Correct Classification Accuracy Research Articles

Accuracy of Cognitive Screening Instruments Reconsidered: overall, Balanced Or Unbiased accuracy?

Aim: To examine three different accuracy metrics for evaluation of cognitive screening instruments: overall correct classification accuracy (Acc), the sum of true positives and negatives divided by the total number tested; balanced accuracy (balanced Acc), half of the sum of sensitivity and specificity; and unbiased accuracy (unbiased Acc), removing biasing effects of random associations between test results and disease prevalence. Materials & methods: Data from a prospective test accuracy study of Mini-Addenbrooke’s Cognitive Examination were used to calculate and plot the Acc measures. Results: Each Acc metric resulted in a similar pattern of results across the range of Mini-Addenbrooke’s Cognitive Examination cut-offs for diagnosis of both dementia and mild cognitive impairment. Acc and balanced Acc gave more optimistic outcomes (closer to possible maximum value of 1) than unbiased Acc. Conclusion: Unbiased Acc may have advantages over Acc and balanced Acc by removing biasing effects of random associations between test result and disease prevalence.

Use of the FLOTAC technique as a new coproparasitological diagnostic method in aquatic mammals and comparison with traditional methods.

The inadequate choice of a diagnostic method or the option for techniques that have low sensitivity and specificity may limit the diagnosis of parasitic agents that affect aquatic mammals. The aim of this study was to evaluate the performance of the FLOTAC technique and compare it with three traditional methods (Willis, sedimentation and centrifugation- flotation) used in the diagnosis of gastrointestinal parasites in aquatic mammals. For this, 129 fecal samples from 12 species were collected. Each sample was submitted to laboratory processing using the Willis, Hoffman techniques, Faust method and FLOTAC. Sensitivity, specificity, real prevalence, estimated prevalence, positive predictive value, negative predictive value, correct classification (accuracy) and incorrect classification were evaluated to compare the different diagnostic methods. The highest frequency of positive samples occurred using FLOTAC (46.51%), compared to Hoffman (23.25%), Faust (10.07%) and Willis techniques (6.97%). In the samples analyzed, the occurrence of Strongylidae eggs and Eimeriidae oocysts was frequently observed. The FLOTAC technique proved to be the most appropriate technique and due to its efficacy, is strongly recommended for coproparasitological evaluations in aquatic mammals.

A Robust Feature-Based Approach for Recognition of Line Coding Schemes

Decoding communication signals in a non-cooperative environment has always been a challenging task. Even after the estimation of various transmission-related parameters, the unknown received signal still cannot be decoded without the correct classification of the incorporated line coding scheme. In this paper, a robust short-sample feature-based approach is presented which recognizes line coding schemes in a sequential manner by an in-depth examination of linked characteristic features. The proposed approach provides an overall correct classification accuracy higher than 90 percent with an input of just 13 bit-waveforms whereas perfect classification accuracy (100 percent) is achieved with just 30 bit-waveforms of the unknown received signal. A detailed comparison considering noiseless as well as noisy channel environment is also carried out vis-à-vis existing approach based on extensive simulation results. Additionally, the paper bridges the gap between theory and simulations to justify the obtained accuracy results for conventional line codes under consideration. The substantial increase in classification accuracy for a smaller number of input bit-waveforms shall aid effective decoding of the unknown received signal even at the initial stages of reception. In general, it can benefit many practical spectrum surveillance applications, where proactiveness is paramount.

Data Classification Methodology for Electronic Noses Using Uniform Manifold Approximation and Projection and Extreme Learning Machine

The classification and use of robust methodologies in sensor array applications of electronic noses (ENs) remain an open problem. Among the several steps used in the developed methodologies, data preprocessing improves the classification accuracy of this type of sensor. Data preprocessing methods, such as data transformation and data reduction, enable the treatment of data with anomalies, such as outliers and features, that do not provide quality information; in addition, they reduce the dimensionality of the data, thereby facilitating the tasks of a machine learning classifier. To help solve this problem, in this study, a machine learning methodology is introduced to improve signal processing and develop methodologies for classification when an EN is used. The proposed methodology involves a normalization stage to scale the data from the sensors, using both the well-known min−max approach and the more recent mean-centered unitary group scaling (MCUGS). Next, a manifold learning algorithm for data reduction is applied using uniform manifold approximation and projection (UMAP). The dimensionality of the data at the input of the classification machine is reduced, and an extreme learning machine (ELM) is used as a machine learning classifier algorithm. To validate the EN classification methodology, three datasets of ENs were used. The first dataset was composed of 3600 measurements of 6 volatile organic compounds performed by employing 16 metal-oxide gas sensors. The second dataset was composed of 235 measurements of 3 different qualities of wine, namely, high, average, and low, as evaluated by using an EN sensor array composed of 6 different sensors. The third dataset was composed of 309 measurements of 3 different gases obtained by using an EN sensor array of 2 sensors. A 5-fold cross-validation approach was used to evaluate the proposed methodology. A test set consisting of 25% of the data was used to validate the methodology with unseen data. The results showed a fully correct average classification accuracy of 1 when the MCUGS, UMAP, and ELM methods were used. Finally, the effect of changing the number of target dimensions on the reduction of the number of data was determined based on the highest average classification accuracy.

Extraction and Spatio-Temporal Analysis of Impervious Surfaces over Dongying Based on Landsat Data

It is necessary to understand the relationship between the impervious surface area (ISA) distribution, variation trends and potential driving forces over Dongying, Shandong Province. We extracted ISA information from Landsat images with 3–5 year intervals during 1995 to 2018 using Minimum Noise Fraction (MNF) transform, Pixel Purity Index (PPI), and Linear Spectral Mixture Analysis (LSMA), followed by the analysis on three driving forces of ISA expansion (physical geography, socioeconomic factors, and urban cultural features). Our results show the retrieved ISA thematic map fit the limited requirement of root mean square error (RMSE). The correct classification accuracy of ISA is greater than 83.08%. Further, the cross–comparison exhibits the general consistent with the ISA distribution of the land use classification map published by the National Basic Geographic Information Center. The gradual increasing trend can be captured on the expansion of ISA from 1995 to 2018. Despite of the central region always shown as the high ISA density, it still keeps increasing annually and radiating the surrounding region, especially in the southward which has formed into a new large–scale and high intensity of ISA in 2015–2018. Though the ISA patches scattered in the west region or along the northern and eastern part of the ocean coastline are still small, the expansion trend of ISA can be detected. The expansion intensity index (EII) of ISA measuring the situation of its expansion changes from the lowest value 0.12% between 1995 and 2000 up to the highest 0.73% between 2000 and 2005. Richly endowed by nature, the city’s natural geographical environment provides an elevated chance of further urbanization. The rapid increase of regional economy provides a fundamental driving force for expanding ISAs. The development of urban culture promotes the sustainable development of ISAs. Our results provide a scientific basis for future urban land use management, construction planning, and environmental protection in Dongying.

Domates meyvelerinin renk parametrelerine göre sertlik sınıflandırması

Aim of study: In this study, firmness classification potential of tomato fruits was investigated by using colour parameters measured with a colour measuring device. Material and methods: 202 ‘Bandita F1’ greenhouse tomatoes were used as trial material. In damage free colour measurements carried out by Minolta CR-400 colour measurement device, L*, a* and b* colour parameters were considered as main parameters. Other colour parameters (a*xb*, a*2, b*2 and a*/b*) were derived from main colour parameters. These colour parameters were associated with tomato firmness. In tomato firmness measurements, the force value at the skin rupture point was used and this value was expressed as tomato firmness. Tomato samples were grouped according to firmness by using clustering analysis method. In addition, linear discrimination analysis method was used in the classification of tomatoes according to firmness. Classification accuracy was improved by linear discrimination analysis and the number of parameters used was decreased with stepwise regression analysis method. The association between tomato firmness and colour parameters (L*, a*, b*, a*xb*, a*2, b*2 and a*/b*) was determined with Pearson Correlation test. Main results: Statistical analysis results showed that the association between tomato firmness and colour parameters was significant (P<0.01). According to linear discrimination analysis results, linear classification accuracy was calculated as 85.64% for main colour parameters approach and as 90.59% for seven colour parameters approach. The results of linear discrimination analysis performed by using the most important three colour parameters determined with stepwise regression analysis method showed that correct classification accuracy of tomatoes was 89.10%. Research highlights: The results showed that firmness classification of tomatoes could be done by using colour parameters and linear discrimination analysis method.

Detection of citrus black spot symptoms using spectral reflectance

Citrus black spot (CBS) disease can usually result in fruit blemish and yield loss on all citrus. Spectral reflectance was utilized to detect CBS symptoms in this study. Hyperspectral images of both healthy and diseased citrus were collected in the spectral region of 396−1010 nm. After raw image calibration, spectral reflectance of diseased (early hard spot, advanced hard spot, cracked spot, early virulent, and virulent) and healthy samples were extracted and used as independent variables for classification. Effective wavelengths were selected using regression coefficients based on partial least squares analysis. K-nearest neighbor models were established to classify the symptoms in each group (early hard spot vs. advanced hard spot, early virulent vs. virulent, hard spot vs. cracked spot, hard spot vs. virulent, cracked spot vs. virulent, diseased vs. healthy, and early stage vs. advanced stage). In diseased vs. healthy group, the models yielded the correct classification accuracies of 99.4 % (using full wavelengths) and 100.0 % (using selected wavelengths) for diseased samples. The correct classification accuracies were 92.5 % (using full wavelengths) and 93.8 % (using selected wavelengths) for early stage samples (early disease). Besides, the selected wavelengths were 549, 668, 706, and 790 nm for diseased vs. healthy group, and 675, 711, and 835 nm for early stage vs. advanced stage group. The overall results demonstrated that spectral reflectance information has the potential to classify different symptoms of CBS.

Toward Food Freshness Monitoring: Coordination Binding-Based Colorimetric Sensor Array for Sulfur-Containing Amino Acids.

Herein, a self-assembled colorimetric chemosensor array composed of off-the-shelf catechol dyes and a metal ion (i.e., Zn2+) has been used for the sulfur-containing amino acids (SCAAs; i.e., glutathione, glutathione disulfide, L–cysteine, DL–homocysteine, and L–cystine). The coordination binding–based chemosensor array (CBSA) fabricated by a competitive assay among SCAAs, Zn2+ ions, and catechol dyes [i.e., pyrocatechol violet (PV), bromopyrogallol red (BPR), pyrogallol red (PR), and alizarin red S (ARS)] yielded fingerprint-like colorimetric changes. We succeeded in the qualification of SCAAs based on pattern recognition [i.e., a linear discrimination analysis (LDA)] with 100% correct classification accuracy. The semiquantification of reduced/oxidized forms of SCAAs was also performed based on LDA. Furthermore, we carried out a spike test of glutathione in food samples using the proposed chemosensor array with regression analysis. It is worth mentioning that we achieved a 91–110% recovery rate in real sample tests, which confirmed the accuracy of the constructed model. Thus, this study represents a step forward in assessing food freshness based on supramolecular analytical methods.

Inter-annual monitoring of land use land cover changes with emphasis on forest reserves under a spatial planning perspective

Monitoring the inter-annual land cover evolution is considered of crucial importance at global level, since it may reveal significant changes across the Earth surface. Primary aim of the paper is to explore the spatiotemporal changes occurred in a highly touristic region which hosts a diversity of high-value natural resources (forests, coastal landscapes, croplands). To this end, a supervised land use image classification has been conducted for two years (2000, 2019) adopting the support vector machine algorithm. The outcomes of the classification have been verified by the overall accuracy (OA) index and kappa coefficient (KC). Both indices indicated high accuracy (over 80% and 0.8 respectively) of correct classification. Next, a matrix and a map of changes were developed to provide a quantitative and qualitative perspective of land use changes. The primary changes occurred were related to the transformation of forest to cropland and vice versa, followed by a mild urban expansion (especially for touristic premises).

Increase in level of detection of secret embedding into compressed JPEG-images based on selection of informative features

The research of informational content of features in the spatial and the frequency domains at steganalysis of the compressed JPEG-images is presented. Modern steganalysis methods, based on which the feature set has been created, are considered. As a method of informative features selection has been applied the greedy algorithm with an exception which has allowed reducing number of features in the set from 43 to 26. The experiments have shown that steganalysis on the basis of informative features allows increasing the accuracy of correct classification of initial images to 94%, of images with attachments by the PM1 and the Jsteg methods by 25 and 18 percent respectively. The issue of steganalysis of images with artificially created distortions is mentioned. The experiments showed that steganalysis based on informative features allow classifying correctly such images with the accuracy 96%.

Defining 'optimal' test cut-off using global test metrics: evidence from a cognitive screening instrument.

Aim: To examine the variation of several global metrics of test accuracy with test cut-off for the diagnosis of dementia. These metrics included some based on the receiver operating characteristiccurve, such as Youden index, and some independent of receiver operating characteristic curve, such as correct classification accuracy. Materials & methods: Data from a test accuracy study of Mini-Addenbrooke's Cognitive Examinationwere used to calculate and plot each global measure against test cut-off. Results: Different 'optimal' cut-points were identified for the different global measures, with a spread of ten points in observed optimal cut-off in the 30-point Mini-Addenbrooke's Cognitive Examination scale. Using these optima gave a large variation in test sensitivity from very high (diagnostic odds ratio) to very low (likelihood to be diagnosed or misdiagnosed), but all had high negative predictive value. Conclusion: The method used to determine the cut-off of cognitive screening instruments may have significant implications for test performance.

Craniometric estimation of ancestry in Thai and Japanese individuals

ABSTRACT There are currently no forensic methods for distinguishing Thais from other individuals of Asian ancestry using craniometrics. Of foreigners visiting or living in Thailand, Japanese people predominate. Remains of Japanese soldiers from the Second World War were excavated in northern Thailand, and hundreds more are thought to have disappeared in this area and nearby countries. This research aims to develop new formulae for ancestry estimation of skulls suspected to be Thai or Japanese. This was achieved by measuring 440 Thai and Japanese skulls. Stepwise discriminant analysis created four formulae. The first formula is for a complete skull, with predicted and correct classification accuracy of 89.3% and tested accuracy of 91.2%. The second formula, cranium only, gave 84.3% predicted and correct classification accuracy and tested accuracy of 85.3%. The third formula, for a male skull, gave predicted and correct classification accuracy of 92.0% and tested accuracy of 85.3%. The fourth formula, for a female skull, produced 89.8% predicted and correct classification accuracy and tested accuracy of 88.2%. Differentiating between Asian subgroups is challenging, but this study demonstrates the potential to distinguish Thai from Japanese individuals in forensic applications. It can be used to clarify ancestry of ‘Asian’ unclaimed bodies found in Thailand.

Detecting Swimming Strokes Using Pattern Recognition Analysis

PURPOSE: While exercises such as walking, running or cycling can be distinguished well by accelerometry, little was reported for swimming. Purpose of this study was to detect four common swimming strokes using a pattern recognition analysis and determine the swimming time of each stroke. METHODS: A total of 17 swimming athletes (9 females, 53%) from the Southeast University, China were recruited and their age (M±SD, male: 20±0.8, female: 19.4±1.0, total: 19.7±0.9 yr.), height (184.5±3.2, 172.1±5.4, 178.3±7.7 cm), body weight (82.9±6.0, 61.3±5.3, 72.1±12.4 kg), years of training on swimming (12.5±1.8, 12.9±1.9, 12.7±1.8 yr.) were collected. Each participant performed breaststroke, front crawl, backstroke and butterfly in their own preferred orders four laps in a 50-meter pool, with an Actigraph GT9X inertia measurement unit on right or left wrist with their own preference. The middle two minutes recording of each stroke were extracted out and divided into 12 segments with 10 seconds each. Each segment was coded based on the stroke type. Two classifiers, linear discriminant analysis (LDA) and support vector machine (SVM), were used for the analysis. Random 13 people were selected into training data and the remaining 4 participants for cross validation. Swimming time of each stroke is the sum of time that recognised as certain stroke. The analysis was performed using R. RESULTS: The accuracy of correct classification is 0.995±0.012 by LDA and 0.984±0.021 by SVM while corresponding cross-validation accuracy are 0.917±0.085 and 0.964±0.046, respectively, with no statistical significant difference between male and female. As a result, SVM was used to further determine the sensitivity and specificity of the algorithm of each stoke and swimming time accuracy:CONCLUSIONS: With a wearable device and SVM like pattern recognise algorithm, swimming strokes can be accurately detected, which provides a great convenience to track the participation time of swimming activities.

Colour Feature Extraction Techniques for Real Time System of Oil Palm Fresh Fruit Bunch Maturity Grading

According to the natural ripeness phenomena of oil palm fruit, the oil palm fresh fruit bunch (FFB) ripeness is divided into three different categories called, under ripe, ripe, and overripe. The current method in the mills for oil palm FFB grading is manually using human graders. However, the manual grading method is subjective and prone to human errors. Thus, accurate classification of oil palm FFB with fast and easy process is necessary in oil palm farms and in the palm oil industry to grade high-quality products, especially when classifying a large amount of fruits. In this paper, an image processing algorithm scenario represented by image acquisition, segmentation, and feature extraction is implemented in real time system for oil palm FFB maturity grading. This study presents an automated inspection for the oil palm FFB using an external grading system processing based on the colour feature extraction technologies; namely, color histogram and statistical color feature (mean and standard deviation), were used to extract the oil palm FFB image’s color features. An artificial neural network (ANN) classifier as supervised machine learning technique is applied to train and test the system performance accuracy based on area under curve (AUC) of the receiver operation characteristic (ROC) as classifier performance evaluation. The result show that the colour histogram technique based on the ANN classifier was observed to be a more robust and accurate classifier, with overall 94% correct ripeness classification accuracy, for oil palm FFB maturity grading compared to the other techniques applied and tested in this study.

Multi‐kernel‐based random vector functional link network with decomposed features for epileptic EEG signal classification

This study proposes an improved hybrid model built with empirical mode decomposition (EMD) features combined with weighted multi-kernel random vector functional link network (WMKRVFLN) where the kernel parameters are optimised with an efficient optimisation algorithm known as water cycle algorithm (WCA) for diagnosis and classification of epileptic electroencephalogram (EEG) signals. The proposed model with optimisation is known as WCA–EMD–WMKRVFLN. The tanh and wavelet kernel functions are contributing together to the effectiveness of the proposed model. The features generated from EMD in terms of intrinsic mode functions (IMFs) are modulated to find important statistical and entropy based features and these features in a reduced form are employed as inputs to the model to classify epileptic EEG signals. The presented approach is evaluated in terms of percentage correct classification accuracy (ACC), specificity and sensitivity using two datasets and is compared with different classifiers and state-of-the-art techniques. The highest accuracies of 99.69% (five-class) and 100% (three-class) achieved using the Bonn-University dataset and 99.0% ACC (two-class) achieved using the Bern-Barcelona dataset. The achieved results report that the presented approach is a promising approach for EEG signal classification and is superior to several state-of-the-art techniques and is highly comparable to many such techniques.

Tree, Shrub, and Grass Classification Using Only RGB Images

In this work, a semantic segmentation-based deep learning method, DeepLabV3+, is applied to classify three vegetation land covers, which are tree, shrub, and grass using only three band color (RGB) images. DeepLabV3+’s detection performance has been studied on low and high resolution datasets that both contain tree, shrub, and grass and some other land cover types. The two datasets are heavily imbalanced where shrub pixels are much fewer than tree and grass pixels. A simple weighting strategy known as median frequency weighting was incorporated into DeepLabV3+ to mitigate the data imbalance issue, which originally used uniform weights. The tree, shrub, grass classification performances are compared when all land cover types are included in the classification and also when classification is limited to the three vegetation classes with both uniform and median frequency weights. Among the three vegetation types, shrub is found to be the most challenging one to classify correctly whereas correct classification accuracy was highest for tree. It is observed that even though the median frequency weighting did not improve the overall accuracy, it resulted in better classification accuracy for the underrepresented classes such as shrub in our case and it also significantly increased the average class accuracy. The classification performance and computation time comparison of DeepLabV3+ with two other pixel-based classification methods on sampled pixels of the three vegetation classes showed that DeepLabV3+ achieves significantly higher accuracy than these methods with a trade-off for longer model training time.

Environmental Noise Classification Using Convolutional Neural Networks with Input Transform for Hearing Aids.

Hearing aids are essential for people with hearing loss, and noise estimation and classification are some of the most important technologies used in devices. This paper presents an environmental noise classification algorithm for hearing aids that uses convolutional neural networks (CNNs) and image signals transformed from sound signals. The algorithm was developed using the data of ten types of noise acquired from living environments where such noises occur. Spectrogram images transformed from sound data are used as the input of the CNNs after processing of the images by a sharpening mask and median filter. The classification results of the proposed algorithm were compared with those of other noise classification methods. A maximum correct classification accuracy of 99.25% was achieved by the proposed algorithm for a spectrogram time length of 1 s, with the correct classification accuracy decreasing with increasing spectrogram time length up to 8 s. For a spectrogram time length of 8 s and using the sharpening mask and median filter, the classification accuracy was 98.73%, which is comparable with the 98.79% achieved by the conventional method for a time length of 1 s. The proposed hearing aid noise classification algorithm thus offers less computational complexity without compromising on performance.

How much are we exposed to alcohol in electronic media? Development of the Alcoholic Beverage Identification Deep Learning Algorithm (ABIDLA)

BackgroundEvidence demonstrates that seeing alcoholic beverages in electronic media increases alcohol initiation and frequent and excessive drinking, particularly among young people. To efficiently assess this exposure, the aim was to develop the Alcoholic Beverage Identification Deep Learning Algorithm (ABIDLA) to automatically identify beer, wine and champagne/sparkling wine from images. MethodsUsing a specifically developed software, three coders annotated 57,186 images downloaded from Google. Supplemented by 10,000 images from ImageNet, images were split randomly into training data (70 %), validation data (10 %) and testing data (20 %). For retest reliability, a fourth coder re-annotated a random subset of 2004 images. Algorithms were trained using two state-of-the-art convolutional neural networks, Resnet (with different depths) and Densenet-121. ResultsWith a correct classification (accuracy) of 73.75 % when using six beverage categories (beer glass, beer bottle, beer can, wine, champagne, and other images), 84.09 % with three (beer, wine/champagne, others) and 85.22 % with two (beer/wine/champagne, others), Densenet-121 slightly outperformed all Resnet models. The highest accuracy was obtained for wine (78.91 %) followed by beer can (77.43 %) and beer cup (73.56 %). Interrater reliability was almost perfect between the coders and the expert (Kappa = .903) and substantial between Densenet-121 and the coders (Kappa = .681). ConclusionsFree from any response or coding burden and with a relatively high accuracy, the ABIDLA offers the possibility to screen all kinds of electronic media for images of alcohol. Providing more comprehensive evidence on exposure to alcoholic beverages is important because exposure instigates alcohol initiation and frequent and excessive drinking.

Classification of Riboswitch Families Using Block Location-Based Feature Extraction (BLBFE) Method.

Purpose: Riboswitches are special non-coding sequences usually located in mRNAs’ un-translated regions and regulate gene expression and consequently cellular function. Furthermore, their interaction with antibiotics has been recently implicated. This raises more interest in development of bioinformatics tools for riboswitch studies. Herein, we describe the development and employment of novel block location-based feature extraction (BLBFE) method for classification of riboswitches. Methods: We have already developed and reported a sequential block finding (SBF) algorithm which, without operating alignment methods, identifies family specific sequential blocks for riboswitch families. Herein, we employed this algorithm for 7 riboswitch families including lysine, cobalamin, glycine, SAM-alpha, SAM-IV, cyclic-di-GMP-I and SAH. Then the study was extended toward implementation of BLBFE method for feature extraction. The outcome features were applied in various classifiers including linear discriminant analysis (LDA), probabilistic neural network (PNN), decision tree and k-nearest neighbors (KNN) classifiers for classification of the riboswitch families. The performance of the classifiers was investigated according to performance measures such as correct classification rate (CCR), accuracy, sensitivity, specificity and f-score. Results: As a result, average CCR for classification of riboswitches was 87.87%. Furthermore, application of BLBFE method in 4 classifiers displayed average accuracies of 93.98% to 96.1%, average sensitivities of 76.76% to 83.61%, average specificities of 96.53% to 97.69% and average f-scores of 74.9% to 81.91%. Conclusion: Our results approved that the proposed method of feature extraction; i.e. BLBFE method; can be successfully used for classification and discrimination of the riboswitch families with high CCR, accuracy, sensitivity, specificity and f-score values.

Machine Learning in 3D Space Gesture Recognition

The rapid increase in the development of robotic systems in a controlled and uncontrolled environment leads to the development of a more natural interaction system. One such interaction is gesture recognition. The proposed paper is a simple approach towards gesture recognition technology where the hand movement in a 3-dimensional space is utilized to write the English alphabets and get the corresponding output in the screen or a display device. In order to perform the experiment, an MPU-6050 accelerometer, a microcontroller and a Bluetooth for wireless connection are used as the hardware components of the system. For each of the letters of the alphabets, the data instances are recorded in its raw form. 20 instances for each letter are recorded and it is then standardized using interpolation. The standardized data is fed as inputs to an SVM (Support Vector Machine) classifier to create a model. The created model is used for classification of future data instances at real time. Our method achieves a correct classification accuracy of 98.94% for the English alphabets’ hand gesture recognition. The primary objective of our approach is the development of a low-cost, low power and easily trained supervised gesture recognition system which identifies hand gesture movement efficiently and accurately. The experimental result obtained is based on use of a single subject.