Multimodal Gait Abnormality Recognition Using a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) Network Based on Multi-Sensor Data Fusion.

Global aging leads to a surge in neurological diseases. Quantitative gait analysis for the early detection of neurological diseases can effectively reduce the impact of the diseases. Recently, extensive research has focused on gait-abnormality-recognition algorithms using a single type of portable sensor. However, these studies are limited by the sensor's type and the task specificity, constraining the widespread application of quantitative gait recognition. In this study, we propose a multimodal gait-abnormality-recognition framework based on a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) network. The as-established framework effectively addresses the challenges arising from smooth data interference and lengthy time series by employing an adaptive sliding window technique. Then, we convert the time series into time-frequency plots to capture the characteristic variations in different abnormality gaits and achieve a unified representation of the multiple data types. This makes our signal processing method adaptable to several types of sensors. Additionally, we use a pre-trained Deep Convolutional Neural Network (DCNN) for feature extraction, and the consequently established CNN-BiLSTM network can achieve high-accuracy recognition by fusing and classifying the multi-sensor input data. To validate the proposed method, we conducted diversified experiments to recognize the gait abnormalities caused by different neuropathic diseases, such as amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD). In the PDgait dataset, the framework achieved an accuracy of 98.89% in the classification of Parkinson's disease severity, surpassing DCLSTM's 96.71%. Moreover, the recognition accuracy of ALS, PD, and HD on the PDgait dataset was 100%, 96.97%, and 95.43% respectively, surpassing the majority of previously reported methods. These experimental results strongly demonstrate the potential of the proposed multimodal framework for gait abnormality identification. Due to the advantages of the framework, such as its suitability for different types of sensors and fewer training parameters, it is more suitable for gait monitoring in daily life and the customization of medical rehabilitation schedules, which will help more patients alleviate the harm caused by their diseases.

The accumulation and toxicity of ZIF-8 nanoparticles in Corbicula fluminea.

Metal-organic frameworks (MOFs) are promising new materials that have been intensively studied and possibly applied to various environmental remediation. However, little is known about the fate and risk of MOFs to living organisms in the water environment. Here, the toxic effects of ZIF-8 nanoparticles (NPs) on benthic organisms were confirmed by sub-chronic toxicity experiments (7 and 14 days) using Corbicula fluminea as the model organism. With exposure doses ranging from 0 to 50 mg/L, ZIF-8 NPs induced oxidative stress behaviors similar to the hormesis effect in the tissues of C. fluminea. The oxidative stress induced by ZIF-8 NPs and the released Zn2+ was the crucial cause of the toxic effects. Besides, we also found that the ZIF-8 NPs and dissolved Zn2+ may result in different mechanisms of toxicity and accumulation depending on the dosages. The Zn2+ release rate of ZIF-8 NPs was high at low dosages, leading to a higher proportion of Zn2+ taken up by C. fluminea than the particulate ZIF-8. Conversely, at high dosages, C. fluminea mainly ingested the ZIF-8 NPs and resulted in increased mortality. The results have important implications for understanding the fate and biological effects of ZIF-8 in natural aquatic environments.

Insights into aqueous reduction of Cr(VI) by biochar and its iron-modified counterpart in the presence of organic acids.

Chromium (Cr) pollution in water has become an environmental and social problem because of the highly toxic nature of Cr(VI). Biochar has been widely used in Cr-containing wastewater treatment due to its adsorption advantage and intrinsic electron-donating ability. In this paper, Cr(VI) was taken as the target pollutant, and corn-straw derived biochar (BC) and its iron-modified counterpart (BC-Fe) were taken as the main adsorbents. The effects of fulvic acid (FA) and lactic acid (LA) on the adsorption efficiency of BC and BC-Fe in aqueous solution were discussed, and the internal reaction mechanism was revealed by SEM, FTIR, XPS, and Zeta potential analysis. The results showed that the BC-Fe pyrolyzed at 600 °C (i.e., BC-Fe600) had good magnetic property and adsorption effect across a wide pH range (pH 3-9) (the maximum removal efficiency was 96%). At the same time, LA had a concentration-dependent promoting effect on Cr(VI) adsorption in the BC600. However, the addition of FA and LA both inhibited the adsorption of Cr(VI) by BC-Fe600 at pH = 5 and 7, with LA showing a more inhibiting effect on Cr(VI) removal (decreased by 16.09% at pH 5) than FA (decreased by 2.09% at pH 5). The addition of FA and LA caused the surface potential of BC-Fe600 to drop, resulting in an increasing electrostatic repulsion between Cr(VI) and the material. However, LA increased the reduction of Cr(VI) on BC-Fe600, possibly through the combined effects of the electron-donating ability of LA and the photolysis of Fe(III)-lactate complexes.

Removal of Cr(VI) by polyaniline embedded polyvinyl alcohol/sodium alginate beads - Extension from water treatment to soil remediation.

Efficient nano-scale chromium (Cr) remediating agents used in the water industry may find their application in soil difficult because of the strong aggregation effect. In this study, a millimeter-sized PANI/PVA/SA composite (PPS) was synthesized by embedding polyaniline (PANI) into polyvinyl alcohol (PVA)/sodium alginate (SA) gel beads. Additionally, the PPS was used to recover hexavalent chromium (Cr(VI)) contaminated water and soil to study the remediation impacts and mechanism. Results showed that the PPS was an irregular sphere with a pore size of 24.24 nm and exhibited strong adsorption capacity (83.1 mg/g) for removing Cr(VI) in water. The Cr(VI) adsorption by PPS could be well described with the pseudo-second-order kinetics and the Redlich-Peterson isotherm model, indicating that the chemical reactions were the controlling step in the Cr(VI) adsorption process. PPS also exhibited excellent physicochemical properties (< 13 mg/L TOC release) and reusability (efficiency of 95.25% after four runs) for Cr(VI) removal. Soil incubation results showed that the 5% PPS (5PPS) treatment could efficiently remove 24.17% of total Cr and 52.47% of Cr(VI) in the contaminated soil after 30 days. Meanwhile, the water-soluble and the leaching Cr contents were decreased by 43.37% and 61.78% in the 5PPS group, respectively. Elemental speciation by XPS revealed that Cr(VI) removal from solution and soil proceeded mainly by electrostatic attraction, reduction, and complexation/chelation. The study implied that PPS could be a useful amendment to remediate both the Cr(VI)-contaminated water and soil.