Rajjyoti Das

A Neuro-Fuzzy Classifier-Cum-Quantifier for Analysis of Alcohols and Alcoholic Beverages Using Responses of Thick-Film Tin Oxide Gas Sensor Array

A novel neuro-fuzzy classifier-cum-quantifier is presented. The proposed classifier retrieves both qualitative and quantitative information simultaneously from the steady-state responses of thick-film tin oxide gas sensor array when it was exposed to seven different kinds of alcohols and alcoholic beverages. The individual concentration bands were represented in the output feature space by fuzzy subsethood measure. The qualitative and quantitative classifications were done by training an artificial neural network (ANN) with backpropagation algorithm. Each output neuron of the network represented one out of the seven alcohols and alcoholic beverage classes and was trained to fire at the fuzzy subsethood value of the particular concentration band of a particular alcohol or alcoholic beverage whose sample was presented to the network. The proposed network gave satisfactory performance and simultaneous qualitative and quantitative classification of the alcohols and alcoholic beverages was obtained using a single neural network.

Fuzzy Entropy Based Neuro-Wavelet Identifier-Cum-Quantifier for Discrimination of Gases/Odors

In this paper, a new approach to design of an odor/gas identifier-cum-quantifier is presented. Dynamic response curves of an oxygen-plasma treated thick-film tin oxide sensor array exposed to four different gases were subjected to continuous wavelet transform (CWT). Appropriate wavelet coefficients were selected using multiscale principal component analysis (MSPCA). Fuzzy entropy and fuzzy subsethood values were calculated for the individual odor/gas and for the particular concentration band of each odor/gas, respectively. The quantitative information was encoded in the fuzzy subsethood values of the particular concentration bands in the output feature space, whereas the fuzzy entropy values were used to normalize the training data set consisting of MSPCA selected wavelet coefficients. A feedforward neural network was trained with a backpropagation algorithm with the training data containing the wavelet coefficients normalized with fuzzy entropies of individual odors/gases. The target data set was made up of the fuzzy subsethood values of the particular concentration band. The proposed network achieved identification and quantification of odors/gases with a 100% success rate. Also, fuzzy entropy based normalization helped to achieve 100% identification/quantification with a reduced number of sensors in the array.

Quantification of Individual Gases/Odors Using Dynamic Responses of Gas Sensor Array With ASM Feature Technique

This paper is a continuation of our previous work in which a new feature technique called average slope multiplication (ASM) was proposed to classify the individual gases/odors using dynamic responses of sensor array. The ASM method is used to quantify the individual gases/odors in this paper. Back propagation algorithm based two different neural network architectures (NNAs) called NNA1 and NNA2 are used to assess the ability of the ASM technique for quantification. The proposed method thus utilizes the newly developed feature method in the first stage and the specially designed neural quantifiers in the next subsequent stages. The ability of the proposed method has been insured by applying it on the published dynamic responses of the thick film gas sensor array. When the raw data were directly fed to the neural quantifiers, the results were 69% and 63% accurate for NNA1 and NNA2, respectively. The principal component analysis preprocessed version of raw data provided 74% and 67% quantification accuracy with the aforementioned architectures respectively. The performances of the ASM data were found to be 100% using both the network architecture without need of further preprocessing, with relatively less number of epochs and without any hidden layer. Thus, the proposed method can be utilized in electronic nose for classification/quantification purpose.

Alcohol and Tobacco Increases Risk of High Risk HPV Infection in Head and Neck Cancer Patients: Study from North-East Region of India

Background Human papilloma virus (HPV) associated Head and Neck Cancers (HNCs) have generated significant amount of research interest in recent times. Due to high incidence of HNCs and lack of sufficient data on high-risk HPV (hr-HPV) infection from North -East region of India, this study was conceived to investigate hr-HPV infection, its types and its association with life style habits such as tobacco, alcohol consumption etc. Methods A total of one hundred and six primary HNC tumor biopsy specimens were collected. These samples were analyzed for hr-HPV DNA (13 HPV types) using hybrid capture 2 (HC2) assay and genotyping was done by E6 nested multiplex PCR (NMPCR). Results The presence of hr-HPV was confirmed in 31.13% (n = 33) and 24.52% (n = 26) of the HNC patients by nested multiplex PCR (NMPCR) and HC2 assay respectively. Among hr-HPV positive cases, out of thirteen hr- HPV types analyzed, only two prevalent genotypes, HPV-16 (81.81%) followed by HPV-18 (18.18%) were found. Significant association was observed between hr-HPV infection with alcohol consumption (p <0.001) and tobacco chewing (p = 0.02) in HNC cases. Compared to HPV-18 infection the HPV-16 was found to be significantly associated with tobacco chewing (p = 0.02) habit. Conclusions Our study demonstrated that tobacco chewing and alcohol consumption may act as risk factors for hr-HPV infection in HNCs from the North-East region of India. This was the first study from North-East India which also assessed the clinical applicability of HC2 assay in HNC patient specimens. We suggest that alcohol, tobacco and hr- HPV infection act synergistically or complement each other in the process of HNC development and progression in the present study population.

A fuzzy entropy based neural network classifier for odor identification of alcoholic beverages using tin oxide sensor array

This paper presents a novel method to odor based identification of alcoholic beverages using steady-state responses of a thick film tin oxide sensor array exposed to four different types of whiskies. A neural classifier designed to perform the identification task was trained by incorporating the class information in the training data set in the form of fuzzy entropies of the respective classes. The performance of the proposed classifier has been compared with that of those reported earlier, which generally employed fuzzy membership values to generate class information. The use of fuzzy entropy measure resulted in better identification of the alcoholic beverages as compared to those which are based on fuzzy membership representation. Fuzzy entropy representation also resulted in precise identification of the alcoholic beverages by using reduced number of sensors in the array.

A study of head and neck cancer patients with special reference to tobacco use and educational level

Background: In India, head and neck cancers (HNCs) are common and constitute 20%–30% of all cancers. The most common risk factors are consumption of tobacco and alcohol. Betel nut chewing with or without tobacco is a major risk factor for HNC in India, especially in the Northeast India. Materials and Methods: This was a hospital-based retrospective study to measure the descriptive scenario of HNC cases along with their demographic and risk factor profile. The patients diagnosed from June 01, 2014, to December 31, 2014, were included in the study. The data of patients were analyzed for age, gender, subsites, stage at diagnosis, pattern and prevalence of tobacco usage, and different education level of patients. Chi-square test was performed to assess the association of gender and tobacco habits. Results: One thousand four hundred and twenty-eight patients were included in the study, M: F was 4:1, hypopharynx in males (36.2%) and mouth in females (39.8%) were leading HNC sites, and majority (83.8%) presented in locally advanced stages. Majority of patients (34.1%) and tobacco users (34.7%) were illiterates, and 82.9% of all HNC patients were tobacco users. Males with cancers of the tongue, hypopharynx, and larynx (P < 0.05) were significantly at an increased risk of developing HNC with tobacco consumption. Conclusion: Our findings suggest that improvement in the education level may lead to decline in the use of tobacco and thereby reduction in the burden of HNC patients.

Papillary thyroid carcinoma presenting with mandibular metastasis: An unusual presentation

Mandibular metastasis from papillary carcinoma of the thyroid is extremely rare. We report here a case of metastatic swelling on the mandible due to papillary carcinoma of the thyroid. The patient presented with jaw swelling and the thyroid lesion was an incidental finding on clinical examination. Computed tomogram scan revealed the presence of a contrast enhanced lesion in the thyroid and lytic expansile lesion in the body of the mandible. The diagnosis of papillary thyroid carcinoma (PTC) with mandibular metastasis was made after cytological examination of both the lesions. The patient was treated with surgery followed by radioiodine ablation. In conclusion, metastatic tumor to the jaw from a PTC is an extremely rare phenomenon and in the differential diagnosis of a metastatic jaw swelling small primary tumors of the thyroid should be excluded.

A fuzzy logic based neural network classifier for qualitative classification of odors/gases

This paper presents a novel approach to odor discrimination using data obtained from the responses of thick film tin oxide sensor array fabricated at our laboratory and employing backpropagation algorithm trained artificial neural network based on fuzzy logic. Fuzzy membership values were used as target vectors to the proposed neural classifier. Three different versions of backpropagation algorithm were used to train the network and their performances have been compared. Superior learning and classification performance was obtained using proposed model trained with TRAINLM version of the backpropagation algorithm.

Basaloid squamous carcinoma of the supraglottic larynx with neuro-endocrine features

Basaloid squamous carcinoma (BSC) is a rare aggressive variant of squamous cell carcinoma and occurs mainly at the larynx, oropharynx and tongue of the head and neck region. Neuro-endocrine differentiation of BSC is further rare occurrence in laryngeal cancers. We report here a case of BSC of supraglottic larynx with neuro-endocrine differentiation, which was treated by radiotherapy and its response to treatment.