Nuclear magnetic resonance (NMR) and its derivatives play a pivotal role in molecular analysis across research and clinical domains. However, the intricate nature of NMR data preprocessing, which is integral for accurate analysis, is not easily understood despite the availability of numerous software tools. This comprehensive review aims to unravel the complexities of preprocessing algorithms in both the time and frequency domains. It covers essential steps such as direct current offset removal, eddy current correction, shift and linear prediction, weighting, zero filling, domain transformation, phase error correction, baseline correction, solvent filtering, calibration and alignment, reference deconvolution, binning/bucketing, peak picking, peak fitting/deconvolution, compound identification, integration and quantification, normalization, and transformation. The review uses plain language to enhance accessibility and understanding. By demystifying the algorithms behind these preprocessing steps, we seek to help researchers and practitioners in navigating the nuances of NMR data preprocessing, ultimately fostering better understanding and practical application in molecular analysis.

Automatic modulation recognition (AMR) has a wide range of applications in wireless communication. To solve the problem that the previous methods convert signal modulation recognition into image recognition, leading to increased time costs and information loss, an AMR approach consisting of the improved deep singular value decomposition (K-SVD) denoising algorithm is suggested. First, the effectiveness of the model for random sine wave denoising is demonstrated by simulation. Second, the original I/Q signals are fed into the modified deep K-SVD model for denoising, skipping the complicated image processing steps. Finally, the noise-reduced signals are input into a multi-channel convolutional long short-term neural network to complete the modulation recognition. To solve the slow convergence problem of iterative shrinkage thresholding algorithms in sparse coding, the fast iterative shrinkage thresholding algorithm is adopted to improve the computational efficiency and obtain a better denoising effect. The experiments show that the improved model has an average recognition accuracy of 91.26%at different signal-to-noise ratio (SNRs) from −2 dB to 18 dB, which is better than the state-of-the-art modulation recognition models.

A new vision-based fall detector is proposed that uses the tsfresh tool to generate features from the bounding box motion parameters of an object and performs classification in a sliding window mode. The efficiency of the generated features is demonstrated compared to the primary ones. Using the auto-sklearn library and a generalized dataset compiled from the UR Fall Detection and CAUCAFall datasets, the best human fall detection model is found. This model based on a gradient boosting classifier achieved 96% accuracy, which is not inferior to well-known detection algorithms, but uses only two primary motion parameters to generate secondary features. A principal component analysis-based class separability study showed that for secondary features 99% of the variance is captured by the first 4 principal components, while for primary features, the first 10 principal components contain only 80% of the data variance. Furthermore, the processing time for generating secondary features and making predictions was found to be relatively short, taking only a few seconds per sequence, highlighting the practical applicability of the proposed approach in real-time fall monitoring systems.

Brain tumor is a life-threatening disease, and its early diagnosis can save human life. Computer-aided brain tumor segmentation and localization in magnetic resonance imaging (MRI) images have emerged as pivotal approaches for expediting the disease diagnosis process. In the past few decades, various researchers combined the strengths of convolutional networks and transformer to perform brain tumor segmentation. However, these models require a large number of trainable weights parameters, and there is still scope for performance improvement in them. To bridge these research gaps, this paper proposes a novel hybrid model named “CT-γ-Net” for effective and efficient brain tumor localization. The proposed CT-γ-Net model follows an encoder-decoder structure in which the convolutional encoder (CE) and transformer encoder (TE) are used for encoding, whereas the convolutional decoder (CD) is utilized for decoding the combined output of CE and TE to generate the segmentation masks. In CE and CD components of the CT-γ-Net model, conventional convolutional layers are replaced by depth-wise separable convolutional layers, as these layers significantly reduce trainable weights parameters. The proposed model achieves 95.5% MeanIoU, 94.82% Dice score, and 99.24% pixel accuracy on a publicly available dataset named the Cancer Imaging Archive. These experimental results demonstrate that the CT-γ-Net model outperformed other state-of-the-art research works, despite using roughly 28%fewer trainable weights parameters. Hence, the proposed model’s lightweight nature and its high performance make it a suitable candidate for deployment on mobile devices, facilitating the precise localization of brain tumor regions in MRI images.

In exploration seismic, the seismic velocity is the key to delineating many physical properties of the subsurface. There are ways to calculate the velocity and, most popularly, it is picked manually for any seismic project. The velocity picking method has a few limitations when it comes to its quality, time consumption in this process, and the money spent during the whole work. The main objective of this paper is to provide velocity estimation of the respective region (three-dimensional seismic) derived from the velocity field available in the region from a few 2D seismic lines. The purpose is to avoid manual velocity picking errors and make the overall velocity in the region more geologically consistent with the surrounding data. Even more importantly, a seismic velocity volume assessment model created through this technique can also support any future 3D seismic imaging.

In today’s fiercely competitive business landscape, data have emerged as a precious asset crucial for any company’s growth. It embodies a genuine catalyst for economic and strategic advantages, distinguishing industry leaders from the rest. Prominent organizations recognize the importance of not just amassing data from diverse sources but also harnessing the transformative power of data analytics for informed determination processes. Within this setting, the data lake solution stands as a robust framework handling vast data sources and enabling data investigations to support decision-making tasks. This paper delves into the realm of intelligent data lake management systems designed to overcome the limitations of traditional business intelligence, which struggles to meet the demands of data-driven decision-making. Data lakes excel in the analysis of data from myriad sources, particularly when data cleaning becomes a time-consuming endeavor. Still, managing diverse datasets devoid of a predefined data structure presents a significant challenge, potentially leading to a data lake devolving into a data swamp. Within this article, we adopt the Latent Dirichlet Allocation model to oversee the data lake environment’s handling, processing, analysis, and display of huge datasets. To evaluate the efficacy of our suggested approach, we conducted comprehensive assessments using the topic coherence metric. Our experiments yielded results indicating the superior accuracy of our approach when applied to the tested datasets.

The unavailability of an annotated dataset for a low-resource Ewe language makes it difficult to develop an automated system to appropriately evaluate public opinion on events, news, policies, and regulations. In this study, we collected and preprocessed a low-resourced document-level Ewe sentiment dataset based on social media comments. We used three features learned by word embeddings (Global vectors, word-to-vector, and FastText) rather than hand-crafted features. We further proposed a novel method termed MC2D-CNN+BiLSTM-Attn to detect the exact sentiment feature from the Ewe dataset. Extensive experiments indicate that the proposed method efficiently classifies various sentiments and is superior to benchmark deep learning methods. Results show that in detecting the precise sentiments from raw Ewe textual context, the BiLSTM incorporating Glove outperforms Word2Vec and FastText embedding with an accuracy of 0.727. Furthermore, Attn+BiLSTM and multichannel convolutional neural network methods incorporating the Word2Vec embedding layer perform better than Glove and FastText embedding with an accuracy of 0.848 and 0.896. In contrast, our proposed method with the same Word2Vec embedding recorded 0.949.