Part-of-Speech (POS) Tagging Using Deep Learning-Based Approaches on the Designed Khasi POS Corpus

Part-of-speech (POS) tagging is one of the research challenging fields in natural language processing (NLP). It requires good knowledge of a particular language with large amounts of data or corpora for feature engineering, which can lead to achieving a good performance of the tagger. Our main contribution in this research work is the designed Khasi POS corpus. Till date, there has been no form of any kind of Khasi corpus developed or formally developed. In the present designed Khasi POS corpus, each word is tagged manually using the designed tagset. Methods of deep learning have been used to experiment with our designed Khasi POS corpus. The POS tagger based on BiLSTM, combinations of BiLSTM with CRF, and character-based embedding with BiLSTM are presented. The main challenges of understanding and handling Natural Language toward Computational linguistics to encounter are anticipated. In the presently designed corpus, we have tried to solve the problems of ambiguities of words concerning their context usage, and also the orthography problems that arise in the designed POS corpus. The designed Khasi corpus size is around 96,100 tokens and consists of 6,616 distinct words. Initially, while running the first few sets of data of around 41,000 tokens in our experiment the taggers are found to yield considerably accurate results. When the Khasi corpus size has been increased to 96,100 tokens, we see an increase in accuracy rate and the analyses are more pertinent. As results, accuracy of 96.81% is achieved for the BiLSTM method, 96.98% for BiLSTM with CRF technique, and 95.86% for character-based with LSTM. Concerning substantial research from the NLP perspectives for Khasi, we also present some of the recently existing POS taggers and other NLP works on the Khasi language for comparative purposes.

3rd and 11th orders of accuracy of ‘linear’ and ‘quadratic’ elements for Poisson equation with irregular interfaces on Cartesian meshes

Purpose The purpose of this paper is as follows: to significantly reduce the computation time (by a factor of 1,000 and more) compared to known numerical techniques for real-world problems with complex interfaces; and to simplify the solution by using trivial unfitted Cartesian meshes (no need in complicated mesh generators for complex geometry). Design/methodology/approach This study extends the recently developed optimal local truncation error method (OLTEM) for the Poisson equation with constant coefficients to a much more general case of discontinuous coefficients that can be applied to domains with different material properties (e.g. different inclusions, multi-material structural components, etc.). This study develops OLTEM using compact 9-point and 25-point stencils that are similar to those for linear and quadratic finite elements. In contrast to finite elements and other known numerical techniques for interface problems with conformed and unfitted meshes, OLTEM with 9-point and 25-point stencils and unfitted Cartesian meshes provides the 3-rd and 11-th order of accuracy for irregular interfaces, respectively; i.e. a huge increase in accuracy by eight orders for the new 'quadratic' elements compared to known techniques at similar computational costs. There are no unknowns on interfaces between different materials; the structure of the global discrete system is the same for homogeneous and heterogeneous materials (the difference in the values of the stencil coefficients). The calculation of the unknown stencil coefficients is based on the minimization of the local truncation error of the stencil equations and yields the optimal order of accuracy of OLTEM at a given stencil width. The numerical results with irregular interfaces show that at the same number of degrees of freedom, OLTEM with the 9-points stencils is even more accurate than the 4-th order finite elements; OLTEM with the 25-points stencils is much more accurate than the 7-th order finite elements with much wider stencils and conformed meshes. Findings The significant increase in accuracy for OLTEM by one order for 'linear' elements and by 8 orders for 'quadratic' elements compared to that for known techniques. This will lead to a huge reduction in the computation time for the problems with complex irregular interfaces. The use of trivial unfitted Cartesian meshes significantly simplifies the solution and reduces the time for the data preparation (no need in complicated mesh generators for complex geometry). Originality/value It has been never seen in the literature such a huge increase in accuracy for the proposed technique compared to existing methods. Due to a high accuracy, the proposed technique will allow the direct solution of multiscale problems without the scale separation.

Vigorous IDS on Nefarious Operations and Threat Analysis Using Ensemble Machine Learning

The geometric increase in the usage of computer networking activities poses problems with the management of network normal operations. These issues had drawn the attention of network security researchers to introduce different kinds of intrusion detection systems (IDS) which monitor data flow in a network for unwanted and illicit operations. The violation of security policies with nefarious motive is what is known as intrusion. The IDS therefore examine traffic passing through networked systems checking for nefarious operations and threats, which then sends warnings if any of these malicious activities are detected. There are 2 types of detection of malicious activities, misuse detection, in this case the information about the passing network traffic is gathered, analyzed, which is then compared with the stored predefined signatures. The other type of detection is the Anomaly detection which is detecting all network activities that deviates from regular user operations. Several researchers have done various works on IDS in which they employed different machine learning (ML), evaluating their work on various datasets. In this paper, an efficient IDS is built using Ensemble machine learning algorithms which is evaluated on CIC-IDS2017, an updated dataset that contains most recent attacks. The results obtained show a great increase in the rate of detection, increase in accuracy as well as reduction in the false positive rates (FPR).

Robust Lane Detection and Tracking Algorithm for Steering Assist Systems

Modern vehicles rely on a multitude of sensors and cameras to both understand the environment around them and assist the driver in different situations. Lane detection is an overall process as it can be used in safety systems such as the lane departure warning system (LDWS). Lane detection may be used in steering assist systems, especially useful at night in the absence of light sources. Although developing such a system can be done simply by using global positioning system (GPS) maps, it is dependent on an internet connection or GPS signal, elements that may be absent in some locations. Because of this, such systems should also rely on computer vision algorithms. In this paper, we improve upon an existing lane detection method, by changing two distinct features, which in turn leads to better optimization and false lane marker rejection. We propose using a probabilistic Hough transform, instead of a regular one, as well as using a parallelogram region of interest (ROI), instead of a trapezoidal one. By using these two methods we obtain an increase in overall runtime of approximately 30%, as well as an increase in accuracy of up to 3%, compared to the original method.

A novel Technique for Improving the Angular Accuracy of Doppler VOR Receivers

Doppler VOR (D-VOR) transmitters are used as navigation aids in aviation. They transmit an omnidirectional phase reference in an amplitude-modulated (AM) sideband and directional phase information on a frequency-modulated (FM) subcarrier. In an airborne D-VOR navigation receiver, a directional information (azimuth angle) related to the position of the aircraft and the location of the transmitter can be derived from the difference of these two phase signals. In this work, the accuracy of AM and FM phase signals is firstly investigated analytically and afterwards verified by measurements. It will be shown that in established procedures, phase inaccuracy is dominated by the AM signal, since the FM signal is about 21 dB less noisy. Subsequently, a novel method is presented that improves the accuracy of the azimuth angle by orders of magnitude in case of D-VOR transmitters. This new method inherently reduces noise of the AM phase and thus yields a significant increase in accuracy. As a result, the remaining FM phase uncertainty becomes dominant for the total uncertainty of the bearing indication. Finally, the application of the new method to real measured signals confirms the theoretical expectations.

Penerapan Metode C4.5 Berbasis Particle Swarm Optimization Untuk Memprediksi Penjualan Obat Pada Apotek Bunda Azka

The application of the C4.5 Algorithm based on Particle Swarm Optimization to classify the level of sales of drugs that are often sold at the Bunda Azka Pharmacy, is a strategic thing to reduce the problems experienced by the pharmacy. Classify the level of sales of drugs sold using the C4.5 method. based on particle swarm optimization, to find out whether the C4.5 method based on particle swarm optimization (PSO) can optimize drug sales in the future. This research method uses a descriptive method, namely by conducting case study research by studying activities in the field, observing and interviewing stakeholders. in the initial step of this research is the determination of the attributes that will be processed into data mining with the help of rapidminer tools, this study the author uses the KDD model as a standardization in the data mining process. at the pharmacy. The data will later be processed using the c4.5 algorithm based on Particle Swarm Optimization to find the accuracy results of the prediction of the data. The data sample used is the number of 65 drug transaction records at the Bunda Azka Pharmacy. In the test results, the accuracy of Particle Swarm Optimization was 78.10%, for class recall drug sales was 72.50% and after using Particle Swarm Optimization increased to 78.33%, while precision had an accuracy of 77.92% and after using Particle Swarm Optimization increased to 80.33%. From the results of testing with Particle Swarm Optimization, there is an increase in accuracy of 7.15% from the research application of the C4.5 Method Based on Particle Swarm Optimization to Predict Drug Sales at Bunda Azka Pharmacy.

A Resilient and Hierarchical IoT-based Solution for Stress Monitoring in Everyday Settings

<div><div><div><p>The conventional mental healthcare regime follows a reactive, symptom-focused, and episodic approach in a non-continuous manner, wherein the individual discretely records their biomarker levels or vital signs for a short period prior to a subsequent doctor’s visit. Recognizing that each individual is unique and requires continuous stress monitoring and personally tailored treatment, we propose a holistic hybrid edge-cloud Wearable Internet of Things (WIoT)-based online stress monitoring solution to address the above needs. To eliminate the latency associated with cloud access, appropriate edge models—Spiking Neural Network (SNN), Conditionally Parameterized Convolutions (CondConv), and Support Vector Machine (SVM)—are trained, enabling low-energy real-time stress assessment near the subjects on the spot. This work leverages design-space exploration for the purpose of optimizing the performance and energy efficiency of machine learning inference at the edge. The cloud exploits a novel multimodal matching network model that outperforms six state-of-the-art stress recognition algorithms by 2-7% in terms of accuracy. An offloading decision process is formulated to strike the right balance between accuracy, latency, and energy. By addressing the interplay of edge-cloud, the proposed hierarchical solution leads to a reduction of 77.89% in response time and 78.56% in energy consumption with only a 7.6% drop in accuracy compared to the IoT-Cloud scheme, and it achieves a 5.8% increase in accuracy on average compared to the IoT-Edge scheme.</p></div></div></div>

Arrhythmia Detection using Deep Belief Network Extracted Features from ECG Signals

Arrhythmia is a disorder of the heart caused by the erratic nature of heartbeats occurring due to conduction failures of the electrical signals in the cardiac muscle. In recent years, research galore has been done towards accurate categorization of heartbeats and electrocardiogram (ECG)-based heartbeat processing. Accurate categorization of different heartbeats is an important step for diagnosis of arrhythmia. This paper primarily focuses on effective feature extraction of the ECG signals for model performance enhancement using an unsupervised Deep Belief Network (DBN) pipelined onto a simple Logistic Regression (LR) classifier. We compare and evaluate the results of data feature enrichment against plain, non-enriched data based on the metrics of precision, recall, specificity, and F1-score and report the extent of increase in performance. Also, we compare the performance of the DBN-LR pipeline with a 1D convolution technique and find that the DBN-LR algorithm achieves a 5% and 10% increase in accuracy when compared to 1D convolution and no feature extraction using DBN respectively.

Arrhythmia Detection Using Deep Belief Network Extracted Features From ECG Signals

Arrhythmia is a disorder of the heart caused by the erratic nature of heartbeats occurring due to conduction failures of the electrical signals in the cardiac muscle. In recent years, research galore has been done towards accurate categorization of heartbeats and electrocardiogram (ECG)-based heartbeat processing. Accurate categorization of different heartbeats is an important step for diagnosis of arrhythmia. This paper primarily focuses on effective feature extraction of the ECG signals for model performance enhancement using an unsupervised Deep Belief Network (DBN) pipelined onto a simple Logistic Regression (LR) classifier. We compare and evaluate the results of data feature enrichment against plain, non-enriched data based on the metrics of precision, recall, specificity, and F1-score and report the extent of increase in performance. Also, we compare the performance of the DBN-LR pipeline with a 1D convolution technique and find that the DBN-LR algorithm achieves a 5% and 10% increase in accuracy when compared to 1D convolution and no feature extraction using DBN respectively.

Explaining transformer-based image captioning models: An empirical analysis

Image Captioning is the task of translating an input image into a textual description. As such, it connects Vision and Language in a generative fashion, with applications that range from multi-modal search engines to help visually impaired people. Although recent years have witnessed an increase in accuracy in such models, this has also brought increasing complexity and challenges in interpretability and visualization. In this work, we focus on Transformer-based image captioning models and provide qualitative and quantitative tools to increase interpretability and assess the grounding and temporal alignment capabilities of such models. Firstly, we employ attribution methods to visualize what the model concentrates on in the input image, at each step of the generation. Further, we propose metrics to evaluate the temporal alignment between model predictions and attribution scores, which allows measuring the grounding capabilities of the model and spot hallucination flaws. Experiments are conducted on three different Transformer-based architectures, employing both traditional and Vision Transformer-based visual features.