Masudur Rahman Siddiquee

Addressing groundwater contamination, this study applies machine learning (ML) algorithms to explore the spatiotemporal dynamics of hexavalent chromium (Cr[VI]) at the Hanford 100-Area. The research uses an extensive long-term monitoring dataset focused on groundwater wells and aquifers to enhance the understanding and management strategies of this complex environmental issue and predict the impact on aquifers due to the contamination in groundwater wells. The challenging nature of the task is due to various factors, such as the geological nature of the soil, pipeline leaks, and mobility of the particles that impact the speed of contamination. The findings demonstrate a random forest (ML)-based approach to predict the contaminant distributions accurately, thus significantly reducing uncertainties in contamination assessments and refining conceptual site models. This approach advances groundwater quality management and sets a precedent for future AI-driven environmental studies.

Long-term environmental monitoring is critical for managing the soil and groundwater at contaminated sites. Recent improvements in state-of-the-art sensor technology, communication networks, and artificial intelligence have created opportunities to modernize this monitoring activity for automated, fast, robust, and predictive monitoring. In such modernization, it is required that sensor locations be optimized to capture the spatiotemporal dynamics of all monitoring variables as well as to make it cost-effective. The legacy monitoring datasets of the target area are important to perform this optimization. In this study, we have developed a machine-learning approach to optimize sensor locations for soil and groundwater monitoring based on ensemble supervised learning and majority voting. For spatial optimization, Gaussian process regression (GPR) is used for spatial interpolation, while the majority voting is applied to accommodate the multivariate temporal dimension. Results show that the algorithms significantly outperform the random selection of the sensor locations for predictive spatiotemporal interpolation. While the method has been applied to a four-dimensional dataset (with two-dimensional space, time, and multiple contaminants), we anticipate that it can be generalizable to higher-dimensional datasets for environmental monitoring sensor location optimization.

The sensor subset selection problem is a crucial task in the field of sensor systems, where the goal is to choose a subset of sensors from a larger pool such that the spatial estimation representation closely approximates the performance of using all the sensors while minimizing the number of sensors required. This is a challenging problem involving trade-offs between performance, cost, and complexity. In this work, a novel approach is proposed, which is based on set encoding and genetic algorithm for addressing the sensor subset selection problem. Our method incorporates a spatial algorithm to minimize the mean squared error (MSE) between the reference field and the selected subset of sensors. The efficiency of this approach is demonstrated by optimizing the sensor selection based on the water table variable using the dataset from the Savannah River Site (SRS) F-Area, a Department of Energy monitored location with groundwater contamination issues. The proposed solution introduces two new crossover methods (Complementary Set Crossover and Uniform Set Crossover) and two new mutation methods (Inclusive Set Mutation and Exclusive Set Mutation) that work with the novel set encoding. The effectiveness of this method is compared with the previously used greedy strategy, showing considerable improvements. The implemented algorithm shows a substantial performance for a 33, 50, and 75 decrease in sensors, achieving an R2 higher than 0.98. This indicates an extremely accurate depiction of the ground truth field using the optimized sensor subset.

Hardware cybersecurity has become a key issue, especially for very large integrated circuits. If counterfeit, forged, or defective ICs present a significant threat to system reliability and security. The growing complexity of digital and mixed-signal systems makes it increasingly challenging yet vital to develop robust methods to assess and confirm the reliability and authenticity of ICs. We introduce a new terahertz testing method for non-destructive and unobtrusive identification of counterfeit, damaged, forged or defective ICs by measuring their response to incident terahertz and sub-terahertz radiation at the circuit pins and analyzing the response using artificial intelligence (AI). These responses create unique signatures for ICs. We generated 2D images by measuring the response on a selected pin of a radio frequency IC (RFIC) scanned by a focused terahertz radiation. By applying the data augmentation processes, we created a secure image data set to train the convolutional neural network (CNN) model. An unsecured image data set representing altered or damaged ICs was generated by modifying the original image data. The trained models identified secure devices with a ~94% accuracy.

Volitional control of prosthetic devices can potentially provide the user with a more natural movement experience. Currently, there is no feasible volitional triggering method to adapt the prosthetic device to user's intention to accelerate during walking. Therefore, real-time prediction of human acceleration intention from the pre-acceleration electroencephalogram (EEG), and subsequent adaptation of the prosthetic device's control parameters for seamless transition remains a daunting research area. In that aspect, this study investigates the neural changes responsive to human intention to accelerate during walking. Furthermore, this study also explores whether the acceleration intention can be predicted from real-time EEG to subsequently enable parametric adaptation for an external prosthetic device. EEG, Inertial Measurement Unit (IMU), and ground reaction force (GRF) signals were collected from one healthy subject during walking with self-paced speed changes. A set of classifiers were explored to classify between constant speed and acceleration. The classifiers showed promising classification performance well above chance level in offline, pseudo-online and real-time scenarios. An accuracy of 85.9±2.9% was achieved in offline scenario, while pseudo-online classification resulted in a true positive rate (TPR) of 81.9±7.4% with 7.7±0.8 false positives/ min and a detection latency of -844±572 ms. In real-time scenario, 9 out of 12 acceleration events were predicted successfully with only 3 false predictions at an average latency of -741 ms. Moreover, offline data analysis suggested suppression of mu and beta rhythms related to gait acceleration between 2 seconds before and 1.5 seconds after the onset of acceleration. A slow increase in negative amplitude was also observed in near DC frequencies of EEG data acquired from the sensorimotor cortex. The findings of this study portray inspiring results in retrieving gait acceleration-associated neural changes for facilitating natural control of assistive devices.

Cancer is one of the primary concerns of mortality throughout the world in the present day. Among different types of cancers, lung cancer (LC) is predominant (21.77% of overall cancer caused death). It is classified into two major categories: oat cell or small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC). The mortality due to NSCLC (~85%) is almost six times higher than the SCLC (15%). The identification of risk factors can reduce cancer burden and human fatality; however, this cannot prevent the severity of LC. In this case, the early diagnosis of LC can be an effective pathway in providing better treatment to the patients, which eventually may result in less fatality. This article offers an overview of several existing screening methods for the early diagnosis of LC. Nevertheless, these methodologies have limitations of reliability towards the diagnosis of cancer malignancy. Therefore, the prospects of different alternative approaches and their challenges to overcome this barrier for the early diagnosis of malignant tumor cells have been articulated in this article.

Recent psychological and neurological studies suggest that human motor preparation and execution are largely affected by the subjective emotional state. Thus, external emotion stimuli can be a potential tool to enhance the detectability of movement intention from pre-movement neural signals. This study investigated whether emotion-evoking music stimulus could improve the performances of a fully predictive Brain-Computer Interface (BCI) system for movement intention detection. For this purpose, electroencephalographical (EEG) signals were recorded from twelve healthy subjects under three emotional conditions: happy, sad, and neutral. The emotions were elicited using external music stimuli while they performed a wrist extension action. Additionally, support vector machine-based offline and pseudo online testing schemes were employed to solve a binary classification problem for determining movement intention from pre-movement EEG. EEG power analysis showed that happy music stimulus resulted in an early occurrence of event-related desynchronization in alpha band compared other emotional states. Happy emotional stimuli also resulted in comparatively better performances in both offline and pseudo online testing paradigms. The results of this study suggest that external happy music stimulus could enhance the early and accurate detectability of human self-paced movement intention and thus could contribute to the predictive capability of state-of-the-art assistive BCIs.

Functional Near-Infrared Spectroscopy (fNIRS) is a hemodynamic modality in human cognitive workload assessment receiving popularity due to its easier implementation, non-invasiveness, low cost and other benefits from the signal-processing point of view. Wearable wireless fNIRS systems used in research have promisingly shown that fNIRS could be used in cognitive workload assessment in out-of-the-lab scenarios, such as in operators’ cognitive workload monitoring. In such a scenario, the wearability of the system is a significant factor affecting user comfort. In this respect, the wearability of the system can be improved if it is possible to minimize an fNIRS system without much compromise of the cognitive workload detection accuracy. In this study, cognitive workload-related hemodynamic changes were acquired using an fNIRS system covering the whole forehead, which is the region of interest in most cognitive workload-monitoring studies. A machine learning approach was applied to explore how the mean accuracy of the cognitive workload classification accuracy varied across various sensing locations on the forehead such as the Left, Mid, Right, Left-Mid, Right-Mid and Whole forehead. The statistical significance analysis result showed that the Mid location could result in significant cognitive workload classification accuracy compared to Whole forehead sensing, with a statistically insignificant difference in the mean accuracy. Thus, the wearable fNIRS system can be improved in terms of wearability by optimizing the sensor location, considering the sensing of the Mid location on the forehead for cognitive workload monitoring.

Prediction of human voluntary gait intention is a very significant task to ensure direct cortical control of real-life assistive technologies for locomotion rehabilitation. Neurophysiological studies provide that human voluntary gait intention is represented by slow DC potentials and power shifts in specific frequency ranges of brain wave, which can be detected 1.5- 2 seconds before the actual onset. The goal of this study was to determine whether it is possible to reliably detect the intention of voluntary gait 'starting' and 'stopping' intention before it takes place. A computational algorithm was designed to implement asynchronous prediction of gait intention in an offline and pseudo-online environment using support vector machine. Six healthy subjects participated in the study and performed self- paced voluntary gait cycles. A combination of advanced wavelet transform algorithms resulted in 88.23±1.59% accuracy, 85.42±4.03% sensitivity and 90.24±2.78% specificity for intention of start detection and 87.04±1.72% accuracy, 82.69±4.13% sensitivity and 89.59±3.04% specificity for intention to stop walking in offline testing. Additionally, the wavelet transform methods accompanied with threshold regulation and majority voting algorithm resulted in a True Positive Rate of 85.5±5.0% and 81.2±3.3% for ‘start’ and ‘stop’ prediction with 6.8±0.7 and 9.4±1.0 False Positives per Minute respectively in pseudo online testing. The average detection latencies were -1002±603 ms and -943±603 ms, respectively, for 'start' and 'stop' prediction. The study provides promising outcomes in terms of TPR, FP/min, and detection latency, which suggests that human voluntary gait intention can be predicted before the onset of movement.

Background: Prediction of Gait intention from pre-movement Electroencephalography (EEG) signals is a vital step in developing a real-time Brain-computer Interface (BCI) for a proper neuro-rehabilitation system. In that respect, this paper investigates the feasibility of a fully predictive methodology to detect the intention to start and stop a gait cycle by utilizing EEG signals obtained before the event occurrence. Methods: An eight-channel, custom-made, EEG system with electrodes placed around the sensorimotor cortex was used to acquire EEG data from six healthy subjects and two amputees. A discrete wavelet transform-based method was employed to capture event related information in alpha and beta bands in the time-frequency domain. The Hjorth parameters, namely activity, mobility, and complexity, were extracted as features while a two-sample unpaired Wilcoxon test was used to get rid of redundant features for better classification accuracy. The feature set thus obtained was then used to classify between ’walk vs. stop’ and ’rest vs. start’ classes using support vector machine (SVM) classifier with RBF kernel in a ten-fold cross-validation scheme. Results: Using a fully predictive intention detection system, 76.41±4.47% accuracy, 72.85±7.48% sensitivity, and 79.93±5.50% specificity were achieved for ’rest vs. start’ classification. While for ’walk vs. stop’ classification, the obtained mean accuracy, sensitivity, and specificity were 74.12±4.12%, 70.24±6.45%, and 77.78±7.01% respectively. Overall average True Positive Rate achieved by this methodology was 72.06±8.27% with 1.45 False Positives/min. Conclusion: Extensive simulations and resulting classification results show that it is possible to achieve statistically similar intention detection accuracy using either only pre-movement EEG features or trans-movement EEG features. The classifier performance shows the potential of the proposed methodology to predict human movement intention exclusively from the pre-movement EEG signal to be applied in real-life prosthetic and neuro-rehabilitation systems.