Third, MC shows no impact on the raw IR spectral dataset. Fourth, it is shown that outliers in the ATR-FTIR spectra of pen inks could be localized. Last but not least, removal of irrelevant signals arising from sample substrate is best achieved via region truncation rather than via PLS or DP methods alone.

External testing (ET), known also as the hold-out validation, is currently considered to be one of the most reliable ways to estimate predictive ability of a statistical model. One safeguard to prevent impermissible peeking in ET is to ensure all replicates of a particular sample is only included in either the test or the training set. Assuming a sample X1 consists of two replicates (i.e. X1a and X1b). The model is claimed to enjoy impermissible peeking if the X1a and X1b are split into the training and the test sets, respectively. Eventually, the resulting prediction model is expected to predict the test sets easily and presents an over-optimistic model performance. In forensic document examinations, an individual pen (IP) can be used to produce multiple ink strokes. In real-world practice, pens are manufactured via bulk production such that one big tank of ink is used to produce a wealth of IPs. In other words, ink strokes produced by varying IPs but of the same pen model are indeed originated from one single source (i.e. the same tank of ink). Eventually, with respect to the aforementioned safeguard, how shall one treat the ink strokes? Are they replicates or independent samples? In this context, the aim of the work is to investigate the validity of the safeguard in splitting dataset for hold-out validation strategy (i.e. ET) in the domain of forensic pen ink analysis. An infrared (IR) spectra of blue gel pen inks was used to demonstrate the practical aspect. The IR spectral data were collected from 1361 ink strokes that originated from 273 IPs of 23 pen models and 10 pen brands. Iterative stratified random sampling was employed to prepare 1000 pairs of training and test sets that were split at ratio 7:3 using two different principles: (a) set IP - selection was conducted at IP level to ensure all the ink strokes originated from a particular IP must be included into either the training or the test sets only; and (b) set NIP - ink strokes of a particular IP were allowed to be spread between the training and the test sets. For each dataset, a series of 50 PLS-DA models were constructed by including the first 50 PLS components incrementally, which were then validated via auto-prediction and ET. Following that, the performances between IP and NIP model series were compared with respect to: (a) model accuracy; (b) model stability; and (c) model fitting. In conclusion, the NIP model series do not show any evidence of advantages from the impermissible peeking since both the NIP and IP model series exhibit quite similar performances in all the three model aspects.

Principal component analysis (PCA) is very useful for data exploration owing to its unsupervised nature; and has been proven to be a powerful multivariate exploratory tool for processing and interpreting high-dimensional data in many fields such as engineering, physical and biological sciences. In particular, PCA has been applied in various forensic problems to provide either a direct or an indirect solution. Despite the fact that improved variants of the classical PCA are consistently described in the literature, this review concerned only with the classical PCA in view of its overwhelming popularity. This review aims to summarize the application strategy of PCA in solving varying forensic problems. In total, 20 PCA application strategies have been derived from over 80 forensic studies published since 2017. The goal of this paper is to shed light on the versatility and capability of PCA in processing high-dimensional data in general and specifically on its potential in forensic studies. Hence, this work is also relevant to other research communities interested in unravelling latent structure from high-dimensional data.

ATR-FTIR spectroscopy in the combination with chemometrics has been practiced over the past decades. Works presented in numerous disciplines provide ample empirical evidence in support for the coupling relationship. However, Data Pre-processing (DP) which constitutes the first step in chemometric analysis pipelines, is seldom given reasonable attentions. The aim of this paper is two-fold: (a) to review contemporary DP practice strategy by ATR-FTIR user, and (b) to critically discuss the rationales that could have been nurturing such practices. In the first part, basic concepts of chemometrics and ATR-FTIR spectroscopy are described. Then, the status quo of DP practice strategy is outlined and critically discussed on whether the contemporary practice has been malpractice or best practice. Finally, rationales that could have possibly contributed to some of the malpractices are discussed.

As a non-destructive analytical method, Raman spectroscopy often provides insufficient information to identify or differentiate the ink used for the preparation of a questioned document. In this study, blue and black ballpoint pen inks deposited on paper substrate were examined in situ by conventional Raman spectroscopy. Inks were successfully classified based on the total number of prominent bands in Raman spectra. It was found that more than 90% of the samples of the same type and color could be differentiated visually using only Raman spectra, i.e. 94 and 95% for blue and black inks, respectively. As a result of this study, a flow chart has been constructed for blue and black ballpoint pen inks allowing their systematic identification. Raman spectroscopy proved to be a fast and precise technique for forensic ink analysis.

Partial least squares-discriminant analysis (PLS-DA) is a versatile algorithm that can be used for predictive and descriptive modelling as well as for discriminative variable selection. However, versatility is both a blessing and a curse and the user needs to optimize a wealth of parameters before reaching reliable and valid outcomes. Over the past two decades, PLS-DA has demonstrated great success in modelling high-dimensional datasets for diverse purposes, e.g. product authentication in food analysis, diseases classification in medical diagnosis, and evidence analysis in forensic science. Despite that, in practice, many users have yet to grasp the essence of constructing a valid and reliable PLS-DA model. As the technology progresses, across every discipline, datasets are evolving into a more complex form, i.e. multi-class, imbalanced and colossal. Indeed, the community is welcoming a new era called big data. In this context, the aim of the article is two-fold: (a) to review, outline and describe the contemporary PLS-DA modelling practice strategies, and (b) to critically discuss the respective knowledge gaps that have emerged in response to the present big data era. This work could complement other available reviews or tutorials on PLS-DA, to provide a timely and user-friendly guide to researchers, especially those working in applied research.

External testing (ET) is preferred over auto-prediction (AP) or k-fold-cross-validation in estimating more realistic predictive ability of a statistical model. With IR spectra, Kennard-stone (KS) sampling algorithm is often used to split the data into training and test sets, i.e. respectively for model construction and for model testing. On the other hand, iterative random sampling (IRS) has not been the favored choice though it is theoretically more likely to produce reliable estimation. The aim of this preliminary work is to compare performances of KS and IRS in sampling a representative training set from an attenuated total reflectance – Fourier transform infrared spectral dataset (of four varieties of blue gel pen inks) for PLS2-DA modeling. The ‘best’ performance achievable from the dataset is estimated with AP on the full dataset (APF, error). Both IRS (n = 200) and KS were used to split the dataset in the ratio of 7:3. The classic decision rule (i.e. maximum value-based) is employed for new sample prediction via partial least squares – discriminant analysis (PLS2-DA). Error rate of each model was estimated repeatedly via: (a) AP on full data (APF, error); (b) AP on training set (APS, error); and (c) ET on the respective test set (ETS, error). A good PLS2-DA model is expected to produce APS, error and EVS, error that is similar to the APF, error. Bearing that in mind, the similarities between (a) APS, error vs. APF, error; (b) ETS, error vs. APF, error and; (c) APS, error vs. ETS, error were evaluated using correlation tests (i.e. Pearson and Spearman’s rank test), using series of PLS2-DA models computed from KS-set and IRS-set, respectively. Overall, models constructed from IRS-set exhibits more similarities between the internal and external error rates than the respective KS-set, i.e. less risk of overfitting. In conclusion, IRS is more reliable than KS in sampling representative training set.

The aim of this study is to propose an approach for the analysis of black ballpoint pen writing inks based on ultra-performance liquid chromatography (UPLC) combined with principal component analysis (PCA). A total of twelve varieties of black ballpoint pens available in the Malaysian market were examined by an UPLC that coupled with a photodiode array detection (PDA). Chromatograms of ink samples were extracted at 279, 370 and 400 nm. Chromatographic data obtained were subjected to PCA after normalization. Seven principal components were produced from a total of 15 raw peaks. The new set of variables was then used for running one-way ANOVA to differentiate 66 pen-pair formed from twelve varieties of black ballpoint pen. The approach proposed here has successfully differentiated all pen-pair thus achieving 100% discrimination power.

Column-wise manipulations (CWM), a group of data pre-processing (DP) techniques composed of mean-centering, Pareto scaling (PS), variance scaling and auto-scaling; are often applied individually or in combination. It has been applied like a norm without thoughtful considerations partly attributed to its simplicity and ease of applications. Theoretically, all variables in IR spectrum are measured on the same scale and seldom have different means and as such rarely require CWM as compared to normalization. This preliminary paper aims to investigate the real needs of each aforementioned CWM in infrared (IR) spectroscopic dataset that is derived from white copy paper. The untreated and pre-processed IR data is then processed with Principal Component Analysis plus Linear Discriminant Analysis (PCA-DA). The impact of CWM on test accuracy of the different PCA-DA models is then compared according to different IR wavenumber intervals. Error of the predictive models is determined via nonparametric bootstrap. Result...

Many literature apply Principal Component Analysis (PCA) as either preliminary visualization or variable con-struction methods or both. Focus of PCA can be on the samples (R-mode PCA) or variables (Q-mode PCA). Traditionally, R-mode PCA has been the usual approach to reduce high-dimensionality data before the application of Linear Discriminant Analysis (LDA), to solve classification problems. Output from PCA composed of two new matrices known as loadings and scores matrices. Each matrix can then be used to produce a plot, i.e. loadings plot aids identification of important variables whereas scores plot presents spatial distribution of samples on new axes that are also known as Principal Components (PCs). Fundamentally, the scores matrix always be the input variables for building classification model. A recent paper uses Q-mode PCA but the focus of analysis was not on the variables but instead on the samples. As a result, the authors have exchanged the use of both loadings and scores plots in which cluster...

The infrared (IR) spectra of different white copy paper types tend to appear indifferent. Discrimination between white copy papers could lead to the solution of forgery cases. In this preliminary study, three varieties of white paper were purchased from local stationery shops in Kuala Lumpur, Malaysia. The papers were classified according to their manufacturers using Partial Least Squares-Discriminant Analysis (PLS-DA) and sparse PLS-DA (sPLS-DA) models. The error rate for the two models on the training and the test data sets were estimated and compared. Results show that the performance of the two models are comparable. By including the first six latent variables in both models, classification accuracy as high as 100% can be achieved.

Principal Component Analysis (PCA) is a commonly used unsupervised exploratory analysis technique. It is also frequently used in dimensionality reduction. This preliminary paper investigates the feasibility of three variants of PCA, i.e. independent PCA (iPCA), sparse PCA (sPCA), and sparse independent PCA (siPCA) on forensic classification of paper based on their IR spectral data. After that, Linear Discriminant Analysis (LDA) models were built using the Principal Components (PCs) produced by the PCA and the three aforementioned variants. The performances of all these four LDA models, i.e. PCA-DA, iPCA-DA, sPCA-DA and siPCA-DA, were evaluated via leave-one-out cross-validation on the data set. The results obtained show that iPCA-DA and siPCA-DA are the most effective models with 100.0% classification accuracy. Then, the effectiveness of siPCA and iPCA models was evaluated based on posterior probability used for predictions of class membership that were derived from leave-one-out cross-validation. As a conclusion, siPCA is identified as the best classification model.

Selection of the most significant variables, i.e. the wavenumber, from an infrared (IR) spectrum is always difficult to be achieved. In this preliminary paper, the feasibility of genetic algorithms (GA) in identifying most informative wavenumbers from 150 IR spectra of papers was investigated. The list of selected wavenumbers was then employed in Linear Discriminant Analysis (LDA). GA procedure was repeated 30 times to get different lists of variables. Then the performances of LDA models were estimated via leave-one-out cross-validation. A total of six to eight wavenumbers were identified to be valuable variables in the GA procedures. All the 30 LDA models achieve correct classification rates between 97.3% to 100.0%. Therefore the GA-LDA model could be a suitable tool for differentiating white papers that appeared to be highly similar in their IR fingerprints.

Infrared (IR) spectral data are always influenced by undesired random and systematic variations. As such, pre-processing of spectral data is normally required before chemometric modeling. Two most widely used pre-processing techniques, i.e. scatter-correction methods and spectral derivatives, were used to pre-process 150 IR spectral data of paper. The algorithms investigated in this preliminary study are Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), Savitzky-Golay (SG) and Gap-Segment (GS). The visual examination of the clustering among three studied varieties of paper, i.e. IK Yellow, One Paper and Save Pack, is accomplished via Principal Component Analysis (PCA). Overall, separation of the three varieties of paper is greatly enhanced after pre-processing. The most significant improvement is obtained with pre-processing via 1st derivative using SG algorithms.

White-copy A4 paper is an important kind of substrate for preparation of most formal as well as informal documents. It often encountered as questioned document in cases such as falsification, embezzlement or forgery. By comparing the questioned piece, (e.g. of a contract) against the rest deemed authentic, forgery indicator could be derived from an inconsistent chemical composition. However, classification and even differentiation of white copy paper have been difficult due to highly similar physical properties and chemical composition. Self-organizing map (SOM) has been proven useful in many published works as a good tool for clustering and classification of samples, especially when involving high-dimensional data. In this preliminary paper, we explore the feasibility of SOM in classifying white copy paper for forensic purposes. A total of 150 infrared spectra were collected from three varieties of white paper using Attenuated Total Reflectance Fourier-transform infrared (ATR-FTIR) spectroscopy. Each IR spectrum composed of over thousands of wavenumbers (i.e. input variables) and resembles chemical fingerprint for the sample. Comparative performance between raw wavenumbers and its reduced form (i.e. principal components, PCs) in SOM modeling also conducted. Results showed that SOM built with PCs is much efficient than built with raw wavenumbers, with the classification accuracy of over 90% is obtained with external validation test. This study shows that SOM coupled with ATR-FTIR spectroscopy could be a potential non-destructive approach for forensic paper analysis.