Search

Precision medicine (PM) is an emerging approach for disease prevention, diagnosis, treatment, and management that holds promise for improving the future of sleep healthcare. This concept of PM is guided by evidence-based medicine for treatment decisions by taking into account individual variability in genes, environment, and lifestyle factors. Chronic sleep loss affects millions of people each year, representing an important public health issue. The same approach can be applied in sleep medicine to treat sleep disorders where the physicians and scientists can make accurate predictions concerning the best strategy for an individual/groups in the prevention, diagnosis, treatment, and management. This review aims to explore the emerging role of PM and its application in sleep medicine through the integration of innovative technology such as artificial intelligence (AI), machine learning (ML), blockchain technology which aids in the diagnosis and therapeutic modalities. An extensive literature search was done in all the major databases such as PubMed/MEDLINE, Web of Science, Scopus, and Google scholar search engines for the keywords “Precision Medicine” AND “Sleep disorders” OR “Sleep medicine,” and the information is extracted and discussed in this review. Though the PM in Sleep Medicine application is in nascent stages, it is very promising in sleep medicine and is expected in many areas of sleep healthcare in the near future. The application of AI and ML in the concept of PM has revamped the testing, diagnosis, and treatment modalities for sleep disorders which hold a promise to translate these benefits to the global population through sustained efforts of innovation.

In the recent years analysis of Electroencephalogram (EEG) signal has played vital role in automatic sleep scoring technique. Classification of sleep stages help in understanding sleep related issues. Manual analysis of sleep scoring is costly, tedious and time-consuming process. It is essential to design an automatic sleep scoring technique which is convenient to patients and simplifies the diagnostic process using EEG signals. Implementation of such technique enable experts to identify sleep related issues. In this paper, EEG signals are recorded for 60 subjects and preprocessed using Infinite Impulse Response (IIR) filter. Sleep stages are classified into three major stages viz stage 1, 2 and 3 with 10 s epoch duration using statistical features of EEG and machine learning algorithms with five-fold cross validation. Proposed method is more feasible for physicians to diagnose sleep disorders and proves to be the better technique with improved accuracy compared to other existing studies.

This paper centers around blockchain-based health services frameworks and presents an extensive review on current work, distinguishing existing and arising difficulties in sleep medicine. We attempt to combine health care, especially sleep medicine, allied with blockchain technology. It addresses the capability of blockchain innovation and how it can potentially be a game-changer in sleep medicine. In the field of sleep health, blockchain technology can improve electronic medical records and health information exchange. Examinations around blockchain are unraveling digital identity, privacy, protection, and security issues in the sleep medical services field. With educated information regarding a patient’s history, doctors can settle on brief clinical choices for secure and more effective consideration. Blockchain improves persistent results, improve consistency, lower costs, and empower better utilization of sleep medicine services related information. The framework will guarantee continued assurance and security concerning medical care information necessities in general and sleep medicine in specific.

Automated classification of sleep stages is in demand to overcome the limitations of manual sleep stage classification. Analyzing sleep stages manually using neurophysiological signals and inspecting visually is very difficult, time-consuming process. Many techniques have been proposed already in the past two decades. Sleep experts, physicians do not have assurance with such techniques concerned with accuracy, specificity and sensitivity. The aim of the paper is to propose an efficient technique for sleep stage classification based on Electroencephalogram (EEG) signals analysis using machine learning algorithms by considering 10 s of epochs. EEG signals have played significant role in automatic sleep stage classification. EEG signals are filtered and decomposed into frequency sub-bands using band-pass filter. Statistical features are extracted and trained with Decision Tree, Support Vector Machine and Random Forest algorithms with different testing dataset percentage. Results show Random Forest algorithm achieves 97.8% of accuracy.

One of the dreadful diseases in the medical industry is prostate cancer and it is growing at a higher rate among men. Hence, it is a necessity to detect cancer in an early stage due to the alarming increase in the reports. Various techniques are introduced for effective prostate cancer detection using histopathology images. Accordingly, an automatic method is proposed for segmenting and classifying prostate cancer. This paper presents the prostate cancer detection method using histopathology images by proposing the fuzzy-based salp swarm algorithm-based rider neural network (SSA-RideNN) classifier. At first, the input image is fed to the pre-processing step and then the segmentation is performed using Color Space transformation and thresholding. Once the segmentation is performed, the feature extraction is done by extracting multiple kernel scale invariant feature transform features along with the texture features that are extracted based on local optimal oriented pattern descriptor to improve the classification accuracy. Finally, the prostate cancer detection is done based on the proposed fuzzy-based SSA-RideNN, which is developed by integrating fuzzy approach with SSA-RideNN. The performance of the proposed fuzzy-based SSA-RideNN is analyzed using sensitivity, specificity, and accuracy. The proposed fuzzy-based SSA-RideNN produces the maximum accuracy of 0.9190, a maximum sensitivity of 0.9084, and maximum specificity of 0.9, indicating its superiority.

Background & Objective: Location of sensors is an important information in wireless sensor networks for monitoring, tracking and surveillance applications. The accurate and quick estimation of the location of sensor nodes plays an important role. Localization refers to creating location awareness for as many sensor nodes as possible. Multi-stage localization of sensor nodes using bio-inspired, heuristic algorithms is the central theme of this paper. Methodology: Biologically inspired heuristic algorithms offer the advantages of simplicity, resourceefficiency and speed. Four such algorithms have been evaluated in this paper for distributed localization of sensor nodes. Two evolutionary computation-based algorithms, namely cultural algorithm and the genetic algorithm, have been presented to optimize the localization process for minimizing the localization error. The results of these algorithms have been compared with those of swarm intelligence- based optimization algorithms, namely the firefly algorithm and the bee algorithm. Simulation results and analysis of stage-wise localization in terms of number of localized nodes, computing time and accuracy have been presented. The tradeoff between localization accuracy and speed has been investigated. Results: The comparative analysis shows that the firefly algorithm performs the localization in the most accurate manner but takes longest convergence time. Conclusion: Further, the cultural algorithm performs the localization in a very quick time; but, results in high localization error.

The advancement of technology has made our life easy and perfect. During the exploration of technology, many new technologies have taken control over the world; one among them is artificial intelligence, which plays a very important role in today’s world. During the development of any product in AI, errors are common specifically during coding. The programmer faces errors and issues while developing code, for which the programmer needs to search the error, debug it, which is time-consuming process. When the program is being developed, the errors or the issues in the program must be solvable by a single click. The algorithm proposed in the paper takes the error statement as input and finds the best solution. With the help of similarity matching and natural language processing, the database is searched for the most similar error and returns you the result. Word frequency and the corresponding word cloud are plotted. If in case the requirement is not matched or less similar data, then the system extracts data from various resources like World Wide Web and responds. This approach helps the user to save time and find the most accurate solution for the error encountered.

There is very limited research going on in Internet-based cognitive behavioral therapy (iCBT). There are also many other psychological, health, and behavioral issues that need to be resolved using an Internet based platform. Although in some of the research one or the other Internet-based cognitive platform is used, there is no research or article describing the various platforms that are available for researchers to carry out their work. This article aims to bridge this gap. In this article an outline of the various existing Internet-based cognitive platforms are provided. The various benefits and uses of particular platforms in areas best suited are also provided with a comparison. We also shed some light on the existing problems of these techniques and the limitations of the platforms. Various platforms along with solutions to the behavioral problems are discussed in this article.

Farmers in India do not get a fair price for their yield. The deal is via middle agents which doesn’t help farmers in making a good profit. Moreover, farmers are opting farming practices that incur high input costs to them by using chemical pesticides. The aim of this paper is to build an android application for recognition of agriculture produce using Deep Learning to provide a platform for farmers to sell and give them a fair share for their produce. At the consumer end, the consumers are guaranteed 100% fresh produce that is chemical-free by adopting Zero Budget Natural Farming (ZBNF). This project will be implemented in the buying–selling platform for agricultural products. The application will be enhanced to display the price of the product when the farmer projects his phone camera onto his produce. He can accept the deal if he is getting a fair share for the produce and thus totally eliminate the involvement of middle agents. In supermarkets, the cashier manually enters the code or scans the barcode attached to the product to print the bill. Sometimes the fruits and vegetables may not have barcodes. By using this application, items can be identified based on their appearance alone. Instead of entering the code or scanning the barcode manually, the phone camera is projected onto the product, the app then recognizes the product. It works even if they are in front for a short duration and are not absolutely still.

Epilepsy is a neurological disorder noticeable by sudden repeated episodes of sensory commotion related with anomalous electrical activity in the brain. Electroencephalogram (EEG) based seizure detection system is a promising non-invasive diagnosis option for refractive epilepsy. EEG signals in this system are decomposed and classified to improve the diagnostic accuracy as compared to human diagnosis. There is a need to explore reliable and faster classification algorithms to develop real time seizure detection system. Due to non linear nature of EEG, non-linear techniques are used to examine the EEG signals. The paper proposes a non linear technique of EEG feature extraction based on the Recurrence Plots (RP), and Recurrence Quantification Analysis (RQA) parameters derived from the RP have been used to categorize the EEG signal information as pre-ictal, ictal and normal classes. RP is an advanced technique of nonlinear data analysis and RQA parameters of RP compute the significant features of signals. These features have been classified using Artificial Neural Network (ANN), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM). In order to improve the current information transfer rate of seizure detection system, the SVM which classifies EEG signals with highest speed with accuracy of 91.2 % is selected for classification.

Agriculture in India faces challenges due to small land- holdings, inadequate resources and lack of agrotechnological information. Earth observations comprising satellite, aerial, and in situ systems have recently ushered in studying, understanding, and monitoring of natural resources with an aim to unfold the intricate behavior of the complex earth’s dynamic processes. In this regard, the research in satellite remote sensing along with aerial photographs have evolved as a multidisciplinary theme useful for this purpose. This paper describes the basic aspects of remote sensing and geographic information systems technology as applicable to precision agriculture making it reality.

The detection of seizure onset and events using electroencephalogram (EEG) signals are important tasks in epilepsy research. The literature available on seizure detection has discussed the implementation of advanced signal processing algorithms using tools accessed over the cloud. However, seizure monitoring application needs near sensor processing due to privacy and latency issues. In this paper, a real time seizure detection system has been implemented using an embedded system. The proposed system is based on ensemble empirical mode decomposition (EEMD) and tunable-Q wavelet transform (TQWT) algorithms. The analysis and classification of non-stationary EEG signals require the wavelet transform with high Q-factor. However, direct use of TQWT increases the computational complexity of feature extraction from multivariate EEG signals. In this paper, the first step is to process the signal by using EEMD to obtain 8 intrinsic mode functions (IMFs). The Kraskov (KraEn), sample (SampEn), and permutation (PermEn) entropy features of IMFs are extracted and based on optimum values, and 4 IMFs are decomposed using TQWT. Secondly, centered correntropy (CenCorrEn) features of the 1 st and 16 th sub-band of TQWT have been used as classifier inputs. The performance of multilayer perceptron neural networks (MLPNN), least squares support vector machine (LSSVM), and random forest (RF) classifiers has been tested on the multichannel EEG data recorded from a local hospital. The RF classifier has produced the highest accuracy of 96.2% in classifying the signals. The proposed scheme has been employed in developing an embedded seizure detection system to assist neurologists in making seizure diagnostic decisions.

Epilepsy is a brain disorder, characterized by transitory and impulsive electrical signal of the brain. The electroencephalogram (EEG)-based seizure detection system used for automated diagnosis of epilepsy requires optimum classification of signals. This paper presents an optimized method for classification as normal and epileptic signals using Empirical-Mode Decomposition (EMD) technique. The Intrinsic-Mode Functions (IMFs) are few symmetric and band-limited signals obtained by applying EMD to the signals. However, optimum selection of IMF features is crucial step in deciding feature set for classification. The 95% confidence ellipse area is calculated from the Second-Order Difference Plot (SODP) of selected IMFs to form features for classification. The feature space is used by the Cosine Similarity Measure Support Vector Machine (CSM-SVM) classifier with optimum feature selection. It is observed that the features formed using ellipse area of dissimilar combination of IMFs have given superior classification performance on EEG data available from the Bonn University, Germany.

Medical industry reports prostate cancer as common and high among men and alarms the necessity for detecting prostate cancer for which the required morphology is extracted from the histopathology images. Commonly, the Gleason grading system remains a perfect factor for grading prostate cancer in men, but pathologists suffer from minute inter- and intra-observer variations. Thus, an automatic method for segmenting and classifying prostate cancer is modeled in this paper. The significance of the developed method is that the segmentation and classification are gland-oriented using the Color Space (CS) transformation and Salp Swarm Optimization Algorithm-based Rider Neural Network (SSA-RideNN). The gland region is considered as the morphology for cancer detection from which the maximal significant regions are extracted as features using multiple-kernel scale-invariant feature transform (MK-SIFT). Here, the RideNN classifier is trained optimally using the proposed Salp–Rider Algorithm (SRA), which is the integration of Salp Swarm Optimization Algorithm (SSA) and Rider Optimization Algorithm (ROA). The experimentation is performed using the histopathology images and the analysis based on sensitivity, accuracy, and specificity reveals that the proposed prostate cancer detection method acquired the maximal accuracy, sensitivity, and specificity of 0.8966, 0.8919, and 0.8596, respectively.

Secure transmitting of data is the most challenging task in network communication. Cryptography is a mechanism to provide message or data confidentiality (i.e. secure transmission of data) and it is an emerging technology, which is important for network security. Cellular network is the most important field of communication. Day by day so many research works are conducting on cryptography and still it's in developing phases. Hence considerable research technique or effort is still needed for secure communication in cellular networks. In this proposed work new cryptosystem is proposed based on the combination of Lorenz equations of chaos theory and KASUMI block cipher. In cryptography random numbers plays an essential role and also in so many fields. In our proposed work random numbers are generated based on chaos theory using Lorenz equations. Generated random numbers are tested using NIST test suite in order to check the randomness. KASUMI block cipher is considered for encryption of the data. The performance evaluation of encrypted data obtained from the proposed method is analyzed based on three parameters like balanced output, Hamming distance and Avalanche effect. An experimental result gives best randomness resulting in improved performance in cryptosystem.

Epilepsy is a chronic brain disorder recognized by amalgamation of sudden transient electrical disturbance. The electroencephalogram (EEG) is an relevant tool for analyzing brain related disorders. Currently, manual reading of EEG is widely adopted by neurologists to diagnose epilepsy and related disorders. The process is erroneous as it involves fatigues due to continuous monitoring of nonstationary signals. The automated seizure detection may assist neurologist to automate the process and diagnose seizure signals with high accuracy. The nonlinearity of the EEG signals is evaluated by decomposing the signals for various types of filters according to the oscillatory behaviour of the signals. The computation of spectral features from the subbands obtained from Discrete Wavelet Transform (DWT) are used as a feature for classifying the different classes of test signals. In this work, two different classification problems have been considered on bivariate signals. First problem is normal (N) and ictal (I) and second is normal (N), inter-ictal (IC) and ictal (I). Features obtained from the EEG signals of these classes are fed to the input of three different classifiers namely, Multilayer Perceptron Artificial Neural Networks (MLPNN) and Least Squares Support Vector Machine (LSSVM). For N-I and N-IC-I classes, we achieved 97.8% classification accuracy using MLPNN on focal and non-focal data from the University of Bern, Barcelona.

Objectives: The aim of present study is to analyze assess the awareness about forensic odontology among dental practitioners in center part of India. Subjects and Methods: A cross-sectional study was conducted in a sample of 100 dental practitioners in Bhilai-Durg and data was collected by means of a questionnaire. Results: About 30% of dental practitioners not maintain dental records in their clinic, 70% maintained dental records. Nearly, 60% dental practitioners use the appropriate method for diagnosis, while rest are not. Sixty-five percent dental practitioners know the accurate and sensitive way of identify individuals. Thirty percent dental practitioner did not know the significance of bite-mark patterns of the teeth, about 75% dental practitioners did not aware that they could testify as an expert witness in the court of law. Only 15% dental practitioners have formal training in collecting, evaluating, and presenting dental evidence. Seventy-five percent dental practitioners not confident to deal with forensic cases. Conclusions: Our study revealed inadequate knowledge, lack of awareness about forensic odontology, among dental practitioners in Chhattisgarh.

Accurate localization of randomly deployed sensor nodes is critically important in wireless sensor networks (WSNs) deployed for monitoring and tracking applications. The localization challenge has been posed as a multidimensional global optimization problem in earlier literature. Many swarm intelligence algorithms have been proposed for accurate localization. The untapped vast potential of the artificial bee colony (ABC) algorithm has inspired the research presented in this paper. The ABC algorithm has been investigated as a tool for anchor-assisted sensor localization in WSNs. Results of Matlab simulation of ABC-based multistage localization have been presented. Further, the results are compared with those of the localization method based on the particle swarm optimization (PSO) algorithm. A comparison of the performances of ABC and PSO algorithms has been presented in terms of the number of nodes localized, localization accuracy and the computation time. The results show that the ABC algorithm delivers higher accuracy of localization than the PSO algorithm does; but, it takes longer to converge. This results in a trade off between speed and accuracy of localization in WSNs.

Multidimensional optimization is critically important in engineering, economics and other disciplines. There are several deterministic approaches to optimization, each of which has its own pros and cons. Swarm intelligence-based optimization algorithms have been gained popularity for their effectiveness and resource efficiency. Two such popular algorithms, namely artificial bee colony (ABC) and particle swarm optimization (PSO) have been investigated in this paper. These algorithms have been implemented to minimize a few unimodal and multimodal benchmark functions. Results have been analyzed and the comparative analysis has been performed in terms of quality of solutions and computing time. Matlab simulation results show that the ABC algorithm delivers more accurate optimization than PSO does; but it suffers from delayed convergence. On the other hand, PSO is faster; but its accuracy is relatively inferior.

Epilepsy is a general neural disorder identified by manifestation of sudden transient electrical disturbance of the brain. The electroencephalogram (EEG) is an important parameter for analyzing brain actions. The understanding of complex behaviour of the neural system is possible with the help of EEG. The EEG is composed of electrical potentials arising from several neurons. A unique topography onto the scalp is result of projection of each source, including separate neural clusters and artifacts from blink or pulse. These scalp maps are mixed according to the principle of linear superposition. The paper explains the development of adaptive filtering technique for eliminating artifacts from EEG signals. Two adaptive techniques have been developed for applying to EEG signals. An adaptive algorithm is used because artifacts are non-periodic and non-stationary by nature. Using Mean Square Error (MSE) and the computational time a comparative study is made to assess the performances of the techniques. The results are compared with other EEG pre-processing methods such as Independent Component Analysis (ICA) and Principal Component Analysis (PCA). The adaptive filtering appears to be very fast but with compromise on accuracy. Therefore, for practical applications in which speed is important than accuracy, adaptive filtering can be employed.

Microbial forensics is a naïve branch that involves multi-disciplinary approach to detection, tracing and evidencing the bio crime, with a predominant microbiological approach by studying evidence from inadvertent microorganism or its toxins released in bioterrorism act, biocrime, or for attribution purposes using advanced molecular techniques. Methods for identification and attribution of potential microbial weapons is challenging and forensic microbiological investigations involves crime scene investigation, chain of custody practices, evidence collection, handling and preservation, evidence shipping, analysis of evidence, interpretation of results, and court presentation. This field is emerging as a necessary for civil security rather than optional. In 21st century, pathogens are readily accessible, and technology is making their use as a weapon more feasible. As an preventive measures, it is important to strengthen microbial forensic capabilities. The sharing of data collected and validated will greatly improve the practice of microbial forensics. Forensic scientists worldwide should contribute to the field of microbial forensics and enhance its capabilities to aid in bringing perpetrators of these heinous attacks to justice. International and National collaborative approaches can be done by setting up a national and international reference laboratory, transparency of analysis.

Impacted teeth are teeth which remain embedded in the jaws past their normal eruption time or which have been blocked from their normal eruption path because of crowding of adjacent teeth or lack of enough jaw size to accommodate their eruption. Impacted teeth can cause a number of problems if left in place. Dermatoglyphics is the study of skin patterns and finger ridges that present on the fingers, toes and the soles. Fingerprint patterns of both hands were analyzed among ten patients with impacted teeth seen clinically and radiographically and equal number of healthy subjects. This study showed that tented arch pattern in index fingers of both the hands has been observed in impacted subjects thus serving as an indicator of genetic susceptibility in the incidence of dental impaction.

This paper proposes a pseudo random number generator using Elman neural network. The proposed neural network is a recurrent neural network able to generate pseudo-random numbers from the weight matrices obtained from the layer weights of the Elman network. The proposed method is not computationally demanding and is easy to implement for varying bit sequences. The random numbers generated using our method have been subjected to frequency test and ENT test program. The results show that recurrent neural networks can be used as a pseudo random number generator(prng).